Upload folder using huggingface_hub
Browse files- .gitattributes +2 -0
- README.md +183 -0
- adapter_config.json +34 -0
- adapter_model.safetensors +3 -0
- all_results.json +12 -0
- checkpoint-350/README.md +202 -0
- checkpoint-350/adapter_config.json +34 -0
- checkpoint-350/adapter_model.safetensors +3 -0
- checkpoint-350/optimizer.pt +3 -0
- checkpoint-350/rng_state.pth +3 -0
- checkpoint-350/scheduler.pt +3 -0
- checkpoint-350/special_tokens_map.json +17 -0
- checkpoint-350/tokenizer.json +3 -0
- checkpoint-350/tokenizer_config.json +2065 -0
- checkpoint-350/trainer_state.json +3043 -0
- checkpoint-350/training_args.bin +3 -0
- eval_results.json +7 -0
- special_tokens_map.json +17 -0
- tokenizer.json +3 -0
- tokenizer_config.json +2065 -0
- train_results.json +8 -0
- trainer_log.jsonl +0 -0
- trainer_state.json +0 -0
- training_args.bin +3 -0
- training_eval_loss.png +0 -0
- training_loss.png +0 -0
.gitattributes
CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
checkpoint-350/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
37 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,183 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
license: other
|
4 |
+
base_model: unsloth/Llama-3.2-3B-Instruct
|
5 |
+
tags:
|
6 |
+
- llama-factory
|
7 |
+
- lora
|
8 |
+
- unsloth
|
9 |
+
- generated_from_trainer
|
10 |
+
model-index:
|
11 |
+
- name: llm3br256
|
12 |
+
results: []
|
13 |
+
---
|
14 |
+
|
15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
16 |
+
should probably proofread and complete it, then remove this comment. -->
|
17 |
+
|
18 |
+
# llm3br256
|
19 |
+
|
20 |
+
This model is a fine-tuned version of [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct) on the rommel_importgenius_4b8 dataset.
|
21 |
+
It achieves the following results on the evaluation set:
|
22 |
+
- Loss: 0.0130
|
23 |
+
|
24 |
+
## Model description
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Intended uses & limitations
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training and evaluation data
|
33 |
+
|
34 |
+
More information needed
|
35 |
+
|
36 |
+
## Training procedure
|
37 |
+
|
38 |
+
### Training hyperparameters
|
39 |
+
|
40 |
+
The following hyperparameters were used during training:
|
41 |
+
- learning_rate: 0.0001
|
42 |
+
- train_batch_size: 4
|
43 |
+
- eval_batch_size: 4
|
44 |
+
- seed: 42
|
45 |
+
- gradient_accumulation_steps: 8
|
46 |
+
- total_train_batch_size: 32
|
47 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
48 |
+
- lr_scheduler_type: cosine
|
49 |
+
- lr_scheduler_warmup_ratio: 0.1
|
50 |
+
- num_epochs: 5.0
|
51 |
+
|
52 |
+
### Training results
|
53 |
+
|
54 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
55 |
+
|:-------------:|:------:|:----:|:---------------:|
|
56 |
+
| 0.0672 | 0.0418 | 5 | 0.0755 |
|
57 |
+
| 0.0476 | 0.0837 | 10 | 0.0452 |
|
58 |
+
| 0.0337 | 0.1255 | 15 | 0.0356 |
|
59 |
+
| 0.0333 | 0.1674 | 20 | 0.0308 |
|
60 |
+
| 0.0258 | 0.2092 | 25 | 0.0272 |
|
61 |
+
| 0.023 | 0.2510 | 30 | 0.0255 |
|
62 |
+
| 0.0202 | 0.2929 | 35 | 0.0234 |
|
63 |
+
| 0.0188 | 0.3347 | 40 | 0.0218 |
|
64 |
+
| 0.0185 | 0.3766 | 45 | 0.0208 |
|
65 |
+
| 0.0199 | 0.4184 | 50 | 0.0200 |
|
66 |
+
| 0.0198 | 0.4603 | 55 | 0.0195 |
|
67 |
+
| 0.0179 | 0.5021 | 60 | 0.0189 |
|
68 |
+
| 0.0185 | 0.5439 | 65 | 0.0186 |
|
69 |
+
| 0.0174 | 0.5858 | 70 | 0.0186 |
|
70 |
+
| 0.0157 | 0.6276 | 75 | 0.0183 |
|
71 |
+
| 0.0175 | 0.6695 | 80 | 0.0176 |
|
72 |
+
| 0.0175 | 0.7113 | 85 | 0.0176 |
|
73 |
+
| 0.0164 | 0.7531 | 90 | 0.0171 |
|
74 |
+
| 0.0182 | 0.7950 | 95 | 0.0168 |
|
75 |
+
| 0.019 | 0.8368 | 100 | 0.0167 |
|
76 |
+
| 0.0163 | 0.8787 | 105 | 0.0158 |
|
77 |
+
| 0.0145 | 0.9205 | 110 | 0.0158 |
|
78 |
+
| 0.0165 | 0.9623 | 115 | 0.0155 |
|
79 |
+
| 0.0205 | 1.0042 | 120 | 0.0152 |
|
80 |
+
| 0.0105 | 1.0460 | 125 | 0.0155 |
|
81 |
+
| 0.0147 | 1.0879 | 130 | 0.0157 |
|
82 |
+
| 0.0148 | 1.1297 | 135 | 0.0160 |
|
83 |
+
| 0.0115 | 1.1715 | 140 | 0.0153 |
|
84 |
+
| 0.0166 | 1.2134 | 145 | 0.0153 |
|
85 |
+
| 0.015 | 1.2552 | 150 | 0.0156 |
|
86 |
+
| 0.0148 | 1.2971 | 155 | 0.0157 |
|
87 |
+
| 0.0112 | 1.3389 | 160 | 0.0159 |
|
88 |
+
| 0.0128 | 1.3808 | 165 | 0.0153 |
|
89 |
+
| 0.0125 | 1.4226 | 170 | 0.0151 |
|
90 |
+
| 0.0137 | 1.4644 | 175 | 0.0150 |
|
91 |
+
| 0.0131 | 1.5063 | 180 | 0.0145 |
|
92 |
+
| 0.0105 | 1.5481 | 185 | 0.0145 |
|
93 |
+
| 0.0126 | 1.5900 | 190 | 0.0144 |
|
94 |
+
| 0.0119 | 1.6318 | 195 | 0.0145 |
|
95 |
+
| 0.016 | 1.6736 | 200 | 0.0147 |
|
96 |
+
| 0.0143 | 1.7155 | 205 | 0.0150 |
|
97 |
+
| 0.0139 | 1.7573 | 210 | 0.0150 |
|
98 |
+
| 0.0139 | 1.7992 | 215 | 0.0145 |
|
99 |
+
| 0.0161 | 1.8410 | 220 | 0.0143 |
|
100 |
+
| 0.0098 | 1.8828 | 225 | 0.0138 |
|
101 |
+
| 0.0108 | 1.9247 | 230 | 0.0140 |
|
102 |
+
| 0.0117 | 1.9665 | 235 | 0.0141 |
|
103 |
+
| 0.0109 | 2.0084 | 240 | 0.0138 |
|
104 |
+
| 0.0093 | 2.0502 | 245 | 0.0145 |
|
105 |
+
| 0.0102 | 2.0921 | 250 | 0.0143 |
|
106 |
+
| 0.0104 | 2.1339 | 255 | 0.0141 |
|
107 |
+
| 0.0108 | 2.1757 | 260 | 0.0147 |
|
108 |
+
| 0.0104 | 2.2176 | 265 | 0.0142 |
|
109 |
+
| 0.0103 | 2.2594 | 270 | 0.0144 |
|
110 |
+
| 0.0107 | 2.3013 | 275 | 0.0144 |
|
111 |
+
| 0.0104 | 2.3431 | 280 | 0.0141 |
|
112 |
+
| 0.0092 | 2.3849 | 285 | 0.0143 |
|
113 |
+
| 0.0107 | 2.4268 | 290 | 0.0140 |
|
114 |
+
| 0.0112 | 2.4686 | 295 | 0.0143 |
|
115 |
+
| 0.01 | 2.5105 | 300 | 0.0143 |
|
116 |
+
| 0.0096 | 2.5523 | 305 | 0.0138 |
|
117 |
+
| 0.0096 | 2.5941 | 310 | 0.0137 |
|
118 |
+
| 0.0099 | 2.6360 | 315 | 0.0137 |
|
119 |
+
| 0.009 | 2.6778 | 320 | 0.0138 |
|
120 |
+
| 0.0097 | 2.7197 | 325 | 0.0137 |
|
121 |
+
| 0.0097 | 2.7615 | 330 | 0.0136 |
|
122 |
+
| 0.0108 | 2.8033 | 335 | 0.0136 |
|
123 |
+
| 0.0092 | 2.8452 | 340 | 0.0132 |
|
124 |
+
| 0.0092 | 2.8870 | 345 | 0.0132 |
|
125 |
+
| 0.0095 | 2.9289 | 350 | 0.0130 |
|
126 |
+
| 0.0094 | 2.9707 | 355 | 0.0127 |
|
127 |
+
| 0.0088 | 3.0126 | 360 | 0.0127 |
|
128 |
+
| 0.0086 | 3.0544 | 365 | 0.0131 |
|
129 |
+
| 0.0094 | 3.0962 | 370 | 0.0134 |
|
130 |
+
| 0.0075 | 3.1381 | 375 | 0.0137 |
|
131 |
+
| 0.0068 | 3.1799 | 380 | 0.0136 |
|
132 |
+
| 0.0096 | 3.2218 | 385 | 0.0136 |
|
133 |
+
| 0.0088 | 3.2636 | 390 | 0.0137 |
|
134 |
+
| 0.008 | 3.3054 | 395 | 0.0138 |
|
135 |
+
| 0.0085 | 3.3473 | 400 | 0.0137 |
|
136 |
+
| 0.0091 | 3.3891 | 405 | 0.0136 |
|
137 |
+
| 0.0049 | 3.4310 | 410 | 0.0134 |
|
138 |
+
| 0.0072 | 3.4728 | 415 | 0.0131 |
|
139 |
+
| 0.0063 | 3.5146 | 420 | 0.0133 |
|
140 |
+
| 0.0076 | 3.5565 | 425 | 0.0131 |
|
141 |
+
| 0.0076 | 3.5983 | 430 | 0.0129 |
|
142 |
+
| 0.0074 | 3.6402 | 435 | 0.0130 |
|
143 |
+
| 0.0074 | 3.6820 | 440 | 0.0132 |
|
144 |
+
| 0.0067 | 3.7238 | 445 | 0.0132 |
|
145 |
+
| 0.0064 | 3.7657 | 450 | 0.0130 |
|
146 |
+
| 0.0091 | 3.8075 | 455 | 0.0130 |
|
147 |
+
| 0.0074 | 3.8494 | 460 | 0.0131 |
|
148 |
+
| 0.0076 | 3.8912 | 465 | 0.0132 |
|
149 |
+
| 0.007 | 3.9331 | 470 | 0.0132 |
|
150 |
+
| 0.0082 | 3.9749 | 475 | 0.0132 |
|
151 |
+
| 0.0059 | 4.0167 | 480 | 0.0133 |
|
152 |
+
| 0.0066 | 4.0586 | 485 | 0.0135 |
|
153 |
+
| 0.0063 | 4.1004 | 490 | 0.0140 |
|
154 |
+
| 0.0059 | 4.1423 | 495 | 0.0144 |
|
155 |
+
| 0.0066 | 4.1841 | 500 | 0.0142 |
|
156 |
+
| 0.0055 | 4.2259 | 505 | 0.0142 |
|
157 |
+
| 0.0067 | 4.2678 | 510 | 0.0142 |
|
158 |
+
| 0.0065 | 4.3096 | 515 | 0.0143 |
|
159 |
+
| 0.0062 | 4.3515 | 520 | 0.0142 |
|
160 |
+
| 0.0065 | 4.3933 | 525 | 0.0141 |
|
161 |
+
| 0.007 | 4.4351 | 530 | 0.0139 |
|
162 |
+
| 0.0058 | 4.4770 | 535 | 0.0139 |
|
163 |
+
| 0.0056 | 4.5188 | 540 | 0.0139 |
|
164 |
+
| 0.0062 | 4.5607 | 545 | 0.0139 |
|
165 |
+
| 0.0061 | 4.6025 | 550 | 0.0139 |
|
166 |
+
| 0.0061 | 4.6444 | 555 | 0.0139 |
|
167 |
+
| 0.0068 | 4.6862 | 560 | 0.0138 |
|
168 |
+
| 0.0069 | 4.7280 | 565 | 0.0139 |
|
169 |
+
| 0.0063 | 4.7699 | 570 | 0.0139 |
|
170 |
+
| 0.0065 | 4.8117 | 575 | 0.0139 |
|
171 |
+
| 0.0064 | 4.8536 | 580 | 0.0139 |
|
172 |
+
| 0.0062 | 4.8954 | 585 | 0.0139 |
|
173 |
+
| 0.0065 | 4.9372 | 590 | 0.0139 |
|
174 |
+
| 0.0055 | 4.9791 | 595 | 0.0139 |
|
175 |
+
|
176 |
+
|
177 |
+
### Framework versions
|
178 |
+
|
179 |
+
- PEFT 0.12.0
|
180 |
+
- Transformers 4.46.1
|
181 |
+
- Pytorch 2.4.0+cu121
|
182 |
+
- Datasets 3.1.0
|
183 |
+
- Tokenizers 0.20.3
|
adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "unsloth/Llama-3.2-3B-Instruct",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 256,
|
14 |
+
"lora_dropout": 0.0,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 256,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"o_proj",
|
24 |
+
"gate_proj",
|
25 |
+
"v_proj",
|
26 |
+
"k_proj",
|
27 |
+
"up_proj",
|
28 |
+
"q_proj",
|
29 |
+
"down_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c0a96be0893a47affa48b3f3c7c840617e108cc336b4840037d99c7aed06051
|
3 |
+
size 1556140392
|
all_results.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 4.97907949790795,
|
3 |
+
"eval_loss": 0.012959836050868034,
|
4 |
+
"eval_runtime": 8.1595,
|
5 |
+
"eval_samples_per_second": 6.128,
|
6 |
+
"eval_steps_per_second": 1.593,
|
7 |
+
"total_flos": 1.199536935920124e+18,
|
8 |
+
"train_loss": 0.012196063881880846,
|
9 |
+
"train_runtime": 9595.7495,
|
10 |
+
"train_samples_per_second": 1.991,
|
11 |
+
"train_steps_per_second": 0.062
|
12 |
+
}
|
checkpoint-350/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: unsloth/Llama-3.2-3B-Instruct
|
3 |
+
library_name: peft
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
### Framework versions
|
201 |
+
|
202 |
+
- PEFT 0.12.0
|
checkpoint-350/adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "unsloth/Llama-3.2-3B-Instruct",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 256,
|
14 |
+
"lora_dropout": 0.0,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 256,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"o_proj",
|
24 |
+
"gate_proj",
|
25 |
+
"v_proj",
|
26 |
+
"k_proj",
|
27 |
+
"up_proj",
|
28 |
+
"q_proj",
|
29 |
+
"down_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
checkpoint-350/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c0a96be0893a47affa48b3f3c7c840617e108cc336b4840037d99c7aed06051
|
3 |
+
size 1556140392
|
checkpoint-350/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6d7cd6bbdf03b690232b702d69987d1a5a2f1bd0de18a650cb3014d1ec40b030
|
3 |
+
size 3112505578
|
checkpoint-350/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:21c40a6487e4db9feaa8ea397060b1e56aadcea55383ed54dba3a9587663cea2
|
3 |
+
size 14308
|
checkpoint-350/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44f26b42ada239f735f6b5d7d7c234ae141be80157eb608a68767a596b8abbfd
|
3 |
+
size 1064
|
checkpoint-350/special_tokens_map.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|begin_of_text|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|eot_id|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "<|eot_id|>"
|
17 |
+
}
|
checkpoint-350/tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
|
3 |
+
size 17209920
|
checkpoint-350/tokenizer_config.json
ADDED
@@ -0,0 +1,2065 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"128000": {
|
4 |
+
"content": "<|begin_of_text|>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"128001": {
|
12 |
+
"content": "<|end_of_text|>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"128002": {
|
20 |
+
"content": "<|reserved_special_token_0|>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"128003": {
|
28 |
+
"content": "<|reserved_special_token_1|>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"128004": {
|
36 |
+
"content": "<|finetune_right_pad_id|>",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
},
|
43 |
+
"128005": {
|
44 |
+
"content": "<|reserved_special_token_2|>",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": true
|
50 |
+
},
|
51 |
+
"128006": {
|
52 |
+
"content": "<|start_header_id|>",
|
53 |
+
"lstrip": false,
|
54 |
+
"normalized": false,
|
55 |
+
"rstrip": false,
|
56 |
+
"single_word": false,
|
57 |
+
"special": true
|
58 |
+
},
|
59 |
+
"128007": {
|
60 |
+
"content": "<|end_header_id|>",
|
61 |
+
"lstrip": false,
|
62 |
+
"normalized": false,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": false,
|
65 |
+
"special": true
|
66 |
+
},
|
67 |
+
"128008": {
|
68 |
+
"content": "<|eom_id|>",
|
69 |
+
"lstrip": false,
|
70 |
+
"normalized": false,
|
71 |
+
"rstrip": false,
|
72 |
+
"single_word": false,
|
73 |
+
"special": true
|
74 |
+
},
|
75 |
+
"128009": {
|
76 |
+
"content": "<|eot_id|>",
|
77 |
+
"lstrip": false,
|
78 |
+
"normalized": false,
|
79 |
+
"rstrip": false,
|
80 |
+
"single_word": false,
|
81 |
+
"special": true
|
82 |
+
},
|
83 |
+
"128010": {
|
84 |
+
"content": "<|python_tag|>",
|
85 |
+
"lstrip": false,
|
86 |
+
"normalized": false,
|
87 |
+
"rstrip": false,
|
88 |
+
"single_word": false,
|
89 |
+
"special": true
|
90 |
+
},
|
91 |
+
"128011": {
|
92 |
+
"content": "<|reserved_special_token_3|>",
|
93 |
+
"lstrip": false,
|
94 |
+
"normalized": false,
|
95 |
+
"rstrip": false,
|
96 |
+
"single_word": false,
|
97 |
+
"special": true
|
98 |
+
},
|
99 |
+
"128012": {
|
100 |
+
"content": "<|reserved_special_token_4|>",
|
101 |
+
"lstrip": false,
|
102 |
+
"normalized": false,
|
103 |
+
"rstrip": false,
|
104 |
+
"single_word": false,
|
105 |
+
"special": true
|
106 |
+
},
|
107 |
+
"128013": {
|
108 |
+
"content": "<|reserved_special_token_5|>",
|
109 |
+
"lstrip": false,
|
110 |
+
"normalized": false,
|
111 |
+
"rstrip": false,
|
112 |
+
"single_word": false,
|
113 |
+
"special": true
|
114 |
+
},
|
115 |
+
"128014": {
|
116 |
+
"content": "<|reserved_special_token_6|>",
|
117 |
+
"lstrip": false,
|
118 |
+
"normalized": false,
|
119 |
+
"rstrip": false,
|
120 |
+
"single_word": false,
|
121 |
+
"special": true
|
122 |
+
},
|
123 |
+
"128015": {
|
124 |
+
"content": "<|reserved_special_token_7|>",
|
125 |
+
"lstrip": false,
|
126 |
+
"normalized": false,
|
127 |
+
"rstrip": false,
|
128 |
+
"single_word": false,
|
129 |
+
"special": true
|
130 |
+
},
|
131 |
+
"128016": {
|
132 |
+
"content": "<|reserved_special_token_8|>",
|
133 |
+
"lstrip": false,
|
134 |
+
"normalized": false,
|
135 |
+
"rstrip": false,
|
136 |
+
"single_word": false,
|
137 |
+
"special": true
|
138 |
+
},
|
139 |
+
"128017": {
|
140 |
+
"content": "<|reserved_special_token_9|>",
|
141 |
+
"lstrip": false,
|
142 |
+
"normalized": false,
|
143 |
+
"rstrip": false,
|
144 |
+
"single_word": false,
|
145 |
+
"special": true
|
146 |
+
},
|
147 |
+
"128018": {
|
148 |
+
"content": "<|reserved_special_token_10|>",
|
149 |
+
"lstrip": false,
|
150 |
+
"normalized": false,
|
151 |
+
"rstrip": false,
|
152 |
+
"single_word": false,
|
153 |
+
"special": true
|
154 |
+
},
|
155 |
+
"128019": {
|
156 |
+
"content": "<|reserved_special_token_11|>",
|
157 |
+
"lstrip": false,
|
158 |
+
"normalized": false,
|
159 |
+
"rstrip": false,
|
160 |
+
"single_word": false,
|
161 |
+
"special": true
|
162 |
+
},
|
163 |
+
"128020": {
|
164 |
+
"content": "<|reserved_special_token_12|>",
|
165 |
+
"lstrip": false,
|
166 |
+
"normalized": false,
|
167 |
+
"rstrip": false,
|
168 |
+
"single_word": false,
|
169 |
+
"special": true
|
170 |
+
},
|
171 |
+
"128021": {
|
172 |
+
"content": "<|reserved_special_token_13|>",
|
173 |
+
"lstrip": false,
|
174 |
+
"normalized": false,
|
175 |
+
"rstrip": false,
|
176 |
+
"single_word": false,
|
177 |
+
"special": true
|
178 |
+
},
|
179 |
+
"128022": {
|
180 |
+
"content": "<|reserved_special_token_14|>",
|
181 |
+
"lstrip": false,
|
182 |
+
"normalized": false,
|
183 |
+
"rstrip": false,
|
184 |
+
"single_word": false,
|
185 |
+
"special": true
|
186 |
+
},
|
187 |
+
"128023": {
|
188 |
+
"content": "<|reserved_special_token_15|>",
|
189 |
+
"lstrip": false,
|
190 |
+
"normalized": false,
|
191 |
+
"rstrip": false,
|
192 |
+
"single_word": false,
|
193 |
+
"special": true
|
194 |
+
},
|
195 |
+
"128024": {
|
196 |
+
"content": "<|reserved_special_token_16|>",
|
197 |
+
"lstrip": false,
|
198 |
+
"normalized": false,
|
199 |
+
"rstrip": false,
|
200 |
+
"single_word": false,
|
201 |
+
"special": true
|
202 |
+
},
|
203 |
+
"128025": {
|
204 |
+
"content": "<|reserved_special_token_17|>",
|
205 |
+
"lstrip": false,
|
206 |
+
"normalized": false,
|
207 |
+
"rstrip": false,
|
208 |
+
"single_word": false,
|
209 |
+
"special": true
|
210 |
+
},
|
211 |
+
"128026": {
|
212 |
+
"content": "<|reserved_special_token_18|>",
|
213 |
+
"lstrip": false,
|
214 |
+
"normalized": false,
|
215 |
+
"rstrip": false,
|
216 |
+
"single_word": false,
|
217 |
+
"special": true
|
218 |
+
},
|
219 |
+
"128027": {
|
220 |
+
"content": "<|reserved_special_token_19|>",
|
221 |
+
"lstrip": false,
|
222 |
+
"normalized": false,
|
223 |
+
"rstrip": false,
|
224 |
+
"single_word": false,
|
225 |
+
"special": true
|
226 |
+
},
|
227 |
+
"128028": {
|
228 |
+
"content": "<|reserved_special_token_20|>",
|
229 |
+
"lstrip": false,
|
230 |
+
"normalized": false,
|
231 |
+
"rstrip": false,
|
232 |
+
"single_word": false,
|
233 |
+
"special": true
|
234 |
+
},
|
235 |
+
"128029": {
|
236 |
+
"content": "<|reserved_special_token_21|>",
|
237 |
+
"lstrip": false,
|
238 |
+
"normalized": false,
|
239 |
+
"rstrip": false,
|
240 |
+
"single_word": false,
|
241 |
+
"special": true
|
242 |
+
},
|
243 |
+
"128030": {
|
244 |
+
"content": "<|reserved_special_token_22|>",
|
245 |
+
"lstrip": false,
|
246 |
+
"normalized": false,
|
247 |
+
"rstrip": false,
|
248 |
+
"single_word": false,
|
249 |
+
"special": true
|
250 |
+
},
|
251 |
+
"128031": {
|
252 |
+
"content": "<|reserved_special_token_23|>",
|
253 |
+
"lstrip": false,
|
254 |
+
"normalized": false,
|
255 |
+
"rstrip": false,
|
256 |
+
"single_word": false,
|
257 |
+
"special": true
|
258 |
+
},
|
259 |
+
"128032": {
|
260 |
+
"content": "<|reserved_special_token_24|>",
|
261 |
+
"lstrip": false,
|
262 |
+
"normalized": false,
|
263 |
+
"rstrip": false,
|
264 |
+
"single_word": false,
|
265 |
+
"special": true
|
266 |
+
},
|
267 |
+
"128033": {
|
268 |
+
"content": "<|reserved_special_token_25|>",
|
269 |
+
"lstrip": false,
|
270 |
+
"normalized": false,
|
271 |
+
"rstrip": false,
|
272 |
+
"single_word": false,
|
273 |
+
"special": true
|
274 |
+
},
|
275 |
+
"128034": {
|
276 |
+
"content": "<|reserved_special_token_26|>",
|
277 |
+
"lstrip": false,
|
278 |
+
"normalized": false,
|
279 |
+
"rstrip": false,
|
280 |
+
"single_word": false,
|
281 |
+
"special": true
|
282 |
+
},
|
283 |
+
"128035": {
|
284 |
+
"content": "<|reserved_special_token_27|>",
|
285 |
+
"lstrip": false,
|
286 |
+
"normalized": false,
|
287 |
+
"rstrip": false,
|
288 |
+
"single_word": false,
|
289 |
+
"special": true
|
290 |
+
},
|
291 |
+
"128036": {
|
292 |
+
"content": "<|reserved_special_token_28|>",
|
293 |
+
"lstrip": false,
|
294 |
+
"normalized": false,
|
295 |
+
"rstrip": false,
|
296 |
+
"single_word": false,
|
297 |
+
"special": true
|
298 |
+
},
|
299 |
+
"128037": {
|
300 |
+
"content": "<|reserved_special_token_29|>",
|
301 |
+
"lstrip": false,
|
302 |
+
"normalized": false,
|
303 |
+
"rstrip": false,
|
304 |
+
"single_word": false,
|
305 |
+
"special": true
|
306 |
+
},
|
307 |
+
"128038": {
|
308 |
+
"content": "<|reserved_special_token_30|>",
|
309 |
+
"lstrip": false,
|
310 |
+
"normalized": false,
|
311 |
+
"rstrip": false,
|
312 |
+
"single_word": false,
|
313 |
+
"special": true
|
314 |
+
},
|
315 |
+
"128039": {
|
316 |
+
"content": "<|reserved_special_token_31|>",
|
317 |
+
"lstrip": false,
|
318 |
+
"normalized": false,
|
319 |
+
"rstrip": false,
|
320 |
+
"single_word": false,
|
321 |
+
"special": true
|
322 |
+
},
|
323 |
+
"128040": {
|
324 |
+
"content": "<|reserved_special_token_32|>",
|
325 |
+
"lstrip": false,
|
326 |
+
"normalized": false,
|
327 |
+
"rstrip": false,
|
328 |
+
"single_word": false,
|
329 |
+
"special": true
|
330 |
+
},
|
331 |
+
"128041": {
|
332 |
+
"content": "<|reserved_special_token_33|>",
|
333 |
+
"lstrip": false,
|
334 |
+
"normalized": false,
|
335 |
+
"rstrip": false,
|
336 |
+
"single_word": false,
|
337 |
+
"special": true
|
338 |
+
},
|
339 |
+
"128042": {
|
340 |
+
"content": "<|reserved_special_token_34|>",
|
341 |
+
"lstrip": false,
|
342 |
+
"normalized": false,
|
343 |
+
"rstrip": false,
|
344 |
+
"single_word": false,
|
345 |
+
"special": true
|
346 |
+
},
|
347 |
+
"128043": {
|
348 |
+
"content": "<|reserved_special_token_35|>",
|
349 |
+
"lstrip": false,
|
350 |
+
"normalized": false,
|
351 |
+
"rstrip": false,
|
352 |
+
"single_word": false,
|
353 |
+
"special": true
|
354 |
+
},
|
355 |
+
"128044": {
|
356 |
+
"content": "<|reserved_special_token_36|>",
|
357 |
+
"lstrip": false,
|
358 |
+
"normalized": false,
|
359 |
+
"rstrip": false,
|
360 |
+
"single_word": false,
|
361 |
+
"special": true
|
362 |
+
},
|
363 |
+
"128045": {
|
364 |
+
"content": "<|reserved_special_token_37|>",
|
365 |
+
"lstrip": false,
|
366 |
+
"normalized": false,
|
367 |
+
"rstrip": false,
|
368 |
+
"single_word": false,
|
369 |
+
"special": true
|
370 |
+
},
|
371 |
+
"128046": {
|
372 |
+
"content": "<|reserved_special_token_38|>",
|
373 |
+
"lstrip": false,
|
374 |
+
"normalized": false,
|
375 |
+
"rstrip": false,
|
376 |
+
"single_word": false,
|
377 |
+
"special": true
|
378 |
+
},
|
379 |
+
"128047": {
|
380 |
+
"content": "<|reserved_special_token_39|>",
|
381 |
+
"lstrip": false,
|
382 |
+
"normalized": false,
|
383 |
+
"rstrip": false,
|
384 |
+
"single_word": false,
|
385 |
+
"special": true
|
386 |
+
},
|
387 |
+
"128048": {
|
388 |
+
"content": "<|reserved_special_token_40|>",
|
389 |
+
"lstrip": false,
|
390 |
+
"normalized": false,
|
391 |
+
"rstrip": false,
|
392 |
+
"single_word": false,
|
393 |
+
"special": true
|
394 |
+
},
|
395 |
+
"128049": {
|
396 |
+
"content": "<|reserved_special_token_41|>",
|
397 |
+
"lstrip": false,
|
398 |
+
"normalized": false,
|
399 |
+
"rstrip": false,
|
400 |
+
"single_word": false,
|
401 |
+
"special": true
|
402 |
+
},
|
403 |
+
"128050": {
|
404 |
+
"content": "<|reserved_special_token_42|>",
|
405 |
+
"lstrip": false,
|
406 |
+
"normalized": false,
|
407 |
+
"rstrip": false,
|
408 |
+
"single_word": false,
|
409 |
+
"special": true
|
410 |
+
},
|
411 |
+
"128051": {
|
412 |
+
"content": "<|reserved_special_token_43|>",
|
413 |
+
"lstrip": false,
|
414 |
+
"normalized": false,
|
415 |
+
"rstrip": false,
|
416 |
+
"single_word": false,
|
417 |
+
"special": true
|
418 |
+
},
|
419 |
+
"128052": {
|
420 |
+
"content": "<|reserved_special_token_44|>",
|
421 |
+
"lstrip": false,
|
422 |
+
"normalized": false,
|
423 |
+
"rstrip": false,
|
424 |
+
"single_word": false,
|
425 |
+
"special": true
|
426 |
+
},
|
427 |
+
"128053": {
|
428 |
+
"content": "<|reserved_special_token_45|>",
|
429 |
+
"lstrip": false,
|
430 |
+
"normalized": false,
|
431 |
+
"rstrip": false,
|
432 |
+
"single_word": false,
|
433 |
+
"special": true
|
434 |
+
},
|
435 |
+
"128054": {
|
436 |
+
"content": "<|reserved_special_token_46|>",
|
437 |
+
"lstrip": false,
|
438 |
+
"normalized": false,
|
439 |
+
"rstrip": false,
|
440 |
+
"single_word": false,
|
441 |
+
"special": true
|
442 |
+
},
|
443 |
+
"128055": {
|
444 |
+
"content": "<|reserved_special_token_47|>",
|
445 |
+
"lstrip": false,
|
446 |
+
"normalized": false,
|
447 |
+
"rstrip": false,
|
448 |
+
"single_word": false,
|
449 |
+
"special": true
|
450 |
+
},
|
451 |
+
"128056": {
|
452 |
+
"content": "<|reserved_special_token_48|>",
|
453 |
+
"lstrip": false,
|
454 |
+
"normalized": false,
|
455 |
+
"rstrip": false,
|
456 |
+
"single_word": false,
|
457 |
+
"special": true
|
458 |
+
},
|
459 |
+
"128057": {
|
460 |
+
"content": "<|reserved_special_token_49|>",
|
461 |
+
"lstrip": false,
|
462 |
+
"normalized": false,
|
463 |
+
"rstrip": false,
|
464 |
+
"single_word": false,
|
465 |
+
"special": true
|
466 |
+
},
|
467 |
+
"128058": {
|
468 |
+
"content": "<|reserved_special_token_50|>",
|
469 |
+
"lstrip": false,
|
470 |
+
"normalized": false,
|
471 |
+
"rstrip": false,
|
472 |
+
"single_word": false,
|
473 |
+
"special": true
|
474 |
+
},
|
475 |
+
"128059": {
|
476 |
+
"content": "<|reserved_special_token_51|>",
|
477 |
+
"lstrip": false,
|
478 |
+
"normalized": false,
|
479 |
+
"rstrip": false,
|
480 |
+
"single_word": false,
|
481 |
+
"special": true
|
482 |
+
},
|
483 |
+
"128060": {
|
484 |
+
"content": "<|reserved_special_token_52|>",
|
485 |
+
"lstrip": false,
|
486 |
+
"normalized": false,
|
487 |
+
"rstrip": false,
|
488 |
+
"single_word": false,
|
489 |
+
"special": true
|
490 |
+
},
|
491 |
+
"128061": {
|
492 |
+
"content": "<|reserved_special_token_53|>",
|
493 |
+
"lstrip": false,
|
494 |
+
"normalized": false,
|
495 |
+
"rstrip": false,
|
496 |
+
"single_word": false,
|
497 |
+
"special": true
|
498 |
+
},
|
499 |
+
"128062": {
|
500 |
+
"content": "<|reserved_special_token_54|>",
|
501 |
+
"lstrip": false,
|
502 |
+
"normalized": false,
|
503 |
+
"rstrip": false,
|
504 |
+
"single_word": false,
|
505 |
+
"special": true
|
506 |
+
},
|
507 |
+
"128063": {
|
508 |
+
"content": "<|reserved_special_token_55|>",
|
509 |
+
"lstrip": false,
|
510 |
+
"normalized": false,
|
511 |
+
"rstrip": false,
|
512 |
+
"single_word": false,
|
513 |
+
"special": true
|
514 |
+
},
|
515 |
+
"128064": {
|
516 |
+
"content": "<|reserved_special_token_56|>",
|
517 |
+
"lstrip": false,
|
518 |
+
"normalized": false,
|
519 |
+
"rstrip": false,
|
520 |
+
"single_word": false,
|
521 |
+
"special": true
|
522 |
+
},
|
523 |
+
"128065": {
|
524 |
+
"content": "<|reserved_special_token_57|>",
|
525 |
+
"lstrip": false,
|
526 |
+
"normalized": false,
|
527 |
+
"rstrip": false,
|
528 |
+
"single_word": false,
|
529 |
+
"special": true
|
530 |
+
},
|
531 |
+
"128066": {
|
532 |
+
"content": "<|reserved_special_token_58|>",
|
533 |
+
"lstrip": false,
|
534 |
+
"normalized": false,
|
535 |
+
"rstrip": false,
|
536 |
+
"single_word": false,
|
537 |
+
"special": true
|
538 |
+
},
|
539 |
+
"128067": {
|
540 |
+
"content": "<|reserved_special_token_59|>",
|
541 |
+
"lstrip": false,
|
542 |
+
"normalized": false,
|
543 |
+
"rstrip": false,
|
544 |
+
"single_word": false,
|
545 |
+
"special": true
|
546 |
+
},
|
547 |
+
"128068": {
|
548 |
+
"content": "<|reserved_special_token_60|>",
|
549 |
+
"lstrip": false,
|
550 |
+
"normalized": false,
|
551 |
+
"rstrip": false,
|
552 |
+
"single_word": false,
|
553 |
+
"special": true
|
554 |
+
},
|
555 |
+
"128069": {
|
556 |
+
"content": "<|reserved_special_token_61|>",
|
557 |
+
"lstrip": false,
|
558 |
+
"normalized": false,
|
559 |
+
"rstrip": false,
|
560 |
+
"single_word": false,
|
561 |
+
"special": true
|
562 |
+
},
|
563 |
+
"128070": {
|
564 |
+
"content": "<|reserved_special_token_62|>",
|
565 |
+
"lstrip": false,
|
566 |
+
"normalized": false,
|
567 |
+
"rstrip": false,
|
568 |
+
"single_word": false,
|
569 |
+
"special": true
|
570 |
+
},
|
571 |
+
"128071": {
|
572 |
+
"content": "<|reserved_special_token_63|>",
|
573 |
+
"lstrip": false,
|
574 |
+
"normalized": false,
|
575 |
+
"rstrip": false,
|
576 |
+
"single_word": false,
|
577 |
+
"special": true
|
578 |
+
},
|
579 |
+
"128072": {
|
580 |
+
"content": "<|reserved_special_token_64|>",
|
581 |
+
"lstrip": false,
|
582 |
+
"normalized": false,
|
583 |
+
"rstrip": false,
|
584 |
+
"single_word": false,
|
585 |
+
"special": true
|
586 |
+
},
|
587 |
+
"128073": {
|
588 |
+
"content": "<|reserved_special_token_65|>",
|
589 |
+
"lstrip": false,
|
590 |
+
"normalized": false,
|
591 |
+
"rstrip": false,
|
592 |
+
"single_word": false,
|
593 |
+
"special": true
|
594 |
+
},
|
595 |
+
"128074": {
|
596 |
+
"content": "<|reserved_special_token_66|>",
|
597 |
+
"lstrip": false,
|
598 |
+
"normalized": false,
|
599 |
+
"rstrip": false,
|
600 |
+
"single_word": false,
|
601 |
+
"special": true
|
602 |
+
},
|
603 |
+
"128075": {
|
604 |
+
"content": "<|reserved_special_token_67|>",
|
605 |
+
"lstrip": false,
|
606 |
+
"normalized": false,
|
607 |
+
"rstrip": false,
|
608 |
+
"single_word": false,
|
609 |
+
"special": true
|
610 |
+
},
|
611 |
+
"128076": {
|
612 |
+
"content": "<|reserved_special_token_68|>",
|
613 |
+
"lstrip": false,
|
614 |
+
"normalized": false,
|
615 |
+
"rstrip": false,
|
616 |
+
"single_word": false,
|
617 |
+
"special": true
|
618 |
+
},
|
619 |
+
"128077": {
|
620 |
+
"content": "<|reserved_special_token_69|>",
|
621 |
+
"lstrip": false,
|
622 |
+
"normalized": false,
|
623 |
+
"rstrip": false,
|
624 |
+
"single_word": false,
|
625 |
+
"special": true
|
626 |
+
},
|
627 |
+
"128078": {
|
628 |
+
"content": "<|reserved_special_token_70|>",
|
629 |
+
"lstrip": false,
|
630 |
+
"normalized": false,
|
631 |
+
"rstrip": false,
|
632 |
+
"single_word": false,
|
633 |
+
"special": true
|
634 |
+
},
|
635 |
+
"128079": {
|
636 |
+
"content": "<|reserved_special_token_71|>",
|
637 |
+
"lstrip": false,
|
638 |
+
"normalized": false,
|
639 |
+
"rstrip": false,
|
640 |
+
"single_word": false,
|
641 |
+
"special": true
|
642 |
+
},
|
643 |
+
"128080": {
|
644 |
+
"content": "<|reserved_special_token_72|>",
|
645 |
+
"lstrip": false,
|
646 |
+
"normalized": false,
|
647 |
+
"rstrip": false,
|
648 |
+
"single_word": false,
|
649 |
+
"special": true
|
650 |
+
},
|
651 |
+
"128081": {
|
652 |
+
"content": "<|reserved_special_token_73|>",
|
653 |
+
"lstrip": false,
|
654 |
+
"normalized": false,
|
655 |
+
"rstrip": false,
|
656 |
+
"single_word": false,
|
657 |
+
"special": true
|
658 |
+
},
|
659 |
+
"128082": {
|
660 |
+
"content": "<|reserved_special_token_74|>",
|
661 |
+
"lstrip": false,
|
662 |
+
"normalized": false,
|
663 |
+
"rstrip": false,
|
664 |
+
"single_word": false,
|
665 |
+
"special": true
|
666 |
+
},
|
667 |
+
"128083": {
|
668 |
+
"content": "<|reserved_special_token_75|>",
|
669 |
+
"lstrip": false,
|
670 |
+
"normalized": false,
|
671 |
+
"rstrip": false,
|
672 |
+
"single_word": false,
|
673 |
+
"special": true
|
674 |
+
},
|
675 |
+
"128084": {
|
676 |
+
"content": "<|reserved_special_token_76|>",
|
677 |
+
"lstrip": false,
|
678 |
+
"normalized": false,
|
679 |
+
"rstrip": false,
|
680 |
+
"single_word": false,
|
681 |
+
"special": true
|
682 |
+
},
|
683 |
+
"128085": {
|
684 |
+
"content": "<|reserved_special_token_77|>",
|
685 |
+
"lstrip": false,
|
686 |
+
"normalized": false,
|
687 |
+
"rstrip": false,
|
688 |
+
"single_word": false,
|
689 |
+
"special": true
|
690 |
+
},
|
691 |
+
"128086": {
|
692 |
+
"content": "<|reserved_special_token_78|>",
|
693 |
+
"lstrip": false,
|
694 |
+
"normalized": false,
|
695 |
+
"rstrip": false,
|
696 |
+
"single_word": false,
|
697 |
+
"special": true
|
698 |
+
},
|
699 |
+
"128087": {
|
700 |
+
"content": "<|reserved_special_token_79|>",
|
701 |
+
"lstrip": false,
|
702 |
+
"normalized": false,
|
703 |
+
"rstrip": false,
|
704 |
+
"single_word": false,
|
705 |
+
"special": true
|
706 |
+
},
|
707 |
+
"128088": {
|
708 |
+
"content": "<|reserved_special_token_80|>",
|
709 |
+
"lstrip": false,
|
710 |
+
"normalized": false,
|
711 |
+
"rstrip": false,
|
712 |
+
"single_word": false,
|
713 |
+
"special": true
|
714 |
+
},
|
715 |
+
"128089": {
|
716 |
+
"content": "<|reserved_special_token_81|>",
|
717 |
+
"lstrip": false,
|
718 |
+
"normalized": false,
|
719 |
+
"rstrip": false,
|
720 |
+
"single_word": false,
|
721 |
+
"special": true
|
722 |
+
},
|
723 |
+
"128090": {
|
724 |
+
"content": "<|reserved_special_token_82|>",
|
725 |
+
"lstrip": false,
|
726 |
+
"normalized": false,
|
727 |
+
"rstrip": false,
|
728 |
+
"single_word": false,
|
729 |
+
"special": true
|
730 |
+
},
|
731 |
+
"128091": {
|
732 |
+
"content": "<|reserved_special_token_83|>",
|
733 |
+
"lstrip": false,
|
734 |
+
"normalized": false,
|
735 |
+
"rstrip": false,
|
736 |
+
"single_word": false,
|
737 |
+
"special": true
|
738 |
+
},
|
739 |
+
"128092": {
|
740 |
+
"content": "<|reserved_special_token_84|>",
|
741 |
+
"lstrip": false,
|
742 |
+
"normalized": false,
|
743 |
+
"rstrip": false,
|
744 |
+
"single_word": false,
|
745 |
+
"special": true
|
746 |
+
},
|
747 |
+
"128093": {
|
748 |
+
"content": "<|reserved_special_token_85|>",
|
749 |
+
"lstrip": false,
|
750 |
+
"normalized": false,
|
751 |
+
"rstrip": false,
|
752 |
+
"single_word": false,
|
753 |
+
"special": true
|
754 |
+
},
|
755 |
+
"128094": {
|
756 |
+
"content": "<|reserved_special_token_86|>",
|
757 |
+
"lstrip": false,
|
758 |
+
"normalized": false,
|
759 |
+
"rstrip": false,
|
760 |
+
"single_word": false,
|
761 |
+
"special": true
|
762 |
+
},
|
763 |
+
"128095": {
|
764 |
+
"content": "<|reserved_special_token_87|>",
|
765 |
+
"lstrip": false,
|
766 |
+
"normalized": false,
|
767 |
+
"rstrip": false,
|
768 |
+
"single_word": false,
|
769 |
+
"special": true
|
770 |
+
},
|
771 |
+
"128096": {
|
772 |
+
"content": "<|reserved_special_token_88|>",
|
773 |
+
"lstrip": false,
|
774 |
+
"normalized": false,
|
775 |
+
"rstrip": false,
|
776 |
+
"single_word": false,
|
777 |
+
"special": true
|
778 |
+
},
|
779 |
+
"128097": {
|
780 |
+
"content": "<|reserved_special_token_89|>",
|
781 |
+
"lstrip": false,
|
782 |
+
"normalized": false,
|
783 |
+
"rstrip": false,
|
784 |
+
"single_word": false,
|
785 |
+
"special": true
|
786 |
+
},
|
787 |
+
"128098": {
|
788 |
+
"content": "<|reserved_special_token_90|>",
|
789 |
+
"lstrip": false,
|
790 |
+
"normalized": false,
|
791 |
+
"rstrip": false,
|
792 |
+
"single_word": false,
|
793 |
+
"special": true
|
794 |
+
},
|
795 |
+
"128099": {
|
796 |
+
"content": "<|reserved_special_token_91|>",
|
797 |
+
"lstrip": false,
|
798 |
+
"normalized": false,
|
799 |
+
"rstrip": false,
|
800 |
+
"single_word": false,
|
801 |
+
"special": true
|
802 |
+
},
|
803 |
+
"128100": {
|
804 |
+
"content": "<|reserved_special_token_92|>",
|
805 |
+
"lstrip": false,
|
806 |
+
"normalized": false,
|
807 |
+
"rstrip": false,
|
808 |
+
"single_word": false,
|
809 |
+
"special": true
|
810 |
+
},
|
811 |
+
"128101": {
|
812 |
+
"content": "<|reserved_special_token_93|>",
|
813 |
+
"lstrip": false,
|
814 |
+
"normalized": false,
|
815 |
+
"rstrip": false,
|
816 |
+
"single_word": false,
|
817 |
+
"special": true
|
818 |
+
},
|
819 |
+
"128102": {
|
820 |
+
"content": "<|reserved_special_token_94|>",
|
821 |
+
"lstrip": false,
|
822 |
+
"normalized": false,
|
823 |
+
"rstrip": false,
|
824 |
+
"single_word": false,
|
825 |
+
"special": true
|
826 |
+
},
|
827 |
+
"128103": {
|
828 |
+
"content": "<|reserved_special_token_95|>",
|
829 |
+
"lstrip": false,
|
830 |
+
"normalized": false,
|
831 |
+
"rstrip": false,
|
832 |
+
"single_word": false,
|
833 |
+
"special": true
|
834 |
+
},
|
835 |
+
"128104": {
|
836 |
+
"content": "<|reserved_special_token_96|>",
|
837 |
+
"lstrip": false,
|
838 |
+
"normalized": false,
|
839 |
+
"rstrip": false,
|
840 |
+
"single_word": false,
|
841 |
+
"special": true
|
842 |
+
},
|
843 |
+
"128105": {
|
844 |
+
"content": "<|reserved_special_token_97|>",
|
845 |
+
"lstrip": false,
|
846 |
+
"normalized": false,
|
847 |
+
"rstrip": false,
|
848 |
+
"single_word": false,
|
849 |
+
"special": true
|
850 |
+
},
|
851 |
+
"128106": {
|
852 |
+
"content": "<|reserved_special_token_98|>",
|
853 |
+
"lstrip": false,
|
854 |
+
"normalized": false,
|
855 |
+
"rstrip": false,
|
856 |
+
"single_word": false,
|
857 |
+
"special": true
|
858 |
+
},
|
859 |
+
"128107": {
|
860 |
+
"content": "<|reserved_special_token_99|>",
|
861 |
+
"lstrip": false,
|
862 |
+
"normalized": false,
|
863 |
+
"rstrip": false,
|
864 |
+
"single_word": false,
|
865 |
+
"special": true
|
866 |
+
},
|
867 |
+
"128108": {
|
868 |
+
"content": "<|reserved_special_token_100|>",
|
869 |
+
"lstrip": false,
|
870 |
+
"normalized": false,
|
871 |
+
"rstrip": false,
|
872 |
+
"single_word": false,
|
873 |
+
"special": true
|
874 |
+
},
|
875 |
+
"128109": {
|
876 |
+
"content": "<|reserved_special_token_101|>",
|
877 |
+
"lstrip": false,
|
878 |
+
"normalized": false,
|
879 |
+
"rstrip": false,
|
880 |
+
"single_word": false,
|
881 |
+
"special": true
|
882 |
+
},
|
883 |
+
"128110": {
|
884 |
+
"content": "<|reserved_special_token_102|>",
|
885 |
+
"lstrip": false,
|
886 |
+
"normalized": false,
|
887 |
+
"rstrip": false,
|
888 |
+
"single_word": false,
|
889 |
+
"special": true
|
890 |
+
},
|
891 |
+
"128111": {
|
892 |
+
"content": "<|reserved_special_token_103|>",
|
893 |
+
"lstrip": false,
|
894 |
+
"normalized": false,
|
895 |
+
"rstrip": false,
|
896 |
+
"single_word": false,
|
897 |
+
"special": true
|
898 |
+
},
|
899 |
+
"128112": {
|
900 |
+
"content": "<|reserved_special_token_104|>",
|
901 |
+
"lstrip": false,
|
902 |
+
"normalized": false,
|
903 |
+
"rstrip": false,
|
904 |
+
"single_word": false,
|
905 |
+
"special": true
|
906 |
+
},
|
907 |
+
"128113": {
|
908 |
+
"content": "<|reserved_special_token_105|>",
|
909 |
+
"lstrip": false,
|
910 |
+
"normalized": false,
|
911 |
+
"rstrip": false,
|
912 |
+
"single_word": false,
|
913 |
+
"special": true
|
914 |
+
},
|
915 |
+
"128114": {
|
916 |
+
"content": "<|reserved_special_token_106|>",
|
917 |
+
"lstrip": false,
|
918 |
+
"normalized": false,
|
919 |
+
"rstrip": false,
|
920 |
+
"single_word": false,
|
921 |
+
"special": true
|
922 |
+
},
|
923 |
+
"128115": {
|
924 |
+
"content": "<|reserved_special_token_107|>",
|
925 |
+
"lstrip": false,
|
926 |
+
"normalized": false,
|
927 |
+
"rstrip": false,
|
928 |
+
"single_word": false,
|
929 |
+
"special": true
|
930 |
+
},
|
931 |
+
"128116": {
|
932 |
+
"content": "<|reserved_special_token_108|>",
|
933 |
+
"lstrip": false,
|
934 |
+
"normalized": false,
|
935 |
+
"rstrip": false,
|
936 |
+
"single_word": false,
|
937 |
+
"special": true
|
938 |
+
},
|
939 |
+
"128117": {
|
940 |
+
"content": "<|reserved_special_token_109|>",
|
941 |
+
"lstrip": false,
|
942 |
+
"normalized": false,
|
943 |
+
"rstrip": false,
|
944 |
+
"single_word": false,
|
945 |
+
"special": true
|
946 |
+
},
|
947 |
+
"128118": {
|
948 |
+
"content": "<|reserved_special_token_110|>",
|
949 |
+
"lstrip": false,
|
950 |
+
"normalized": false,
|
951 |
+
"rstrip": false,
|
952 |
+
"single_word": false,
|
953 |
+
"special": true
|
954 |
+
},
|
955 |
+
"128119": {
|
956 |
+
"content": "<|reserved_special_token_111|>",
|
957 |
+
"lstrip": false,
|
958 |
+
"normalized": false,
|
959 |
+
"rstrip": false,
|
960 |
+
"single_word": false,
|
961 |
+
"special": true
|
962 |
+
},
|
963 |
+
"128120": {
|
964 |
+
"content": "<|reserved_special_token_112|>",
|
965 |
+
"lstrip": false,
|
966 |
+
"normalized": false,
|
967 |
+
"rstrip": false,
|
968 |
+
"single_word": false,
|
969 |
+
"special": true
|
970 |
+
},
|
971 |
+
"128121": {
|
972 |
+
"content": "<|reserved_special_token_113|>",
|
973 |
+
"lstrip": false,
|
974 |
+
"normalized": false,
|
975 |
+
"rstrip": false,
|
976 |
+
"single_word": false,
|
977 |
+
"special": true
|
978 |
+
},
|
979 |
+
"128122": {
|
980 |
+
"content": "<|reserved_special_token_114|>",
|
981 |
+
"lstrip": false,
|
982 |
+
"normalized": false,
|
983 |
+
"rstrip": false,
|
984 |
+
"single_word": false,
|
985 |
+
"special": true
|
986 |
+
},
|
987 |
+
"128123": {
|
988 |
+
"content": "<|reserved_special_token_115|>",
|
989 |
+
"lstrip": false,
|
990 |
+
"normalized": false,
|
991 |
+
"rstrip": false,
|
992 |
+
"single_word": false,
|
993 |
+
"special": true
|
994 |
+
},
|
995 |
+
"128124": {
|
996 |
+
"content": "<|reserved_special_token_116|>",
|
997 |
+
"lstrip": false,
|
998 |
+
"normalized": false,
|
999 |
+
"rstrip": false,
|
1000 |
+
"single_word": false,
|
1001 |
+
"special": true
|
1002 |
+
},
|
1003 |
+
"128125": {
|
1004 |
+
"content": "<|reserved_special_token_117|>",
|
1005 |
+
"lstrip": false,
|
1006 |
+
"normalized": false,
|
1007 |
+
"rstrip": false,
|
1008 |
+
"single_word": false,
|
1009 |
+
"special": true
|
1010 |
+
},
|
1011 |
+
"128126": {
|
1012 |
+
"content": "<|reserved_special_token_118|>",
|
1013 |
+
"lstrip": false,
|
1014 |
+
"normalized": false,
|
1015 |
+
"rstrip": false,
|
1016 |
+
"single_word": false,
|
1017 |
+
"special": true
|
1018 |
+
},
|
1019 |
+
"128127": {
|
1020 |
+
"content": "<|reserved_special_token_119|>",
|
1021 |
+
"lstrip": false,
|
1022 |
+
"normalized": false,
|
1023 |
+
"rstrip": false,
|
1024 |
+
"single_word": false,
|
1025 |
+
"special": true
|
1026 |
+
},
|
1027 |
+
"128128": {
|
1028 |
+
"content": "<|reserved_special_token_120|>",
|
1029 |
+
"lstrip": false,
|
1030 |
+
"normalized": false,
|
1031 |
+
"rstrip": false,
|
1032 |
+
"single_word": false,
|
1033 |
+
"special": true
|
1034 |
+
},
|
1035 |
+
"128129": {
|
1036 |
+
"content": "<|reserved_special_token_121|>",
|
1037 |
+
"lstrip": false,
|
1038 |
+
"normalized": false,
|
1039 |
+
"rstrip": false,
|
1040 |
+
"single_word": false,
|
1041 |
+
"special": true
|
1042 |
+
},
|
1043 |
+
"128130": {
|
1044 |
+
"content": "<|reserved_special_token_122|>",
|
1045 |
+
"lstrip": false,
|
1046 |
+
"normalized": false,
|
1047 |
+
"rstrip": false,
|
1048 |
+
"single_word": false,
|
1049 |
+
"special": true
|
1050 |
+
},
|
1051 |
+
"128131": {
|
1052 |
+
"content": "<|reserved_special_token_123|>",
|
1053 |
+
"lstrip": false,
|
1054 |
+
"normalized": false,
|
1055 |
+
"rstrip": false,
|
1056 |
+
"single_word": false,
|
1057 |
+
"special": true
|
1058 |
+
},
|
1059 |
+
"128132": {
|
1060 |
+
"content": "<|reserved_special_token_124|>",
|
1061 |
+
"lstrip": false,
|
1062 |
+
"normalized": false,
|
1063 |
+
"rstrip": false,
|
1064 |
+
"single_word": false,
|
1065 |
+
"special": true
|
1066 |
+
},
|
1067 |
+
"128133": {
|
1068 |
+
"content": "<|reserved_special_token_125|>",
|
1069 |
+
"lstrip": false,
|
1070 |
+
"normalized": false,
|
1071 |
+
"rstrip": false,
|
1072 |
+
"single_word": false,
|
1073 |
+
"special": true
|
1074 |
+
},
|
1075 |
+
"128134": {
|
1076 |
+
"content": "<|reserved_special_token_126|>",
|
1077 |
+
"lstrip": false,
|
1078 |
+
"normalized": false,
|
1079 |
+
"rstrip": false,
|
1080 |
+
"single_word": false,
|
1081 |
+
"special": true
|
1082 |
+
},
|
1083 |
+
"128135": {
|
1084 |
+
"content": "<|reserved_special_token_127|>",
|
1085 |
+
"lstrip": false,
|
1086 |
+
"normalized": false,
|
1087 |
+
"rstrip": false,
|
1088 |
+
"single_word": false,
|
1089 |
+
"special": true
|
1090 |
+
},
|
1091 |
+
"128136": {
|
1092 |
+
"content": "<|reserved_special_token_128|>",
|
1093 |
+
"lstrip": false,
|
1094 |
+
"normalized": false,
|
1095 |
+
"rstrip": false,
|
1096 |
+
"single_word": false,
|
1097 |
+
"special": true
|
1098 |
+
},
|
1099 |
+
"128137": {
|
1100 |
+
"content": "<|reserved_special_token_129|>",
|
1101 |
+
"lstrip": false,
|
1102 |
+
"normalized": false,
|
1103 |
+
"rstrip": false,
|
1104 |
+
"single_word": false,
|
1105 |
+
"special": true
|
1106 |
+
},
|
1107 |
+
"128138": {
|
1108 |
+
"content": "<|reserved_special_token_130|>",
|
1109 |
+
"lstrip": false,
|
1110 |
+
"normalized": false,
|
1111 |
+
"rstrip": false,
|
1112 |
+
"single_word": false,
|
1113 |
+
"special": true
|
1114 |
+
},
|
1115 |
+
"128139": {
|
1116 |
+
"content": "<|reserved_special_token_131|>",
|
1117 |
+
"lstrip": false,
|
1118 |
+
"normalized": false,
|
1119 |
+
"rstrip": false,
|
1120 |
+
"single_word": false,
|
1121 |
+
"special": true
|
1122 |
+
},
|
1123 |
+
"128140": {
|
1124 |
+
"content": "<|reserved_special_token_132|>",
|
1125 |
+
"lstrip": false,
|
1126 |
+
"normalized": false,
|
1127 |
+
"rstrip": false,
|
1128 |
+
"single_word": false,
|
1129 |
+
"special": true
|
1130 |
+
},
|
1131 |
+
"128141": {
|
1132 |
+
"content": "<|reserved_special_token_133|>",
|
1133 |
+
"lstrip": false,
|
1134 |
+
"normalized": false,
|
1135 |
+
"rstrip": false,
|
1136 |
+
"single_word": false,
|
1137 |
+
"special": true
|
1138 |
+
},
|
1139 |
+
"128142": {
|
1140 |
+
"content": "<|reserved_special_token_134|>",
|
1141 |
+
"lstrip": false,
|
1142 |
+
"normalized": false,
|
1143 |
+
"rstrip": false,
|
1144 |
+
"single_word": false,
|
1145 |
+
"special": true
|
1146 |
+
},
|
1147 |
+
"128143": {
|
1148 |
+
"content": "<|reserved_special_token_135|>",
|
1149 |
+
"lstrip": false,
|
1150 |
+
"normalized": false,
|
1151 |
+
"rstrip": false,
|
1152 |
+
"single_word": false,
|
1153 |
+
"special": true
|
1154 |
+
},
|
1155 |
+
"128144": {
|
1156 |
+
"content": "<|reserved_special_token_136|>",
|
1157 |
+
"lstrip": false,
|
1158 |
+
"normalized": false,
|
1159 |
+
"rstrip": false,
|
1160 |
+
"single_word": false,
|
1161 |
+
"special": true
|
1162 |
+
},
|
1163 |
+
"128145": {
|
1164 |
+
"content": "<|reserved_special_token_137|>",
|
1165 |
+
"lstrip": false,
|
1166 |
+
"normalized": false,
|
1167 |
+
"rstrip": false,
|
1168 |
+
"single_word": false,
|
1169 |
+
"special": true
|
1170 |
+
},
|
1171 |
+
"128146": {
|
1172 |
+
"content": "<|reserved_special_token_138|>",
|
1173 |
+
"lstrip": false,
|
1174 |
+
"normalized": false,
|
1175 |
+
"rstrip": false,
|
1176 |
+
"single_word": false,
|
1177 |
+
"special": true
|
1178 |
+
},
|
1179 |
+
"128147": {
|
1180 |
+
"content": "<|reserved_special_token_139|>",
|
1181 |
+
"lstrip": false,
|
1182 |
+
"normalized": false,
|
1183 |
+
"rstrip": false,
|
1184 |
+
"single_word": false,
|
1185 |
+
"special": true
|
1186 |
+
},
|
1187 |
+
"128148": {
|
1188 |
+
"content": "<|reserved_special_token_140|>",
|
1189 |
+
"lstrip": false,
|
1190 |
+
"normalized": false,
|
1191 |
+
"rstrip": false,
|
1192 |
+
"single_word": false,
|
1193 |
+
"special": true
|
1194 |
+
},
|
1195 |
+
"128149": {
|
1196 |
+
"content": "<|reserved_special_token_141|>",
|
1197 |
+
"lstrip": false,
|
1198 |
+
"normalized": false,
|
1199 |
+
"rstrip": false,
|
1200 |
+
"single_word": false,
|
1201 |
+
"special": true
|
1202 |
+
},
|
1203 |
+
"128150": {
|
1204 |
+
"content": "<|reserved_special_token_142|>",
|
1205 |
+
"lstrip": false,
|
1206 |
+
"normalized": false,
|
1207 |
+
"rstrip": false,
|
1208 |
+
"single_word": false,
|
1209 |
+
"special": true
|
1210 |
+
},
|
1211 |
+
"128151": {
|
1212 |
+
"content": "<|reserved_special_token_143|>",
|
1213 |
+
"lstrip": false,
|
1214 |
+
"normalized": false,
|
1215 |
+
"rstrip": false,
|
1216 |
+
"single_word": false,
|
1217 |
+
"special": true
|
1218 |
+
},
|
1219 |
+
"128152": {
|
1220 |
+
"content": "<|reserved_special_token_144|>",
|
1221 |
+
"lstrip": false,
|
1222 |
+
"normalized": false,
|
1223 |
+
"rstrip": false,
|
1224 |
+
"single_word": false,
|
1225 |
+
"special": true
|
1226 |
+
},
|
1227 |
+
"128153": {
|
1228 |
+
"content": "<|reserved_special_token_145|>",
|
1229 |
+
"lstrip": false,
|
1230 |
+
"normalized": false,
|
1231 |
+
"rstrip": false,
|
1232 |
+
"single_word": false,
|
1233 |
+
"special": true
|
1234 |
+
},
|
1235 |
+
"128154": {
|
1236 |
+
"content": "<|reserved_special_token_146|>",
|
1237 |
+
"lstrip": false,
|
1238 |
+
"normalized": false,
|
1239 |
+
"rstrip": false,
|
1240 |
+
"single_word": false,
|
1241 |
+
"special": true
|
1242 |
+
},
|
1243 |
+
"128155": {
|
1244 |
+
"content": "<|reserved_special_token_147|>",
|
1245 |
+
"lstrip": false,
|
1246 |
+
"normalized": false,
|
1247 |
+
"rstrip": false,
|
1248 |
+
"single_word": false,
|
1249 |
+
"special": true
|
1250 |
+
},
|
1251 |
+
"128156": {
|
1252 |
+
"content": "<|reserved_special_token_148|>",
|
1253 |
+
"lstrip": false,
|
1254 |
+
"normalized": false,
|
1255 |
+
"rstrip": false,
|
1256 |
+
"single_word": false,
|
1257 |
+
"special": true
|
1258 |
+
},
|
1259 |
+
"128157": {
|
1260 |
+
"content": "<|reserved_special_token_149|>",
|
1261 |
+
"lstrip": false,
|
1262 |
+
"normalized": false,
|
1263 |
+
"rstrip": false,
|
1264 |
+
"single_word": false,
|
1265 |
+
"special": true
|
1266 |
+
},
|
1267 |
+
"128158": {
|
1268 |
+
"content": "<|reserved_special_token_150|>",
|
1269 |
+
"lstrip": false,
|
1270 |
+
"normalized": false,
|
1271 |
+
"rstrip": false,
|
1272 |
+
"single_word": false,
|
1273 |
+
"special": true
|
1274 |
+
},
|
1275 |
+
"128159": {
|
1276 |
+
"content": "<|reserved_special_token_151|>",
|
1277 |
+
"lstrip": false,
|
1278 |
+
"normalized": false,
|
1279 |
+
"rstrip": false,
|
1280 |
+
"single_word": false,
|
1281 |
+
"special": true
|
1282 |
+
},
|
1283 |
+
"128160": {
|
1284 |
+
"content": "<|reserved_special_token_152|>",
|
1285 |
+
"lstrip": false,
|
1286 |
+
"normalized": false,
|
1287 |
+
"rstrip": false,
|
1288 |
+
"single_word": false,
|
1289 |
+
"special": true
|
1290 |
+
},
|
1291 |
+
"128161": {
|
1292 |
+
"content": "<|reserved_special_token_153|>",
|
1293 |
+
"lstrip": false,
|
1294 |
+
"normalized": false,
|
1295 |
+
"rstrip": false,
|
1296 |
+
"single_word": false,
|
1297 |
+
"special": true
|
1298 |
+
},
|
1299 |
+
"128162": {
|
1300 |
+
"content": "<|reserved_special_token_154|>",
|
1301 |
+
"lstrip": false,
|
1302 |
+
"normalized": false,
|
1303 |
+
"rstrip": false,
|
1304 |
+
"single_word": false,
|
1305 |
+
"special": true
|
1306 |
+
},
|
1307 |
+
"128163": {
|
1308 |
+
"content": "<|reserved_special_token_155|>",
|
1309 |
+
"lstrip": false,
|
1310 |
+
"normalized": false,
|
1311 |
+
"rstrip": false,
|
1312 |
+
"single_word": false,
|
1313 |
+
"special": true
|
1314 |
+
},
|
1315 |
+
"128164": {
|
1316 |
+
"content": "<|reserved_special_token_156|>",
|
1317 |
+
"lstrip": false,
|
1318 |
+
"normalized": false,
|
1319 |
+
"rstrip": false,
|
1320 |
+
"single_word": false,
|
1321 |
+
"special": true
|
1322 |
+
},
|
1323 |
+
"128165": {
|
1324 |
+
"content": "<|reserved_special_token_157|>",
|
1325 |
+
"lstrip": false,
|
1326 |
+
"normalized": false,
|
1327 |
+
"rstrip": false,
|
1328 |
+
"single_word": false,
|
1329 |
+
"special": true
|
1330 |
+
},
|
1331 |
+
"128166": {
|
1332 |
+
"content": "<|reserved_special_token_158|>",
|
1333 |
+
"lstrip": false,
|
1334 |
+
"normalized": false,
|
1335 |
+
"rstrip": false,
|
1336 |
+
"single_word": false,
|
1337 |
+
"special": true
|
1338 |
+
},
|
1339 |
+
"128167": {
|
1340 |
+
"content": "<|reserved_special_token_159|>",
|
1341 |
+
"lstrip": false,
|
1342 |
+
"normalized": false,
|
1343 |
+
"rstrip": false,
|
1344 |
+
"single_word": false,
|
1345 |
+
"special": true
|
1346 |
+
},
|
1347 |
+
"128168": {
|
1348 |
+
"content": "<|reserved_special_token_160|>",
|
1349 |
+
"lstrip": false,
|
1350 |
+
"normalized": false,
|
1351 |
+
"rstrip": false,
|
1352 |
+
"single_word": false,
|
1353 |
+
"special": true
|
1354 |
+
},
|
1355 |
+
"128169": {
|
1356 |
+
"content": "<|reserved_special_token_161|>",
|
1357 |
+
"lstrip": false,
|
1358 |
+
"normalized": false,
|
1359 |
+
"rstrip": false,
|
1360 |
+
"single_word": false,
|
1361 |
+
"special": true
|
1362 |
+
},
|
1363 |
+
"128170": {
|
1364 |
+
"content": "<|reserved_special_token_162|>",
|
1365 |
+
"lstrip": false,
|
1366 |
+
"normalized": false,
|
1367 |
+
"rstrip": false,
|
1368 |
+
"single_word": false,
|
1369 |
+
"special": true
|
1370 |
+
},
|
1371 |
+
"128171": {
|
1372 |
+
"content": "<|reserved_special_token_163|>",
|
1373 |
+
"lstrip": false,
|
1374 |
+
"normalized": false,
|
1375 |
+
"rstrip": false,
|
1376 |
+
"single_word": false,
|
1377 |
+
"special": true
|
1378 |
+
},
|
1379 |
+
"128172": {
|
1380 |
+
"content": "<|reserved_special_token_164|>",
|
1381 |
+
"lstrip": false,
|
1382 |
+
"normalized": false,
|
1383 |
+
"rstrip": false,
|
1384 |
+
"single_word": false,
|
1385 |
+
"special": true
|
1386 |
+
},
|
1387 |
+
"128173": {
|
1388 |
+
"content": "<|reserved_special_token_165|>",
|
1389 |
+
"lstrip": false,
|
1390 |
+
"normalized": false,
|
1391 |
+
"rstrip": false,
|
1392 |
+
"single_word": false,
|
1393 |
+
"special": true
|
1394 |
+
},
|
1395 |
+
"128174": {
|
1396 |
+
"content": "<|reserved_special_token_166|>",
|
1397 |
+
"lstrip": false,
|
1398 |
+
"normalized": false,
|
1399 |
+
"rstrip": false,
|
1400 |
+
"single_word": false,
|
1401 |
+
"special": true
|
1402 |
+
},
|
1403 |
+
"128175": {
|
1404 |
+
"content": "<|reserved_special_token_167|>",
|
1405 |
+
"lstrip": false,
|
1406 |
+
"normalized": false,
|
1407 |
+
"rstrip": false,
|
1408 |
+
"single_word": false,
|
1409 |
+
"special": true
|
1410 |
+
},
|
1411 |
+
"128176": {
|
1412 |
+
"content": "<|reserved_special_token_168|>",
|
1413 |
+
"lstrip": false,
|
1414 |
+
"normalized": false,
|
1415 |
+
"rstrip": false,
|
1416 |
+
"single_word": false,
|
1417 |
+
"special": true
|
1418 |
+
},
|
1419 |
+
"128177": {
|
1420 |
+
"content": "<|reserved_special_token_169|>",
|
1421 |
+
"lstrip": false,
|
1422 |
+
"normalized": false,
|
1423 |
+
"rstrip": false,
|
1424 |
+
"single_word": false,
|
1425 |
+
"special": true
|
1426 |
+
},
|
1427 |
+
"128178": {
|
1428 |
+
"content": "<|reserved_special_token_170|>",
|
1429 |
+
"lstrip": false,
|
1430 |
+
"normalized": false,
|
1431 |
+
"rstrip": false,
|
1432 |
+
"single_word": false,
|
1433 |
+
"special": true
|
1434 |
+
},
|
1435 |
+
"128179": {
|
1436 |
+
"content": "<|reserved_special_token_171|>",
|
1437 |
+
"lstrip": false,
|
1438 |
+
"normalized": false,
|
1439 |
+
"rstrip": false,
|
1440 |
+
"single_word": false,
|
1441 |
+
"special": true
|
1442 |
+
},
|
1443 |
+
"128180": {
|
1444 |
+
"content": "<|reserved_special_token_172|>",
|
1445 |
+
"lstrip": false,
|
1446 |
+
"normalized": false,
|
1447 |
+
"rstrip": false,
|
1448 |
+
"single_word": false,
|
1449 |
+
"special": true
|
1450 |
+
},
|
1451 |
+
"128181": {
|
1452 |
+
"content": "<|reserved_special_token_173|>",
|
1453 |
+
"lstrip": false,
|
1454 |
+
"normalized": false,
|
1455 |
+
"rstrip": false,
|
1456 |
+
"single_word": false,
|
1457 |
+
"special": true
|
1458 |
+
},
|
1459 |
+
"128182": {
|
1460 |
+
"content": "<|reserved_special_token_174|>",
|
1461 |
+
"lstrip": false,
|
1462 |
+
"normalized": false,
|
1463 |
+
"rstrip": false,
|
1464 |
+
"single_word": false,
|
1465 |
+
"special": true
|
1466 |
+
},
|
1467 |
+
"128183": {
|
1468 |
+
"content": "<|reserved_special_token_175|>",
|
1469 |
+
"lstrip": false,
|
1470 |
+
"normalized": false,
|
1471 |
+
"rstrip": false,
|
1472 |
+
"single_word": false,
|
1473 |
+
"special": true
|
1474 |
+
},
|
1475 |
+
"128184": {
|
1476 |
+
"content": "<|reserved_special_token_176|>",
|
1477 |
+
"lstrip": false,
|
1478 |
+
"normalized": false,
|
1479 |
+
"rstrip": false,
|
1480 |
+
"single_word": false,
|
1481 |
+
"special": true
|
1482 |
+
},
|
1483 |
+
"128185": {
|
1484 |
+
"content": "<|reserved_special_token_177|>",
|
1485 |
+
"lstrip": false,
|
1486 |
+
"normalized": false,
|
1487 |
+
"rstrip": false,
|
1488 |
+
"single_word": false,
|
1489 |
+
"special": true
|
1490 |
+
},
|
1491 |
+
"128186": {
|
1492 |
+
"content": "<|reserved_special_token_178|>",
|
1493 |
+
"lstrip": false,
|
1494 |
+
"normalized": false,
|
1495 |
+
"rstrip": false,
|
1496 |
+
"single_word": false,
|
1497 |
+
"special": true
|
1498 |
+
},
|
1499 |
+
"128187": {
|
1500 |
+
"content": "<|reserved_special_token_179|>",
|
1501 |
+
"lstrip": false,
|
1502 |
+
"normalized": false,
|
1503 |
+
"rstrip": false,
|
1504 |
+
"single_word": false,
|
1505 |
+
"special": true
|
1506 |
+
},
|
1507 |
+
"128188": {
|
1508 |
+
"content": "<|reserved_special_token_180|>",
|
1509 |
+
"lstrip": false,
|
1510 |
+
"normalized": false,
|
1511 |
+
"rstrip": false,
|
1512 |
+
"single_word": false,
|
1513 |
+
"special": true
|
1514 |
+
},
|
1515 |
+
"128189": {
|
1516 |
+
"content": "<|reserved_special_token_181|>",
|
1517 |
+
"lstrip": false,
|
1518 |
+
"normalized": false,
|
1519 |
+
"rstrip": false,
|
1520 |
+
"single_word": false,
|
1521 |
+
"special": true
|
1522 |
+
},
|
1523 |
+
"128190": {
|
1524 |
+
"content": "<|reserved_special_token_182|>",
|
1525 |
+
"lstrip": false,
|
1526 |
+
"normalized": false,
|
1527 |
+
"rstrip": false,
|
1528 |
+
"single_word": false,
|
1529 |
+
"special": true
|
1530 |
+
},
|
1531 |
+
"128191": {
|
1532 |
+
"content": "<|reserved_special_token_183|>",
|
1533 |
+
"lstrip": false,
|
1534 |
+
"normalized": false,
|
1535 |
+
"rstrip": false,
|
1536 |
+
"single_word": false,
|
1537 |
+
"special": true
|
1538 |
+
},
|
1539 |
+
"128192": {
|
1540 |
+
"content": "<|reserved_special_token_184|>",
|
1541 |
+
"lstrip": false,
|
1542 |
+
"normalized": false,
|
1543 |
+
"rstrip": false,
|
1544 |
+
"single_word": false,
|
1545 |
+
"special": true
|
1546 |
+
},
|
1547 |
+
"128193": {
|
1548 |
+
"content": "<|reserved_special_token_185|>",
|
1549 |
+
"lstrip": false,
|
1550 |
+
"normalized": false,
|
1551 |
+
"rstrip": false,
|
1552 |
+
"single_word": false,
|
1553 |
+
"special": true
|
1554 |
+
},
|
1555 |
+
"128194": {
|
1556 |
+
"content": "<|reserved_special_token_186|>",
|
1557 |
+
"lstrip": false,
|
1558 |
+
"normalized": false,
|
1559 |
+
"rstrip": false,
|
1560 |
+
"single_word": false,
|
1561 |
+
"special": true
|
1562 |
+
},
|
1563 |
+
"128195": {
|
1564 |
+
"content": "<|reserved_special_token_187|>",
|
1565 |
+
"lstrip": false,
|
1566 |
+
"normalized": false,
|
1567 |
+
"rstrip": false,
|
1568 |
+
"single_word": false,
|
1569 |
+
"special": true
|
1570 |
+
},
|
1571 |
+
"128196": {
|
1572 |
+
"content": "<|reserved_special_token_188|>",
|
1573 |
+
"lstrip": false,
|
1574 |
+
"normalized": false,
|
1575 |
+
"rstrip": false,
|
1576 |
+
"single_word": false,
|
1577 |
+
"special": true
|
1578 |
+
},
|
1579 |
+
"128197": {
|
1580 |
+
"content": "<|reserved_special_token_189|>",
|
1581 |
+
"lstrip": false,
|
1582 |
+
"normalized": false,
|
1583 |
+
"rstrip": false,
|
1584 |
+
"single_word": false,
|
1585 |
+
"special": true
|
1586 |
+
},
|
1587 |
+
"128198": {
|
1588 |
+
"content": "<|reserved_special_token_190|>",
|
1589 |
+
"lstrip": false,
|
1590 |
+
"normalized": false,
|
1591 |
+
"rstrip": false,
|
1592 |
+
"single_word": false,
|
1593 |
+
"special": true
|
1594 |
+
},
|
1595 |
+
"128199": {
|
1596 |
+
"content": "<|reserved_special_token_191|>",
|
1597 |
+
"lstrip": false,
|
1598 |
+
"normalized": false,
|
1599 |
+
"rstrip": false,
|
1600 |
+
"single_word": false,
|
1601 |
+
"special": true
|
1602 |
+
},
|
1603 |
+
"128200": {
|
1604 |
+
"content": "<|reserved_special_token_192|>",
|
1605 |
+
"lstrip": false,
|
1606 |
+
"normalized": false,
|
1607 |
+
"rstrip": false,
|
1608 |
+
"single_word": false,
|
1609 |
+
"special": true
|
1610 |
+
},
|
1611 |
+
"128201": {
|
1612 |
+
"content": "<|reserved_special_token_193|>",
|
1613 |
+
"lstrip": false,
|
1614 |
+
"normalized": false,
|
1615 |
+
"rstrip": false,
|
1616 |
+
"single_word": false,
|
1617 |
+
"special": true
|
1618 |
+
},
|
1619 |
+
"128202": {
|
1620 |
+
"content": "<|reserved_special_token_194|>",
|
1621 |
+
"lstrip": false,
|
1622 |
+
"normalized": false,
|
1623 |
+
"rstrip": false,
|
1624 |
+
"single_word": false,
|
1625 |
+
"special": true
|
1626 |
+
},
|
1627 |
+
"128203": {
|
1628 |
+
"content": "<|reserved_special_token_195|>",
|
1629 |
+
"lstrip": false,
|
1630 |
+
"normalized": false,
|
1631 |
+
"rstrip": false,
|
1632 |
+
"single_word": false,
|
1633 |
+
"special": true
|
1634 |
+
},
|
1635 |
+
"128204": {
|
1636 |
+
"content": "<|reserved_special_token_196|>",
|
1637 |
+
"lstrip": false,
|
1638 |
+
"normalized": false,
|
1639 |
+
"rstrip": false,
|
1640 |
+
"single_word": false,
|
1641 |
+
"special": true
|
1642 |
+
},
|
1643 |
+
"128205": {
|
1644 |
+
"content": "<|reserved_special_token_197|>",
|
1645 |
+
"lstrip": false,
|
1646 |
+
"normalized": false,
|
1647 |
+
"rstrip": false,
|
1648 |
+
"single_word": false,
|
1649 |
+
"special": true
|
1650 |
+
},
|
1651 |
+
"128206": {
|
1652 |
+
"content": "<|reserved_special_token_198|>",
|
1653 |
+
"lstrip": false,
|
1654 |
+
"normalized": false,
|
1655 |
+
"rstrip": false,
|
1656 |
+
"single_word": false,
|
1657 |
+
"special": true
|
1658 |
+
},
|
1659 |
+
"128207": {
|
1660 |
+
"content": "<|reserved_special_token_199|>",
|
1661 |
+
"lstrip": false,
|
1662 |
+
"normalized": false,
|
1663 |
+
"rstrip": false,
|
1664 |
+
"single_word": false,
|
1665 |
+
"special": true
|
1666 |
+
},
|
1667 |
+
"128208": {
|
1668 |
+
"content": "<|reserved_special_token_200|>",
|
1669 |
+
"lstrip": false,
|
1670 |
+
"normalized": false,
|
1671 |
+
"rstrip": false,
|
1672 |
+
"single_word": false,
|
1673 |
+
"special": true
|
1674 |
+
},
|
1675 |
+
"128209": {
|
1676 |
+
"content": "<|reserved_special_token_201|>",
|
1677 |
+
"lstrip": false,
|
1678 |
+
"normalized": false,
|
1679 |
+
"rstrip": false,
|
1680 |
+
"single_word": false,
|
1681 |
+
"special": true
|
1682 |
+
},
|
1683 |
+
"128210": {
|
1684 |
+
"content": "<|reserved_special_token_202|>",
|
1685 |
+
"lstrip": false,
|
1686 |
+
"normalized": false,
|
1687 |
+
"rstrip": false,
|
1688 |
+
"single_word": false,
|
1689 |
+
"special": true
|
1690 |
+
},
|
1691 |
+
"128211": {
|
1692 |
+
"content": "<|reserved_special_token_203|>",
|
1693 |
+
"lstrip": false,
|
1694 |
+
"normalized": false,
|
1695 |
+
"rstrip": false,
|
1696 |
+
"single_word": false,
|
1697 |
+
"special": true
|
1698 |
+
},
|
1699 |
+
"128212": {
|
1700 |
+
"content": "<|reserved_special_token_204|>",
|
1701 |
+
"lstrip": false,
|
1702 |
+
"normalized": false,
|
1703 |
+
"rstrip": false,
|
1704 |
+
"single_word": false,
|
1705 |
+
"special": true
|
1706 |
+
},
|
1707 |
+
"128213": {
|
1708 |
+
"content": "<|reserved_special_token_205|>",
|
1709 |
+
"lstrip": false,
|
1710 |
+
"normalized": false,
|
1711 |
+
"rstrip": false,
|
1712 |
+
"single_word": false,
|
1713 |
+
"special": true
|
1714 |
+
},
|
1715 |
+
"128214": {
|
1716 |
+
"content": "<|reserved_special_token_206|>",
|
1717 |
+
"lstrip": false,
|
1718 |
+
"normalized": false,
|
1719 |
+
"rstrip": false,
|
1720 |
+
"single_word": false,
|
1721 |
+
"special": true
|
1722 |
+
},
|
1723 |
+
"128215": {
|
1724 |
+
"content": "<|reserved_special_token_207|>",
|
1725 |
+
"lstrip": false,
|
1726 |
+
"normalized": false,
|
1727 |
+
"rstrip": false,
|
1728 |
+
"single_word": false,
|
1729 |
+
"special": true
|
1730 |
+
},
|
1731 |
+
"128216": {
|
1732 |
+
"content": "<|reserved_special_token_208|>",
|
1733 |
+
"lstrip": false,
|
1734 |
+
"normalized": false,
|
1735 |
+
"rstrip": false,
|
1736 |
+
"single_word": false,
|
1737 |
+
"special": true
|
1738 |
+
},
|
1739 |
+
"128217": {
|
1740 |
+
"content": "<|reserved_special_token_209|>",
|
1741 |
+
"lstrip": false,
|
1742 |
+
"normalized": false,
|
1743 |
+
"rstrip": false,
|
1744 |
+
"single_word": false,
|
1745 |
+
"special": true
|
1746 |
+
},
|
1747 |
+
"128218": {
|
1748 |
+
"content": "<|reserved_special_token_210|>",
|
1749 |
+
"lstrip": false,
|
1750 |
+
"normalized": false,
|
1751 |
+
"rstrip": false,
|
1752 |
+
"single_word": false,
|
1753 |
+
"special": true
|
1754 |
+
},
|
1755 |
+
"128219": {
|
1756 |
+
"content": "<|reserved_special_token_211|>",
|
1757 |
+
"lstrip": false,
|
1758 |
+
"normalized": false,
|
1759 |
+
"rstrip": false,
|
1760 |
+
"single_word": false,
|
1761 |
+
"special": true
|
1762 |
+
},
|
1763 |
+
"128220": {
|
1764 |
+
"content": "<|reserved_special_token_212|>",
|
1765 |
+
"lstrip": false,
|
1766 |
+
"normalized": false,
|
1767 |
+
"rstrip": false,
|
1768 |
+
"single_word": false,
|
1769 |
+
"special": true
|
1770 |
+
},
|
1771 |
+
"128221": {
|
1772 |
+
"content": "<|reserved_special_token_213|>",
|
1773 |
+
"lstrip": false,
|
1774 |
+
"normalized": false,
|
1775 |
+
"rstrip": false,
|
1776 |
+
"single_word": false,
|
1777 |
+
"special": true
|
1778 |
+
},
|
1779 |
+
"128222": {
|
1780 |
+
"content": "<|reserved_special_token_214|>",
|
1781 |
+
"lstrip": false,
|
1782 |
+
"normalized": false,
|
1783 |
+
"rstrip": false,
|
1784 |
+
"single_word": false,
|
1785 |
+
"special": true
|
1786 |
+
},
|
1787 |
+
"128223": {
|
1788 |
+
"content": "<|reserved_special_token_215|>",
|
1789 |
+
"lstrip": false,
|
1790 |
+
"normalized": false,
|
1791 |
+
"rstrip": false,
|
1792 |
+
"single_word": false,
|
1793 |
+
"special": true
|
1794 |
+
},
|
1795 |
+
"128224": {
|
1796 |
+
"content": "<|reserved_special_token_216|>",
|
1797 |
+
"lstrip": false,
|
1798 |
+
"normalized": false,
|
1799 |
+
"rstrip": false,
|
1800 |
+
"single_word": false,
|
1801 |
+
"special": true
|
1802 |
+
},
|
1803 |
+
"128225": {
|
1804 |
+
"content": "<|reserved_special_token_217|>",
|
1805 |
+
"lstrip": false,
|
1806 |
+
"normalized": false,
|
1807 |
+
"rstrip": false,
|
1808 |
+
"single_word": false,
|
1809 |
+
"special": true
|
1810 |
+
},
|
1811 |
+
"128226": {
|
1812 |
+
"content": "<|reserved_special_token_218|>",
|
1813 |
+
"lstrip": false,
|
1814 |
+
"normalized": false,
|
1815 |
+
"rstrip": false,
|
1816 |
+
"single_word": false,
|
1817 |
+
"special": true
|
1818 |
+
},
|
1819 |
+
"128227": {
|
1820 |
+
"content": "<|reserved_special_token_219|>",
|
1821 |
+
"lstrip": false,
|
1822 |
+
"normalized": false,
|
1823 |
+
"rstrip": false,
|
1824 |
+
"single_word": false,
|
1825 |
+
"special": true
|
1826 |
+
},
|
1827 |
+
"128228": {
|
1828 |
+
"content": "<|reserved_special_token_220|>",
|
1829 |
+
"lstrip": false,
|
1830 |
+
"normalized": false,
|
1831 |
+
"rstrip": false,
|
1832 |
+
"single_word": false,
|
1833 |
+
"special": true
|
1834 |
+
},
|
1835 |
+
"128229": {
|
1836 |
+
"content": "<|reserved_special_token_221|>",
|
1837 |
+
"lstrip": false,
|
1838 |
+
"normalized": false,
|
1839 |
+
"rstrip": false,
|
1840 |
+
"single_word": false,
|
1841 |
+
"special": true
|
1842 |
+
},
|
1843 |
+
"128230": {
|
1844 |
+
"content": "<|reserved_special_token_222|>",
|
1845 |
+
"lstrip": false,
|
1846 |
+
"normalized": false,
|
1847 |
+
"rstrip": false,
|
1848 |
+
"single_word": false,
|
1849 |
+
"special": true
|
1850 |
+
},
|
1851 |
+
"128231": {
|
1852 |
+
"content": "<|reserved_special_token_223|>",
|
1853 |
+
"lstrip": false,
|
1854 |
+
"normalized": false,
|
1855 |
+
"rstrip": false,
|
1856 |
+
"single_word": false,
|
1857 |
+
"special": true
|
1858 |
+
},
|
1859 |
+
"128232": {
|
1860 |
+
"content": "<|reserved_special_token_224|>",
|
1861 |
+
"lstrip": false,
|
1862 |
+
"normalized": false,
|
1863 |
+
"rstrip": false,
|
1864 |
+
"single_word": false,
|
1865 |
+
"special": true
|
1866 |
+
},
|
1867 |
+
"128233": {
|
1868 |
+
"content": "<|reserved_special_token_225|>",
|
1869 |
+
"lstrip": false,
|
1870 |
+
"normalized": false,
|
1871 |
+
"rstrip": false,
|
1872 |
+
"single_word": false,
|
1873 |
+
"special": true
|
1874 |
+
},
|
1875 |
+
"128234": {
|
1876 |
+
"content": "<|reserved_special_token_226|>",
|
1877 |
+
"lstrip": false,
|
1878 |
+
"normalized": false,
|
1879 |
+
"rstrip": false,
|
1880 |
+
"single_word": false,
|
1881 |
+
"special": true
|
1882 |
+
},
|
1883 |
+
"128235": {
|
1884 |
+
"content": "<|reserved_special_token_227|>",
|
1885 |
+
"lstrip": false,
|
1886 |
+
"normalized": false,
|
1887 |
+
"rstrip": false,
|
1888 |
+
"single_word": false,
|
1889 |
+
"special": true
|
1890 |
+
},
|
1891 |
+
"128236": {
|
1892 |
+
"content": "<|reserved_special_token_228|>",
|
1893 |
+
"lstrip": false,
|
1894 |
+
"normalized": false,
|
1895 |
+
"rstrip": false,
|
1896 |
+
"single_word": false,
|
1897 |
+
"special": true
|
1898 |
+
},
|
1899 |
+
"128237": {
|
1900 |
+
"content": "<|reserved_special_token_229|>",
|
1901 |
+
"lstrip": false,
|
1902 |
+
"normalized": false,
|
1903 |
+
"rstrip": false,
|
1904 |
+
"single_word": false,
|
1905 |
+
"special": true
|
1906 |
+
},
|
1907 |
+
"128238": {
|
1908 |
+
"content": "<|reserved_special_token_230|>",
|
1909 |
+
"lstrip": false,
|
1910 |
+
"normalized": false,
|
1911 |
+
"rstrip": false,
|
1912 |
+
"single_word": false,
|
1913 |
+
"special": true
|
1914 |
+
},
|
1915 |
+
"128239": {
|
1916 |
+
"content": "<|reserved_special_token_231|>",
|
1917 |
+
"lstrip": false,
|
1918 |
+
"normalized": false,
|
1919 |
+
"rstrip": false,
|
1920 |
+
"single_word": false,
|
1921 |
+
"special": true
|
1922 |
+
},
|
1923 |
+
"128240": {
|
1924 |
+
"content": "<|reserved_special_token_232|>",
|
1925 |
+
"lstrip": false,
|
1926 |
+
"normalized": false,
|
1927 |
+
"rstrip": false,
|
1928 |
+
"single_word": false,
|
1929 |
+
"special": true
|
1930 |
+
},
|
1931 |
+
"128241": {
|
1932 |
+
"content": "<|reserved_special_token_233|>",
|
1933 |
+
"lstrip": false,
|
1934 |
+
"normalized": false,
|
1935 |
+
"rstrip": false,
|
1936 |
+
"single_word": false,
|
1937 |
+
"special": true
|
1938 |
+
},
|
1939 |
+
"128242": {
|
1940 |
+
"content": "<|reserved_special_token_234|>",
|
1941 |
+
"lstrip": false,
|
1942 |
+
"normalized": false,
|
1943 |
+
"rstrip": false,
|
1944 |
+
"single_word": false,
|
1945 |
+
"special": true
|
1946 |
+
},
|
1947 |
+
"128243": {
|
1948 |
+
"content": "<|reserved_special_token_235|>",
|
1949 |
+
"lstrip": false,
|
1950 |
+
"normalized": false,
|
1951 |
+
"rstrip": false,
|
1952 |
+
"single_word": false,
|
1953 |
+
"special": true
|
1954 |
+
},
|
1955 |
+
"128244": {
|
1956 |
+
"content": "<|reserved_special_token_236|>",
|
1957 |
+
"lstrip": false,
|
1958 |
+
"normalized": false,
|
1959 |
+
"rstrip": false,
|
1960 |
+
"single_word": false,
|
1961 |
+
"special": true
|
1962 |
+
},
|
1963 |
+
"128245": {
|
1964 |
+
"content": "<|reserved_special_token_237|>",
|
1965 |
+
"lstrip": false,
|
1966 |
+
"normalized": false,
|
1967 |
+
"rstrip": false,
|
1968 |
+
"single_word": false,
|
1969 |
+
"special": true
|
1970 |
+
},
|
1971 |
+
"128246": {
|
1972 |
+
"content": "<|reserved_special_token_238|>",
|
1973 |
+
"lstrip": false,
|
1974 |
+
"normalized": false,
|
1975 |
+
"rstrip": false,
|
1976 |
+
"single_word": false,
|
1977 |
+
"special": true
|
1978 |
+
},
|
1979 |
+
"128247": {
|
1980 |
+
"content": "<|reserved_special_token_239|>",
|
1981 |
+
"lstrip": false,
|
1982 |
+
"normalized": false,
|
1983 |
+
"rstrip": false,
|
1984 |
+
"single_word": false,
|
1985 |
+
"special": true
|
1986 |
+
},
|
1987 |
+
"128248": {
|
1988 |
+
"content": "<|reserved_special_token_240|>",
|
1989 |
+
"lstrip": false,
|
1990 |
+
"normalized": false,
|
1991 |
+
"rstrip": false,
|
1992 |
+
"single_word": false,
|
1993 |
+
"special": true
|
1994 |
+
},
|
1995 |
+
"128249": {
|
1996 |
+
"content": "<|reserved_special_token_241|>",
|
1997 |
+
"lstrip": false,
|
1998 |
+
"normalized": false,
|
1999 |
+
"rstrip": false,
|
2000 |
+
"single_word": false,
|
2001 |
+
"special": true
|
2002 |
+
},
|
2003 |
+
"128250": {
|
2004 |
+
"content": "<|reserved_special_token_242|>",
|
2005 |
+
"lstrip": false,
|
2006 |
+
"normalized": false,
|
2007 |
+
"rstrip": false,
|
2008 |
+
"single_word": false,
|
2009 |
+
"special": true
|
2010 |
+
},
|
2011 |
+
"128251": {
|
2012 |
+
"content": "<|reserved_special_token_243|>",
|
2013 |
+
"lstrip": false,
|
2014 |
+
"normalized": false,
|
2015 |
+
"rstrip": false,
|
2016 |
+
"single_word": false,
|
2017 |
+
"special": true
|
2018 |
+
},
|
2019 |
+
"128252": {
|
2020 |
+
"content": "<|reserved_special_token_244|>",
|
2021 |
+
"lstrip": false,
|
2022 |
+
"normalized": false,
|
2023 |
+
"rstrip": false,
|
2024 |
+
"single_word": false,
|
2025 |
+
"special": true
|
2026 |
+
},
|
2027 |
+
"128253": {
|
2028 |
+
"content": "<|reserved_special_token_245|>",
|
2029 |
+
"lstrip": false,
|
2030 |
+
"normalized": false,
|
2031 |
+
"rstrip": false,
|
2032 |
+
"single_word": false,
|
2033 |
+
"special": true
|
2034 |
+
},
|
2035 |
+
"128254": {
|
2036 |
+
"content": "<|reserved_special_token_246|>",
|
2037 |
+
"lstrip": false,
|
2038 |
+
"normalized": false,
|
2039 |
+
"rstrip": false,
|
2040 |
+
"single_word": false,
|
2041 |
+
"special": true
|
2042 |
+
},
|
2043 |
+
"128255": {
|
2044 |
+
"content": "<|reserved_special_token_247|>",
|
2045 |
+
"lstrip": false,
|
2046 |
+
"normalized": false,
|
2047 |
+
"rstrip": false,
|
2048 |
+
"single_word": false,
|
2049 |
+
"special": true
|
2050 |
+
}
|
2051 |
+
},
|
2052 |
+
"bos_token": "<|begin_of_text|>",
|
2053 |
+
"chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- if strftime_now is defined %}\n {%- set date_string = strftime_now(\"%d %b %Y\") %}\n {%- else %}\n {%- set date_string = \"26 Jul 2024\" %}\n {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {{- \"<|eot_id|>\" }}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
|
2054 |
+
"clean_up_tokenization_spaces": true,
|
2055 |
+
"eos_token": "<|eot_id|>",
|
2056 |
+
"model_input_names": [
|
2057 |
+
"input_ids",
|
2058 |
+
"attention_mask"
|
2059 |
+
],
|
2060 |
+
"model_max_length": 131072,
|
2061 |
+
"pad_token": "<|eot_id|>",
|
2062 |
+
"padding_side": "right",
|
2063 |
+
"split_special_tokens": false,
|
2064 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
2065 |
+
}
|
checkpoint-350/trainer_state.json
ADDED
@@ -0,0 +1,3043 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.012959838844835758,
|
3 |
+
"best_model_checkpoint": "/home/paperspace/Data/models/rommel_importgenius_4b8/llm3br256/checkpoint-350",
|
4 |
+
"epoch": 2.928870292887029,
|
5 |
+
"eval_steps": 5,
|
6 |
+
"global_step": 350,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.008368200836820083,
|
13 |
+
"grad_norm": 0.2135079950094223,
|
14 |
+
"learning_rate": 1.6666666666666667e-06,
|
15 |
+
"loss": 0.0776,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.016736401673640166,
|
20 |
+
"grad_norm": 0.18678432703018188,
|
21 |
+
"learning_rate": 3.3333333333333333e-06,
|
22 |
+
"loss": 0.0663,
|
23 |
+
"step": 2
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.02510460251046025,
|
27 |
+
"grad_norm": 0.18199113011360168,
|
28 |
+
"learning_rate": 5e-06,
|
29 |
+
"loss": 0.0666,
|
30 |
+
"step": 3
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.03347280334728033,
|
34 |
+
"grad_norm": 0.13908497989177704,
|
35 |
+
"learning_rate": 6.666666666666667e-06,
|
36 |
+
"loss": 0.0596,
|
37 |
+
"step": 4
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.04184100418410042,
|
41 |
+
"grad_norm": 0.1845937818288803,
|
42 |
+
"learning_rate": 8.333333333333334e-06,
|
43 |
+
"loss": 0.0672,
|
44 |
+
"step": 5
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.04184100418410042,
|
48 |
+
"eval_loss": 0.07553808391094208,
|
49 |
+
"eval_runtime": 10.1109,
|
50 |
+
"eval_samples_per_second": 4.945,
|
51 |
+
"eval_steps_per_second": 1.286,
|
52 |
+
"step": 5
|
53 |
+
},
|
54 |
+
{
|
55 |
+
"epoch": 0.0502092050209205,
|
56 |
+
"grad_norm": 0.1750287413597107,
|
57 |
+
"learning_rate": 1e-05,
|
58 |
+
"loss": 0.0618,
|
59 |
+
"step": 6
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 0.058577405857740586,
|
63 |
+
"grad_norm": 0.1204298809170723,
|
64 |
+
"learning_rate": 1.1666666666666668e-05,
|
65 |
+
"loss": 0.0529,
|
66 |
+
"step": 7
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 0.06694560669456066,
|
70 |
+
"grad_norm": 0.12102019786834717,
|
71 |
+
"learning_rate": 1.3333333333333333e-05,
|
72 |
+
"loss": 0.0519,
|
73 |
+
"step": 8
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 0.07531380753138076,
|
77 |
+
"grad_norm": 0.1123175099492073,
|
78 |
+
"learning_rate": 1.5e-05,
|
79 |
+
"loss": 0.0494,
|
80 |
+
"step": 9
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.08368200836820083,
|
84 |
+
"grad_norm": 0.08419068902730942,
|
85 |
+
"learning_rate": 1.6666666666666667e-05,
|
86 |
+
"loss": 0.0476,
|
87 |
+
"step": 10
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.08368200836820083,
|
91 |
+
"eval_loss": 0.04517042636871338,
|
92 |
+
"eval_runtime": 8.1834,
|
93 |
+
"eval_samples_per_second": 6.11,
|
94 |
+
"eval_steps_per_second": 1.589,
|
95 |
+
"step": 10
|
96 |
+
},
|
97 |
+
{
|
98 |
+
"epoch": 0.09205020920502092,
|
99 |
+
"grad_norm": 0.0977497473359108,
|
100 |
+
"learning_rate": 1.8333333333333333e-05,
|
101 |
+
"loss": 0.0382,
|
102 |
+
"step": 11
|
103 |
+
},
|
104 |
+
{
|
105 |
+
"epoch": 0.100418410041841,
|
106 |
+
"grad_norm": 0.09294793009757996,
|
107 |
+
"learning_rate": 2e-05,
|
108 |
+
"loss": 0.0374,
|
109 |
+
"step": 12
|
110 |
+
},
|
111 |
+
{
|
112 |
+
"epoch": 0.1087866108786611,
|
113 |
+
"grad_norm": 0.0773313045501709,
|
114 |
+
"learning_rate": 2.1666666666666667e-05,
|
115 |
+
"loss": 0.0365,
|
116 |
+
"step": 13
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.11715481171548117,
|
120 |
+
"grad_norm": 0.07890919595956802,
|
121 |
+
"learning_rate": 2.3333333333333336e-05,
|
122 |
+
"loss": 0.0323,
|
123 |
+
"step": 14
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 0.12552301255230125,
|
127 |
+
"grad_norm": 0.0590483732521534,
|
128 |
+
"learning_rate": 2.5e-05,
|
129 |
+
"loss": 0.0337,
|
130 |
+
"step": 15
|
131 |
+
},
|
132 |
+
{
|
133 |
+
"epoch": 0.12552301255230125,
|
134 |
+
"eval_loss": 0.03555193170905113,
|
135 |
+
"eval_runtime": 8.2187,
|
136 |
+
"eval_samples_per_second": 6.084,
|
137 |
+
"eval_steps_per_second": 1.582,
|
138 |
+
"step": 15
|
139 |
+
},
|
140 |
+
{
|
141 |
+
"epoch": 0.13389121338912133,
|
142 |
+
"grad_norm": 0.05162455514073372,
|
143 |
+
"learning_rate": 2.6666666666666667e-05,
|
144 |
+
"loss": 0.0336,
|
145 |
+
"step": 16
|
146 |
+
},
|
147 |
+
{
|
148 |
+
"epoch": 0.14225941422594143,
|
149 |
+
"grad_norm": 0.04780131205916405,
|
150 |
+
"learning_rate": 2.8333333333333335e-05,
|
151 |
+
"loss": 0.0303,
|
152 |
+
"step": 17
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 0.1506276150627615,
|
156 |
+
"grad_norm": 0.05417422577738762,
|
157 |
+
"learning_rate": 3e-05,
|
158 |
+
"loss": 0.0303,
|
159 |
+
"step": 18
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.1589958158995816,
|
163 |
+
"grad_norm": 0.05216076225042343,
|
164 |
+
"learning_rate": 3.1666666666666666e-05,
|
165 |
+
"loss": 0.0329,
|
166 |
+
"step": 19
|
167 |
+
},
|
168 |
+
{
|
169 |
+
"epoch": 0.16736401673640167,
|
170 |
+
"grad_norm": 0.04367639496922493,
|
171 |
+
"learning_rate": 3.3333333333333335e-05,
|
172 |
+
"loss": 0.0333,
|
173 |
+
"step": 20
|
174 |
+
},
|
175 |
+
{
|
176 |
+
"epoch": 0.16736401673640167,
|
177 |
+
"eval_loss": 0.030791474506258965,
|
178 |
+
"eval_runtime": 8.1829,
|
179 |
+
"eval_samples_per_second": 6.11,
|
180 |
+
"eval_steps_per_second": 1.589,
|
181 |
+
"step": 20
|
182 |
+
},
|
183 |
+
{
|
184 |
+
"epoch": 0.17573221757322174,
|
185 |
+
"grad_norm": 0.0510227307677269,
|
186 |
+
"learning_rate": 3.5e-05,
|
187 |
+
"loss": 0.0302,
|
188 |
+
"step": 21
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 0.18410041841004185,
|
192 |
+
"grad_norm": 0.03975889831781387,
|
193 |
+
"learning_rate": 3.6666666666666666e-05,
|
194 |
+
"loss": 0.0293,
|
195 |
+
"step": 22
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 0.19246861924686193,
|
199 |
+
"grad_norm": 0.033559419214725494,
|
200 |
+
"learning_rate": 3.8333333333333334e-05,
|
201 |
+
"loss": 0.0276,
|
202 |
+
"step": 23
|
203 |
+
},
|
204 |
+
{
|
205 |
+
"epoch": 0.200836820083682,
|
206 |
+
"grad_norm": 0.03443528711795807,
|
207 |
+
"learning_rate": 4e-05,
|
208 |
+
"loss": 0.0255,
|
209 |
+
"step": 24
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 0.20920502092050208,
|
213 |
+
"grad_norm": 0.04452834278345108,
|
214 |
+
"learning_rate": 4.166666666666667e-05,
|
215 |
+
"loss": 0.0258,
|
216 |
+
"step": 25
|
217 |
+
},
|
218 |
+
{
|
219 |
+
"epoch": 0.20920502092050208,
|
220 |
+
"eval_loss": 0.027234511449933052,
|
221 |
+
"eval_runtime": 8.2238,
|
222 |
+
"eval_samples_per_second": 6.08,
|
223 |
+
"eval_steps_per_second": 1.581,
|
224 |
+
"step": 25
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 0.2175732217573222,
|
228 |
+
"grad_norm": 0.04225548356771469,
|
229 |
+
"learning_rate": 4.3333333333333334e-05,
|
230 |
+
"loss": 0.0265,
|
231 |
+
"step": 26
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 0.22594142259414227,
|
235 |
+
"grad_norm": 0.035125982016325,
|
236 |
+
"learning_rate": 4.5e-05,
|
237 |
+
"loss": 0.0248,
|
238 |
+
"step": 27
|
239 |
+
},
|
240 |
+
{
|
241 |
+
"epoch": 0.23430962343096234,
|
242 |
+
"grad_norm": 0.0293523371219635,
|
243 |
+
"learning_rate": 4.666666666666667e-05,
|
244 |
+
"loss": 0.0233,
|
245 |
+
"step": 28
|
246 |
+
},
|
247 |
+
{
|
248 |
+
"epoch": 0.24267782426778242,
|
249 |
+
"grad_norm": 0.046518724411726,
|
250 |
+
"learning_rate": 4.8333333333333334e-05,
|
251 |
+
"loss": 0.025,
|
252 |
+
"step": 29
|
253 |
+
},
|
254 |
+
{
|
255 |
+
"epoch": 0.2510460251046025,
|
256 |
+
"grad_norm": 0.031807683408260345,
|
257 |
+
"learning_rate": 5e-05,
|
258 |
+
"loss": 0.023,
|
259 |
+
"step": 30
|
260 |
+
},
|
261 |
+
{
|
262 |
+
"epoch": 0.2510460251046025,
|
263 |
+
"eval_loss": 0.025461601093411446,
|
264 |
+
"eval_runtime": 8.1735,
|
265 |
+
"eval_samples_per_second": 6.117,
|
266 |
+
"eval_steps_per_second": 1.591,
|
267 |
+
"step": 30
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 0.2594142259414226,
|
271 |
+
"grad_norm": 0.03979400172829628,
|
272 |
+
"learning_rate": 5.166666666666667e-05,
|
273 |
+
"loss": 0.0225,
|
274 |
+
"step": 31
|
275 |
+
},
|
276 |
+
{
|
277 |
+
"epoch": 0.26778242677824265,
|
278 |
+
"grad_norm": 0.030477149412035942,
|
279 |
+
"learning_rate": 5.333333333333333e-05,
|
280 |
+
"loss": 0.0212,
|
281 |
+
"step": 32
|
282 |
+
},
|
283 |
+
{
|
284 |
+
"epoch": 0.27615062761506276,
|
285 |
+
"grad_norm": 0.029403740540146828,
|
286 |
+
"learning_rate": 5.500000000000001e-05,
|
287 |
+
"loss": 0.0223,
|
288 |
+
"step": 33
|
289 |
+
},
|
290 |
+
{
|
291 |
+
"epoch": 0.28451882845188287,
|
292 |
+
"grad_norm": 0.03240867331624031,
|
293 |
+
"learning_rate": 5.666666666666667e-05,
|
294 |
+
"loss": 0.024,
|
295 |
+
"step": 34
|
296 |
+
},
|
297 |
+
{
|
298 |
+
"epoch": 0.2928870292887029,
|
299 |
+
"grad_norm": 0.032563403248786926,
|
300 |
+
"learning_rate": 5.833333333333334e-05,
|
301 |
+
"loss": 0.0202,
|
302 |
+
"step": 35
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 0.2928870292887029,
|
306 |
+
"eval_loss": 0.023448586463928223,
|
307 |
+
"eval_runtime": 8.2019,
|
308 |
+
"eval_samples_per_second": 6.096,
|
309 |
+
"eval_steps_per_second": 1.585,
|
310 |
+
"step": 35
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.301255230125523,
|
314 |
+
"grad_norm": 0.029798880219459534,
|
315 |
+
"learning_rate": 6e-05,
|
316 |
+
"loss": 0.0214,
|
317 |
+
"step": 36
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.30962343096234307,
|
321 |
+
"grad_norm": 0.02481868863105774,
|
322 |
+
"learning_rate": 6.166666666666667e-05,
|
323 |
+
"loss": 0.0175,
|
324 |
+
"step": 37
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.3179916317991632,
|
328 |
+
"grad_norm": 0.029312577098608017,
|
329 |
+
"learning_rate": 6.333333333333333e-05,
|
330 |
+
"loss": 0.0207,
|
331 |
+
"step": 38
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.3263598326359833,
|
335 |
+
"grad_norm": 0.035519231110811234,
|
336 |
+
"learning_rate": 6.500000000000001e-05,
|
337 |
+
"loss": 0.019,
|
338 |
+
"step": 39
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.33472803347280333,
|
342 |
+
"grad_norm": 0.019138505682349205,
|
343 |
+
"learning_rate": 6.666666666666667e-05,
|
344 |
+
"loss": 0.0188,
|
345 |
+
"step": 40
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.33472803347280333,
|
349 |
+
"eval_loss": 0.02175285294651985,
|
350 |
+
"eval_runtime": 8.1801,
|
351 |
+
"eval_samples_per_second": 6.112,
|
352 |
+
"eval_steps_per_second": 1.589,
|
353 |
+
"step": 40
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 0.34309623430962344,
|
357 |
+
"grad_norm": 0.028007732704281807,
|
358 |
+
"learning_rate": 6.833333333333333e-05,
|
359 |
+
"loss": 0.0198,
|
360 |
+
"step": 41
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 0.3514644351464435,
|
364 |
+
"grad_norm": 0.02277914620935917,
|
365 |
+
"learning_rate": 7e-05,
|
366 |
+
"loss": 0.0214,
|
367 |
+
"step": 42
|
368 |
+
},
|
369 |
+
{
|
370 |
+
"epoch": 0.3598326359832636,
|
371 |
+
"grad_norm": 0.03379930928349495,
|
372 |
+
"learning_rate": 7.166666666666667e-05,
|
373 |
+
"loss": 0.0228,
|
374 |
+
"step": 43
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 0.3682008368200837,
|
378 |
+
"grad_norm": 0.02658325619995594,
|
379 |
+
"learning_rate": 7.333333333333333e-05,
|
380 |
+
"loss": 0.0201,
|
381 |
+
"step": 44
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 0.37656903765690375,
|
385 |
+
"grad_norm": 0.0228717178106308,
|
386 |
+
"learning_rate": 7.500000000000001e-05,
|
387 |
+
"loss": 0.0185,
|
388 |
+
"step": 45
|
389 |
+
},
|
390 |
+
{
|
391 |
+
"epoch": 0.37656903765690375,
|
392 |
+
"eval_loss": 0.02076469548046589,
|
393 |
+
"eval_runtime": 8.1924,
|
394 |
+
"eval_samples_per_second": 6.103,
|
395 |
+
"eval_steps_per_second": 1.587,
|
396 |
+
"step": 45
|
397 |
+
},
|
398 |
+
{
|
399 |
+
"epoch": 0.38493723849372385,
|
400 |
+
"grad_norm": 0.022528983652591705,
|
401 |
+
"learning_rate": 7.666666666666667e-05,
|
402 |
+
"loss": 0.0175,
|
403 |
+
"step": 46
|
404 |
+
},
|
405 |
+
{
|
406 |
+
"epoch": 0.39330543933054396,
|
407 |
+
"grad_norm": 0.02600259892642498,
|
408 |
+
"learning_rate": 7.833333333333333e-05,
|
409 |
+
"loss": 0.0199,
|
410 |
+
"step": 47
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 0.401673640167364,
|
414 |
+
"grad_norm": 0.022605430334806442,
|
415 |
+
"learning_rate": 8e-05,
|
416 |
+
"loss": 0.0178,
|
417 |
+
"step": 48
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 0.4100418410041841,
|
421 |
+
"grad_norm": 0.020774831995368004,
|
422 |
+
"learning_rate": 8.166666666666667e-05,
|
423 |
+
"loss": 0.0168,
|
424 |
+
"step": 49
|
425 |
+
},
|
426 |
+
{
|
427 |
+
"epoch": 0.41841004184100417,
|
428 |
+
"grad_norm": 0.02565855346620083,
|
429 |
+
"learning_rate": 8.333333333333334e-05,
|
430 |
+
"loss": 0.0199,
|
431 |
+
"step": 50
|
432 |
+
},
|
433 |
+
{
|
434 |
+
"epoch": 0.41841004184100417,
|
435 |
+
"eval_loss": 0.020035894587635994,
|
436 |
+
"eval_runtime": 8.1839,
|
437 |
+
"eval_samples_per_second": 6.11,
|
438 |
+
"eval_steps_per_second": 1.588,
|
439 |
+
"step": 50
|
440 |
+
},
|
441 |
+
{
|
442 |
+
"epoch": 0.42677824267782427,
|
443 |
+
"grad_norm": 0.027278423309326172,
|
444 |
+
"learning_rate": 8.5e-05,
|
445 |
+
"loss": 0.0208,
|
446 |
+
"step": 51
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 0.4351464435146444,
|
450 |
+
"grad_norm": 0.022894414141774178,
|
451 |
+
"learning_rate": 8.666666666666667e-05,
|
452 |
+
"loss": 0.0166,
|
453 |
+
"step": 52
|
454 |
+
},
|
455 |
+
{
|
456 |
+
"epoch": 0.4435146443514644,
|
457 |
+
"grad_norm": 0.02473956160247326,
|
458 |
+
"learning_rate": 8.833333333333333e-05,
|
459 |
+
"loss": 0.021,
|
460 |
+
"step": 53
|
461 |
+
},
|
462 |
+
{
|
463 |
+
"epoch": 0.45188284518828453,
|
464 |
+
"grad_norm": 0.02041654661297798,
|
465 |
+
"learning_rate": 9e-05,
|
466 |
+
"loss": 0.0189,
|
467 |
+
"step": 54
|
468 |
+
},
|
469 |
+
{
|
470 |
+
"epoch": 0.4602510460251046,
|
471 |
+
"grad_norm": 0.022939356043934822,
|
472 |
+
"learning_rate": 9.166666666666667e-05,
|
473 |
+
"loss": 0.0198,
|
474 |
+
"step": 55
|
475 |
+
},
|
476 |
+
{
|
477 |
+
"epoch": 0.4602510460251046,
|
478 |
+
"eval_loss": 0.019482074305415154,
|
479 |
+
"eval_runtime": 8.206,
|
480 |
+
"eval_samples_per_second": 6.093,
|
481 |
+
"eval_steps_per_second": 1.584,
|
482 |
+
"step": 55
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 0.4686192468619247,
|
486 |
+
"grad_norm": 0.018536586314439774,
|
487 |
+
"learning_rate": 9.333333333333334e-05,
|
488 |
+
"loss": 0.0176,
|
489 |
+
"step": 56
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 0.4769874476987448,
|
493 |
+
"grad_norm": 0.02208622545003891,
|
494 |
+
"learning_rate": 9.5e-05,
|
495 |
+
"loss": 0.0189,
|
496 |
+
"step": 57
|
497 |
+
},
|
498 |
+
{
|
499 |
+
"epoch": 0.48535564853556484,
|
500 |
+
"grad_norm": 0.021715424954891205,
|
501 |
+
"learning_rate": 9.666666666666667e-05,
|
502 |
+
"loss": 0.0176,
|
503 |
+
"step": 58
|
504 |
+
},
|
505 |
+
{
|
506 |
+
"epoch": 0.49372384937238495,
|
507 |
+
"grad_norm": 0.022242875769734383,
|
508 |
+
"learning_rate": 9.833333333333333e-05,
|
509 |
+
"loss": 0.0208,
|
510 |
+
"step": 59
|
511 |
+
},
|
512 |
+
{
|
513 |
+
"epoch": 0.502092050209205,
|
514 |
+
"grad_norm": 0.022756585851311684,
|
515 |
+
"learning_rate": 0.0001,
|
516 |
+
"loss": 0.0179,
|
517 |
+
"step": 60
|
518 |
+
},
|
519 |
+
{
|
520 |
+
"epoch": 0.502092050209205,
|
521 |
+
"eval_loss": 0.018894275650382042,
|
522 |
+
"eval_runtime": 8.1933,
|
523 |
+
"eval_samples_per_second": 6.103,
|
524 |
+
"eval_steps_per_second": 1.587,
|
525 |
+
"step": 60
|
526 |
+
},
|
527 |
+
{
|
528 |
+
"epoch": 0.5104602510460251,
|
529 |
+
"grad_norm": 0.021328022703528404,
|
530 |
+
"learning_rate": 9.999913795300544e-05,
|
531 |
+
"loss": 0.0183,
|
532 |
+
"step": 61
|
533 |
+
},
|
534 |
+
{
|
535 |
+
"epoch": 0.5188284518828452,
|
536 |
+
"grad_norm": 0.018391713500022888,
|
537 |
+
"learning_rate": 9.999655184174672e-05,
|
538 |
+
"loss": 0.0172,
|
539 |
+
"step": 62
|
540 |
+
},
|
541 |
+
{
|
542 |
+
"epoch": 0.5271966527196653,
|
543 |
+
"grad_norm": 0.019118035212159157,
|
544 |
+
"learning_rate": 9.999224175539785e-05,
|
545 |
+
"loss": 0.0172,
|
546 |
+
"step": 63
|
547 |
+
},
|
548 |
+
{
|
549 |
+
"epoch": 0.5355648535564853,
|
550 |
+
"grad_norm": 0.024857187643647194,
|
551 |
+
"learning_rate": 9.99862078425787e-05,
|
552 |
+
"loss": 0.0192,
|
553 |
+
"step": 64
|
554 |
+
},
|
555 |
+
{
|
556 |
+
"epoch": 0.5439330543933054,
|
557 |
+
"grad_norm": 0.025595078244805336,
|
558 |
+
"learning_rate": 9.997845031134992e-05,
|
559 |
+
"loss": 0.0185,
|
560 |
+
"step": 65
|
561 |
+
},
|
562 |
+
{
|
563 |
+
"epoch": 0.5439330543933054,
|
564 |
+
"eval_loss": 0.018585730344057083,
|
565 |
+
"eval_runtime": 8.172,
|
566 |
+
"eval_samples_per_second": 6.118,
|
567 |
+
"eval_steps_per_second": 1.591,
|
568 |
+
"step": 65
|
569 |
+
},
|
570 |
+
{
|
571 |
+
"epoch": 0.5523012552301255,
|
572 |
+
"grad_norm": 0.02300618588924408,
|
573 |
+
"learning_rate": 9.996896942920578e-05,
|
574 |
+
"loss": 0.0174,
|
575 |
+
"step": 66
|
576 |
+
},
|
577 |
+
{
|
578 |
+
"epoch": 0.5606694560669456,
|
579 |
+
"grad_norm": 0.022543633356690407,
|
580 |
+
"learning_rate": 9.99577655230649e-05,
|
581 |
+
"loss": 0.0155,
|
582 |
+
"step": 67
|
583 |
+
},
|
584 |
+
{
|
585 |
+
"epoch": 0.5690376569037657,
|
586 |
+
"grad_norm": 0.028140394017100334,
|
587 |
+
"learning_rate": 9.994483897925905e-05,
|
588 |
+
"loss": 0.0167,
|
589 |
+
"step": 68
|
590 |
+
},
|
591 |
+
{
|
592 |
+
"epoch": 0.5774058577405857,
|
593 |
+
"grad_norm": 0.027847809717059135,
|
594 |
+
"learning_rate": 9.993019024351974e-05,
|
595 |
+
"loss": 0.0184,
|
596 |
+
"step": 69
|
597 |
+
},
|
598 |
+
{
|
599 |
+
"epoch": 0.5857740585774058,
|
600 |
+
"grad_norm": 0.02762455679476261,
|
601 |
+
"learning_rate": 9.991381982096292e-05,
|
602 |
+
"loss": 0.0174,
|
603 |
+
"step": 70
|
604 |
+
},
|
605 |
+
{
|
606 |
+
"epoch": 0.5857740585774058,
|
607 |
+
"eval_loss": 0.018603580072522163,
|
608 |
+
"eval_runtime": 8.1911,
|
609 |
+
"eval_samples_per_second": 6.104,
|
610 |
+
"eval_steps_per_second": 1.587,
|
611 |
+
"step": 70
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 0.5941422594142259,
|
615 |
+
"grad_norm": 0.02379084751009941,
|
616 |
+
"learning_rate": 9.989572827607153e-05,
|
617 |
+
"loss": 0.0151,
|
618 |
+
"step": 71
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 0.602510460251046,
|
622 |
+
"grad_norm": 0.028387486934661865,
|
623 |
+
"learning_rate": 9.987591623267606e-05,
|
624 |
+
"loss": 0.0192,
|
625 |
+
"step": 72
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 0.6108786610878661,
|
629 |
+
"grad_norm": 0.029841607436537743,
|
630 |
+
"learning_rate": 9.9854384373933e-05,
|
631 |
+
"loss": 0.0166,
|
632 |
+
"step": 73
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 0.6192468619246861,
|
636 |
+
"grad_norm": 0.024572154507040977,
|
637 |
+
"learning_rate": 9.983113344230129e-05,
|
638 |
+
"loss": 0.0181,
|
639 |
+
"step": 74
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.6276150627615062,
|
643 |
+
"grad_norm": 0.024675268679857254,
|
644 |
+
"learning_rate": 9.98061642395168e-05,
|
645 |
+
"loss": 0.0157,
|
646 |
+
"step": 75
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 0.6276150627615062,
|
650 |
+
"eval_loss": 0.0182618610560894,
|
651 |
+
"eval_runtime": 8.1895,
|
652 |
+
"eval_samples_per_second": 6.105,
|
653 |
+
"eval_steps_per_second": 1.587,
|
654 |
+
"step": 75
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 0.6359832635983264,
|
658 |
+
"grad_norm": 0.019830523058772087,
|
659 |
+
"learning_rate": 9.977947762656455e-05,
|
660 |
+
"loss": 0.0183,
|
661 |
+
"step": 76
|
662 |
+
},
|
663 |
+
{
|
664 |
+
"epoch": 0.6443514644351465,
|
665 |
+
"grad_norm": 0.017791615799069405,
|
666 |
+
"learning_rate": 9.975107452364913e-05,
|
667 |
+
"loss": 0.0174,
|
668 |
+
"step": 77
|
669 |
+
},
|
670 |
+
{
|
671 |
+
"epoch": 0.6527196652719666,
|
672 |
+
"grad_norm": 0.01926375925540924,
|
673 |
+
"learning_rate": 9.972095591016294e-05,
|
674 |
+
"loss": 0.0158,
|
675 |
+
"step": 78
|
676 |
+
},
|
677 |
+
{
|
678 |
+
"epoch": 0.6610878661087866,
|
679 |
+
"grad_norm": 0.022102929651737213,
|
680 |
+
"learning_rate": 9.968912282465236e-05,
|
681 |
+
"loss": 0.0155,
|
682 |
+
"step": 79
|
683 |
+
},
|
684 |
+
{
|
685 |
+
"epoch": 0.6694560669456067,
|
686 |
+
"grad_norm": 0.024682268500328064,
|
687 |
+
"learning_rate": 9.965557636478203e-05,
|
688 |
+
"loss": 0.0175,
|
689 |
+
"step": 80
|
690 |
+
},
|
691 |
+
{
|
692 |
+
"epoch": 0.6694560669456067,
|
693 |
+
"eval_loss": 0.017632750794291496,
|
694 |
+
"eval_runtime": 8.184,
|
695 |
+
"eval_samples_per_second": 6.11,
|
696 |
+
"eval_steps_per_second": 1.588,
|
697 |
+
"step": 80
|
698 |
+
},
|
699 |
+
{
|
700 |
+
"epoch": 0.6778242677824268,
|
701 |
+
"grad_norm": 0.022384189069271088,
|
702 |
+
"learning_rate": 9.962031768729693e-05,
|
703 |
+
"loss": 0.0184,
|
704 |
+
"step": 81
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 0.6861924686192469,
|
708 |
+
"grad_norm": 0.024247104302048683,
|
709 |
+
"learning_rate": 9.958334800798256e-05,
|
710 |
+
"loss": 0.0162,
|
711 |
+
"step": 82
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 0.694560669456067,
|
715 |
+
"grad_norm": 0.02073194645345211,
|
716 |
+
"learning_rate": 9.954466860162295e-05,
|
717 |
+
"loss": 0.0146,
|
718 |
+
"step": 83
|
719 |
+
},
|
720 |
+
{
|
721 |
+
"epoch": 0.702928870292887,
|
722 |
+
"grad_norm": 0.021671872586011887,
|
723 |
+
"learning_rate": 9.950428080195675e-05,
|
724 |
+
"loss": 0.0183,
|
725 |
+
"step": 84
|
726 |
+
},
|
727 |
+
{
|
728 |
+
"epoch": 0.7112970711297071,
|
729 |
+
"grad_norm": 0.022358493879437447,
|
730 |
+
"learning_rate": 9.94621860016312e-05,
|
731 |
+
"loss": 0.0175,
|
732 |
+
"step": 85
|
733 |
+
},
|
734 |
+
{
|
735 |
+
"epoch": 0.7112970711297071,
|
736 |
+
"eval_loss": 0.01763150468468666,
|
737 |
+
"eval_runtime": 8.1866,
|
738 |
+
"eval_samples_per_second": 6.108,
|
739 |
+
"eval_steps_per_second": 1.588,
|
740 |
+
"step": 85
|
741 |
+
},
|
742 |
+
{
|
743 |
+
"epoch": 0.7196652719665272,
|
744 |
+
"grad_norm": 0.027475032955408096,
|
745 |
+
"learning_rate": 9.941838565215413e-05,
|
746 |
+
"loss": 0.018,
|
747 |
+
"step": 86
|
748 |
+
},
|
749 |
+
{
|
750 |
+
"epoch": 0.7280334728033473,
|
751 |
+
"grad_norm": 0.022491537034511566,
|
752 |
+
"learning_rate": 9.937288126384396e-05,
|
753 |
+
"loss": 0.0189,
|
754 |
+
"step": 87
|
755 |
+
},
|
756 |
+
{
|
757 |
+
"epoch": 0.7364016736401674,
|
758 |
+
"grad_norm": 0.017695261165499687,
|
759 |
+
"learning_rate": 9.932567440577751e-05,
|
760 |
+
"loss": 0.0169,
|
761 |
+
"step": 88
|
762 |
+
},
|
763 |
+
{
|
764 |
+
"epoch": 0.7447698744769874,
|
765 |
+
"grad_norm": 0.021199015900492668,
|
766 |
+
"learning_rate": 9.9276766705736e-05,
|
767 |
+
"loss": 0.016,
|
768 |
+
"step": 89
|
769 |
+
},
|
770 |
+
{
|
771 |
+
"epoch": 0.7531380753138075,
|
772 |
+
"grad_norm": 0.02306659147143364,
|
773 |
+
"learning_rate": 9.922615985014887e-05,
|
774 |
+
"loss": 0.0164,
|
775 |
+
"step": 90
|
776 |
+
},
|
777 |
+
{
|
778 |
+
"epoch": 0.7531380753138075,
|
779 |
+
"eval_loss": 0.017131321132183075,
|
780 |
+
"eval_runtime": 8.1843,
|
781 |
+
"eval_samples_per_second": 6.109,
|
782 |
+
"eval_steps_per_second": 1.588,
|
783 |
+
"step": 90
|
784 |
+
},
|
785 |
+
{
|
786 |
+
"epoch": 0.7615062761506276,
|
787 |
+
"grad_norm": 0.023978663608431816,
|
788 |
+
"learning_rate": 9.91738555840356e-05,
|
789 |
+
"loss": 0.0176,
|
790 |
+
"step": 91
|
791 |
+
},
|
792 |
+
{
|
793 |
+
"epoch": 0.7698744769874477,
|
794 |
+
"grad_norm": 0.020384812727570534,
|
795 |
+
"learning_rate": 9.911985571094564e-05,
|
796 |
+
"loss": 0.0178,
|
797 |
+
"step": 92
|
798 |
+
},
|
799 |
+
{
|
800 |
+
"epoch": 0.7782426778242678,
|
801 |
+
"grad_norm": 0.02201078273355961,
|
802 |
+
"learning_rate": 9.906416209289608e-05,
|
803 |
+
"loss": 0.0161,
|
804 |
+
"step": 93
|
805 |
+
},
|
806 |
+
{
|
807 |
+
"epoch": 0.7866108786610879,
|
808 |
+
"grad_norm": 0.021811528131365776,
|
809 |
+
"learning_rate": 9.900677665030762e-05,
|
810 |
+
"loss": 0.0161,
|
811 |
+
"step": 94
|
812 |
+
},
|
813 |
+
{
|
814 |
+
"epoch": 0.7949790794979079,
|
815 |
+
"grad_norm": 0.0257060918956995,
|
816 |
+
"learning_rate": 9.894770136193814e-05,
|
817 |
+
"loss": 0.0182,
|
818 |
+
"step": 95
|
819 |
+
},
|
820 |
+
{
|
821 |
+
"epoch": 0.7949790794979079,
|
822 |
+
"eval_loss": 0.016829807311296463,
|
823 |
+
"eval_runtime": 8.1842,
|
824 |
+
"eval_samples_per_second": 6.109,
|
825 |
+
"eval_steps_per_second": 1.588,
|
826 |
+
"step": 95
|
827 |
+
},
|
828 |
+
{
|
829 |
+
"epoch": 0.803347280334728,
|
830 |
+
"grad_norm": 0.018415937200188637,
|
831 |
+
"learning_rate": 9.888693826481467e-05,
|
832 |
+
"loss": 0.0154,
|
833 |
+
"step": 96
|
834 |
+
},
|
835 |
+
{
|
836 |
+
"epoch": 0.8117154811715481,
|
837 |
+
"grad_norm": 0.02051800675690174,
|
838 |
+
"learning_rate": 9.882448945416298e-05,
|
839 |
+
"loss": 0.0168,
|
840 |
+
"step": 97
|
841 |
+
},
|
842 |
+
{
|
843 |
+
"epoch": 0.8200836820083682,
|
844 |
+
"grad_norm": 0.01812230981886387,
|
845 |
+
"learning_rate": 9.87603570833355e-05,
|
846 |
+
"loss": 0.0142,
|
847 |
+
"step": 98
|
848 |
+
},
|
849 |
+
{
|
850 |
+
"epoch": 0.8284518828451883,
|
851 |
+
"grad_norm": 0.02094101719558239,
|
852 |
+
"learning_rate": 9.869454336373689e-05,
|
853 |
+
"loss": 0.0163,
|
854 |
+
"step": 99
|
855 |
+
},
|
856 |
+
{
|
857 |
+
"epoch": 0.8368200836820083,
|
858 |
+
"grad_norm": 0.02226194366812706,
|
859 |
+
"learning_rate": 9.862705056474795e-05,
|
860 |
+
"loss": 0.019,
|
861 |
+
"step": 100
|
862 |
+
},
|
863 |
+
{
|
864 |
+
"epoch": 0.8368200836820083,
|
865 |
+
"eval_loss": 0.016707511618733406,
|
866 |
+
"eval_runtime": 8.1876,
|
867 |
+
"eval_samples_per_second": 6.107,
|
868 |
+
"eval_steps_per_second": 1.588,
|
869 |
+
"step": 100
|
870 |
+
},
|
871 |
+
{
|
872 |
+
"epoch": 0.8451882845188284,
|
873 |
+
"grad_norm": 0.018342219293117523,
|
874 |
+
"learning_rate": 9.855788101364722e-05,
|
875 |
+
"loss": 0.0139,
|
876 |
+
"step": 101
|
877 |
+
},
|
878 |
+
{
|
879 |
+
"epoch": 0.8535564853556485,
|
880 |
+
"grad_norm": 0.024607762694358826,
|
881 |
+
"learning_rate": 9.848703709553089e-05,
|
882 |
+
"loss": 0.017,
|
883 |
+
"step": 102
|
884 |
+
},
|
885 |
+
{
|
886 |
+
"epoch": 0.8619246861924686,
|
887 |
+
"grad_norm": 0.021850740537047386,
|
888 |
+
"learning_rate": 9.841452125323041e-05,
|
889 |
+
"loss": 0.0171,
|
890 |
+
"step": 103
|
891 |
+
},
|
892 |
+
{
|
893 |
+
"epoch": 0.8702928870292888,
|
894 |
+
"grad_norm": 0.022089634090662003,
|
895 |
+
"learning_rate": 9.834033598722831e-05,
|
896 |
+
"loss": 0.0151,
|
897 |
+
"step": 104
|
898 |
+
},
|
899 |
+
{
|
900 |
+
"epoch": 0.8786610878661087,
|
901 |
+
"grad_norm": 0.01841079257428646,
|
902 |
+
"learning_rate": 9.826448385557207e-05,
|
903 |
+
"loss": 0.0163,
|
904 |
+
"step": 105
|
905 |
+
},
|
906 |
+
{
|
907 |
+
"epoch": 0.8786610878661087,
|
908 |
+
"eval_loss": 0.01583385095000267,
|
909 |
+
"eval_runtime": 8.2041,
|
910 |
+
"eval_samples_per_second": 6.094,
|
911 |
+
"eval_steps_per_second": 1.585,
|
912 |
+
"step": 105
|
913 |
+
},
|
914 |
+
{
|
915 |
+
"epoch": 0.8870292887029289,
|
916 |
+
"grad_norm": 0.020294038578867912,
|
917 |
+
"learning_rate": 9.818696747378573e-05,
|
918 |
+
"loss": 0.0177,
|
919 |
+
"step": 106
|
920 |
+
},
|
921 |
+
{
|
922 |
+
"epoch": 0.895397489539749,
|
923 |
+
"grad_norm": 0.015671249479055405,
|
924 |
+
"learning_rate": 9.810778951477986e-05,
|
925 |
+
"loss": 0.0144,
|
926 |
+
"step": 107
|
927 |
+
},
|
928 |
+
{
|
929 |
+
"epoch": 0.9037656903765691,
|
930 |
+
"grad_norm": 0.018139947205781937,
|
931 |
+
"learning_rate": 9.802695270875932e-05,
|
932 |
+
"loss": 0.0154,
|
933 |
+
"step": 108
|
934 |
+
},
|
935 |
+
{
|
936 |
+
"epoch": 0.9121338912133892,
|
937 |
+
"grad_norm": 0.018227294087409973,
|
938 |
+
"learning_rate": 9.794445984312915e-05,
|
939 |
+
"loss": 0.0149,
|
940 |
+
"step": 109
|
941 |
+
},
|
942 |
+
{
|
943 |
+
"epoch": 0.9205020920502092,
|
944 |
+
"grad_norm": 0.015631545335054398,
|
945 |
+
"learning_rate": 9.786031376239842e-05,
|
946 |
+
"loss": 0.0145,
|
947 |
+
"step": 110
|
948 |
+
},
|
949 |
+
{
|
950 |
+
"epoch": 0.9205020920502092,
|
951 |
+
"eval_loss": 0.0157511904835701,
|
952 |
+
"eval_runtime": 8.1802,
|
953 |
+
"eval_samples_per_second": 6.112,
|
954 |
+
"eval_steps_per_second": 1.589,
|
955 |
+
"step": 110
|
956 |
+
},
|
957 |
+
{
|
958 |
+
"epoch": 0.9288702928870293,
|
959 |
+
"grad_norm": 0.019501695409417152,
|
960 |
+
"learning_rate": 9.777451736808216e-05,
|
961 |
+
"loss": 0.0138,
|
962 |
+
"step": 111
|
963 |
+
},
|
964 |
+
{
|
965 |
+
"epoch": 0.9372384937238494,
|
966 |
+
"grad_norm": 0.018380407243967056,
|
967 |
+
"learning_rate": 9.768707361860134e-05,
|
968 |
+
"loss": 0.0155,
|
969 |
+
"step": 112
|
970 |
+
},
|
971 |
+
{
|
972 |
+
"epoch": 0.9456066945606695,
|
973 |
+
"grad_norm": 0.016666430979967117,
|
974 |
+
"learning_rate": 9.75979855291808e-05,
|
975 |
+
"loss": 0.0153,
|
976 |
+
"step": 113
|
977 |
+
},
|
978 |
+
{
|
979 |
+
"epoch": 0.9539748953974896,
|
980 |
+
"grad_norm": 0.019959956407546997,
|
981 |
+
"learning_rate": 9.750725617174534e-05,
|
982 |
+
"loss": 0.0162,
|
983 |
+
"step": 114
|
984 |
+
},
|
985 |
+
{
|
986 |
+
"epoch": 0.9623430962343096,
|
987 |
+
"grad_norm": 0.019904401153326035,
|
988 |
+
"learning_rate": 9.741488867481376e-05,
|
989 |
+
"loss": 0.0165,
|
990 |
+
"step": 115
|
991 |
+
},
|
992 |
+
{
|
993 |
+
"epoch": 0.9623430962343096,
|
994 |
+
"eval_loss": 0.015494490042328835,
|
995 |
+
"eval_runtime": 8.1797,
|
996 |
+
"eval_samples_per_second": 6.113,
|
997 |
+
"eval_steps_per_second": 1.589,
|
998 |
+
"step": 115
|
999 |
+
},
|
1000 |
+
{
|
1001 |
+
"epoch": 0.9707112970711297,
|
1002 |
+
"grad_norm": 0.02116929367184639,
|
1003 |
+
"learning_rate": 9.7320886223391e-05,
|
1004 |
+
"loss": 0.0153,
|
1005 |
+
"step": 116
|
1006 |
+
},
|
1007 |
+
{
|
1008 |
+
"epoch": 0.9790794979079498,
|
1009 |
+
"grad_norm": 0.019681984558701515,
|
1010 |
+
"learning_rate": 9.722525205885825e-05,
|
1011 |
+
"loss": 0.0149,
|
1012 |
+
"step": 117
|
1013 |
+
},
|
1014 |
+
{
|
1015 |
+
"epoch": 0.9874476987447699,
|
1016 |
+
"grad_norm": 0.02032177522778511,
|
1017 |
+
"learning_rate": 9.712798947886128e-05,
|
1018 |
+
"loss": 0.0148,
|
1019 |
+
"step": 118
|
1020 |
+
},
|
1021 |
+
{
|
1022 |
+
"epoch": 0.99581589958159,
|
1023 |
+
"grad_norm": 0.021595895290374756,
|
1024 |
+
"learning_rate": 9.702910183719671e-05,
|
1025 |
+
"loss": 0.0199,
|
1026 |
+
"step": 119
|
1027 |
+
},
|
1028 |
+
{
|
1029 |
+
"epoch": 1.00418410041841,
|
1030 |
+
"grad_norm": 0.027728823944926262,
|
1031 |
+
"learning_rate": 9.692859254369631e-05,
|
1032 |
+
"loss": 0.0205,
|
1033 |
+
"step": 120
|
1034 |
+
},
|
1035 |
+
{
|
1036 |
+
"epoch": 1.00418410041841,
|
1037 |
+
"eval_loss": 0.015181933529675007,
|
1038 |
+
"eval_runtime": 8.1872,
|
1039 |
+
"eval_samples_per_second": 6.107,
|
1040 |
+
"eval_steps_per_second": 1.588,
|
1041 |
+
"step": 120
|
1042 |
+
},
|
1043 |
+
{
|
1044 |
+
"epoch": 1.0125523012552302,
|
1045 |
+
"grad_norm": 0.017031384631991386,
|
1046 |
+
"learning_rate": 9.682646506410943e-05,
|
1047 |
+
"loss": 0.0152,
|
1048 |
+
"step": 121
|
1049 |
+
},
|
1050 |
+
{
|
1051 |
+
"epoch": 1.0209205020920502,
|
1052 |
+
"grad_norm": 0.01707589253783226,
|
1053 |
+
"learning_rate": 9.672272291998355e-05,
|
1054 |
+
"loss": 0.0127,
|
1055 |
+
"step": 122
|
1056 |
+
},
|
1057 |
+
{
|
1058 |
+
"epoch": 1.0292887029288702,
|
1059 |
+
"grad_norm": 0.02119339071214199,
|
1060 |
+
"learning_rate": 9.661736968854283e-05,
|
1061 |
+
"loss": 0.0143,
|
1062 |
+
"step": 123
|
1063 |
+
},
|
1064 |
+
{
|
1065 |
+
"epoch": 1.0376569037656904,
|
1066 |
+
"grad_norm": 0.01858825981616974,
|
1067 |
+
"learning_rate": 9.651040900256471e-05,
|
1068 |
+
"loss": 0.0145,
|
1069 |
+
"step": 124
|
1070 |
+
},
|
1071 |
+
{
|
1072 |
+
"epoch": 1.0460251046025104,
|
1073 |
+
"grad_norm": 0.013188479468226433,
|
1074 |
+
"learning_rate": 9.640184455025471e-05,
|
1075 |
+
"loss": 0.0105,
|
1076 |
+
"step": 125
|
1077 |
+
},
|
1078 |
+
{
|
1079 |
+
"epoch": 1.0460251046025104,
|
1080 |
+
"eval_loss": 0.015529554337263107,
|
1081 |
+
"eval_runtime": 8.1918,
|
1082 |
+
"eval_samples_per_second": 6.104,
|
1083 |
+
"eval_steps_per_second": 1.587,
|
1084 |
+
"step": 125
|
1085 |
+
},
|
1086 |
+
{
|
1087 |
+
"epoch": 1.0543933054393306,
|
1088 |
+
"grad_norm": 0.01512962393462658,
|
1089 |
+
"learning_rate": 9.629168007511924e-05,
|
1090 |
+
"loss": 0.0121,
|
1091 |
+
"step": 126
|
1092 |
+
},
|
1093 |
+
{
|
1094 |
+
"epoch": 1.0627615062761506,
|
1095 |
+
"grad_norm": 0.018388476222753525,
|
1096 |
+
"learning_rate": 9.617991937583648e-05,
|
1097 |
+
"loss": 0.0154,
|
1098 |
+
"step": 127
|
1099 |
+
},
|
1100 |
+
{
|
1101 |
+
"epoch": 1.0711297071129706,
|
1102 |
+
"grad_norm": 0.018059156835079193,
|
1103 |
+
"learning_rate": 9.60665663061254e-05,
|
1104 |
+
"loss": 0.0163,
|
1105 |
+
"step": 128
|
1106 |
+
},
|
1107 |
+
{
|
1108 |
+
"epoch": 1.0794979079497908,
|
1109 |
+
"grad_norm": 0.015875034034252167,
|
1110 |
+
"learning_rate": 9.595162477461298e-05,
|
1111 |
+
"loss": 0.0126,
|
1112 |
+
"step": 129
|
1113 |
+
},
|
1114 |
+
{
|
1115 |
+
"epoch": 1.0878661087866108,
|
1116 |
+
"grad_norm": 0.01882511004805565,
|
1117 |
+
"learning_rate": 9.583509874469923e-05,
|
1118 |
+
"loss": 0.0147,
|
1119 |
+
"step": 130
|
1120 |
+
},
|
1121 |
+
{
|
1122 |
+
"epoch": 1.0878661087866108,
|
1123 |
+
"eval_loss": 0.015730947256088257,
|
1124 |
+
"eval_runtime": 8.1997,
|
1125 |
+
"eval_samples_per_second": 6.098,
|
1126 |
+
"eval_steps_per_second": 1.585,
|
1127 |
+
"step": 130
|
1128 |
+
},
|
1129 |
+
{
|
1130 |
+
"epoch": 1.096234309623431,
|
1131 |
+
"grad_norm": 0.01482024509459734,
|
1132 |
+
"learning_rate": 9.571699223442074e-05,
|
1133 |
+
"loss": 0.0129,
|
1134 |
+
"step": 131
|
1135 |
+
},
|
1136 |
+
{
|
1137 |
+
"epoch": 1.104602510460251,
|
1138 |
+
"grad_norm": 0.017418276518583298,
|
1139 |
+
"learning_rate": 9.559730931631198e-05,
|
1140 |
+
"loss": 0.0137,
|
1141 |
+
"step": 132
|
1142 |
+
},
|
1143 |
+
{
|
1144 |
+
"epoch": 1.112970711297071,
|
1145 |
+
"grad_norm": 0.017272206023335457,
|
1146 |
+
"learning_rate": 9.5476054117265e-05,
|
1147 |
+
"loss": 0.0119,
|
1148 |
+
"step": 133
|
1149 |
+
},
|
1150 |
+
{
|
1151 |
+
"epoch": 1.1213389121338913,
|
1152 |
+
"grad_norm": 0.02229718305170536,
|
1153 |
+
"learning_rate": 9.535323081838691e-05,
|
1154 |
+
"loss": 0.0153,
|
1155 |
+
"step": 134
|
1156 |
+
},
|
1157 |
+
{
|
1158 |
+
"epoch": 1.1297071129707112,
|
1159 |
+
"grad_norm": 0.021549543365836143,
|
1160 |
+
"learning_rate": 9.522884365485598e-05,
|
1161 |
+
"loss": 0.0148,
|
1162 |
+
"step": 135
|
1163 |
+
},
|
1164 |
+
{
|
1165 |
+
"epoch": 1.1297071129707112,
|
1166 |
+
"eval_loss": 0.015986260026693344,
|
1167 |
+
"eval_runtime": 8.1904,
|
1168 |
+
"eval_samples_per_second": 6.105,
|
1169 |
+
"eval_steps_per_second": 1.587,
|
1170 |
+
"step": 135
|
1171 |
+
},
|
1172 |
+
{
|
1173 |
+
"epoch": 1.1380753138075315,
|
1174 |
+
"grad_norm": 0.01844065822660923,
|
1175 |
+
"learning_rate": 9.510289691577544e-05,
|
1176 |
+
"loss": 0.0138,
|
1177 |
+
"step": 136
|
1178 |
+
},
|
1179 |
+
{
|
1180 |
+
"epoch": 1.1464435146443515,
|
1181 |
+
"grad_norm": 0.022018112242221832,
|
1182 |
+
"learning_rate": 9.49753949440256e-05,
|
1183 |
+
"loss": 0.017,
|
1184 |
+
"step": 137
|
1185 |
+
},
|
1186 |
+
{
|
1187 |
+
"epoch": 1.1548117154811715,
|
1188 |
+
"grad_norm": 0.015306939370930195,
|
1189 |
+
"learning_rate": 9.484634213611411e-05,
|
1190 |
+
"loss": 0.0114,
|
1191 |
+
"step": 138
|
1192 |
+
},
|
1193 |
+
{
|
1194 |
+
"epoch": 1.1631799163179917,
|
1195 |
+
"grad_norm": 0.017746033146977425,
|
1196 |
+
"learning_rate": 9.471574294202439e-05,
|
1197 |
+
"loss": 0.0132,
|
1198 |
+
"step": 139
|
1199 |
+
},
|
1200 |
+
{
|
1201 |
+
"epoch": 1.1715481171548117,
|
1202 |
+
"grad_norm": 0.01575053483247757,
|
1203 |
+
"learning_rate": 9.458360186506213e-05,
|
1204 |
+
"loss": 0.0115,
|
1205 |
+
"step": 140
|
1206 |
+
},
|
1207 |
+
{
|
1208 |
+
"epoch": 1.1715481171548117,
|
1209 |
+
"eval_loss": 0.015280088409781456,
|
1210 |
+
"eval_runtime": 8.1915,
|
1211 |
+
"eval_samples_per_second": 6.104,
|
1212 |
+
"eval_steps_per_second": 1.587,
|
1213 |
+
"step": 140
|
1214 |
+
},
|
1215 |
+
{
|
1216 |
+
"epoch": 1.1799163179916319,
|
1217 |
+
"grad_norm": 0.019290335476398468,
|
1218 |
+
"learning_rate": 9.444992346170007e-05,
|
1219 |
+
"loss": 0.0131,
|
1220 |
+
"step": 141
|
1221 |
+
},
|
1222 |
+
{
|
1223 |
+
"epoch": 1.1882845188284519,
|
1224 |
+
"grad_norm": 0.0183683130890131,
|
1225 |
+
"learning_rate": 9.431471234142087e-05,
|
1226 |
+
"loss": 0.0136,
|
1227 |
+
"step": 142
|
1228 |
+
},
|
1229 |
+
{
|
1230 |
+
"epoch": 1.196652719665272,
|
1231 |
+
"grad_norm": 0.020060362294316292,
|
1232 |
+
"learning_rate": 9.41779731665581e-05,
|
1233 |
+
"loss": 0.0149,
|
1234 |
+
"step": 143
|
1235 |
+
},
|
1236 |
+
{
|
1237 |
+
"epoch": 1.205020920502092,
|
1238 |
+
"grad_norm": 0.017927493900060654,
|
1239 |
+
"learning_rate": 9.403971065213555e-05,
|
1240 |
+
"loss": 0.0128,
|
1241 |
+
"step": 144
|
1242 |
+
},
|
1243 |
+
{
|
1244 |
+
"epoch": 1.213389121338912,
|
1245 |
+
"grad_norm": 0.022669749334454536,
|
1246 |
+
"learning_rate": 9.389992956570462e-05,
|
1247 |
+
"loss": 0.0166,
|
1248 |
+
"step": 145
|
1249 |
+
},
|
1250 |
+
{
|
1251 |
+
"epoch": 1.213389121338912,
|
1252 |
+
"eval_loss": 0.015301547013223171,
|
1253 |
+
"eval_runtime": 8.1792,
|
1254 |
+
"eval_samples_per_second": 6.113,
|
1255 |
+
"eval_steps_per_second": 1.589,
|
1256 |
+
"step": 145
|
1257 |
+
},
|
1258 |
+
{
|
1259 |
+
"epoch": 1.2217573221757323,
|
1260 |
+
"grad_norm": 0.022278638556599617,
|
1261 |
+
"learning_rate": 9.375863472717993e-05,
|
1262 |
+
"loss": 0.0171,
|
1263 |
+
"step": 146
|
1264 |
+
},
|
1265 |
+
{
|
1266 |
+
"epoch": 1.2301255230125523,
|
1267 |
+
"grad_norm": 0.019489524886012077,
|
1268 |
+
"learning_rate": 9.361583100867313e-05,
|
1269 |
+
"loss": 0.013,
|
1270 |
+
"step": 147
|
1271 |
+
},
|
1272 |
+
{
|
1273 |
+
"epoch": 1.2384937238493725,
|
1274 |
+
"grad_norm": 0.018918950110673904,
|
1275 |
+
"learning_rate": 9.347152333432485e-05,
|
1276 |
+
"loss": 0.0139,
|
1277 |
+
"step": 148
|
1278 |
+
},
|
1279 |
+
{
|
1280 |
+
"epoch": 1.2468619246861925,
|
1281 |
+
"grad_norm": 0.01829618029296398,
|
1282 |
+
"learning_rate": 9.332571668013499e-05,
|
1283 |
+
"loss": 0.0147,
|
1284 |
+
"step": 149
|
1285 |
+
},
|
1286 |
+
{
|
1287 |
+
"epoch": 1.2552301255230125,
|
1288 |
+
"grad_norm": 0.018324939534068108,
|
1289 |
+
"learning_rate": 9.317841607379107e-05,
|
1290 |
+
"loss": 0.015,
|
1291 |
+
"step": 150
|
1292 |
+
},
|
1293 |
+
{
|
1294 |
+
"epoch": 1.2552301255230125,
|
1295 |
+
"eval_loss": 0.015605509281158447,
|
1296 |
+
"eval_runtime": 8.195,
|
1297 |
+
"eval_samples_per_second": 6.101,
|
1298 |
+
"eval_steps_per_second": 1.586,
|
1299 |
+
"step": 150
|
1300 |
+
},
|
1301 |
+
{
|
1302 |
+
"epoch": 1.2635983263598327,
|
1303 |
+
"grad_norm": 0.015184380114078522,
|
1304 |
+
"learning_rate": 9.302962659449486e-05,
|
1305 |
+
"loss": 0.0125,
|
1306 |
+
"step": 151
|
1307 |
+
},
|
1308 |
+
{
|
1309 |
+
"epoch": 1.2719665271966527,
|
1310 |
+
"grad_norm": 0.02084585465490818,
|
1311 |
+
"learning_rate": 9.287935337278733e-05,
|
1312 |
+
"loss": 0.0139,
|
1313 |
+
"step": 152
|
1314 |
+
},
|
1315 |
+
{
|
1316 |
+
"epoch": 1.280334728033473,
|
1317 |
+
"grad_norm": 0.022940685972571373,
|
1318 |
+
"learning_rate": 9.272760159037164e-05,
|
1319 |
+
"loss": 0.0168,
|
1320 |
+
"step": 153
|
1321 |
+
},
|
1322 |
+
{
|
1323 |
+
"epoch": 1.288702928870293,
|
1324 |
+
"grad_norm": 0.014851168729364872,
|
1325 |
+
"learning_rate": 9.25743764799345e-05,
|
1326 |
+
"loss": 0.0107,
|
1327 |
+
"step": 154
|
1328 |
+
},
|
1329 |
+
{
|
1330 |
+
"epoch": 1.297071129707113,
|
1331 |
+
"grad_norm": 0.01901235058903694,
|
1332 |
+
"learning_rate": 9.241968332496575e-05,
|
1333 |
+
"loss": 0.0148,
|
1334 |
+
"step": 155
|
1335 |
+
},
|
1336 |
+
{
|
1337 |
+
"epoch": 1.297071129707113,
|
1338 |
+
"eval_loss": 0.015689246356487274,
|
1339 |
+
"eval_runtime": 8.1747,
|
1340 |
+
"eval_samples_per_second": 6.116,
|
1341 |
+
"eval_steps_per_second": 1.59,
|
1342 |
+
"step": 155
|
1343 |
+
},
|
1344 |
+
{
|
1345 |
+
"epoch": 1.3054393305439331,
|
1346 |
+
"grad_norm": 0.019857851788401604,
|
1347 |
+
"learning_rate": 9.226352745957616e-05,
|
1348 |
+
"loss": 0.0121,
|
1349 |
+
"step": 156
|
1350 |
+
},
|
1351 |
+
{
|
1352 |
+
"epoch": 1.3138075313807531,
|
1353 |
+
"grad_norm": 0.020181361585855484,
|
1354 |
+
"learning_rate": 9.210591426831352e-05,
|
1355 |
+
"loss": 0.0138,
|
1356 |
+
"step": 157
|
1357 |
+
},
|
1358 |
+
{
|
1359 |
+
"epoch": 1.3221757322175733,
|
1360 |
+
"grad_norm": 0.0159543976187706,
|
1361 |
+
"learning_rate": 9.194684918597694e-05,
|
1362 |
+
"loss": 0.0119,
|
1363 |
+
"step": 158
|
1364 |
+
},
|
1365 |
+
{
|
1366 |
+
"epoch": 1.3305439330543933,
|
1367 |
+
"grad_norm": 0.015190091915428638,
|
1368 |
+
"learning_rate": 9.178633769742945e-05,
|
1369 |
+
"loss": 0.0122,
|
1370 |
+
"step": 159
|
1371 |
+
},
|
1372 |
+
{
|
1373 |
+
"epoch": 1.3389121338912133,
|
1374 |
+
"grad_norm": 0.01558399386703968,
|
1375 |
+
"learning_rate": 9.162438533740892e-05,
|
1376 |
+
"loss": 0.0112,
|
1377 |
+
"step": 160
|
1378 |
+
},
|
1379 |
+
{
|
1380 |
+
"epoch": 1.3389121338912133,
|
1381 |
+
"eval_loss": 0.01591303013265133,
|
1382 |
+
"eval_runtime": 8.203,
|
1383 |
+
"eval_samples_per_second": 6.095,
|
1384 |
+
"eval_steps_per_second": 1.585,
|
1385 |
+
"step": 160
|
1386 |
+
},
|
1387 |
+
{
|
1388 |
+
"epoch": 1.3472803347280335,
|
1389 |
+
"grad_norm": 0.020452240481972694,
|
1390 |
+
"learning_rate": 9.146099769033715e-05,
|
1391 |
+
"loss": 0.0141,
|
1392 |
+
"step": 161
|
1393 |
+
},
|
1394 |
+
{
|
1395 |
+
"epoch": 1.3556485355648535,
|
1396 |
+
"grad_norm": 0.01579088531434536,
|
1397 |
+
"learning_rate": 9.129618039012736e-05,
|
1398 |
+
"loss": 0.0123,
|
1399 |
+
"step": 162
|
1400 |
+
},
|
1401 |
+
{
|
1402 |
+
"epoch": 1.3640167364016738,
|
1403 |
+
"grad_norm": 0.01603122055530548,
|
1404 |
+
"learning_rate": 9.112993911998984e-05,
|
1405 |
+
"loss": 0.0142,
|
1406 |
+
"step": 163
|
1407 |
+
},
|
1408 |
+
{
|
1409 |
+
"epoch": 1.3723849372384938,
|
1410 |
+
"grad_norm": 0.018658515065908432,
|
1411 |
+
"learning_rate": 9.096227961223613e-05,
|
1412 |
+
"loss": 0.0149,
|
1413 |
+
"step": 164
|
1414 |
+
},
|
1415 |
+
{
|
1416 |
+
"epoch": 1.3807531380753137,
|
1417 |
+
"grad_norm": 0.01548719685524702,
|
1418 |
+
"learning_rate": 9.07932076480812e-05,
|
1419 |
+
"loss": 0.0128,
|
1420 |
+
"step": 165
|
1421 |
+
},
|
1422 |
+
{
|
1423 |
+
"epoch": 1.3807531380753137,
|
1424 |
+
"eval_loss": 0.015296611934900284,
|
1425 |
+
"eval_runtime": 8.1994,
|
1426 |
+
"eval_samples_per_second": 6.098,
|
1427 |
+
"eval_steps_per_second": 1.585,
|
1428 |
+
"step": 165
|
1429 |
+
},
|
1430 |
+
{
|
1431 |
+
"epoch": 1.389121338912134,
|
1432 |
+
"grad_norm": 0.019366098567843437,
|
1433 |
+
"learning_rate": 9.06227290574442e-05,
|
1434 |
+
"loss": 0.0136,
|
1435 |
+
"step": 166
|
1436 |
+
},
|
1437 |
+
{
|
1438 |
+
"epoch": 1.397489539748954,
|
1439 |
+
"grad_norm": 0.015139399096369743,
|
1440 |
+
"learning_rate": 9.045084971874738e-05,
|
1441 |
+
"loss": 0.0111,
|
1442 |
+
"step": 167
|
1443 |
+
},
|
1444 |
+
{
|
1445 |
+
"epoch": 1.4058577405857742,
|
1446 |
+
"grad_norm": 0.02105526067316532,
|
1447 |
+
"learning_rate": 9.027757555871344e-05,
|
1448 |
+
"loss": 0.0146,
|
1449 |
+
"step": 168
|
1450 |
+
},
|
1451 |
+
{
|
1452 |
+
"epoch": 1.4142259414225942,
|
1453 |
+
"grad_norm": 0.020205028355121613,
|
1454 |
+
"learning_rate": 9.010291255216117e-05,
|
1455 |
+
"loss": 0.0142,
|
1456 |
+
"step": 169
|
1457 |
+
},
|
1458 |
+
{
|
1459 |
+
"epoch": 1.4225941422594142,
|
1460 |
+
"grad_norm": 0.018409285694360733,
|
1461 |
+
"learning_rate": 8.99268667217993e-05,
|
1462 |
+
"loss": 0.0125,
|
1463 |
+
"step": 170
|
1464 |
+
},
|
1465 |
+
{
|
1466 |
+
"epoch": 1.4225941422594142,
|
1467 |
+
"eval_loss": 0.015141828916966915,
|
1468 |
+
"eval_runtime": 8.1926,
|
1469 |
+
"eval_samples_per_second": 6.103,
|
1470 |
+
"eval_steps_per_second": 1.587,
|
1471 |
+
"step": 170
|
1472 |
+
},
|
1473 |
+
{
|
1474 |
+
"epoch": 1.4309623430962344,
|
1475 |
+
"grad_norm": 0.0186452716588974,
|
1476 |
+
"learning_rate": 8.974944413801906e-05,
|
1477 |
+
"loss": 0.0158,
|
1478 |
+
"step": 171
|
1479 |
+
},
|
1480 |
+
{
|
1481 |
+
"epoch": 1.4393305439330544,
|
1482 |
+
"grad_norm": 0.017251404002308846,
|
1483 |
+
"learning_rate": 8.957065091868459e-05,
|
1484 |
+
"loss": 0.0138,
|
1485 |
+
"step": 172
|
1486 |
+
},
|
1487 |
+
{
|
1488 |
+
"epoch": 1.4476987447698746,
|
1489 |
+
"grad_norm": 0.015452460385859013,
|
1490 |
+
"learning_rate": 8.939049322892223e-05,
|
1491 |
+
"loss": 0.0104,
|
1492 |
+
"step": 173
|
1493 |
+
},
|
1494 |
+
{
|
1495 |
+
"epoch": 1.4560669456066946,
|
1496 |
+
"grad_norm": 0.018598852679133415,
|
1497 |
+
"learning_rate": 8.920897728090777e-05,
|
1498 |
+
"loss": 0.0142,
|
1499 |
+
"step": 174
|
1500 |
+
},
|
1501 |
+
{
|
1502 |
+
"epoch": 1.4644351464435146,
|
1503 |
+
"grad_norm": 0.017056932672858238,
|
1504 |
+
"learning_rate": 8.902610933365229e-05,
|
1505 |
+
"loss": 0.0137,
|
1506 |
+
"step": 175
|
1507 |
+
},
|
1508 |
+
{
|
1509 |
+
"epoch": 1.4644351464435146,
|
1510 |
+
"eval_loss": 0.015005652792751789,
|
1511 |
+
"eval_runtime": 8.1766,
|
1512 |
+
"eval_samples_per_second": 6.115,
|
1513 |
+
"eval_steps_per_second": 1.59,
|
1514 |
+
"step": 175
|
1515 |
+
},
|
1516 |
+
{
|
1517 |
+
"epoch": 1.4728033472803348,
|
1518 |
+
"grad_norm": 0.017095167189836502,
|
1519 |
+
"learning_rate": 8.88418956927864e-05,
|
1520 |
+
"loss": 0.0143,
|
1521 |
+
"step": 176
|
1522 |
+
},
|
1523 |
+
{
|
1524 |
+
"epoch": 1.4811715481171548,
|
1525 |
+
"grad_norm": 0.016802068799734116,
|
1526 |
+
"learning_rate": 8.865634271034268e-05,
|
1527 |
+
"loss": 0.0144,
|
1528 |
+
"step": 177
|
1529 |
+
},
|
1530 |
+
{
|
1531 |
+
"epoch": 1.489539748953975,
|
1532 |
+
"grad_norm": 0.015921777114272118,
|
1533 |
+
"learning_rate": 8.846945678453677e-05,
|
1534 |
+
"loss": 0.0138,
|
1535 |
+
"step": 178
|
1536 |
+
},
|
1537 |
+
{
|
1538 |
+
"epoch": 1.497907949790795,
|
1539 |
+
"grad_norm": 0.016825497150421143,
|
1540 |
+
"learning_rate": 8.828124435954672e-05,
|
1541 |
+
"loss": 0.0147,
|
1542 |
+
"step": 179
|
1543 |
+
},
|
1544 |
+
{
|
1545 |
+
"epoch": 1.506276150627615,
|
1546 |
+
"grad_norm": 0.01446506567299366,
|
1547 |
+
"learning_rate": 8.809171192529073e-05,
|
1548 |
+
"loss": 0.0131,
|
1549 |
+
"step": 180
|
1550 |
+
},
|
1551 |
+
{
|
1552 |
+
"epoch": 1.506276150627615,
|
1553 |
+
"eval_loss": 0.014517219737172127,
|
1554 |
+
"eval_runtime": 8.201,
|
1555 |
+
"eval_samples_per_second": 6.097,
|
1556 |
+
"eval_steps_per_second": 1.585,
|
1557 |
+
"step": 180
|
1558 |
+
},
|
1559 |
+
{
|
1560 |
+
"epoch": 1.514644351464435,
|
1561 |
+
"grad_norm": 0.016049686819314957,
|
1562 |
+
"learning_rate": 8.790086601720339e-05,
|
1563 |
+
"loss": 0.0137,
|
1564 |
+
"step": 181
|
1565 |
+
},
|
1566 |
+
{
|
1567 |
+
"epoch": 1.5230125523012552,
|
1568 |
+
"grad_norm": 0.015877775847911835,
|
1569 |
+
"learning_rate": 8.77087132160104e-05,
|
1570 |
+
"loss": 0.0126,
|
1571 |
+
"step": 182
|
1572 |
+
},
|
1573 |
+
{
|
1574 |
+
"epoch": 1.5313807531380754,
|
1575 |
+
"grad_norm": 0.01960177719593048,
|
1576 |
+
"learning_rate": 8.751526014750153e-05,
|
1577 |
+
"loss": 0.0149,
|
1578 |
+
"step": 183
|
1579 |
+
},
|
1580 |
+
{
|
1581 |
+
"epoch": 1.5397489539748954,
|
1582 |
+
"grad_norm": 0.0134076913818717,
|
1583 |
+
"learning_rate": 8.732051348230223e-05,
|
1584 |
+
"loss": 0.0114,
|
1585 |
+
"step": 184
|
1586 |
+
},
|
1587 |
+
{
|
1588 |
+
"epoch": 1.5481171548117154,
|
1589 |
+
"grad_norm": 0.012596129439771175,
|
1590 |
+
"learning_rate": 8.712447993564361e-05,
|
1591 |
+
"loss": 0.0105,
|
1592 |
+
"step": 185
|
1593 |
+
},
|
1594 |
+
{
|
1595 |
+
"epoch": 1.5481171548117154,
|
1596 |
+
"eval_loss": 0.014493227005004883,
|
1597 |
+
"eval_runtime": 8.1918,
|
1598 |
+
"eval_samples_per_second": 6.104,
|
1599 |
+
"eval_steps_per_second": 1.587,
|
1600 |
+
"step": 185
|
1601 |
+
},
|
1602 |
+
{
|
1603 |
+
"epoch": 1.5564853556485354,
|
1604 |
+
"grad_norm": 0.016738103702664375,
|
1605 |
+
"learning_rate": 8.692716626713084e-05,
|
1606 |
+
"loss": 0.0133,
|
1607 |
+
"step": 186
|
1608 |
+
},
|
1609 |
+
{
|
1610 |
+
"epoch": 1.5648535564853556,
|
1611 |
+
"grad_norm": 0.02182360552251339,
|
1612 |
+
"learning_rate": 8.672857928051013e-05,
|
1613 |
+
"loss": 0.014,
|
1614 |
+
"step": 187
|
1615 |
+
},
|
1616 |
+
{
|
1617 |
+
"epoch": 1.5732217573221758,
|
1618 |
+
"grad_norm": 0.017175616696476936,
|
1619 |
+
"learning_rate": 8.652872582343408e-05,
|
1620 |
+
"loss": 0.011,
|
1621 |
+
"step": 188
|
1622 |
+
},
|
1623 |
+
{
|
1624 |
+
"epoch": 1.5815899581589958,
|
1625 |
+
"grad_norm": 0.01974942907691002,
|
1626 |
+
"learning_rate": 8.632761278722556e-05,
|
1627 |
+
"loss": 0.0147,
|
1628 |
+
"step": 189
|
1629 |
+
},
|
1630 |
+
{
|
1631 |
+
"epoch": 1.5899581589958158,
|
1632 |
+
"grad_norm": 0.016432059928774834,
|
1633 |
+
"learning_rate": 8.612524710664012e-05,
|
1634 |
+
"loss": 0.0126,
|
1635 |
+
"step": 190
|
1636 |
+
},
|
1637 |
+
{
|
1638 |
+
"epoch": 1.5899581589958158,
|
1639 |
+
"eval_loss": 0.014403114095330238,
|
1640 |
+
"eval_runtime": 8.1978,
|
1641 |
+
"eval_samples_per_second": 6.099,
|
1642 |
+
"eval_steps_per_second": 1.586,
|
1643 |
+
"step": 190
|
1644 |
+
},
|
1645 |
+
{
|
1646 |
+
"epoch": 1.5983263598326358,
|
1647 |
+
"grad_norm": 0.01811247691512108,
|
1648 |
+
"learning_rate": 8.592163575962682e-05,
|
1649 |
+
"loss": 0.0128,
|
1650 |
+
"step": 191
|
1651 |
+
},
|
1652 |
+
{
|
1653 |
+
"epoch": 1.606694560669456,
|
1654 |
+
"grad_norm": 0.017857994884252548,
|
1655 |
+
"learning_rate": 8.571678576708766e-05,
|
1656 |
+
"loss": 0.0117,
|
1657 |
+
"step": 192
|
1658 |
+
},
|
1659 |
+
{
|
1660 |
+
"epoch": 1.6150627615062763,
|
1661 |
+
"grad_norm": 0.02201293222606182,
|
1662 |
+
"learning_rate": 8.551070419263545e-05,
|
1663 |
+
"loss": 0.017,
|
1664 |
+
"step": 193
|
1665 |
+
},
|
1666 |
+
{
|
1667 |
+
"epoch": 1.6234309623430963,
|
1668 |
+
"grad_norm": 0.018607452511787415,
|
1669 |
+
"learning_rate": 8.530339814235027e-05,
|
1670 |
+
"loss": 0.0123,
|
1671 |
+
"step": 194
|
1672 |
+
},
|
1673 |
+
{
|
1674 |
+
"epoch": 1.6317991631799162,
|
1675 |
+
"grad_norm": 0.015770630910992622,
|
1676 |
+
"learning_rate": 8.509487476453442e-05,
|
1677 |
+
"loss": 0.0119,
|
1678 |
+
"step": 195
|
1679 |
+
},
|
1680 |
+
{
|
1681 |
+
"epoch": 1.6317991631799162,
|
1682 |
+
"eval_loss": 0.014461501501500607,
|
1683 |
+
"eval_runtime": 8.1846,
|
1684 |
+
"eval_samples_per_second": 6.109,
|
1685 |
+
"eval_steps_per_second": 1.588,
|
1686 |
+
"step": 195
|
1687 |
+
},
|
1688 |
+
{
|
1689 |
+
"epoch": 1.6401673640167362,
|
1690 |
+
"grad_norm": 0.015161648392677307,
|
1691 |
+
"learning_rate": 8.488514124946594e-05,
|
1692 |
+
"loss": 0.0137,
|
1693 |
+
"step": 196
|
1694 |
+
},
|
1695 |
+
{
|
1696 |
+
"epoch": 1.6485355648535565,
|
1697 |
+
"grad_norm": 0.015444417484104633,
|
1698 |
+
"learning_rate": 8.46742048291507e-05,
|
1699 |
+
"loss": 0.0116,
|
1700 |
+
"step": 197
|
1701 |
+
},
|
1702 |
+
{
|
1703 |
+
"epoch": 1.6569037656903767,
|
1704 |
+
"grad_norm": 0.018221288919448853,
|
1705 |
+
"learning_rate": 8.446207277707296e-05,
|
1706 |
+
"loss": 0.0135,
|
1707 |
+
"step": 198
|
1708 |
+
},
|
1709 |
+
{
|
1710 |
+
"epoch": 1.6652719665271967,
|
1711 |
+
"grad_norm": 0.017886707559227943,
|
1712 |
+
"learning_rate": 8.424875240794467e-05,
|
1713 |
+
"loss": 0.0117,
|
1714 |
+
"step": 199
|
1715 |
+
},
|
1716 |
+
{
|
1717 |
+
"epoch": 1.6736401673640167,
|
1718 |
+
"grad_norm": 0.021269524469971657,
|
1719 |
+
"learning_rate": 8.403425107745316e-05,
|
1720 |
+
"loss": 0.016,
|
1721 |
+
"step": 200
|
1722 |
+
},
|
1723 |
+
{
|
1724 |
+
"epoch": 1.6736401673640167,
|
1725 |
+
"eval_loss": 0.014672570861876011,
|
1726 |
+
"eval_runtime": 8.2192,
|
1727 |
+
"eval_samples_per_second": 6.083,
|
1728 |
+
"eval_steps_per_second": 1.582,
|
1729 |
+
"step": 200
|
1730 |
+
},
|
1731 |
+
{
|
1732 |
+
"epoch": 1.6820083682008367,
|
1733 |
+
"grad_norm": 0.014137690886855125,
|
1734 |
+
"learning_rate": 8.381857618200746e-05,
|
1735 |
+
"loss": 0.0107,
|
1736 |
+
"step": 201
|
1737 |
+
},
|
1738 |
+
{
|
1739 |
+
"epoch": 1.6903765690376569,
|
1740 |
+
"grad_norm": 0.017183968797326088,
|
1741 |
+
"learning_rate": 8.360173515848343e-05,
|
1742 |
+
"loss": 0.0127,
|
1743 |
+
"step": 202
|
1744 |
+
},
|
1745 |
+
{
|
1746 |
+
"epoch": 1.698744769874477,
|
1747 |
+
"grad_norm": 0.018049761652946472,
|
1748 |
+
"learning_rate": 8.33837354839672e-05,
|
1749 |
+
"loss": 0.0099,
|
1750 |
+
"step": 203
|
1751 |
+
},
|
1752 |
+
{
|
1753 |
+
"epoch": 1.707112970711297,
|
1754 |
+
"grad_norm": 0.020697997882962227,
|
1755 |
+
"learning_rate": 8.316458467549729e-05,
|
1756 |
+
"loss": 0.0131,
|
1757 |
+
"step": 204
|
1758 |
+
},
|
1759 |
+
{
|
1760 |
+
"epoch": 1.715481171548117,
|
1761 |
+
"grad_norm": 0.022819431498646736,
|
1762 |
+
"learning_rate": 8.294429028980556e-05,
|
1763 |
+
"loss": 0.0143,
|
1764 |
+
"step": 205
|
1765 |
+
},
|
1766 |
+
{
|
1767 |
+
"epoch": 1.715481171548117,
|
1768 |
+
"eval_loss": 0.014957732520997524,
|
1769 |
+
"eval_runtime": 8.2053,
|
1770 |
+
"eval_samples_per_second": 6.094,
|
1771 |
+
"eval_steps_per_second": 1.584,
|
1772 |
+
"step": 205
|
1773 |
+
},
|
1774 |
+
{
|
1775 |
+
"epoch": 1.723849372384937,
|
1776 |
+
"grad_norm": 0.020023057237267494,
|
1777 |
+
"learning_rate": 8.272285992305653e-05,
|
1778 |
+
"loss": 0.014,
|
1779 |
+
"step": 206
|
1780 |
+
},
|
1781 |
+
{
|
1782 |
+
"epoch": 1.7322175732217573,
|
1783 |
+
"grad_norm": 0.01683293841779232,
|
1784 |
+
"learning_rate": 8.250030121058547e-05,
|
1785 |
+
"loss": 0.0112,
|
1786 |
+
"step": 207
|
1787 |
+
},
|
1788 |
+
{
|
1789 |
+
"epoch": 1.7405857740585775,
|
1790 |
+
"grad_norm": 0.01992541179060936,
|
1791 |
+
"learning_rate": 8.227662182663518e-05,
|
1792 |
+
"loss": 0.0129,
|
1793 |
+
"step": 208
|
1794 |
+
},
|
1795 |
+
{
|
1796 |
+
"epoch": 1.7489539748953975,
|
1797 |
+
"grad_norm": 0.01862913742661476,
|
1798 |
+
"learning_rate": 8.205182948409125e-05,
|
1799 |
+
"loss": 0.0131,
|
1800 |
+
"step": 209
|
1801 |
+
},
|
1802 |
+
{
|
1803 |
+
"epoch": 1.7573221757322175,
|
1804 |
+
"grad_norm": 0.01816224865615368,
|
1805 |
+
"learning_rate": 8.182593193421625e-05,
|
1806 |
+
"loss": 0.0139,
|
1807 |
+
"step": 210
|
1808 |
+
},
|
1809 |
+
{
|
1810 |
+
"epoch": 1.7573221757322175,
|
1811 |
+
"eval_loss": 0.014965851791203022,
|
1812 |
+
"eval_runtime": 8.2076,
|
1813 |
+
"eval_samples_per_second": 6.092,
|
1814 |
+
"eval_steps_per_second": 1.584,
|
1815 |
+
"step": 210
|
1816 |
+
},
|
1817 |
+
{
|
1818 |
+
"epoch": 1.7656903765690377,
|
1819 |
+
"grad_norm": 0.015293323434889317,
|
1820 |
+
"learning_rate": 8.159893696638232e-05,
|
1821 |
+
"loss": 0.0122,
|
1822 |
+
"step": 211
|
1823 |
+
},
|
1824 |
+
{
|
1825 |
+
"epoch": 1.7740585774058577,
|
1826 |
+
"grad_norm": 0.013619404286146164,
|
1827 |
+
"learning_rate": 8.137085240780262e-05,
|
1828 |
+
"loss": 0.0107,
|
1829 |
+
"step": 212
|
1830 |
+
},
|
1831 |
+
{
|
1832 |
+
"epoch": 1.782426778242678,
|
1833 |
+
"grad_norm": 0.015562871471047401,
|
1834 |
+
"learning_rate": 8.114168612326153e-05,
|
1835 |
+
"loss": 0.0106,
|
1836 |
+
"step": 213
|
1837 |
+
},
|
1838 |
+
{
|
1839 |
+
"epoch": 1.790794979079498,
|
1840 |
+
"grad_norm": 0.017086800187826157,
|
1841 |
+
"learning_rate": 8.091144601484332e-05,
|
1842 |
+
"loss": 0.0131,
|
1843 |
+
"step": 214
|
1844 |
+
},
|
1845 |
+
{
|
1846 |
+
"epoch": 1.799163179916318,
|
1847 |
+
"grad_norm": 0.020527249202132225,
|
1848 |
+
"learning_rate": 8.06801400216597e-05,
|
1849 |
+
"loss": 0.0139,
|
1850 |
+
"step": 215
|
1851 |
+
},
|
1852 |
+
{
|
1853 |
+
"epoch": 1.799163179916318,
|
1854 |
+
"eval_loss": 0.01450226828455925,
|
1855 |
+
"eval_runtime": 8.1927,
|
1856 |
+
"eval_samples_per_second": 6.103,
|
1857 |
+
"eval_steps_per_second": 1.587,
|
1858 |
+
"step": 215
|
1859 |
+
},
|
1860 |
+
{
|
1861 |
+
"epoch": 1.8075313807531381,
|
1862 |
+
"grad_norm": 0.015211045742034912,
|
1863 |
+
"learning_rate": 8.044777611957613e-05,
|
1864 |
+
"loss": 0.0114,
|
1865 |
+
"step": 216
|
1866 |
+
},
|
1867 |
+
{
|
1868 |
+
"epoch": 1.8158995815899581,
|
1869 |
+
"grad_norm": 0.01953182741999626,
|
1870 |
+
"learning_rate": 8.021436232093675e-05,
|
1871 |
+
"loss": 0.0136,
|
1872 |
+
"step": 217
|
1873 |
+
},
|
1874 |
+
{
|
1875 |
+
"epoch": 1.8242677824267783,
|
1876 |
+
"grad_norm": 0.018059900030493736,
|
1877 |
+
"learning_rate": 7.997990667428811e-05,
|
1878 |
+
"loss": 0.013,
|
1879 |
+
"step": 218
|
1880 |
+
},
|
1881 |
+
{
|
1882 |
+
"epoch": 1.8326359832635983,
|
1883 |
+
"grad_norm": 0.019347647204995155,
|
1884 |
+
"learning_rate": 7.974441726410164e-05,
|
1885 |
+
"loss": 0.0142,
|
1886 |
+
"step": 219
|
1887 |
+
},
|
1888 |
+
{
|
1889 |
+
"epoch": 1.8410041841004183,
|
1890 |
+
"grad_norm": 0.016715556383132935,
|
1891 |
+
"learning_rate": 7.950790221049484e-05,
|
1892 |
+
"loss": 0.0161,
|
1893 |
+
"step": 220
|
1894 |
+
},
|
1895 |
+
{
|
1896 |
+
"epoch": 1.8410041841004183,
|
1897 |
+
"eval_loss": 0.014255787245929241,
|
1898 |
+
"eval_runtime": 8.1832,
|
1899 |
+
"eval_samples_per_second": 6.11,
|
1900 |
+
"eval_steps_per_second": 1.589,
|
1901 |
+
"step": 220
|
1902 |
+
},
|
1903 |
+
{
|
1904 |
+
"epoch": 1.8493723849372385,
|
1905 |
+
"grad_norm": 0.015245197340846062,
|
1906 |
+
"learning_rate": 7.927036966895138e-05,
|
1907 |
+
"loss": 0.0117,
|
1908 |
+
"step": 221
|
1909 |
+
},
|
1910 |
+
{
|
1911 |
+
"epoch": 1.8577405857740585,
|
1912 |
+
"grad_norm": 0.016146808862686157,
|
1913 |
+
"learning_rate": 7.90318278300398e-05,
|
1914 |
+
"loss": 0.0132,
|
1915 |
+
"step": 222
|
1916 |
+
},
|
1917 |
+
{
|
1918 |
+
"epoch": 1.8661087866108788,
|
1919 |
+
"grad_norm": 0.01640206389129162,
|
1920 |
+
"learning_rate": 7.879228491913111e-05,
|
1921 |
+
"loss": 0.012,
|
1922 |
+
"step": 223
|
1923 |
+
},
|
1924 |
+
{
|
1925 |
+
"epoch": 1.8744769874476988,
|
1926 |
+
"grad_norm": 0.01924493908882141,
|
1927 |
+
"learning_rate": 7.855174919611517e-05,
|
1928 |
+
"loss": 0.0135,
|
1929 |
+
"step": 224
|
1930 |
+
},
|
1931 |
+
{
|
1932 |
+
"epoch": 1.8828451882845187,
|
1933 |
+
"grad_norm": 0.01706533320248127,
|
1934 |
+
"learning_rate": 7.831022895511587e-05,
|
1935 |
+
"loss": 0.0098,
|
1936 |
+
"step": 225
|
1937 |
+
},
|
1938 |
+
{
|
1939 |
+
"epoch": 1.8828451882845187,
|
1940 |
+
"eval_loss": 0.013838106766343117,
|
1941 |
+
"eval_runtime": 8.1961,
|
1942 |
+
"eval_samples_per_second": 6.1,
|
1943 |
+
"eval_steps_per_second": 1.586,
|
1944 |
+
"step": 225
|
1945 |
+
},
|
1946 |
+
{
|
1947 |
+
"epoch": 1.891213389121339,
|
1948 |
+
"grad_norm": 0.01932067796587944,
|
1949 |
+
"learning_rate": 7.80677325242051e-05,
|
1950 |
+
"loss": 0.0144,
|
1951 |
+
"step": 226
|
1952 |
+
},
|
1953 |
+
{
|
1954 |
+
"epoch": 1.899581589958159,
|
1955 |
+
"grad_norm": 0.018316643312573433,
|
1956 |
+
"learning_rate": 7.782426826511564e-05,
|
1957 |
+
"loss": 0.0124,
|
1958 |
+
"step": 227
|
1959 |
+
},
|
1960 |
+
{
|
1961 |
+
"epoch": 1.9079497907949792,
|
1962 |
+
"grad_norm": 0.016697222366929054,
|
1963 |
+
"learning_rate": 7.757984457295284e-05,
|
1964 |
+
"loss": 0.0125,
|
1965 |
+
"step": 228
|
1966 |
+
},
|
1967 |
+
{
|
1968 |
+
"epoch": 1.9163179916317992,
|
1969 |
+
"grad_norm": 0.014732821844518185,
|
1970 |
+
"learning_rate": 7.733446987590505e-05,
|
1971 |
+
"loss": 0.0115,
|
1972 |
+
"step": 229
|
1973 |
+
},
|
1974 |
+
{
|
1975 |
+
"epoch": 1.9246861924686192,
|
1976 |
+
"grad_norm": 0.01892097480595112,
|
1977 |
+
"learning_rate": 7.708815263495308e-05,
|
1978 |
+
"loss": 0.0108,
|
1979 |
+
"step": 230
|
1980 |
+
},
|
1981 |
+
{
|
1982 |
+
"epoch": 1.9246861924686192,
|
1983 |
+
"eval_loss": 0.014023682102560997,
|
1984 |
+
"eval_runtime": 8.1828,
|
1985 |
+
"eval_samples_per_second": 6.11,
|
1986 |
+
"eval_steps_per_second": 1.589,
|
1987 |
+
"step": 230
|
1988 |
+
},
|
1989 |
+
{
|
1990 |
+
"epoch": 1.9330543933054394,
|
1991 |
+
"grad_norm": 0.018761448562145233,
|
1992 |
+
"learning_rate": 7.684090134357839e-05,
|
1993 |
+
"loss": 0.014,
|
1994 |
+
"step": 231
|
1995 |
+
},
|
1996 |
+
{
|
1997 |
+
"epoch": 1.9414225941422594,
|
1998 |
+
"grad_norm": 0.01908651366829872,
|
1999 |
+
"learning_rate": 7.65927245274703e-05,
|
2000 |
+
"loss": 0.0102,
|
2001 |
+
"step": 232
|
2002 |
+
},
|
2003 |
+
{
|
2004 |
+
"epoch": 1.9497907949790796,
|
2005 |
+
"grad_norm": 0.018542446196079254,
|
2006 |
+
"learning_rate": 7.634363074423199e-05,
|
2007 |
+
"loss": 0.0133,
|
2008 |
+
"step": 233
|
2009 |
+
},
|
2010 |
+
{
|
2011 |
+
"epoch": 1.9581589958158996,
|
2012 |
+
"grad_norm": 0.018298540264368057,
|
2013 |
+
"learning_rate": 7.609362858308531e-05,
|
2014 |
+
"loss": 0.0139,
|
2015 |
+
"step": 234
|
2016 |
+
},
|
2017 |
+
{
|
2018 |
+
"epoch": 1.9665271966527196,
|
2019 |
+
"grad_norm": 0.01675599068403244,
|
2020 |
+
"learning_rate": 7.58427266645747e-05,
|
2021 |
+
"loss": 0.0117,
|
2022 |
+
"step": 235
|
2023 |
+
},
|
2024 |
+
{
|
2025 |
+
"epoch": 1.9665271966527196,
|
2026 |
+
"eval_loss": 0.014116828329861164,
|
2027 |
+
"eval_runtime": 8.1955,
|
2028 |
+
"eval_samples_per_second": 6.101,
|
2029 |
+
"eval_steps_per_second": 1.586,
|
2030 |
+
"step": 235
|
2031 |
+
},
|
2032 |
+
{
|
2033 |
+
"epoch": 1.9748953974895398,
|
2034 |
+
"grad_norm": 0.020569469779729843,
|
2035 |
+
"learning_rate": 7.559093364027001e-05,
|
2036 |
+
"loss": 0.0141,
|
2037 |
+
"step": 236
|
2038 |
+
},
|
2039 |
+
{
|
2040 |
+
"epoch": 1.9832635983263598,
|
2041 |
+
"grad_norm": 0.016174696385860443,
|
2042 |
+
"learning_rate": 7.5338258192468e-05,
|
2043 |
+
"loss": 0.0105,
|
2044 |
+
"step": 237
|
2045 |
+
},
|
2046 |
+
{
|
2047 |
+
"epoch": 1.99163179916318,
|
2048 |
+
"grad_norm": 0.02071259915828705,
|
2049 |
+
"learning_rate": 7.508470903389311e-05,
|
2050 |
+
"loss": 0.0138,
|
2051 |
+
"step": 238
|
2052 |
+
},
|
2053 |
+
{
|
2054 |
+
"epoch": 2.0,
|
2055 |
+
"grad_norm": 0.022858325392007828,
|
2056 |
+
"learning_rate": 7.48302949073969e-05,
|
2057 |
+
"loss": 0.0166,
|
2058 |
+
"step": 239
|
2059 |
+
},
|
2060 |
+
{
|
2061 |
+
"epoch": 2.00836820083682,
|
2062 |
+
"grad_norm": 0.01647881604731083,
|
2063 |
+
"learning_rate": 7.457502458565672e-05,
|
2064 |
+
"loss": 0.0109,
|
2065 |
+
"step": 240
|
2066 |
+
},
|
2067 |
+
{
|
2068 |
+
"epoch": 2.00836820083682,
|
2069 |
+
"eval_loss": 0.013845333829522133,
|
2070 |
+
"eval_runtime": 8.1876,
|
2071 |
+
"eval_samples_per_second": 6.107,
|
2072 |
+
"eval_steps_per_second": 1.588,
|
2073 |
+
"step": 240
|
2074 |
+
},
|
2075 |
+
{
|
2076 |
+
"epoch": 2.01673640167364,
|
2077 |
+
"grad_norm": 0.01600758358836174,
|
2078 |
+
"learning_rate": 7.431890687087313e-05,
|
2079 |
+
"loss": 0.0102,
|
2080 |
+
"step": 241
|
2081 |
+
},
|
2082 |
+
{
|
2083 |
+
"epoch": 2.0251046025104604,
|
2084 |
+
"grad_norm": 0.013506948947906494,
|
2085 |
+
"learning_rate": 7.406195059446636e-05,
|
2086 |
+
"loss": 0.0103,
|
2087 |
+
"step": 242
|
2088 |
+
},
|
2089 |
+
{
|
2090 |
+
"epoch": 2.0334728033472804,
|
2091 |
+
"grad_norm": 0.019151534885168076,
|
2092 |
+
"learning_rate": 7.380416461677187e-05,
|
2093 |
+
"loss": 0.0119,
|
2094 |
+
"step": 243
|
2095 |
+
},
|
2096 |
+
{
|
2097 |
+
"epoch": 2.0418410041841004,
|
2098 |
+
"grad_norm": 0.01597500592470169,
|
2099 |
+
"learning_rate": 7.354555782673473e-05,
|
2100 |
+
"loss": 0.0107,
|
2101 |
+
"step": 244
|
2102 |
+
},
|
2103 |
+
{
|
2104 |
+
"epoch": 2.0502092050209204,
|
2105 |
+
"grad_norm": 0.014115000143647194,
|
2106 |
+
"learning_rate": 7.328613914160318e-05,
|
2107 |
+
"loss": 0.0093,
|
2108 |
+
"step": 245
|
2109 |
+
},
|
2110 |
+
{
|
2111 |
+
"epoch": 2.0502092050209204,
|
2112 |
+
"eval_loss": 0.014546514488756657,
|
2113 |
+
"eval_runtime": 8.1884,
|
2114 |
+
"eval_samples_per_second": 6.106,
|
2115 |
+
"eval_steps_per_second": 1.588,
|
2116 |
+
"step": 245
|
2117 |
+
},
|
2118 |
+
{
|
2119 |
+
"epoch": 2.0585774058577404,
|
2120 |
+
"grad_norm": 0.01916162669658661,
|
2121 |
+
"learning_rate": 7.302591750662116e-05,
|
2122 |
+
"loss": 0.0117,
|
2123 |
+
"step": 246
|
2124 |
+
},
|
2125 |
+
{
|
2126 |
+
"epoch": 2.066945606694561,
|
2127 |
+
"grad_norm": 0.019530242308974266,
|
2128 |
+
"learning_rate": 7.276490189471977e-05,
|
2129 |
+
"loss": 0.01,
|
2130 |
+
"step": 247
|
2131 |
+
},
|
2132 |
+
{
|
2133 |
+
"epoch": 2.075313807531381,
|
2134 |
+
"grad_norm": 0.02205420657992363,
|
2135 |
+
"learning_rate": 7.250310130620799e-05,
|
2136 |
+
"loss": 0.0111,
|
2137 |
+
"step": 248
|
2138 |
+
},
|
2139 |
+
{
|
2140 |
+
"epoch": 2.083682008368201,
|
2141 |
+
"grad_norm": 0.025347299873828888,
|
2142 |
+
"learning_rate": 7.224052476846222e-05,
|
2143 |
+
"loss": 0.0115,
|
2144 |
+
"step": 249
|
2145 |
+
},
|
2146 |
+
{
|
2147 |
+
"epoch": 2.092050209205021,
|
2148 |
+
"grad_norm": 0.018653597682714462,
|
2149 |
+
"learning_rate": 7.197718133561508e-05,
|
2150 |
+
"loss": 0.0102,
|
2151 |
+
"step": 250
|
2152 |
+
},
|
2153 |
+
{
|
2154 |
+
"epoch": 2.092050209205021,
|
2155 |
+
"eval_loss": 0.014336950145661831,
|
2156 |
+
"eval_runtime": 8.2008,
|
2157 |
+
"eval_samples_per_second": 6.097,
|
2158 |
+
"eval_steps_per_second": 1.585,
|
2159 |
+
"step": 250
|
2160 |
+
},
|
2161 |
+
{
|
2162 |
+
"epoch": 2.100418410041841,
|
2163 |
+
"grad_norm": 0.01541041024029255,
|
2164 |
+
"learning_rate": 7.171308008824316e-05,
|
2165 |
+
"loss": 0.0105,
|
2166 |
+
"step": 251
|
2167 |
+
},
|
2168 |
+
{
|
2169 |
+
"epoch": 2.1087866108786613,
|
2170 |
+
"grad_norm": 0.014182745479047298,
|
2171 |
+
"learning_rate": 7.144823013305394e-05,
|
2172 |
+
"loss": 0.0085,
|
2173 |
+
"step": 252
|
2174 |
+
},
|
2175 |
+
{
|
2176 |
+
"epoch": 2.1171548117154813,
|
2177 |
+
"grad_norm": 0.022554123774170876,
|
2178 |
+
"learning_rate": 7.118264060257169e-05,
|
2179 |
+
"loss": 0.0116,
|
2180 |
+
"step": 253
|
2181 |
+
},
|
2182 |
+
{
|
2183 |
+
"epoch": 2.1255230125523012,
|
2184 |
+
"grad_norm": 0.02267191931605339,
|
2185 |
+
"learning_rate": 7.091632065482272e-05,
|
2186 |
+
"loss": 0.0115,
|
2187 |
+
"step": 254
|
2188 |
+
},
|
2189 |
+
{
|
2190 |
+
"epoch": 2.1338912133891212,
|
2191 |
+
"grad_norm": 0.01669103093445301,
|
2192 |
+
"learning_rate": 7.064927947301943e-05,
|
2193 |
+
"loss": 0.0104,
|
2194 |
+
"step": 255
|
2195 |
+
},
|
2196 |
+
{
|
2197 |
+
"epoch": 2.1338912133891212,
|
2198 |
+
"eval_loss": 0.014133421704173088,
|
2199 |
+
"eval_runtime": 8.1833,
|
2200 |
+
"eval_samples_per_second": 6.11,
|
2201 |
+
"eval_steps_per_second": 1.589,
|
2202 |
+
"step": 255
|
2203 |
+
},
|
2204 |
+
{
|
2205 |
+
"epoch": 2.1422594142259412,
|
2206 |
+
"grad_norm": 0.01666867360472679,
|
2207 |
+
"learning_rate": 7.038152626524373e-05,
|
2208 |
+
"loss": 0.0097,
|
2209 |
+
"step": 256
|
2210 |
+
},
|
2211 |
+
{
|
2212 |
+
"epoch": 2.1506276150627617,
|
2213 |
+
"grad_norm": 0.0202019102871418,
|
2214 |
+
"learning_rate": 7.011307026412958e-05,
|
2215 |
+
"loss": 0.0106,
|
2216 |
+
"step": 257
|
2217 |
+
},
|
2218 |
+
{
|
2219 |
+
"epoch": 2.1589958158995817,
|
2220 |
+
"grad_norm": 0.017287522554397583,
|
2221 |
+
"learning_rate": 6.984392072654453e-05,
|
2222 |
+
"loss": 0.0105,
|
2223 |
+
"step": 258
|
2224 |
+
},
|
2225 |
+
{
|
2226 |
+
"epoch": 2.1673640167364017,
|
2227 |
+
"grad_norm": 0.014798184856772423,
|
2228 |
+
"learning_rate": 6.957408693327055e-05,
|
2229 |
+
"loss": 0.0096,
|
2230 |
+
"step": 259
|
2231 |
+
},
|
2232 |
+
{
|
2233 |
+
"epoch": 2.1757322175732217,
|
2234 |
+
"grad_norm": 0.016632311046123505,
|
2235 |
+
"learning_rate": 6.930357818868409e-05,
|
2236 |
+
"loss": 0.0108,
|
2237 |
+
"step": 260
|
2238 |
+
},
|
2239 |
+
{
|
2240 |
+
"epoch": 2.1757322175732217,
|
2241 |
+
"eval_loss": 0.0147059615701437,
|
2242 |
+
"eval_runtime": 8.1958,
|
2243 |
+
"eval_samples_per_second": 6.101,
|
2244 |
+
"eval_steps_per_second": 1.586,
|
2245 |
+
"step": 260
|
2246 |
+
},
|
2247 |
+
{
|
2248 |
+
"epoch": 2.1841004184100417,
|
2249 |
+
"grad_norm": 0.016555817797780037,
|
2250 |
+
"learning_rate": 6.903240382043514e-05,
|
2251 |
+
"loss": 0.011,
|
2252 |
+
"step": 261
|
2253 |
+
},
|
2254 |
+
{
|
2255 |
+
"epoch": 2.192468619246862,
|
2256 |
+
"grad_norm": 0.015979807823896408,
|
2257 |
+
"learning_rate": 6.876057317912569e-05,
|
2258 |
+
"loss": 0.0108,
|
2259 |
+
"step": 262
|
2260 |
+
},
|
2261 |
+
{
|
2262 |
+
"epoch": 2.200836820083682,
|
2263 |
+
"grad_norm": 0.014860883355140686,
|
2264 |
+
"learning_rate": 6.848809563798721e-05,
|
2265 |
+
"loss": 0.0106,
|
2266 |
+
"step": 263
|
2267 |
+
},
|
2268 |
+
{
|
2269 |
+
"epoch": 2.209205020920502,
|
2270 |
+
"grad_norm": 0.016682744026184082,
|
2271 |
+
"learning_rate": 6.821498059255752e-05,
|
2272 |
+
"loss": 0.0101,
|
2273 |
+
"step": 264
|
2274 |
+
},
|
2275 |
+
{
|
2276 |
+
"epoch": 2.217573221757322,
|
2277 |
+
"grad_norm": 0.017817750573158264,
|
2278 |
+
"learning_rate": 6.79412374603568e-05,
|
2279 |
+
"loss": 0.0104,
|
2280 |
+
"step": 265
|
2281 |
+
},
|
2282 |
+
{
|
2283 |
+
"epoch": 2.217573221757322,
|
2284 |
+
"eval_loss": 0.014249371364712715,
|
2285 |
+
"eval_runtime": 8.1965,
|
2286 |
+
"eval_samples_per_second": 6.1,
|
2287 |
+
"eval_steps_per_second": 1.586,
|
2288 |
+
"step": 265
|
2289 |
+
},
|
2290 |
+
{
|
2291 |
+
"epoch": 2.225941422594142,
|
2292 |
+
"grad_norm": 0.014692910015583038,
|
2293 |
+
"learning_rate": 6.766687568056281e-05,
|
2294 |
+
"loss": 0.0093,
|
2295 |
+
"step": 266
|
2296 |
+
},
|
2297 |
+
{
|
2298 |
+
"epoch": 2.2343096234309625,
|
2299 |
+
"grad_norm": 0.01461927779018879,
|
2300 |
+
"learning_rate": 6.739190471368548e-05,
|
2301 |
+
"loss": 0.0099,
|
2302 |
+
"step": 267
|
2303 |
+
},
|
2304 |
+
{
|
2305 |
+
"epoch": 2.2426778242677825,
|
2306 |
+
"grad_norm": 0.01550222933292389,
|
2307 |
+
"learning_rate": 6.711633404124062e-05,
|
2308 |
+
"loss": 0.0105,
|
2309 |
+
"step": 268
|
2310 |
+
},
|
2311 |
+
{
|
2312 |
+
"epoch": 2.2510460251046025,
|
2313 |
+
"grad_norm": 0.01469459943473339,
|
2314 |
+
"learning_rate": 6.684017316542302e-05,
|
2315 |
+
"loss": 0.01,
|
2316 |
+
"step": 269
|
2317 |
+
},
|
2318 |
+
{
|
2319 |
+
"epoch": 2.2594142259414225,
|
2320 |
+
"grad_norm": 0.018585605546832085,
|
2321 |
+
"learning_rate": 6.656343160877881e-05,
|
2322 |
+
"loss": 0.0103,
|
2323 |
+
"step": 270
|
2324 |
+
},
|
2325 |
+
{
|
2326 |
+
"epoch": 2.2594142259414225,
|
2327 |
+
"eval_loss": 0.014431845396757126,
|
2328 |
+
"eval_runtime": 8.1882,
|
2329 |
+
"eval_samples_per_second": 6.106,
|
2330 |
+
"eval_steps_per_second": 1.588,
|
2331 |
+
"step": 270
|
2332 |
+
},
|
2333 |
+
{
|
2334 |
+
"epoch": 2.2677824267782425,
|
2335 |
+
"grad_norm": 0.01749185100197792,
|
2336 |
+
"learning_rate": 6.628611891387706e-05,
|
2337 |
+
"loss": 0.0098,
|
2338 |
+
"step": 271
|
2339 |
+
},
|
2340 |
+
{
|
2341 |
+
"epoch": 2.276150627615063,
|
2342 |
+
"grad_norm": 0.019719472154974937,
|
2343 |
+
"learning_rate": 6.600824464298082e-05,
|
2344 |
+
"loss": 0.0103,
|
2345 |
+
"step": 272
|
2346 |
+
},
|
2347 |
+
{
|
2348 |
+
"epoch": 2.284518828451883,
|
2349 |
+
"grad_norm": 0.019530480727553368,
|
2350 |
+
"learning_rate": 6.572981837771726e-05,
|
2351 |
+
"loss": 0.0106,
|
2352 |
+
"step": 273
|
2353 |
+
},
|
2354 |
+
{
|
2355 |
+
"epoch": 2.292887029288703,
|
2356 |
+
"grad_norm": 0.020081467926502228,
|
2357 |
+
"learning_rate": 6.545084971874738e-05,
|
2358 |
+
"loss": 0.0105,
|
2359 |
+
"step": 274
|
2360 |
+
},
|
2361 |
+
{
|
2362 |
+
"epoch": 2.301255230125523,
|
2363 |
+
"grad_norm": 0.016815155744552612,
|
2364 |
+
"learning_rate": 6.517134828543496e-05,
|
2365 |
+
"loss": 0.0107,
|
2366 |
+
"step": 275
|
2367 |
+
},
|
2368 |
+
{
|
2369 |
+
"epoch": 2.301255230125523,
|
2370 |
+
"eval_loss": 0.01435365341603756,
|
2371 |
+
"eval_runtime": 8.1841,
|
2372 |
+
"eval_samples_per_second": 6.109,
|
2373 |
+
"eval_steps_per_second": 1.588,
|
2374 |
+
"step": 275
|
2375 |
+
},
|
2376 |
+
{
|
2377 |
+
"epoch": 2.309623430962343,
|
2378 |
+
"grad_norm": 0.02080889418721199,
|
2379 |
+
"learning_rate": 6.489132371551482e-05,
|
2380 |
+
"loss": 0.0107,
|
2381 |
+
"step": 276
|
2382 |
+
},
|
2383 |
+
{
|
2384 |
+
"epoch": 2.3179916317991633,
|
2385 |
+
"grad_norm": 0.019815733656287193,
|
2386 |
+
"learning_rate": 6.461078566476054e-05,
|
2387 |
+
"loss": 0.0108,
|
2388 |
+
"step": 277
|
2389 |
+
},
|
2390 |
+
{
|
2391 |
+
"epoch": 2.3263598326359833,
|
2392 |
+
"grad_norm": 0.020922286435961723,
|
2393 |
+
"learning_rate": 6.43297438066514e-05,
|
2394 |
+
"loss": 0.0115,
|
2395 |
+
"step": 278
|
2396 |
+
},
|
2397 |
+
{
|
2398 |
+
"epoch": 2.3347280334728033,
|
2399 |
+
"grad_norm": 0.01711447723209858,
|
2400 |
+
"learning_rate": 6.404820783203901e-05,
|
2401 |
+
"loss": 0.0101,
|
2402 |
+
"step": 279
|
2403 |
+
},
|
2404 |
+
{
|
2405 |
+
"epoch": 2.3430962343096233,
|
2406 |
+
"grad_norm": 0.016599150374531746,
|
2407 |
+
"learning_rate": 6.3766187448813e-05,
|
2408 |
+
"loss": 0.0104,
|
2409 |
+
"step": 280
|
2410 |
+
},
|
2411 |
+
{
|
2412 |
+
"epoch": 2.3430962343096233,
|
2413 |
+
"eval_loss": 0.01405297126621008,
|
2414 |
+
"eval_runtime": 8.1827,
|
2415 |
+
"eval_samples_per_second": 6.11,
|
2416 |
+
"eval_steps_per_second": 1.589,
|
2417 |
+
"step": 280
|
2418 |
+
},
|
2419 |
+
{
|
2420 |
+
"epoch": 2.3514644351464433,
|
2421 |
+
"grad_norm": 0.01762828603386879,
|
2422 |
+
"learning_rate": 6.348369238156631e-05,
|
2423 |
+
"loss": 0.0099,
|
2424 |
+
"step": 281
|
2425 |
+
},
|
2426 |
+
{
|
2427 |
+
"epoch": 2.3598326359832638,
|
2428 |
+
"grad_norm": 0.014734679833054543,
|
2429 |
+
"learning_rate": 6.32007323712599e-05,
|
2430 |
+
"loss": 0.0094,
|
2431 |
+
"step": 282
|
2432 |
+
},
|
2433 |
+
{
|
2434 |
+
"epoch": 2.3682008368200838,
|
2435 |
+
"grad_norm": 0.01771124079823494,
|
2436 |
+
"learning_rate": 6.29173171748868e-05,
|
2437 |
+
"loss": 0.0106,
|
2438 |
+
"step": 283
|
2439 |
+
},
|
2440 |
+
{
|
2441 |
+
"epoch": 2.3765690376569037,
|
2442 |
+
"grad_norm": 0.01341992523521185,
|
2443 |
+
"learning_rate": 6.263345656513576e-05,
|
2444 |
+
"loss": 0.0096,
|
2445 |
+
"step": 284
|
2446 |
+
},
|
2447 |
+
{
|
2448 |
+
"epoch": 2.3849372384937237,
|
2449 |
+
"grad_norm": 0.014316578395664692,
|
2450 |
+
"learning_rate": 6.234916033005421e-05,
|
2451 |
+
"loss": 0.0092,
|
2452 |
+
"step": 285
|
2453 |
+
},
|
2454 |
+
{
|
2455 |
+
"epoch": 2.3849372384937237,
|
2456 |
+
"eval_loss": 0.014250432141125202,
|
2457 |
+
"eval_runtime": 8.1935,
|
2458 |
+
"eval_samples_per_second": 6.102,
|
2459 |
+
"eval_steps_per_second": 1.587,
|
2460 |
+
"step": 285
|
2461 |
+
},
|
2462 |
+
{
|
2463 |
+
"epoch": 2.393305439330544,
|
2464 |
+
"grad_norm": 0.017734510824084282,
|
2465 |
+
"learning_rate": 6.206443827271073e-05,
|
2466 |
+
"loss": 0.011,
|
2467 |
+
"step": 286
|
2468 |
+
},
|
2469 |
+
{
|
2470 |
+
"epoch": 2.401673640167364,
|
2471 |
+
"grad_norm": 0.016910862177610397,
|
2472 |
+
"learning_rate": 6.17793002108571e-05,
|
2473 |
+
"loss": 0.0101,
|
2474 |
+
"step": 287
|
2475 |
+
},
|
2476 |
+
{
|
2477 |
+
"epoch": 2.410041841004184,
|
2478 |
+
"grad_norm": 0.015546726994216442,
|
2479 |
+
"learning_rate": 6.149375597658967e-05,
|
2480 |
+
"loss": 0.0092,
|
2481 |
+
"step": 288
|
2482 |
+
},
|
2483 |
+
{
|
2484 |
+
"epoch": 2.418410041841004,
|
2485 |
+
"grad_norm": 0.01636183261871338,
|
2486 |
+
"learning_rate": 6.12078154160104e-05,
|
2487 |
+
"loss": 0.0105,
|
2488 |
+
"step": 289
|
2489 |
+
},
|
2490 |
+
{
|
2491 |
+
"epoch": 2.426778242677824,
|
2492 |
+
"grad_norm": 0.01692620851099491,
|
2493 |
+
"learning_rate": 6.092148838888732e-05,
|
2494 |
+
"loss": 0.0107,
|
2495 |
+
"step": 290
|
2496 |
+
},
|
2497 |
+
{
|
2498 |
+
"epoch": 2.426778242677824,
|
2499 |
+
"eval_loss": 0.01402355171740055,
|
2500 |
+
"eval_runtime": 8.183,
|
2501 |
+
"eval_samples_per_second": 6.11,
|
2502 |
+
"eval_steps_per_second": 1.589,
|
2503 |
+
"step": 290
|
2504 |
+
},
|
2505 |
+
{
|
2506 |
+
"epoch": 2.435146443514644,
|
2507 |
+
"grad_norm": 0.01607348956167698,
|
2508 |
+
"learning_rate": 6.0634784768314564e-05,
|
2509 |
+
"loss": 0.0107,
|
2510 |
+
"step": 291
|
2511 |
+
},
|
2512 |
+
{
|
2513 |
+
"epoch": 2.4435146443514646,
|
2514 |
+
"grad_norm": 0.019470971077680588,
|
2515 |
+
"learning_rate": 6.0347714440371924e-05,
|
2516 |
+
"loss": 0.0095,
|
2517 |
+
"step": 292
|
2518 |
+
},
|
2519 |
+
{
|
2520 |
+
"epoch": 2.4518828451882846,
|
2521 |
+
"grad_norm": 0.014622722752392292,
|
2522 |
+
"learning_rate": 6.0060287303783924e-05,
|
2523 |
+
"loss": 0.011,
|
2524 |
+
"step": 293
|
2525 |
+
},
|
2526 |
+
{
|
2527 |
+
"epoch": 2.4602510460251046,
|
2528 |
+
"grad_norm": 0.02121814712882042,
|
2529 |
+
"learning_rate": 5.977251326957852e-05,
|
2530 |
+
"loss": 0.0099,
|
2531 |
+
"step": 294
|
2532 |
+
},
|
2533 |
+
{
|
2534 |
+
"epoch": 2.4686192468619246,
|
2535 |
+
"grad_norm": 0.018752707168459892,
|
2536 |
+
"learning_rate": 5.9484402260745386e-05,
|
2537 |
+
"loss": 0.0112,
|
2538 |
+
"step": 295
|
2539 |
+
},
|
2540 |
+
{
|
2541 |
+
"epoch": 2.4686192468619246,
|
2542 |
+
"eval_loss": 0.014348245225846767,
|
2543 |
+
"eval_runtime": 8.19,
|
2544 |
+
"eval_samples_per_second": 6.105,
|
2545 |
+
"eval_steps_per_second": 1.587,
|
2546 |
+
"step": 295
|
2547 |
+
},
|
2548 |
+
{
|
2549 |
+
"epoch": 2.476987447698745,
|
2550 |
+
"grad_norm": 0.016945000737905502,
|
2551 |
+
"learning_rate": 5.919596421189368e-05,
|
2552 |
+
"loss": 0.0096,
|
2553 |
+
"step": 296
|
2554 |
+
},
|
2555 |
+
{
|
2556 |
+
"epoch": 2.485355648535565,
|
2557 |
+
"grad_norm": 0.0150624830275774,
|
2558 |
+
"learning_rate": 5.8907209068909554e-05,
|
2559 |
+
"loss": 0.0085,
|
2560 |
+
"step": 297
|
2561 |
+
},
|
2562 |
+
{
|
2563 |
+
"epoch": 2.493723849372385,
|
2564 |
+
"grad_norm": 0.01675923727452755,
|
2565 |
+
"learning_rate": 5.8618146788613105e-05,
|
2566 |
+
"loss": 0.0101,
|
2567 |
+
"step": 298
|
2568 |
+
},
|
2569 |
+
{
|
2570 |
+
"epoch": 2.502092050209205,
|
2571 |
+
"grad_norm": 0.01698216423392296,
|
2572 |
+
"learning_rate": 5.832878733841513e-05,
|
2573 |
+
"loss": 0.0102,
|
2574 |
+
"step": 299
|
2575 |
+
},
|
2576 |
+
{
|
2577 |
+
"epoch": 2.510460251046025,
|
2578 |
+
"grad_norm": 0.01541865710169077,
|
2579 |
+
"learning_rate": 5.803914069597342e-05,
|
2580 |
+
"loss": 0.01,
|
2581 |
+
"step": 300
|
2582 |
+
},
|
2583 |
+
{
|
2584 |
+
"epoch": 2.510460251046025,
|
2585 |
+
"eval_loss": 0.014326265081763268,
|
2586 |
+
"eval_runtime": 8.1855,
|
2587 |
+
"eval_samples_per_second": 6.108,
|
2588 |
+
"eval_steps_per_second": 1.588,
|
2589 |
+
"step": 300
|
2590 |
+
},
|
2591 |
+
{
|
2592 |
+
"epoch": 2.518828451882845,
|
2593 |
+
"grad_norm": 0.015604431740939617,
|
2594 |
+
"learning_rate": 5.7749216848848664e-05,
|
2595 |
+
"loss": 0.0092,
|
2596 |
+
"step": 301
|
2597 |
+
},
|
2598 |
+
{
|
2599 |
+
"epoch": 2.5271966527196654,
|
2600 |
+
"grad_norm": 0.019720997661352158,
|
2601 |
+
"learning_rate": 5.7459025794160136e-05,
|
2602 |
+
"loss": 0.0109,
|
2603 |
+
"step": 302
|
2604 |
+
},
|
2605 |
+
{
|
2606 |
+
"epoch": 2.5355648535564854,
|
2607 |
+
"grad_norm": 0.014376216568052769,
|
2608 |
+
"learning_rate": 5.716857753824086e-05,
|
2609 |
+
"loss": 0.0089,
|
2610 |
+
"step": 303
|
2611 |
+
},
|
2612 |
+
{
|
2613 |
+
"epoch": 2.5439330543933054,
|
2614 |
+
"grad_norm": 0.015419202856719494,
|
2615 |
+
"learning_rate": 5.6877882096292715e-05,
|
2616 |
+
"loss": 0.0095,
|
2617 |
+
"step": 304
|
2618 |
+
},
|
2619 |
+
{
|
2620 |
+
"epoch": 2.5523012552301254,
|
2621 |
+
"grad_norm": 0.018142806366086006,
|
2622 |
+
"learning_rate": 5.6586949492040944e-05,
|
2623 |
+
"loss": 0.0096,
|
2624 |
+
"step": 305
|
2625 |
+
},
|
2626 |
+
{
|
2627 |
+
"epoch": 2.5523012552301254,
|
2628 |
+
"eval_loss": 0.01382070779800415,
|
2629 |
+
"eval_runtime": 8.2064,
|
2630 |
+
"eval_samples_per_second": 6.093,
|
2631 |
+
"eval_steps_per_second": 1.584,
|
2632 |
+
"step": 305
|
2633 |
+
},
|
2634 |
+
{
|
2635 |
+
"epoch": 2.560669456066946,
|
2636 |
+
"grad_norm": 0.016867833212018013,
|
2637 |
+
"learning_rate": 5.629578975738865e-05,
|
2638 |
+
"loss": 0.0099,
|
2639 |
+
"step": 306
|
2640 |
+
},
|
2641 |
+
{
|
2642 |
+
"epoch": 2.569037656903766,
|
2643 |
+
"grad_norm": 0.01875397376716137,
|
2644 |
+
"learning_rate": 5.6004412932070835e-05,
|
2645 |
+
"loss": 0.0104,
|
2646 |
+
"step": 307
|
2647 |
+
},
|
2648 |
+
{
|
2649 |
+
"epoch": 2.577405857740586,
|
2650 |
+
"grad_norm": 0.018324118107557297,
|
2651 |
+
"learning_rate": 5.57128290633081e-05,
|
2652 |
+
"loss": 0.0096,
|
2653 |
+
"step": 308
|
2654 |
+
},
|
2655 |
+
{
|
2656 |
+
"epoch": 2.585774058577406,
|
2657 |
+
"grad_norm": 0.014931274577975273,
|
2658 |
+
"learning_rate": 5.542104820546041e-05,
|
2659 |
+
"loss": 0.0095,
|
2660 |
+
"step": 309
|
2661 |
+
},
|
2662 |
+
{
|
2663 |
+
"epoch": 2.594142259414226,
|
2664 |
+
"grad_norm": 0.020742323249578476,
|
2665 |
+
"learning_rate": 5.512908041968018e-05,
|
2666 |
+
"loss": 0.0096,
|
2667 |
+
"step": 310
|
2668 |
+
},
|
2669 |
+
{
|
2670 |
+
"epoch": 2.594142259414226,
|
2671 |
+
"eval_loss": 0.013671735301613808,
|
2672 |
+
"eval_runtime": 8.1946,
|
2673 |
+
"eval_samples_per_second": 6.102,
|
2674 |
+
"eval_steps_per_second": 1.586,
|
2675 |
+
"step": 310
|
2676 |
+
},
|
2677 |
+
{
|
2678 |
+
"epoch": 2.602510460251046,
|
2679 |
+
"grad_norm": 0.016727490350604057,
|
2680 |
+
"learning_rate": 5.483693577356552e-05,
|
2681 |
+
"loss": 0.01,
|
2682 |
+
"step": 311
|
2683 |
+
},
|
2684 |
+
{
|
2685 |
+
"epoch": 2.6108786610878663,
|
2686 |
+
"grad_norm": 0.015919320285320282,
|
2687 |
+
"learning_rate": 5.454462434081302e-05,
|
2688 |
+
"loss": 0.0099,
|
2689 |
+
"step": 312
|
2690 |
+
},
|
2691 |
+
{
|
2692 |
+
"epoch": 2.6192468619246863,
|
2693 |
+
"grad_norm": 0.01895716041326523,
|
2694 |
+
"learning_rate": 5.425215620087033e-05,
|
2695 |
+
"loss": 0.0097,
|
2696 |
+
"step": 313
|
2697 |
+
},
|
2698 |
+
{
|
2699 |
+
"epoch": 2.6276150627615062,
|
2700 |
+
"grad_norm": 0.0199336726218462,
|
2701 |
+
"learning_rate": 5.395954143858871e-05,
|
2702 |
+
"loss": 0.0108,
|
2703 |
+
"step": 314
|
2704 |
+
},
|
2705 |
+
{
|
2706 |
+
"epoch": 2.6359832635983262,
|
2707 |
+
"grad_norm": 0.016174420714378357,
|
2708 |
+
"learning_rate": 5.36667901438752e-05,
|
2709 |
+
"loss": 0.0099,
|
2710 |
+
"step": 315
|
2711 |
+
},
|
2712 |
+
{
|
2713 |
+
"epoch": 2.6359832635983262,
|
2714 |
+
"eval_loss": 0.013724744319915771,
|
2715 |
+
"eval_runtime": 8.2179,
|
2716 |
+
"eval_samples_per_second": 6.084,
|
2717 |
+
"eval_steps_per_second": 1.582,
|
2718 |
+
"step": 315
|
2719 |
+
},
|
2720 |
+
{
|
2721 |
+
"epoch": 2.6443514644351467,
|
2722 |
+
"grad_norm": 0.0191593486815691,
|
2723 |
+
"learning_rate": 5.337391241134476e-05,
|
2724 |
+
"loss": 0.0104,
|
2725 |
+
"step": 316
|
2726 |
+
},
|
2727 |
+
{
|
2728 |
+
"epoch": 2.6527196652719667,
|
2729 |
+
"grad_norm": 0.017469942569732666,
|
2730 |
+
"learning_rate": 5.3080918339972175e-05,
|
2731 |
+
"loss": 0.0101,
|
2732 |
+
"step": 317
|
2733 |
+
},
|
2734 |
+
{
|
2735 |
+
"epoch": 2.6610878661087867,
|
2736 |
+
"grad_norm": 0.024253906682133675,
|
2737 |
+
"learning_rate": 5.278781803274375e-05,
|
2738 |
+
"loss": 0.0109,
|
2739 |
+
"step": 318
|
2740 |
+
},
|
2741 |
+
{
|
2742 |
+
"epoch": 2.6694560669456067,
|
2743 |
+
"grad_norm": 0.020112276077270508,
|
2744 |
+
"learning_rate": 5.249462159630908e-05,
|
2745 |
+
"loss": 0.0105,
|
2746 |
+
"step": 319
|
2747 |
+
},
|
2748 |
+
{
|
2749 |
+
"epoch": 2.6778242677824267,
|
2750 |
+
"grad_norm": 0.017300646752119064,
|
2751 |
+
"learning_rate": 5.220133914063239e-05,
|
2752 |
+
"loss": 0.009,
|
2753 |
+
"step": 320
|
2754 |
+
},
|
2755 |
+
{
|
2756 |
+
"epoch": 2.6778242677824267,
|
2757 |
+
"eval_loss": 0.013836627826094627,
|
2758 |
+
"eval_runtime": 8.1921,
|
2759 |
+
"eval_samples_per_second": 6.103,
|
2760 |
+
"eval_steps_per_second": 1.587,
|
2761 |
+
"step": 320
|
2762 |
+
},
|
2763 |
+
{
|
2764 |
+
"epoch": 2.6861924686192467,
|
2765 |
+
"grad_norm": 0.01683647558093071,
|
2766 |
+
"learning_rate": 5.1907980778644114e-05,
|
2767 |
+
"loss": 0.0097,
|
2768 |
+
"step": 321
|
2769 |
+
},
|
2770 |
+
{
|
2771 |
+
"epoch": 2.694560669456067,
|
2772 |
+
"grad_norm": 0.02241523563861847,
|
2773 |
+
"learning_rate": 5.161455662589201e-05,
|
2774 |
+
"loss": 0.0112,
|
2775 |
+
"step": 322
|
2776 |
+
},
|
2777 |
+
{
|
2778 |
+
"epoch": 2.702928870292887,
|
2779 |
+
"grad_norm": 0.017464108765125275,
|
2780 |
+
"learning_rate": 5.132107680019241e-05,
|
2781 |
+
"loss": 0.0106,
|
2782 |
+
"step": 323
|
2783 |
+
},
|
2784 |
+
{
|
2785 |
+
"epoch": 2.711297071129707,
|
2786 |
+
"grad_norm": 0.014207069762051105,
|
2787 |
+
"learning_rate": 5.102755142128143e-05,
|
2788 |
+
"loss": 0.0092,
|
2789 |
+
"step": 324
|
2790 |
+
},
|
2791 |
+
{
|
2792 |
+
"epoch": 2.719665271966527,
|
2793 |
+
"grad_norm": 0.01582857221364975,
|
2794 |
+
"learning_rate": 5.073399061046583e-05,
|
2795 |
+
"loss": 0.0097,
|
2796 |
+
"step": 325
|
2797 |
+
},
|
2798 |
+
{
|
2799 |
+
"epoch": 2.719665271966527,
|
2800 |
+
"eval_loss": 0.01370433159172535,
|
2801 |
+
"eval_runtime": 8.1877,
|
2802 |
+
"eval_samples_per_second": 6.107,
|
2803 |
+
"eval_steps_per_second": 1.588,
|
2804 |
+
"step": 325
|
2805 |
+
},
|
2806 |
+
{
|
2807 |
+
"epoch": 2.7280334728033475,
|
2808 |
+
"grad_norm": 0.015251656994223595,
|
2809 |
+
"learning_rate": 5.044040449027426e-05,
|
2810 |
+
"loss": 0.0091,
|
2811 |
+
"step": 326
|
2812 |
+
},
|
2813 |
+
{
|
2814 |
+
"epoch": 2.7364016736401675,
|
2815 |
+
"grad_norm": 0.01971331425011158,
|
2816 |
+
"learning_rate": 5.0146803184108006e-05,
|
2817 |
+
"loss": 0.0097,
|
2818 |
+
"step": 327
|
2819 |
+
},
|
2820 |
+
{
|
2821 |
+
"epoch": 2.7447698744769875,
|
2822 |
+
"grad_norm": 0.017107218503952026,
|
2823 |
+
"learning_rate": 4.9853196815892e-05,
|
2824 |
+
"loss": 0.0105,
|
2825 |
+
"step": 328
|
2826 |
+
},
|
2827 |
+
{
|
2828 |
+
"epoch": 2.7531380753138075,
|
2829 |
+
"grad_norm": 0.016256961971521378,
|
2830 |
+
"learning_rate": 4.9559595509725744e-05,
|
2831 |
+
"loss": 0.0091,
|
2832 |
+
"step": 329
|
2833 |
+
},
|
2834 |
+
{
|
2835 |
+
"epoch": 2.7615062761506275,
|
2836 |
+
"grad_norm": 0.016966141760349274,
|
2837 |
+
"learning_rate": 4.926600938953418e-05,
|
2838 |
+
"loss": 0.0097,
|
2839 |
+
"step": 330
|
2840 |
+
},
|
2841 |
+
{
|
2842 |
+
"epoch": 2.7615062761506275,
|
2843 |
+
"eval_loss": 0.01360410638153553,
|
2844 |
+
"eval_runtime": 8.2179,
|
2845 |
+
"eval_samples_per_second": 6.084,
|
2846 |
+
"eval_steps_per_second": 1.582,
|
2847 |
+
"step": 330
|
2848 |
+
},
|
2849 |
+
{
|
2850 |
+
"epoch": 2.7698744769874475,
|
2851 |
+
"grad_norm": 0.016130153089761734,
|
2852 |
+
"learning_rate": 4.89724485787186e-05,
|
2853 |
+
"loss": 0.0094,
|
2854 |
+
"step": 331
|
2855 |
+
},
|
2856 |
+
{
|
2857 |
+
"epoch": 2.778242677824268,
|
2858 |
+
"grad_norm": 0.016650136560201645,
|
2859 |
+
"learning_rate": 4.86789231998076e-05,
|
2860 |
+
"loss": 0.0092,
|
2861 |
+
"step": 332
|
2862 |
+
},
|
2863 |
+
{
|
2864 |
+
"epoch": 2.786610878661088,
|
2865 |
+
"grad_norm": 0.015621655620634556,
|
2866 |
+
"learning_rate": 4.8385443374108e-05,
|
2867 |
+
"loss": 0.0093,
|
2868 |
+
"step": 333
|
2869 |
+
},
|
2870 |
+
{
|
2871 |
+
"epoch": 2.794979079497908,
|
2872 |
+
"grad_norm": 0.024522442370653152,
|
2873 |
+
"learning_rate": 4.809201922135589e-05,
|
2874 |
+
"loss": 0.0116,
|
2875 |
+
"step": 334
|
2876 |
+
},
|
2877 |
+
{
|
2878 |
+
"epoch": 2.803347280334728,
|
2879 |
+
"grad_norm": 0.016756724566221237,
|
2880 |
+
"learning_rate": 4.7798660859367615e-05,
|
2881 |
+
"loss": 0.0108,
|
2882 |
+
"step": 335
|
2883 |
+
},
|
2884 |
+
{
|
2885 |
+
"epoch": 2.803347280334728,
|
2886 |
+
"eval_loss": 0.013578813523054123,
|
2887 |
+
"eval_runtime": 8.195,
|
2888 |
+
"eval_samples_per_second": 6.101,
|
2889 |
+
"eval_steps_per_second": 1.586,
|
2890 |
+
"step": 335
|
2891 |
+
},
|
2892 |
+
{
|
2893 |
+
"epoch": 2.8117154811715483,
|
2894 |
+
"grad_norm": 0.01872294582426548,
|
2895 |
+
"learning_rate": 4.750537840369095e-05,
|
2896 |
+
"loss": 0.0097,
|
2897 |
+
"step": 336
|
2898 |
+
},
|
2899 |
+
{
|
2900 |
+
"epoch": 2.8200836820083683,
|
2901 |
+
"grad_norm": 0.01649293303489685,
|
2902 |
+
"learning_rate": 4.721218196725627e-05,
|
2903 |
+
"loss": 0.0092,
|
2904 |
+
"step": 337
|
2905 |
+
},
|
2906 |
+
{
|
2907 |
+
"epoch": 2.8284518828451883,
|
2908 |
+
"grad_norm": 0.017666228115558624,
|
2909 |
+
"learning_rate": 4.691908166002784e-05,
|
2910 |
+
"loss": 0.0114,
|
2911 |
+
"step": 338
|
2912 |
+
},
|
2913 |
+
{
|
2914 |
+
"epoch": 2.8368200836820083,
|
2915 |
+
"grad_norm": 0.014805554412305355,
|
2916 |
+
"learning_rate": 4.662608758865524e-05,
|
2917 |
+
"loss": 0.0102,
|
2918 |
+
"step": 339
|
2919 |
+
},
|
2920 |
+
{
|
2921 |
+
"epoch": 2.8451882845188283,
|
2922 |
+
"grad_norm": 0.015506643801927567,
|
2923 |
+
"learning_rate": 4.633320985612481e-05,
|
2924 |
+
"loss": 0.0092,
|
2925 |
+
"step": 340
|
2926 |
+
},
|
2927 |
+
{
|
2928 |
+
"epoch": 2.8451882845188283,
|
2929 |
+
"eval_loss": 0.01316875871270895,
|
2930 |
+
"eval_runtime": 8.1877,
|
2931 |
+
"eval_samples_per_second": 6.107,
|
2932 |
+
"eval_steps_per_second": 1.588,
|
2933 |
+
"step": 340
|
2934 |
+
},
|
2935 |
+
{
|
2936 |
+
"epoch": 2.8535564853556483,
|
2937 |
+
"grad_norm": 0.016277095302939415,
|
2938 |
+
"learning_rate": 4.60404585614113e-05,
|
2939 |
+
"loss": 0.0093,
|
2940 |
+
"step": 341
|
2941 |
+
},
|
2942 |
+
{
|
2943 |
+
"epoch": 2.8619246861924688,
|
2944 |
+
"grad_norm": 0.015483858995139599,
|
2945 |
+
"learning_rate": 4.5747843799129684e-05,
|
2946 |
+
"loss": 0.0101,
|
2947 |
+
"step": 342
|
2948 |
+
},
|
2949 |
+
{
|
2950 |
+
"epoch": 2.8702928870292888,
|
2951 |
+
"grad_norm": 0.014321762137115002,
|
2952 |
+
"learning_rate": 4.545537565918699e-05,
|
2953 |
+
"loss": 0.0098,
|
2954 |
+
"step": 343
|
2955 |
+
},
|
2956 |
+
{
|
2957 |
+
"epoch": 2.8786610878661087,
|
2958 |
+
"grad_norm": 0.014206680469214916,
|
2959 |
+
"learning_rate": 4.5163064226434475e-05,
|
2960 |
+
"loss": 0.009,
|
2961 |
+
"step": 344
|
2962 |
+
},
|
2963 |
+
{
|
2964 |
+
"epoch": 2.8870292887029287,
|
2965 |
+
"grad_norm": 0.013214725069701672,
|
2966 |
+
"learning_rate": 4.487091958031984e-05,
|
2967 |
+
"loss": 0.0092,
|
2968 |
+
"step": 345
|
2969 |
+
},
|
2970 |
+
{
|
2971 |
+
"epoch": 2.8870292887029287,
|
2972 |
+
"eval_loss": 0.013155767694115639,
|
2973 |
+
"eval_runtime": 8.1971,
|
2974 |
+
"eval_samples_per_second": 6.1,
|
2975 |
+
"eval_steps_per_second": 1.586,
|
2976 |
+
"step": 345
|
2977 |
+
},
|
2978 |
+
{
|
2979 |
+
"epoch": 2.895397489539749,
|
2980 |
+
"grad_norm": 0.01570652797818184,
|
2981 |
+
"learning_rate": 4.457895179453961e-05,
|
2982 |
+
"loss": 0.0101,
|
2983 |
+
"step": 346
|
2984 |
+
},
|
2985 |
+
{
|
2986 |
+
"epoch": 2.903765690376569,
|
2987 |
+
"grad_norm": 0.013275294564664364,
|
2988 |
+
"learning_rate": 4.42871709366919e-05,
|
2989 |
+
"loss": 0.0096,
|
2990 |
+
"step": 347
|
2991 |
+
},
|
2992 |
+
{
|
2993 |
+
"epoch": 2.912133891213389,
|
2994 |
+
"grad_norm": 0.017738599330186844,
|
2995 |
+
"learning_rate": 4.3995587067929177e-05,
|
2996 |
+
"loss": 0.0106,
|
2997 |
+
"step": 348
|
2998 |
+
},
|
2999 |
+
{
|
3000 |
+
"epoch": 2.920502092050209,
|
3001 |
+
"grad_norm": 0.02087695151567459,
|
3002 |
+
"learning_rate": 4.3704210242611346e-05,
|
3003 |
+
"loss": 0.0105,
|
3004 |
+
"step": 349
|
3005 |
+
},
|
3006 |
+
{
|
3007 |
+
"epoch": 2.928870292887029,
|
3008 |
+
"grad_norm": 0.01522638276219368,
|
3009 |
+
"learning_rate": 4.341305050795907e-05,
|
3010 |
+
"loss": 0.0095,
|
3011 |
+
"step": 350
|
3012 |
+
},
|
3013 |
+
{
|
3014 |
+
"epoch": 2.928870292887029,
|
3015 |
+
"eval_loss": 0.012959838844835758,
|
3016 |
+
"eval_runtime": 8.1869,
|
3017 |
+
"eval_samples_per_second": 6.107,
|
3018 |
+
"eval_steps_per_second": 1.588,
|
3019 |
+
"step": 350
|
3020 |
+
}
|
3021 |
+
],
|
3022 |
+
"logging_steps": 1,
|
3023 |
+
"max_steps": 595,
|
3024 |
+
"num_input_tokens_seen": 0,
|
3025 |
+
"num_train_epochs": 5,
|
3026 |
+
"save_steps": 50,
|
3027 |
+
"stateful_callbacks": {
|
3028 |
+
"TrainerControl": {
|
3029 |
+
"args": {
|
3030 |
+
"should_epoch_stop": false,
|
3031 |
+
"should_evaluate": false,
|
3032 |
+
"should_log": false,
|
3033 |
+
"should_save": true,
|
3034 |
+
"should_training_stop": false
|
3035 |
+
},
|
3036 |
+
"attributes": {}
|
3037 |
+
}
|
3038 |
+
},
|
3039 |
+
"total_flos": 7.049248100004495e+17,
|
3040 |
+
"train_batch_size": 4,
|
3041 |
+
"trial_name": null,
|
3042 |
+
"trial_params": null
|
3043 |
+
}
|
checkpoint-350/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e665038fe922eed5452cc8aa2677ba331714cf00575ebbdd2bb83108b97f4bd3
|
3 |
+
size 5496
|
eval_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 4.97907949790795,
|
3 |
+
"eval_loss": 0.012959836050868034,
|
4 |
+
"eval_runtime": 8.1595,
|
5 |
+
"eval_samples_per_second": 6.128,
|
6 |
+
"eval_steps_per_second": 1.593
|
7 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|begin_of_text|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|eot_id|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "<|eot_id|>"
|
17 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
|
3 |
+
size 17209920
|
tokenizer_config.json
ADDED
@@ -0,0 +1,2065 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"128000": {
|
4 |
+
"content": "<|begin_of_text|>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"128001": {
|
12 |
+
"content": "<|end_of_text|>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"128002": {
|
20 |
+
"content": "<|reserved_special_token_0|>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"128003": {
|
28 |
+
"content": "<|reserved_special_token_1|>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"128004": {
|
36 |
+
"content": "<|finetune_right_pad_id|>",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
},
|
43 |
+
"128005": {
|
44 |
+
"content": "<|reserved_special_token_2|>",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": true
|
50 |
+
},
|
51 |
+
"128006": {
|
52 |
+
"content": "<|start_header_id|>",
|
53 |
+
"lstrip": false,
|
54 |
+
"normalized": false,
|
55 |
+
"rstrip": false,
|
56 |
+
"single_word": false,
|
57 |
+
"special": true
|
58 |
+
},
|
59 |
+
"128007": {
|
60 |
+
"content": "<|end_header_id|>",
|
61 |
+
"lstrip": false,
|
62 |
+
"normalized": false,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": false,
|
65 |
+
"special": true
|
66 |
+
},
|
67 |
+
"128008": {
|
68 |
+
"content": "<|eom_id|>",
|
69 |
+
"lstrip": false,
|
70 |
+
"normalized": false,
|
71 |
+
"rstrip": false,
|
72 |
+
"single_word": false,
|
73 |
+
"special": true
|
74 |
+
},
|
75 |
+
"128009": {
|
76 |
+
"content": "<|eot_id|>",
|
77 |
+
"lstrip": false,
|
78 |
+
"normalized": false,
|
79 |
+
"rstrip": false,
|
80 |
+
"single_word": false,
|
81 |
+
"special": true
|
82 |
+
},
|
83 |
+
"128010": {
|
84 |
+
"content": "<|python_tag|>",
|
85 |
+
"lstrip": false,
|
86 |
+
"normalized": false,
|
87 |
+
"rstrip": false,
|
88 |
+
"single_word": false,
|
89 |
+
"special": true
|
90 |
+
},
|
91 |
+
"128011": {
|
92 |
+
"content": "<|reserved_special_token_3|>",
|
93 |
+
"lstrip": false,
|
94 |
+
"normalized": false,
|
95 |
+
"rstrip": false,
|
96 |
+
"single_word": false,
|
97 |
+
"special": true
|
98 |
+
},
|
99 |
+
"128012": {
|
100 |
+
"content": "<|reserved_special_token_4|>",
|
101 |
+
"lstrip": false,
|
102 |
+
"normalized": false,
|
103 |
+
"rstrip": false,
|
104 |
+
"single_word": false,
|
105 |
+
"special": true
|
106 |
+
},
|
107 |
+
"128013": {
|
108 |
+
"content": "<|reserved_special_token_5|>",
|
109 |
+
"lstrip": false,
|
110 |
+
"normalized": false,
|
111 |
+
"rstrip": false,
|
112 |
+
"single_word": false,
|
113 |
+
"special": true
|
114 |
+
},
|
115 |
+
"128014": {
|
116 |
+
"content": "<|reserved_special_token_6|>",
|
117 |
+
"lstrip": false,
|
118 |
+
"normalized": false,
|
119 |
+
"rstrip": false,
|
120 |
+
"single_word": false,
|
121 |
+
"special": true
|
122 |
+
},
|
123 |
+
"128015": {
|
124 |
+
"content": "<|reserved_special_token_7|>",
|
125 |
+
"lstrip": false,
|
126 |
+
"normalized": false,
|
127 |
+
"rstrip": false,
|
128 |
+
"single_word": false,
|
129 |
+
"special": true
|
130 |
+
},
|
131 |
+
"128016": {
|
132 |
+
"content": "<|reserved_special_token_8|>",
|
133 |
+
"lstrip": false,
|
134 |
+
"normalized": false,
|
135 |
+
"rstrip": false,
|
136 |
+
"single_word": false,
|
137 |
+
"special": true
|
138 |
+
},
|
139 |
+
"128017": {
|
140 |
+
"content": "<|reserved_special_token_9|>",
|
141 |
+
"lstrip": false,
|
142 |
+
"normalized": false,
|
143 |
+
"rstrip": false,
|
144 |
+
"single_word": false,
|
145 |
+
"special": true
|
146 |
+
},
|
147 |
+
"128018": {
|
148 |
+
"content": "<|reserved_special_token_10|>",
|
149 |
+
"lstrip": false,
|
150 |
+
"normalized": false,
|
151 |
+
"rstrip": false,
|
152 |
+
"single_word": false,
|
153 |
+
"special": true
|
154 |
+
},
|
155 |
+
"128019": {
|
156 |
+
"content": "<|reserved_special_token_11|>",
|
157 |
+
"lstrip": false,
|
158 |
+
"normalized": false,
|
159 |
+
"rstrip": false,
|
160 |
+
"single_word": false,
|
161 |
+
"special": true
|
162 |
+
},
|
163 |
+
"128020": {
|
164 |
+
"content": "<|reserved_special_token_12|>",
|
165 |
+
"lstrip": false,
|
166 |
+
"normalized": false,
|
167 |
+
"rstrip": false,
|
168 |
+
"single_word": false,
|
169 |
+
"special": true
|
170 |
+
},
|
171 |
+
"128021": {
|
172 |
+
"content": "<|reserved_special_token_13|>",
|
173 |
+
"lstrip": false,
|
174 |
+
"normalized": false,
|
175 |
+
"rstrip": false,
|
176 |
+
"single_word": false,
|
177 |
+
"special": true
|
178 |
+
},
|
179 |
+
"128022": {
|
180 |
+
"content": "<|reserved_special_token_14|>",
|
181 |
+
"lstrip": false,
|
182 |
+
"normalized": false,
|
183 |
+
"rstrip": false,
|
184 |
+
"single_word": false,
|
185 |
+
"special": true
|
186 |
+
},
|
187 |
+
"128023": {
|
188 |
+
"content": "<|reserved_special_token_15|>",
|
189 |
+
"lstrip": false,
|
190 |
+
"normalized": false,
|
191 |
+
"rstrip": false,
|
192 |
+
"single_word": false,
|
193 |
+
"special": true
|
194 |
+
},
|
195 |
+
"128024": {
|
196 |
+
"content": "<|reserved_special_token_16|>",
|
197 |
+
"lstrip": false,
|
198 |
+
"normalized": false,
|
199 |
+
"rstrip": false,
|
200 |
+
"single_word": false,
|
201 |
+
"special": true
|
202 |
+
},
|
203 |
+
"128025": {
|
204 |
+
"content": "<|reserved_special_token_17|>",
|
205 |
+
"lstrip": false,
|
206 |
+
"normalized": false,
|
207 |
+
"rstrip": false,
|
208 |
+
"single_word": false,
|
209 |
+
"special": true
|
210 |
+
},
|
211 |
+
"128026": {
|
212 |
+
"content": "<|reserved_special_token_18|>",
|
213 |
+
"lstrip": false,
|
214 |
+
"normalized": false,
|
215 |
+
"rstrip": false,
|
216 |
+
"single_word": false,
|
217 |
+
"special": true
|
218 |
+
},
|
219 |
+
"128027": {
|
220 |
+
"content": "<|reserved_special_token_19|>",
|
221 |
+
"lstrip": false,
|
222 |
+
"normalized": false,
|
223 |
+
"rstrip": false,
|
224 |
+
"single_word": false,
|
225 |
+
"special": true
|
226 |
+
},
|
227 |
+
"128028": {
|
228 |
+
"content": "<|reserved_special_token_20|>",
|
229 |
+
"lstrip": false,
|
230 |
+
"normalized": false,
|
231 |
+
"rstrip": false,
|
232 |
+
"single_word": false,
|
233 |
+
"special": true
|
234 |
+
},
|
235 |
+
"128029": {
|
236 |
+
"content": "<|reserved_special_token_21|>",
|
237 |
+
"lstrip": false,
|
238 |
+
"normalized": false,
|
239 |
+
"rstrip": false,
|
240 |
+
"single_word": false,
|
241 |
+
"special": true
|
242 |
+
},
|
243 |
+
"128030": {
|
244 |
+
"content": "<|reserved_special_token_22|>",
|
245 |
+
"lstrip": false,
|
246 |
+
"normalized": false,
|
247 |
+
"rstrip": false,
|
248 |
+
"single_word": false,
|
249 |
+
"special": true
|
250 |
+
},
|
251 |
+
"128031": {
|
252 |
+
"content": "<|reserved_special_token_23|>",
|
253 |
+
"lstrip": false,
|
254 |
+
"normalized": false,
|
255 |
+
"rstrip": false,
|
256 |
+
"single_word": false,
|
257 |
+
"special": true
|
258 |
+
},
|
259 |
+
"128032": {
|
260 |
+
"content": "<|reserved_special_token_24|>",
|
261 |
+
"lstrip": false,
|
262 |
+
"normalized": false,
|
263 |
+
"rstrip": false,
|
264 |
+
"single_word": false,
|
265 |
+
"special": true
|
266 |
+
},
|
267 |
+
"128033": {
|
268 |
+
"content": "<|reserved_special_token_25|>",
|
269 |
+
"lstrip": false,
|
270 |
+
"normalized": false,
|
271 |
+
"rstrip": false,
|
272 |
+
"single_word": false,
|
273 |
+
"special": true
|
274 |
+
},
|
275 |
+
"128034": {
|
276 |
+
"content": "<|reserved_special_token_26|>",
|
277 |
+
"lstrip": false,
|
278 |
+
"normalized": false,
|
279 |
+
"rstrip": false,
|
280 |
+
"single_word": false,
|
281 |
+
"special": true
|
282 |
+
},
|
283 |
+
"128035": {
|
284 |
+
"content": "<|reserved_special_token_27|>",
|
285 |
+
"lstrip": false,
|
286 |
+
"normalized": false,
|
287 |
+
"rstrip": false,
|
288 |
+
"single_word": false,
|
289 |
+
"special": true
|
290 |
+
},
|
291 |
+
"128036": {
|
292 |
+
"content": "<|reserved_special_token_28|>",
|
293 |
+
"lstrip": false,
|
294 |
+
"normalized": false,
|
295 |
+
"rstrip": false,
|
296 |
+
"single_word": false,
|
297 |
+
"special": true
|
298 |
+
},
|
299 |
+
"128037": {
|
300 |
+
"content": "<|reserved_special_token_29|>",
|
301 |
+
"lstrip": false,
|
302 |
+
"normalized": false,
|
303 |
+
"rstrip": false,
|
304 |
+
"single_word": false,
|
305 |
+
"special": true
|
306 |
+
},
|
307 |
+
"128038": {
|
308 |
+
"content": "<|reserved_special_token_30|>",
|
309 |
+
"lstrip": false,
|
310 |
+
"normalized": false,
|
311 |
+
"rstrip": false,
|
312 |
+
"single_word": false,
|
313 |
+
"special": true
|
314 |
+
},
|
315 |
+
"128039": {
|
316 |
+
"content": "<|reserved_special_token_31|>",
|
317 |
+
"lstrip": false,
|
318 |
+
"normalized": false,
|
319 |
+
"rstrip": false,
|
320 |
+
"single_word": false,
|
321 |
+
"special": true
|
322 |
+
},
|
323 |
+
"128040": {
|
324 |
+
"content": "<|reserved_special_token_32|>",
|
325 |
+
"lstrip": false,
|
326 |
+
"normalized": false,
|
327 |
+
"rstrip": false,
|
328 |
+
"single_word": false,
|
329 |
+
"special": true
|
330 |
+
},
|
331 |
+
"128041": {
|
332 |
+
"content": "<|reserved_special_token_33|>",
|
333 |
+
"lstrip": false,
|
334 |
+
"normalized": false,
|
335 |
+
"rstrip": false,
|
336 |
+
"single_word": false,
|
337 |
+
"special": true
|
338 |
+
},
|
339 |
+
"128042": {
|
340 |
+
"content": "<|reserved_special_token_34|>",
|
341 |
+
"lstrip": false,
|
342 |
+
"normalized": false,
|
343 |
+
"rstrip": false,
|
344 |
+
"single_word": false,
|
345 |
+
"special": true
|
346 |
+
},
|
347 |
+
"128043": {
|
348 |
+
"content": "<|reserved_special_token_35|>",
|
349 |
+
"lstrip": false,
|
350 |
+
"normalized": false,
|
351 |
+
"rstrip": false,
|
352 |
+
"single_word": false,
|
353 |
+
"special": true
|
354 |
+
},
|
355 |
+
"128044": {
|
356 |
+
"content": "<|reserved_special_token_36|>",
|
357 |
+
"lstrip": false,
|
358 |
+
"normalized": false,
|
359 |
+
"rstrip": false,
|
360 |
+
"single_word": false,
|
361 |
+
"special": true
|
362 |
+
},
|
363 |
+
"128045": {
|
364 |
+
"content": "<|reserved_special_token_37|>",
|
365 |
+
"lstrip": false,
|
366 |
+
"normalized": false,
|
367 |
+
"rstrip": false,
|
368 |
+
"single_word": false,
|
369 |
+
"special": true
|
370 |
+
},
|
371 |
+
"128046": {
|
372 |
+
"content": "<|reserved_special_token_38|>",
|
373 |
+
"lstrip": false,
|
374 |
+
"normalized": false,
|
375 |
+
"rstrip": false,
|
376 |
+
"single_word": false,
|
377 |
+
"special": true
|
378 |
+
},
|
379 |
+
"128047": {
|
380 |
+
"content": "<|reserved_special_token_39|>",
|
381 |
+
"lstrip": false,
|
382 |
+
"normalized": false,
|
383 |
+
"rstrip": false,
|
384 |
+
"single_word": false,
|
385 |
+
"special": true
|
386 |
+
},
|
387 |
+
"128048": {
|
388 |
+
"content": "<|reserved_special_token_40|>",
|
389 |
+
"lstrip": false,
|
390 |
+
"normalized": false,
|
391 |
+
"rstrip": false,
|
392 |
+
"single_word": false,
|
393 |
+
"special": true
|
394 |
+
},
|
395 |
+
"128049": {
|
396 |
+
"content": "<|reserved_special_token_41|>",
|
397 |
+
"lstrip": false,
|
398 |
+
"normalized": false,
|
399 |
+
"rstrip": false,
|
400 |
+
"single_word": false,
|
401 |
+
"special": true
|
402 |
+
},
|
403 |
+
"128050": {
|
404 |
+
"content": "<|reserved_special_token_42|>",
|
405 |
+
"lstrip": false,
|
406 |
+
"normalized": false,
|
407 |
+
"rstrip": false,
|
408 |
+
"single_word": false,
|
409 |
+
"special": true
|
410 |
+
},
|
411 |
+
"128051": {
|
412 |
+
"content": "<|reserved_special_token_43|>",
|
413 |
+
"lstrip": false,
|
414 |
+
"normalized": false,
|
415 |
+
"rstrip": false,
|
416 |
+
"single_word": false,
|
417 |
+
"special": true
|
418 |
+
},
|
419 |
+
"128052": {
|
420 |
+
"content": "<|reserved_special_token_44|>",
|
421 |
+
"lstrip": false,
|
422 |
+
"normalized": false,
|
423 |
+
"rstrip": false,
|
424 |
+
"single_word": false,
|
425 |
+
"special": true
|
426 |
+
},
|
427 |
+
"128053": {
|
428 |
+
"content": "<|reserved_special_token_45|>",
|
429 |
+
"lstrip": false,
|
430 |
+
"normalized": false,
|
431 |
+
"rstrip": false,
|
432 |
+
"single_word": false,
|
433 |
+
"special": true
|
434 |
+
},
|
435 |
+
"128054": {
|
436 |
+
"content": "<|reserved_special_token_46|>",
|
437 |
+
"lstrip": false,
|
438 |
+
"normalized": false,
|
439 |
+
"rstrip": false,
|
440 |
+
"single_word": false,
|
441 |
+
"special": true
|
442 |
+
},
|
443 |
+
"128055": {
|
444 |
+
"content": "<|reserved_special_token_47|>",
|
445 |
+
"lstrip": false,
|
446 |
+
"normalized": false,
|
447 |
+
"rstrip": false,
|
448 |
+
"single_word": false,
|
449 |
+
"special": true
|
450 |
+
},
|
451 |
+
"128056": {
|
452 |
+
"content": "<|reserved_special_token_48|>",
|
453 |
+
"lstrip": false,
|
454 |
+
"normalized": false,
|
455 |
+
"rstrip": false,
|
456 |
+
"single_word": false,
|
457 |
+
"special": true
|
458 |
+
},
|
459 |
+
"128057": {
|
460 |
+
"content": "<|reserved_special_token_49|>",
|
461 |
+
"lstrip": false,
|
462 |
+
"normalized": false,
|
463 |
+
"rstrip": false,
|
464 |
+
"single_word": false,
|
465 |
+
"special": true
|
466 |
+
},
|
467 |
+
"128058": {
|
468 |
+
"content": "<|reserved_special_token_50|>",
|
469 |
+
"lstrip": false,
|
470 |
+
"normalized": false,
|
471 |
+
"rstrip": false,
|
472 |
+
"single_word": false,
|
473 |
+
"special": true
|
474 |
+
},
|
475 |
+
"128059": {
|
476 |
+
"content": "<|reserved_special_token_51|>",
|
477 |
+
"lstrip": false,
|
478 |
+
"normalized": false,
|
479 |
+
"rstrip": false,
|
480 |
+
"single_word": false,
|
481 |
+
"special": true
|
482 |
+
},
|
483 |
+
"128060": {
|
484 |
+
"content": "<|reserved_special_token_52|>",
|
485 |
+
"lstrip": false,
|
486 |
+
"normalized": false,
|
487 |
+
"rstrip": false,
|
488 |
+
"single_word": false,
|
489 |
+
"special": true
|
490 |
+
},
|
491 |
+
"128061": {
|
492 |
+
"content": "<|reserved_special_token_53|>",
|
493 |
+
"lstrip": false,
|
494 |
+
"normalized": false,
|
495 |
+
"rstrip": false,
|
496 |
+
"single_word": false,
|
497 |
+
"special": true
|
498 |
+
},
|
499 |
+
"128062": {
|
500 |
+
"content": "<|reserved_special_token_54|>",
|
501 |
+
"lstrip": false,
|
502 |
+
"normalized": false,
|
503 |
+
"rstrip": false,
|
504 |
+
"single_word": false,
|
505 |
+
"special": true
|
506 |
+
},
|
507 |
+
"128063": {
|
508 |
+
"content": "<|reserved_special_token_55|>",
|
509 |
+
"lstrip": false,
|
510 |
+
"normalized": false,
|
511 |
+
"rstrip": false,
|
512 |
+
"single_word": false,
|
513 |
+
"special": true
|
514 |
+
},
|
515 |
+
"128064": {
|
516 |
+
"content": "<|reserved_special_token_56|>",
|
517 |
+
"lstrip": false,
|
518 |
+
"normalized": false,
|
519 |
+
"rstrip": false,
|
520 |
+
"single_word": false,
|
521 |
+
"special": true
|
522 |
+
},
|
523 |
+
"128065": {
|
524 |
+
"content": "<|reserved_special_token_57|>",
|
525 |
+
"lstrip": false,
|
526 |
+
"normalized": false,
|
527 |
+
"rstrip": false,
|
528 |
+
"single_word": false,
|
529 |
+
"special": true
|
530 |
+
},
|
531 |
+
"128066": {
|
532 |
+
"content": "<|reserved_special_token_58|>",
|
533 |
+
"lstrip": false,
|
534 |
+
"normalized": false,
|
535 |
+
"rstrip": false,
|
536 |
+
"single_word": false,
|
537 |
+
"special": true
|
538 |
+
},
|
539 |
+
"128067": {
|
540 |
+
"content": "<|reserved_special_token_59|>",
|
541 |
+
"lstrip": false,
|
542 |
+
"normalized": false,
|
543 |
+
"rstrip": false,
|
544 |
+
"single_word": false,
|
545 |
+
"special": true
|
546 |
+
},
|
547 |
+
"128068": {
|
548 |
+
"content": "<|reserved_special_token_60|>",
|
549 |
+
"lstrip": false,
|
550 |
+
"normalized": false,
|
551 |
+
"rstrip": false,
|
552 |
+
"single_word": false,
|
553 |
+
"special": true
|
554 |
+
},
|
555 |
+
"128069": {
|
556 |
+
"content": "<|reserved_special_token_61|>",
|
557 |
+
"lstrip": false,
|
558 |
+
"normalized": false,
|
559 |
+
"rstrip": false,
|
560 |
+
"single_word": false,
|
561 |
+
"special": true
|
562 |
+
},
|
563 |
+
"128070": {
|
564 |
+
"content": "<|reserved_special_token_62|>",
|
565 |
+
"lstrip": false,
|
566 |
+
"normalized": false,
|
567 |
+
"rstrip": false,
|
568 |
+
"single_word": false,
|
569 |
+
"special": true
|
570 |
+
},
|
571 |
+
"128071": {
|
572 |
+
"content": "<|reserved_special_token_63|>",
|
573 |
+
"lstrip": false,
|
574 |
+
"normalized": false,
|
575 |
+
"rstrip": false,
|
576 |
+
"single_word": false,
|
577 |
+
"special": true
|
578 |
+
},
|
579 |
+
"128072": {
|
580 |
+
"content": "<|reserved_special_token_64|>",
|
581 |
+
"lstrip": false,
|
582 |
+
"normalized": false,
|
583 |
+
"rstrip": false,
|
584 |
+
"single_word": false,
|
585 |
+
"special": true
|
586 |
+
},
|
587 |
+
"128073": {
|
588 |
+
"content": "<|reserved_special_token_65|>",
|
589 |
+
"lstrip": false,
|
590 |
+
"normalized": false,
|
591 |
+
"rstrip": false,
|
592 |
+
"single_word": false,
|
593 |
+
"special": true
|
594 |
+
},
|
595 |
+
"128074": {
|
596 |
+
"content": "<|reserved_special_token_66|>",
|
597 |
+
"lstrip": false,
|
598 |
+
"normalized": false,
|
599 |
+
"rstrip": false,
|
600 |
+
"single_word": false,
|
601 |
+
"special": true
|
602 |
+
},
|
603 |
+
"128075": {
|
604 |
+
"content": "<|reserved_special_token_67|>",
|
605 |
+
"lstrip": false,
|
606 |
+
"normalized": false,
|
607 |
+
"rstrip": false,
|
608 |
+
"single_word": false,
|
609 |
+
"special": true
|
610 |
+
},
|
611 |
+
"128076": {
|
612 |
+
"content": "<|reserved_special_token_68|>",
|
613 |
+
"lstrip": false,
|
614 |
+
"normalized": false,
|
615 |
+
"rstrip": false,
|
616 |
+
"single_word": false,
|
617 |
+
"special": true
|
618 |
+
},
|
619 |
+
"128077": {
|
620 |
+
"content": "<|reserved_special_token_69|>",
|
621 |
+
"lstrip": false,
|
622 |
+
"normalized": false,
|
623 |
+
"rstrip": false,
|
624 |
+
"single_word": false,
|
625 |
+
"special": true
|
626 |
+
},
|
627 |
+
"128078": {
|
628 |
+
"content": "<|reserved_special_token_70|>",
|
629 |
+
"lstrip": false,
|
630 |
+
"normalized": false,
|
631 |
+
"rstrip": false,
|
632 |
+
"single_word": false,
|
633 |
+
"special": true
|
634 |
+
},
|
635 |
+
"128079": {
|
636 |
+
"content": "<|reserved_special_token_71|>",
|
637 |
+
"lstrip": false,
|
638 |
+
"normalized": false,
|
639 |
+
"rstrip": false,
|
640 |
+
"single_word": false,
|
641 |
+
"special": true
|
642 |
+
},
|
643 |
+
"128080": {
|
644 |
+
"content": "<|reserved_special_token_72|>",
|
645 |
+
"lstrip": false,
|
646 |
+
"normalized": false,
|
647 |
+
"rstrip": false,
|
648 |
+
"single_word": false,
|
649 |
+
"special": true
|
650 |
+
},
|
651 |
+
"128081": {
|
652 |
+
"content": "<|reserved_special_token_73|>",
|
653 |
+
"lstrip": false,
|
654 |
+
"normalized": false,
|
655 |
+
"rstrip": false,
|
656 |
+
"single_word": false,
|
657 |
+
"special": true
|
658 |
+
},
|
659 |
+
"128082": {
|
660 |
+
"content": "<|reserved_special_token_74|>",
|
661 |
+
"lstrip": false,
|
662 |
+
"normalized": false,
|
663 |
+
"rstrip": false,
|
664 |
+
"single_word": false,
|
665 |
+
"special": true
|
666 |
+
},
|
667 |
+
"128083": {
|
668 |
+
"content": "<|reserved_special_token_75|>",
|
669 |
+
"lstrip": false,
|
670 |
+
"normalized": false,
|
671 |
+
"rstrip": false,
|
672 |
+
"single_word": false,
|
673 |
+
"special": true
|
674 |
+
},
|
675 |
+
"128084": {
|
676 |
+
"content": "<|reserved_special_token_76|>",
|
677 |
+
"lstrip": false,
|
678 |
+
"normalized": false,
|
679 |
+
"rstrip": false,
|
680 |
+
"single_word": false,
|
681 |
+
"special": true
|
682 |
+
},
|
683 |
+
"128085": {
|
684 |
+
"content": "<|reserved_special_token_77|>",
|
685 |
+
"lstrip": false,
|
686 |
+
"normalized": false,
|
687 |
+
"rstrip": false,
|
688 |
+
"single_word": false,
|
689 |
+
"special": true
|
690 |
+
},
|
691 |
+
"128086": {
|
692 |
+
"content": "<|reserved_special_token_78|>",
|
693 |
+
"lstrip": false,
|
694 |
+
"normalized": false,
|
695 |
+
"rstrip": false,
|
696 |
+
"single_word": false,
|
697 |
+
"special": true
|
698 |
+
},
|
699 |
+
"128087": {
|
700 |
+
"content": "<|reserved_special_token_79|>",
|
701 |
+
"lstrip": false,
|
702 |
+
"normalized": false,
|
703 |
+
"rstrip": false,
|
704 |
+
"single_word": false,
|
705 |
+
"special": true
|
706 |
+
},
|
707 |
+
"128088": {
|
708 |
+
"content": "<|reserved_special_token_80|>",
|
709 |
+
"lstrip": false,
|
710 |
+
"normalized": false,
|
711 |
+
"rstrip": false,
|
712 |
+
"single_word": false,
|
713 |
+
"special": true
|
714 |
+
},
|
715 |
+
"128089": {
|
716 |
+
"content": "<|reserved_special_token_81|>",
|
717 |
+
"lstrip": false,
|
718 |
+
"normalized": false,
|
719 |
+
"rstrip": false,
|
720 |
+
"single_word": false,
|
721 |
+
"special": true
|
722 |
+
},
|
723 |
+
"128090": {
|
724 |
+
"content": "<|reserved_special_token_82|>",
|
725 |
+
"lstrip": false,
|
726 |
+
"normalized": false,
|
727 |
+
"rstrip": false,
|
728 |
+
"single_word": false,
|
729 |
+
"special": true
|
730 |
+
},
|
731 |
+
"128091": {
|
732 |
+
"content": "<|reserved_special_token_83|>",
|
733 |
+
"lstrip": false,
|
734 |
+
"normalized": false,
|
735 |
+
"rstrip": false,
|
736 |
+
"single_word": false,
|
737 |
+
"special": true
|
738 |
+
},
|
739 |
+
"128092": {
|
740 |
+
"content": "<|reserved_special_token_84|>",
|
741 |
+
"lstrip": false,
|
742 |
+
"normalized": false,
|
743 |
+
"rstrip": false,
|
744 |
+
"single_word": false,
|
745 |
+
"special": true
|
746 |
+
},
|
747 |
+
"128093": {
|
748 |
+
"content": "<|reserved_special_token_85|>",
|
749 |
+
"lstrip": false,
|
750 |
+
"normalized": false,
|
751 |
+
"rstrip": false,
|
752 |
+
"single_word": false,
|
753 |
+
"special": true
|
754 |
+
},
|
755 |
+
"128094": {
|
756 |
+
"content": "<|reserved_special_token_86|>",
|
757 |
+
"lstrip": false,
|
758 |
+
"normalized": false,
|
759 |
+
"rstrip": false,
|
760 |
+
"single_word": false,
|
761 |
+
"special": true
|
762 |
+
},
|
763 |
+
"128095": {
|
764 |
+
"content": "<|reserved_special_token_87|>",
|
765 |
+
"lstrip": false,
|
766 |
+
"normalized": false,
|
767 |
+
"rstrip": false,
|
768 |
+
"single_word": false,
|
769 |
+
"special": true
|
770 |
+
},
|
771 |
+
"128096": {
|
772 |
+
"content": "<|reserved_special_token_88|>",
|
773 |
+
"lstrip": false,
|
774 |
+
"normalized": false,
|
775 |
+
"rstrip": false,
|
776 |
+
"single_word": false,
|
777 |
+
"special": true
|
778 |
+
},
|
779 |
+
"128097": {
|
780 |
+
"content": "<|reserved_special_token_89|>",
|
781 |
+
"lstrip": false,
|
782 |
+
"normalized": false,
|
783 |
+
"rstrip": false,
|
784 |
+
"single_word": false,
|
785 |
+
"special": true
|
786 |
+
},
|
787 |
+
"128098": {
|
788 |
+
"content": "<|reserved_special_token_90|>",
|
789 |
+
"lstrip": false,
|
790 |
+
"normalized": false,
|
791 |
+
"rstrip": false,
|
792 |
+
"single_word": false,
|
793 |
+
"special": true
|
794 |
+
},
|
795 |
+
"128099": {
|
796 |
+
"content": "<|reserved_special_token_91|>",
|
797 |
+
"lstrip": false,
|
798 |
+
"normalized": false,
|
799 |
+
"rstrip": false,
|
800 |
+
"single_word": false,
|
801 |
+
"special": true
|
802 |
+
},
|
803 |
+
"128100": {
|
804 |
+
"content": "<|reserved_special_token_92|>",
|
805 |
+
"lstrip": false,
|
806 |
+
"normalized": false,
|
807 |
+
"rstrip": false,
|
808 |
+
"single_word": false,
|
809 |
+
"special": true
|
810 |
+
},
|
811 |
+
"128101": {
|
812 |
+
"content": "<|reserved_special_token_93|>",
|
813 |
+
"lstrip": false,
|
814 |
+
"normalized": false,
|
815 |
+
"rstrip": false,
|
816 |
+
"single_word": false,
|
817 |
+
"special": true
|
818 |
+
},
|
819 |
+
"128102": {
|
820 |
+
"content": "<|reserved_special_token_94|>",
|
821 |
+
"lstrip": false,
|
822 |
+
"normalized": false,
|
823 |
+
"rstrip": false,
|
824 |
+
"single_word": false,
|
825 |
+
"special": true
|
826 |
+
},
|
827 |
+
"128103": {
|
828 |
+
"content": "<|reserved_special_token_95|>",
|
829 |
+
"lstrip": false,
|
830 |
+
"normalized": false,
|
831 |
+
"rstrip": false,
|
832 |
+
"single_word": false,
|
833 |
+
"special": true
|
834 |
+
},
|
835 |
+
"128104": {
|
836 |
+
"content": "<|reserved_special_token_96|>",
|
837 |
+
"lstrip": false,
|
838 |
+
"normalized": false,
|
839 |
+
"rstrip": false,
|
840 |
+
"single_word": false,
|
841 |
+
"special": true
|
842 |
+
},
|
843 |
+
"128105": {
|
844 |
+
"content": "<|reserved_special_token_97|>",
|
845 |
+
"lstrip": false,
|
846 |
+
"normalized": false,
|
847 |
+
"rstrip": false,
|
848 |
+
"single_word": false,
|
849 |
+
"special": true
|
850 |
+
},
|
851 |
+
"128106": {
|
852 |
+
"content": "<|reserved_special_token_98|>",
|
853 |
+
"lstrip": false,
|
854 |
+
"normalized": false,
|
855 |
+
"rstrip": false,
|
856 |
+
"single_word": false,
|
857 |
+
"special": true
|
858 |
+
},
|
859 |
+
"128107": {
|
860 |
+
"content": "<|reserved_special_token_99|>",
|
861 |
+
"lstrip": false,
|
862 |
+
"normalized": false,
|
863 |
+
"rstrip": false,
|
864 |
+
"single_word": false,
|
865 |
+
"special": true
|
866 |
+
},
|
867 |
+
"128108": {
|
868 |
+
"content": "<|reserved_special_token_100|>",
|
869 |
+
"lstrip": false,
|
870 |
+
"normalized": false,
|
871 |
+
"rstrip": false,
|
872 |
+
"single_word": false,
|
873 |
+
"special": true
|
874 |
+
},
|
875 |
+
"128109": {
|
876 |
+
"content": "<|reserved_special_token_101|>",
|
877 |
+
"lstrip": false,
|
878 |
+
"normalized": false,
|
879 |
+
"rstrip": false,
|
880 |
+
"single_word": false,
|
881 |
+
"special": true
|
882 |
+
},
|
883 |
+
"128110": {
|
884 |
+
"content": "<|reserved_special_token_102|>",
|
885 |
+
"lstrip": false,
|
886 |
+
"normalized": false,
|
887 |
+
"rstrip": false,
|
888 |
+
"single_word": false,
|
889 |
+
"special": true
|
890 |
+
},
|
891 |
+
"128111": {
|
892 |
+
"content": "<|reserved_special_token_103|>",
|
893 |
+
"lstrip": false,
|
894 |
+
"normalized": false,
|
895 |
+
"rstrip": false,
|
896 |
+
"single_word": false,
|
897 |
+
"special": true
|
898 |
+
},
|
899 |
+
"128112": {
|
900 |
+
"content": "<|reserved_special_token_104|>",
|
901 |
+
"lstrip": false,
|
902 |
+
"normalized": false,
|
903 |
+
"rstrip": false,
|
904 |
+
"single_word": false,
|
905 |
+
"special": true
|
906 |
+
},
|
907 |
+
"128113": {
|
908 |
+
"content": "<|reserved_special_token_105|>",
|
909 |
+
"lstrip": false,
|
910 |
+
"normalized": false,
|
911 |
+
"rstrip": false,
|
912 |
+
"single_word": false,
|
913 |
+
"special": true
|
914 |
+
},
|
915 |
+
"128114": {
|
916 |
+
"content": "<|reserved_special_token_106|>",
|
917 |
+
"lstrip": false,
|
918 |
+
"normalized": false,
|
919 |
+
"rstrip": false,
|
920 |
+
"single_word": false,
|
921 |
+
"special": true
|
922 |
+
},
|
923 |
+
"128115": {
|
924 |
+
"content": "<|reserved_special_token_107|>",
|
925 |
+
"lstrip": false,
|
926 |
+
"normalized": false,
|
927 |
+
"rstrip": false,
|
928 |
+
"single_word": false,
|
929 |
+
"special": true
|
930 |
+
},
|
931 |
+
"128116": {
|
932 |
+
"content": "<|reserved_special_token_108|>",
|
933 |
+
"lstrip": false,
|
934 |
+
"normalized": false,
|
935 |
+
"rstrip": false,
|
936 |
+
"single_word": false,
|
937 |
+
"special": true
|
938 |
+
},
|
939 |
+
"128117": {
|
940 |
+
"content": "<|reserved_special_token_109|>",
|
941 |
+
"lstrip": false,
|
942 |
+
"normalized": false,
|
943 |
+
"rstrip": false,
|
944 |
+
"single_word": false,
|
945 |
+
"special": true
|
946 |
+
},
|
947 |
+
"128118": {
|
948 |
+
"content": "<|reserved_special_token_110|>",
|
949 |
+
"lstrip": false,
|
950 |
+
"normalized": false,
|
951 |
+
"rstrip": false,
|
952 |
+
"single_word": false,
|
953 |
+
"special": true
|
954 |
+
},
|
955 |
+
"128119": {
|
956 |
+
"content": "<|reserved_special_token_111|>",
|
957 |
+
"lstrip": false,
|
958 |
+
"normalized": false,
|
959 |
+
"rstrip": false,
|
960 |
+
"single_word": false,
|
961 |
+
"special": true
|
962 |
+
},
|
963 |
+
"128120": {
|
964 |
+
"content": "<|reserved_special_token_112|>",
|
965 |
+
"lstrip": false,
|
966 |
+
"normalized": false,
|
967 |
+
"rstrip": false,
|
968 |
+
"single_word": false,
|
969 |
+
"special": true
|
970 |
+
},
|
971 |
+
"128121": {
|
972 |
+
"content": "<|reserved_special_token_113|>",
|
973 |
+
"lstrip": false,
|
974 |
+
"normalized": false,
|
975 |
+
"rstrip": false,
|
976 |
+
"single_word": false,
|
977 |
+
"special": true
|
978 |
+
},
|
979 |
+
"128122": {
|
980 |
+
"content": "<|reserved_special_token_114|>",
|
981 |
+
"lstrip": false,
|
982 |
+
"normalized": false,
|
983 |
+
"rstrip": false,
|
984 |
+
"single_word": false,
|
985 |
+
"special": true
|
986 |
+
},
|
987 |
+
"128123": {
|
988 |
+
"content": "<|reserved_special_token_115|>",
|
989 |
+
"lstrip": false,
|
990 |
+
"normalized": false,
|
991 |
+
"rstrip": false,
|
992 |
+
"single_word": false,
|
993 |
+
"special": true
|
994 |
+
},
|
995 |
+
"128124": {
|
996 |
+
"content": "<|reserved_special_token_116|>",
|
997 |
+
"lstrip": false,
|
998 |
+
"normalized": false,
|
999 |
+
"rstrip": false,
|
1000 |
+
"single_word": false,
|
1001 |
+
"special": true
|
1002 |
+
},
|
1003 |
+
"128125": {
|
1004 |
+
"content": "<|reserved_special_token_117|>",
|
1005 |
+
"lstrip": false,
|
1006 |
+
"normalized": false,
|
1007 |
+
"rstrip": false,
|
1008 |
+
"single_word": false,
|
1009 |
+
"special": true
|
1010 |
+
},
|
1011 |
+
"128126": {
|
1012 |
+
"content": "<|reserved_special_token_118|>",
|
1013 |
+
"lstrip": false,
|
1014 |
+
"normalized": false,
|
1015 |
+
"rstrip": false,
|
1016 |
+
"single_word": false,
|
1017 |
+
"special": true
|
1018 |
+
},
|
1019 |
+
"128127": {
|
1020 |
+
"content": "<|reserved_special_token_119|>",
|
1021 |
+
"lstrip": false,
|
1022 |
+
"normalized": false,
|
1023 |
+
"rstrip": false,
|
1024 |
+
"single_word": false,
|
1025 |
+
"special": true
|
1026 |
+
},
|
1027 |
+
"128128": {
|
1028 |
+
"content": "<|reserved_special_token_120|>",
|
1029 |
+
"lstrip": false,
|
1030 |
+
"normalized": false,
|
1031 |
+
"rstrip": false,
|
1032 |
+
"single_word": false,
|
1033 |
+
"special": true
|
1034 |
+
},
|
1035 |
+
"128129": {
|
1036 |
+
"content": "<|reserved_special_token_121|>",
|
1037 |
+
"lstrip": false,
|
1038 |
+
"normalized": false,
|
1039 |
+
"rstrip": false,
|
1040 |
+
"single_word": false,
|
1041 |
+
"special": true
|
1042 |
+
},
|
1043 |
+
"128130": {
|
1044 |
+
"content": "<|reserved_special_token_122|>",
|
1045 |
+
"lstrip": false,
|
1046 |
+
"normalized": false,
|
1047 |
+
"rstrip": false,
|
1048 |
+
"single_word": false,
|
1049 |
+
"special": true
|
1050 |
+
},
|
1051 |
+
"128131": {
|
1052 |
+
"content": "<|reserved_special_token_123|>",
|
1053 |
+
"lstrip": false,
|
1054 |
+
"normalized": false,
|
1055 |
+
"rstrip": false,
|
1056 |
+
"single_word": false,
|
1057 |
+
"special": true
|
1058 |
+
},
|
1059 |
+
"128132": {
|
1060 |
+
"content": "<|reserved_special_token_124|>",
|
1061 |
+
"lstrip": false,
|
1062 |
+
"normalized": false,
|
1063 |
+
"rstrip": false,
|
1064 |
+
"single_word": false,
|
1065 |
+
"special": true
|
1066 |
+
},
|
1067 |
+
"128133": {
|
1068 |
+
"content": "<|reserved_special_token_125|>",
|
1069 |
+
"lstrip": false,
|
1070 |
+
"normalized": false,
|
1071 |
+
"rstrip": false,
|
1072 |
+
"single_word": false,
|
1073 |
+
"special": true
|
1074 |
+
},
|
1075 |
+
"128134": {
|
1076 |
+
"content": "<|reserved_special_token_126|>",
|
1077 |
+
"lstrip": false,
|
1078 |
+
"normalized": false,
|
1079 |
+
"rstrip": false,
|
1080 |
+
"single_word": false,
|
1081 |
+
"special": true
|
1082 |
+
},
|
1083 |
+
"128135": {
|
1084 |
+
"content": "<|reserved_special_token_127|>",
|
1085 |
+
"lstrip": false,
|
1086 |
+
"normalized": false,
|
1087 |
+
"rstrip": false,
|
1088 |
+
"single_word": false,
|
1089 |
+
"special": true
|
1090 |
+
},
|
1091 |
+
"128136": {
|
1092 |
+
"content": "<|reserved_special_token_128|>",
|
1093 |
+
"lstrip": false,
|
1094 |
+
"normalized": false,
|
1095 |
+
"rstrip": false,
|
1096 |
+
"single_word": false,
|
1097 |
+
"special": true
|
1098 |
+
},
|
1099 |
+
"128137": {
|
1100 |
+
"content": "<|reserved_special_token_129|>",
|
1101 |
+
"lstrip": false,
|
1102 |
+
"normalized": false,
|
1103 |
+
"rstrip": false,
|
1104 |
+
"single_word": false,
|
1105 |
+
"special": true
|
1106 |
+
},
|
1107 |
+
"128138": {
|
1108 |
+
"content": "<|reserved_special_token_130|>",
|
1109 |
+
"lstrip": false,
|
1110 |
+
"normalized": false,
|
1111 |
+
"rstrip": false,
|
1112 |
+
"single_word": false,
|
1113 |
+
"special": true
|
1114 |
+
},
|
1115 |
+
"128139": {
|
1116 |
+
"content": "<|reserved_special_token_131|>",
|
1117 |
+
"lstrip": false,
|
1118 |
+
"normalized": false,
|
1119 |
+
"rstrip": false,
|
1120 |
+
"single_word": false,
|
1121 |
+
"special": true
|
1122 |
+
},
|
1123 |
+
"128140": {
|
1124 |
+
"content": "<|reserved_special_token_132|>",
|
1125 |
+
"lstrip": false,
|
1126 |
+
"normalized": false,
|
1127 |
+
"rstrip": false,
|
1128 |
+
"single_word": false,
|
1129 |
+
"special": true
|
1130 |
+
},
|
1131 |
+
"128141": {
|
1132 |
+
"content": "<|reserved_special_token_133|>",
|
1133 |
+
"lstrip": false,
|
1134 |
+
"normalized": false,
|
1135 |
+
"rstrip": false,
|
1136 |
+
"single_word": false,
|
1137 |
+
"special": true
|
1138 |
+
},
|
1139 |
+
"128142": {
|
1140 |
+
"content": "<|reserved_special_token_134|>",
|
1141 |
+
"lstrip": false,
|
1142 |
+
"normalized": false,
|
1143 |
+
"rstrip": false,
|
1144 |
+
"single_word": false,
|
1145 |
+
"special": true
|
1146 |
+
},
|
1147 |
+
"128143": {
|
1148 |
+
"content": "<|reserved_special_token_135|>",
|
1149 |
+
"lstrip": false,
|
1150 |
+
"normalized": false,
|
1151 |
+
"rstrip": false,
|
1152 |
+
"single_word": false,
|
1153 |
+
"special": true
|
1154 |
+
},
|
1155 |
+
"128144": {
|
1156 |
+
"content": "<|reserved_special_token_136|>",
|
1157 |
+
"lstrip": false,
|
1158 |
+
"normalized": false,
|
1159 |
+
"rstrip": false,
|
1160 |
+
"single_word": false,
|
1161 |
+
"special": true
|
1162 |
+
},
|
1163 |
+
"128145": {
|
1164 |
+
"content": "<|reserved_special_token_137|>",
|
1165 |
+
"lstrip": false,
|
1166 |
+
"normalized": false,
|
1167 |
+
"rstrip": false,
|
1168 |
+
"single_word": false,
|
1169 |
+
"special": true
|
1170 |
+
},
|
1171 |
+
"128146": {
|
1172 |
+
"content": "<|reserved_special_token_138|>",
|
1173 |
+
"lstrip": false,
|
1174 |
+
"normalized": false,
|
1175 |
+
"rstrip": false,
|
1176 |
+
"single_word": false,
|
1177 |
+
"special": true
|
1178 |
+
},
|
1179 |
+
"128147": {
|
1180 |
+
"content": "<|reserved_special_token_139|>",
|
1181 |
+
"lstrip": false,
|
1182 |
+
"normalized": false,
|
1183 |
+
"rstrip": false,
|
1184 |
+
"single_word": false,
|
1185 |
+
"special": true
|
1186 |
+
},
|
1187 |
+
"128148": {
|
1188 |
+
"content": "<|reserved_special_token_140|>",
|
1189 |
+
"lstrip": false,
|
1190 |
+
"normalized": false,
|
1191 |
+
"rstrip": false,
|
1192 |
+
"single_word": false,
|
1193 |
+
"special": true
|
1194 |
+
},
|
1195 |
+
"128149": {
|
1196 |
+
"content": "<|reserved_special_token_141|>",
|
1197 |
+
"lstrip": false,
|
1198 |
+
"normalized": false,
|
1199 |
+
"rstrip": false,
|
1200 |
+
"single_word": false,
|
1201 |
+
"special": true
|
1202 |
+
},
|
1203 |
+
"128150": {
|
1204 |
+
"content": "<|reserved_special_token_142|>",
|
1205 |
+
"lstrip": false,
|
1206 |
+
"normalized": false,
|
1207 |
+
"rstrip": false,
|
1208 |
+
"single_word": false,
|
1209 |
+
"special": true
|
1210 |
+
},
|
1211 |
+
"128151": {
|
1212 |
+
"content": "<|reserved_special_token_143|>",
|
1213 |
+
"lstrip": false,
|
1214 |
+
"normalized": false,
|
1215 |
+
"rstrip": false,
|
1216 |
+
"single_word": false,
|
1217 |
+
"special": true
|
1218 |
+
},
|
1219 |
+
"128152": {
|
1220 |
+
"content": "<|reserved_special_token_144|>",
|
1221 |
+
"lstrip": false,
|
1222 |
+
"normalized": false,
|
1223 |
+
"rstrip": false,
|
1224 |
+
"single_word": false,
|
1225 |
+
"special": true
|
1226 |
+
},
|
1227 |
+
"128153": {
|
1228 |
+
"content": "<|reserved_special_token_145|>",
|
1229 |
+
"lstrip": false,
|
1230 |
+
"normalized": false,
|
1231 |
+
"rstrip": false,
|
1232 |
+
"single_word": false,
|
1233 |
+
"special": true
|
1234 |
+
},
|
1235 |
+
"128154": {
|
1236 |
+
"content": "<|reserved_special_token_146|>",
|
1237 |
+
"lstrip": false,
|
1238 |
+
"normalized": false,
|
1239 |
+
"rstrip": false,
|
1240 |
+
"single_word": false,
|
1241 |
+
"special": true
|
1242 |
+
},
|
1243 |
+
"128155": {
|
1244 |
+
"content": "<|reserved_special_token_147|>",
|
1245 |
+
"lstrip": false,
|
1246 |
+
"normalized": false,
|
1247 |
+
"rstrip": false,
|
1248 |
+
"single_word": false,
|
1249 |
+
"special": true
|
1250 |
+
},
|
1251 |
+
"128156": {
|
1252 |
+
"content": "<|reserved_special_token_148|>",
|
1253 |
+
"lstrip": false,
|
1254 |
+
"normalized": false,
|
1255 |
+
"rstrip": false,
|
1256 |
+
"single_word": false,
|
1257 |
+
"special": true
|
1258 |
+
},
|
1259 |
+
"128157": {
|
1260 |
+
"content": "<|reserved_special_token_149|>",
|
1261 |
+
"lstrip": false,
|
1262 |
+
"normalized": false,
|
1263 |
+
"rstrip": false,
|
1264 |
+
"single_word": false,
|
1265 |
+
"special": true
|
1266 |
+
},
|
1267 |
+
"128158": {
|
1268 |
+
"content": "<|reserved_special_token_150|>",
|
1269 |
+
"lstrip": false,
|
1270 |
+
"normalized": false,
|
1271 |
+
"rstrip": false,
|
1272 |
+
"single_word": false,
|
1273 |
+
"special": true
|
1274 |
+
},
|
1275 |
+
"128159": {
|
1276 |
+
"content": "<|reserved_special_token_151|>",
|
1277 |
+
"lstrip": false,
|
1278 |
+
"normalized": false,
|
1279 |
+
"rstrip": false,
|
1280 |
+
"single_word": false,
|
1281 |
+
"special": true
|
1282 |
+
},
|
1283 |
+
"128160": {
|
1284 |
+
"content": "<|reserved_special_token_152|>",
|
1285 |
+
"lstrip": false,
|
1286 |
+
"normalized": false,
|
1287 |
+
"rstrip": false,
|
1288 |
+
"single_word": false,
|
1289 |
+
"special": true
|
1290 |
+
},
|
1291 |
+
"128161": {
|
1292 |
+
"content": "<|reserved_special_token_153|>",
|
1293 |
+
"lstrip": false,
|
1294 |
+
"normalized": false,
|
1295 |
+
"rstrip": false,
|
1296 |
+
"single_word": false,
|
1297 |
+
"special": true
|
1298 |
+
},
|
1299 |
+
"128162": {
|
1300 |
+
"content": "<|reserved_special_token_154|>",
|
1301 |
+
"lstrip": false,
|
1302 |
+
"normalized": false,
|
1303 |
+
"rstrip": false,
|
1304 |
+
"single_word": false,
|
1305 |
+
"special": true
|
1306 |
+
},
|
1307 |
+
"128163": {
|
1308 |
+
"content": "<|reserved_special_token_155|>",
|
1309 |
+
"lstrip": false,
|
1310 |
+
"normalized": false,
|
1311 |
+
"rstrip": false,
|
1312 |
+
"single_word": false,
|
1313 |
+
"special": true
|
1314 |
+
},
|
1315 |
+
"128164": {
|
1316 |
+
"content": "<|reserved_special_token_156|>",
|
1317 |
+
"lstrip": false,
|
1318 |
+
"normalized": false,
|
1319 |
+
"rstrip": false,
|
1320 |
+
"single_word": false,
|
1321 |
+
"special": true
|
1322 |
+
},
|
1323 |
+
"128165": {
|
1324 |
+
"content": "<|reserved_special_token_157|>",
|
1325 |
+
"lstrip": false,
|
1326 |
+
"normalized": false,
|
1327 |
+
"rstrip": false,
|
1328 |
+
"single_word": false,
|
1329 |
+
"special": true
|
1330 |
+
},
|
1331 |
+
"128166": {
|
1332 |
+
"content": "<|reserved_special_token_158|>",
|
1333 |
+
"lstrip": false,
|
1334 |
+
"normalized": false,
|
1335 |
+
"rstrip": false,
|
1336 |
+
"single_word": false,
|
1337 |
+
"special": true
|
1338 |
+
},
|
1339 |
+
"128167": {
|
1340 |
+
"content": "<|reserved_special_token_159|>",
|
1341 |
+
"lstrip": false,
|
1342 |
+
"normalized": false,
|
1343 |
+
"rstrip": false,
|
1344 |
+
"single_word": false,
|
1345 |
+
"special": true
|
1346 |
+
},
|
1347 |
+
"128168": {
|
1348 |
+
"content": "<|reserved_special_token_160|>",
|
1349 |
+
"lstrip": false,
|
1350 |
+
"normalized": false,
|
1351 |
+
"rstrip": false,
|
1352 |
+
"single_word": false,
|
1353 |
+
"special": true
|
1354 |
+
},
|
1355 |
+
"128169": {
|
1356 |
+
"content": "<|reserved_special_token_161|>",
|
1357 |
+
"lstrip": false,
|
1358 |
+
"normalized": false,
|
1359 |
+
"rstrip": false,
|
1360 |
+
"single_word": false,
|
1361 |
+
"special": true
|
1362 |
+
},
|
1363 |
+
"128170": {
|
1364 |
+
"content": "<|reserved_special_token_162|>",
|
1365 |
+
"lstrip": false,
|
1366 |
+
"normalized": false,
|
1367 |
+
"rstrip": false,
|
1368 |
+
"single_word": false,
|
1369 |
+
"special": true
|
1370 |
+
},
|
1371 |
+
"128171": {
|
1372 |
+
"content": "<|reserved_special_token_163|>",
|
1373 |
+
"lstrip": false,
|
1374 |
+
"normalized": false,
|
1375 |
+
"rstrip": false,
|
1376 |
+
"single_word": false,
|
1377 |
+
"special": true
|
1378 |
+
},
|
1379 |
+
"128172": {
|
1380 |
+
"content": "<|reserved_special_token_164|>",
|
1381 |
+
"lstrip": false,
|
1382 |
+
"normalized": false,
|
1383 |
+
"rstrip": false,
|
1384 |
+
"single_word": false,
|
1385 |
+
"special": true
|
1386 |
+
},
|
1387 |
+
"128173": {
|
1388 |
+
"content": "<|reserved_special_token_165|>",
|
1389 |
+
"lstrip": false,
|
1390 |
+
"normalized": false,
|
1391 |
+
"rstrip": false,
|
1392 |
+
"single_word": false,
|
1393 |
+
"special": true
|
1394 |
+
},
|
1395 |
+
"128174": {
|
1396 |
+
"content": "<|reserved_special_token_166|>",
|
1397 |
+
"lstrip": false,
|
1398 |
+
"normalized": false,
|
1399 |
+
"rstrip": false,
|
1400 |
+
"single_word": false,
|
1401 |
+
"special": true
|
1402 |
+
},
|
1403 |
+
"128175": {
|
1404 |
+
"content": "<|reserved_special_token_167|>",
|
1405 |
+
"lstrip": false,
|
1406 |
+
"normalized": false,
|
1407 |
+
"rstrip": false,
|
1408 |
+
"single_word": false,
|
1409 |
+
"special": true
|
1410 |
+
},
|
1411 |
+
"128176": {
|
1412 |
+
"content": "<|reserved_special_token_168|>",
|
1413 |
+
"lstrip": false,
|
1414 |
+
"normalized": false,
|
1415 |
+
"rstrip": false,
|
1416 |
+
"single_word": false,
|
1417 |
+
"special": true
|
1418 |
+
},
|
1419 |
+
"128177": {
|
1420 |
+
"content": "<|reserved_special_token_169|>",
|
1421 |
+
"lstrip": false,
|
1422 |
+
"normalized": false,
|
1423 |
+
"rstrip": false,
|
1424 |
+
"single_word": false,
|
1425 |
+
"special": true
|
1426 |
+
},
|
1427 |
+
"128178": {
|
1428 |
+
"content": "<|reserved_special_token_170|>",
|
1429 |
+
"lstrip": false,
|
1430 |
+
"normalized": false,
|
1431 |
+
"rstrip": false,
|
1432 |
+
"single_word": false,
|
1433 |
+
"special": true
|
1434 |
+
},
|
1435 |
+
"128179": {
|
1436 |
+
"content": "<|reserved_special_token_171|>",
|
1437 |
+
"lstrip": false,
|
1438 |
+
"normalized": false,
|
1439 |
+
"rstrip": false,
|
1440 |
+
"single_word": false,
|
1441 |
+
"special": true
|
1442 |
+
},
|
1443 |
+
"128180": {
|
1444 |
+
"content": "<|reserved_special_token_172|>",
|
1445 |
+
"lstrip": false,
|
1446 |
+
"normalized": false,
|
1447 |
+
"rstrip": false,
|
1448 |
+
"single_word": false,
|
1449 |
+
"special": true
|
1450 |
+
},
|
1451 |
+
"128181": {
|
1452 |
+
"content": "<|reserved_special_token_173|>",
|
1453 |
+
"lstrip": false,
|
1454 |
+
"normalized": false,
|
1455 |
+
"rstrip": false,
|
1456 |
+
"single_word": false,
|
1457 |
+
"special": true
|
1458 |
+
},
|
1459 |
+
"128182": {
|
1460 |
+
"content": "<|reserved_special_token_174|>",
|
1461 |
+
"lstrip": false,
|
1462 |
+
"normalized": false,
|
1463 |
+
"rstrip": false,
|
1464 |
+
"single_word": false,
|
1465 |
+
"special": true
|
1466 |
+
},
|
1467 |
+
"128183": {
|
1468 |
+
"content": "<|reserved_special_token_175|>",
|
1469 |
+
"lstrip": false,
|
1470 |
+
"normalized": false,
|
1471 |
+
"rstrip": false,
|
1472 |
+
"single_word": false,
|
1473 |
+
"special": true
|
1474 |
+
},
|
1475 |
+
"128184": {
|
1476 |
+
"content": "<|reserved_special_token_176|>",
|
1477 |
+
"lstrip": false,
|
1478 |
+
"normalized": false,
|
1479 |
+
"rstrip": false,
|
1480 |
+
"single_word": false,
|
1481 |
+
"special": true
|
1482 |
+
},
|
1483 |
+
"128185": {
|
1484 |
+
"content": "<|reserved_special_token_177|>",
|
1485 |
+
"lstrip": false,
|
1486 |
+
"normalized": false,
|
1487 |
+
"rstrip": false,
|
1488 |
+
"single_word": false,
|
1489 |
+
"special": true
|
1490 |
+
},
|
1491 |
+
"128186": {
|
1492 |
+
"content": "<|reserved_special_token_178|>",
|
1493 |
+
"lstrip": false,
|
1494 |
+
"normalized": false,
|
1495 |
+
"rstrip": false,
|
1496 |
+
"single_word": false,
|
1497 |
+
"special": true
|
1498 |
+
},
|
1499 |
+
"128187": {
|
1500 |
+
"content": "<|reserved_special_token_179|>",
|
1501 |
+
"lstrip": false,
|
1502 |
+
"normalized": false,
|
1503 |
+
"rstrip": false,
|
1504 |
+
"single_word": false,
|
1505 |
+
"special": true
|
1506 |
+
},
|
1507 |
+
"128188": {
|
1508 |
+
"content": "<|reserved_special_token_180|>",
|
1509 |
+
"lstrip": false,
|
1510 |
+
"normalized": false,
|
1511 |
+
"rstrip": false,
|
1512 |
+
"single_word": false,
|
1513 |
+
"special": true
|
1514 |
+
},
|
1515 |
+
"128189": {
|
1516 |
+
"content": "<|reserved_special_token_181|>",
|
1517 |
+
"lstrip": false,
|
1518 |
+
"normalized": false,
|
1519 |
+
"rstrip": false,
|
1520 |
+
"single_word": false,
|
1521 |
+
"special": true
|
1522 |
+
},
|
1523 |
+
"128190": {
|
1524 |
+
"content": "<|reserved_special_token_182|>",
|
1525 |
+
"lstrip": false,
|
1526 |
+
"normalized": false,
|
1527 |
+
"rstrip": false,
|
1528 |
+
"single_word": false,
|
1529 |
+
"special": true
|
1530 |
+
},
|
1531 |
+
"128191": {
|
1532 |
+
"content": "<|reserved_special_token_183|>",
|
1533 |
+
"lstrip": false,
|
1534 |
+
"normalized": false,
|
1535 |
+
"rstrip": false,
|
1536 |
+
"single_word": false,
|
1537 |
+
"special": true
|
1538 |
+
},
|
1539 |
+
"128192": {
|
1540 |
+
"content": "<|reserved_special_token_184|>",
|
1541 |
+
"lstrip": false,
|
1542 |
+
"normalized": false,
|
1543 |
+
"rstrip": false,
|
1544 |
+
"single_word": false,
|
1545 |
+
"special": true
|
1546 |
+
},
|
1547 |
+
"128193": {
|
1548 |
+
"content": "<|reserved_special_token_185|>",
|
1549 |
+
"lstrip": false,
|
1550 |
+
"normalized": false,
|
1551 |
+
"rstrip": false,
|
1552 |
+
"single_word": false,
|
1553 |
+
"special": true
|
1554 |
+
},
|
1555 |
+
"128194": {
|
1556 |
+
"content": "<|reserved_special_token_186|>",
|
1557 |
+
"lstrip": false,
|
1558 |
+
"normalized": false,
|
1559 |
+
"rstrip": false,
|
1560 |
+
"single_word": false,
|
1561 |
+
"special": true
|
1562 |
+
},
|
1563 |
+
"128195": {
|
1564 |
+
"content": "<|reserved_special_token_187|>",
|
1565 |
+
"lstrip": false,
|
1566 |
+
"normalized": false,
|
1567 |
+
"rstrip": false,
|
1568 |
+
"single_word": false,
|
1569 |
+
"special": true
|
1570 |
+
},
|
1571 |
+
"128196": {
|
1572 |
+
"content": "<|reserved_special_token_188|>",
|
1573 |
+
"lstrip": false,
|
1574 |
+
"normalized": false,
|
1575 |
+
"rstrip": false,
|
1576 |
+
"single_word": false,
|
1577 |
+
"special": true
|
1578 |
+
},
|
1579 |
+
"128197": {
|
1580 |
+
"content": "<|reserved_special_token_189|>",
|
1581 |
+
"lstrip": false,
|
1582 |
+
"normalized": false,
|
1583 |
+
"rstrip": false,
|
1584 |
+
"single_word": false,
|
1585 |
+
"special": true
|
1586 |
+
},
|
1587 |
+
"128198": {
|
1588 |
+
"content": "<|reserved_special_token_190|>",
|
1589 |
+
"lstrip": false,
|
1590 |
+
"normalized": false,
|
1591 |
+
"rstrip": false,
|
1592 |
+
"single_word": false,
|
1593 |
+
"special": true
|
1594 |
+
},
|
1595 |
+
"128199": {
|
1596 |
+
"content": "<|reserved_special_token_191|>",
|
1597 |
+
"lstrip": false,
|
1598 |
+
"normalized": false,
|
1599 |
+
"rstrip": false,
|
1600 |
+
"single_word": false,
|
1601 |
+
"special": true
|
1602 |
+
},
|
1603 |
+
"128200": {
|
1604 |
+
"content": "<|reserved_special_token_192|>",
|
1605 |
+
"lstrip": false,
|
1606 |
+
"normalized": false,
|
1607 |
+
"rstrip": false,
|
1608 |
+
"single_word": false,
|
1609 |
+
"special": true
|
1610 |
+
},
|
1611 |
+
"128201": {
|
1612 |
+
"content": "<|reserved_special_token_193|>",
|
1613 |
+
"lstrip": false,
|
1614 |
+
"normalized": false,
|
1615 |
+
"rstrip": false,
|
1616 |
+
"single_word": false,
|
1617 |
+
"special": true
|
1618 |
+
},
|
1619 |
+
"128202": {
|
1620 |
+
"content": "<|reserved_special_token_194|>",
|
1621 |
+
"lstrip": false,
|
1622 |
+
"normalized": false,
|
1623 |
+
"rstrip": false,
|
1624 |
+
"single_word": false,
|
1625 |
+
"special": true
|
1626 |
+
},
|
1627 |
+
"128203": {
|
1628 |
+
"content": "<|reserved_special_token_195|>",
|
1629 |
+
"lstrip": false,
|
1630 |
+
"normalized": false,
|
1631 |
+
"rstrip": false,
|
1632 |
+
"single_word": false,
|
1633 |
+
"special": true
|
1634 |
+
},
|
1635 |
+
"128204": {
|
1636 |
+
"content": "<|reserved_special_token_196|>",
|
1637 |
+
"lstrip": false,
|
1638 |
+
"normalized": false,
|
1639 |
+
"rstrip": false,
|
1640 |
+
"single_word": false,
|
1641 |
+
"special": true
|
1642 |
+
},
|
1643 |
+
"128205": {
|
1644 |
+
"content": "<|reserved_special_token_197|>",
|
1645 |
+
"lstrip": false,
|
1646 |
+
"normalized": false,
|
1647 |
+
"rstrip": false,
|
1648 |
+
"single_word": false,
|
1649 |
+
"special": true
|
1650 |
+
},
|
1651 |
+
"128206": {
|
1652 |
+
"content": "<|reserved_special_token_198|>",
|
1653 |
+
"lstrip": false,
|
1654 |
+
"normalized": false,
|
1655 |
+
"rstrip": false,
|
1656 |
+
"single_word": false,
|
1657 |
+
"special": true
|
1658 |
+
},
|
1659 |
+
"128207": {
|
1660 |
+
"content": "<|reserved_special_token_199|>",
|
1661 |
+
"lstrip": false,
|
1662 |
+
"normalized": false,
|
1663 |
+
"rstrip": false,
|
1664 |
+
"single_word": false,
|
1665 |
+
"special": true
|
1666 |
+
},
|
1667 |
+
"128208": {
|
1668 |
+
"content": "<|reserved_special_token_200|>",
|
1669 |
+
"lstrip": false,
|
1670 |
+
"normalized": false,
|
1671 |
+
"rstrip": false,
|
1672 |
+
"single_word": false,
|
1673 |
+
"special": true
|
1674 |
+
},
|
1675 |
+
"128209": {
|
1676 |
+
"content": "<|reserved_special_token_201|>",
|
1677 |
+
"lstrip": false,
|
1678 |
+
"normalized": false,
|
1679 |
+
"rstrip": false,
|
1680 |
+
"single_word": false,
|
1681 |
+
"special": true
|
1682 |
+
},
|
1683 |
+
"128210": {
|
1684 |
+
"content": "<|reserved_special_token_202|>",
|
1685 |
+
"lstrip": false,
|
1686 |
+
"normalized": false,
|
1687 |
+
"rstrip": false,
|
1688 |
+
"single_word": false,
|
1689 |
+
"special": true
|
1690 |
+
},
|
1691 |
+
"128211": {
|
1692 |
+
"content": "<|reserved_special_token_203|>",
|
1693 |
+
"lstrip": false,
|
1694 |
+
"normalized": false,
|
1695 |
+
"rstrip": false,
|
1696 |
+
"single_word": false,
|
1697 |
+
"special": true
|
1698 |
+
},
|
1699 |
+
"128212": {
|
1700 |
+
"content": "<|reserved_special_token_204|>",
|
1701 |
+
"lstrip": false,
|
1702 |
+
"normalized": false,
|
1703 |
+
"rstrip": false,
|
1704 |
+
"single_word": false,
|
1705 |
+
"special": true
|
1706 |
+
},
|
1707 |
+
"128213": {
|
1708 |
+
"content": "<|reserved_special_token_205|>",
|
1709 |
+
"lstrip": false,
|
1710 |
+
"normalized": false,
|
1711 |
+
"rstrip": false,
|
1712 |
+
"single_word": false,
|
1713 |
+
"special": true
|
1714 |
+
},
|
1715 |
+
"128214": {
|
1716 |
+
"content": "<|reserved_special_token_206|>",
|
1717 |
+
"lstrip": false,
|
1718 |
+
"normalized": false,
|
1719 |
+
"rstrip": false,
|
1720 |
+
"single_word": false,
|
1721 |
+
"special": true
|
1722 |
+
},
|
1723 |
+
"128215": {
|
1724 |
+
"content": "<|reserved_special_token_207|>",
|
1725 |
+
"lstrip": false,
|
1726 |
+
"normalized": false,
|
1727 |
+
"rstrip": false,
|
1728 |
+
"single_word": false,
|
1729 |
+
"special": true
|
1730 |
+
},
|
1731 |
+
"128216": {
|
1732 |
+
"content": "<|reserved_special_token_208|>",
|
1733 |
+
"lstrip": false,
|
1734 |
+
"normalized": false,
|
1735 |
+
"rstrip": false,
|
1736 |
+
"single_word": false,
|
1737 |
+
"special": true
|
1738 |
+
},
|
1739 |
+
"128217": {
|
1740 |
+
"content": "<|reserved_special_token_209|>",
|
1741 |
+
"lstrip": false,
|
1742 |
+
"normalized": false,
|
1743 |
+
"rstrip": false,
|
1744 |
+
"single_word": false,
|
1745 |
+
"special": true
|
1746 |
+
},
|
1747 |
+
"128218": {
|
1748 |
+
"content": "<|reserved_special_token_210|>",
|
1749 |
+
"lstrip": false,
|
1750 |
+
"normalized": false,
|
1751 |
+
"rstrip": false,
|
1752 |
+
"single_word": false,
|
1753 |
+
"special": true
|
1754 |
+
},
|
1755 |
+
"128219": {
|
1756 |
+
"content": "<|reserved_special_token_211|>",
|
1757 |
+
"lstrip": false,
|
1758 |
+
"normalized": false,
|
1759 |
+
"rstrip": false,
|
1760 |
+
"single_word": false,
|
1761 |
+
"special": true
|
1762 |
+
},
|
1763 |
+
"128220": {
|
1764 |
+
"content": "<|reserved_special_token_212|>",
|
1765 |
+
"lstrip": false,
|
1766 |
+
"normalized": false,
|
1767 |
+
"rstrip": false,
|
1768 |
+
"single_word": false,
|
1769 |
+
"special": true
|
1770 |
+
},
|
1771 |
+
"128221": {
|
1772 |
+
"content": "<|reserved_special_token_213|>",
|
1773 |
+
"lstrip": false,
|
1774 |
+
"normalized": false,
|
1775 |
+
"rstrip": false,
|
1776 |
+
"single_word": false,
|
1777 |
+
"special": true
|
1778 |
+
},
|
1779 |
+
"128222": {
|
1780 |
+
"content": "<|reserved_special_token_214|>",
|
1781 |
+
"lstrip": false,
|
1782 |
+
"normalized": false,
|
1783 |
+
"rstrip": false,
|
1784 |
+
"single_word": false,
|
1785 |
+
"special": true
|
1786 |
+
},
|
1787 |
+
"128223": {
|
1788 |
+
"content": "<|reserved_special_token_215|>",
|
1789 |
+
"lstrip": false,
|
1790 |
+
"normalized": false,
|
1791 |
+
"rstrip": false,
|
1792 |
+
"single_word": false,
|
1793 |
+
"special": true
|
1794 |
+
},
|
1795 |
+
"128224": {
|
1796 |
+
"content": "<|reserved_special_token_216|>",
|
1797 |
+
"lstrip": false,
|
1798 |
+
"normalized": false,
|
1799 |
+
"rstrip": false,
|
1800 |
+
"single_word": false,
|
1801 |
+
"special": true
|
1802 |
+
},
|
1803 |
+
"128225": {
|
1804 |
+
"content": "<|reserved_special_token_217|>",
|
1805 |
+
"lstrip": false,
|
1806 |
+
"normalized": false,
|
1807 |
+
"rstrip": false,
|
1808 |
+
"single_word": false,
|
1809 |
+
"special": true
|
1810 |
+
},
|
1811 |
+
"128226": {
|
1812 |
+
"content": "<|reserved_special_token_218|>",
|
1813 |
+
"lstrip": false,
|
1814 |
+
"normalized": false,
|
1815 |
+
"rstrip": false,
|
1816 |
+
"single_word": false,
|
1817 |
+
"special": true
|
1818 |
+
},
|
1819 |
+
"128227": {
|
1820 |
+
"content": "<|reserved_special_token_219|>",
|
1821 |
+
"lstrip": false,
|
1822 |
+
"normalized": false,
|
1823 |
+
"rstrip": false,
|
1824 |
+
"single_word": false,
|
1825 |
+
"special": true
|
1826 |
+
},
|
1827 |
+
"128228": {
|
1828 |
+
"content": "<|reserved_special_token_220|>",
|
1829 |
+
"lstrip": false,
|
1830 |
+
"normalized": false,
|
1831 |
+
"rstrip": false,
|
1832 |
+
"single_word": false,
|
1833 |
+
"special": true
|
1834 |
+
},
|
1835 |
+
"128229": {
|
1836 |
+
"content": "<|reserved_special_token_221|>",
|
1837 |
+
"lstrip": false,
|
1838 |
+
"normalized": false,
|
1839 |
+
"rstrip": false,
|
1840 |
+
"single_word": false,
|
1841 |
+
"special": true
|
1842 |
+
},
|
1843 |
+
"128230": {
|
1844 |
+
"content": "<|reserved_special_token_222|>",
|
1845 |
+
"lstrip": false,
|
1846 |
+
"normalized": false,
|
1847 |
+
"rstrip": false,
|
1848 |
+
"single_word": false,
|
1849 |
+
"special": true
|
1850 |
+
},
|
1851 |
+
"128231": {
|
1852 |
+
"content": "<|reserved_special_token_223|>",
|
1853 |
+
"lstrip": false,
|
1854 |
+
"normalized": false,
|
1855 |
+
"rstrip": false,
|
1856 |
+
"single_word": false,
|
1857 |
+
"special": true
|
1858 |
+
},
|
1859 |
+
"128232": {
|
1860 |
+
"content": "<|reserved_special_token_224|>",
|
1861 |
+
"lstrip": false,
|
1862 |
+
"normalized": false,
|
1863 |
+
"rstrip": false,
|
1864 |
+
"single_word": false,
|
1865 |
+
"special": true
|
1866 |
+
},
|
1867 |
+
"128233": {
|
1868 |
+
"content": "<|reserved_special_token_225|>",
|
1869 |
+
"lstrip": false,
|
1870 |
+
"normalized": false,
|
1871 |
+
"rstrip": false,
|
1872 |
+
"single_word": false,
|
1873 |
+
"special": true
|
1874 |
+
},
|
1875 |
+
"128234": {
|
1876 |
+
"content": "<|reserved_special_token_226|>",
|
1877 |
+
"lstrip": false,
|
1878 |
+
"normalized": false,
|
1879 |
+
"rstrip": false,
|
1880 |
+
"single_word": false,
|
1881 |
+
"special": true
|
1882 |
+
},
|
1883 |
+
"128235": {
|
1884 |
+
"content": "<|reserved_special_token_227|>",
|
1885 |
+
"lstrip": false,
|
1886 |
+
"normalized": false,
|
1887 |
+
"rstrip": false,
|
1888 |
+
"single_word": false,
|
1889 |
+
"special": true
|
1890 |
+
},
|
1891 |
+
"128236": {
|
1892 |
+
"content": "<|reserved_special_token_228|>",
|
1893 |
+
"lstrip": false,
|
1894 |
+
"normalized": false,
|
1895 |
+
"rstrip": false,
|
1896 |
+
"single_word": false,
|
1897 |
+
"special": true
|
1898 |
+
},
|
1899 |
+
"128237": {
|
1900 |
+
"content": "<|reserved_special_token_229|>",
|
1901 |
+
"lstrip": false,
|
1902 |
+
"normalized": false,
|
1903 |
+
"rstrip": false,
|
1904 |
+
"single_word": false,
|
1905 |
+
"special": true
|
1906 |
+
},
|
1907 |
+
"128238": {
|
1908 |
+
"content": "<|reserved_special_token_230|>",
|
1909 |
+
"lstrip": false,
|
1910 |
+
"normalized": false,
|
1911 |
+
"rstrip": false,
|
1912 |
+
"single_word": false,
|
1913 |
+
"special": true
|
1914 |
+
},
|
1915 |
+
"128239": {
|
1916 |
+
"content": "<|reserved_special_token_231|>",
|
1917 |
+
"lstrip": false,
|
1918 |
+
"normalized": false,
|
1919 |
+
"rstrip": false,
|
1920 |
+
"single_word": false,
|
1921 |
+
"special": true
|
1922 |
+
},
|
1923 |
+
"128240": {
|
1924 |
+
"content": "<|reserved_special_token_232|>",
|
1925 |
+
"lstrip": false,
|
1926 |
+
"normalized": false,
|
1927 |
+
"rstrip": false,
|
1928 |
+
"single_word": false,
|
1929 |
+
"special": true
|
1930 |
+
},
|
1931 |
+
"128241": {
|
1932 |
+
"content": "<|reserved_special_token_233|>",
|
1933 |
+
"lstrip": false,
|
1934 |
+
"normalized": false,
|
1935 |
+
"rstrip": false,
|
1936 |
+
"single_word": false,
|
1937 |
+
"special": true
|
1938 |
+
},
|
1939 |
+
"128242": {
|
1940 |
+
"content": "<|reserved_special_token_234|>",
|
1941 |
+
"lstrip": false,
|
1942 |
+
"normalized": false,
|
1943 |
+
"rstrip": false,
|
1944 |
+
"single_word": false,
|
1945 |
+
"special": true
|
1946 |
+
},
|
1947 |
+
"128243": {
|
1948 |
+
"content": "<|reserved_special_token_235|>",
|
1949 |
+
"lstrip": false,
|
1950 |
+
"normalized": false,
|
1951 |
+
"rstrip": false,
|
1952 |
+
"single_word": false,
|
1953 |
+
"special": true
|
1954 |
+
},
|
1955 |
+
"128244": {
|
1956 |
+
"content": "<|reserved_special_token_236|>",
|
1957 |
+
"lstrip": false,
|
1958 |
+
"normalized": false,
|
1959 |
+
"rstrip": false,
|
1960 |
+
"single_word": false,
|
1961 |
+
"special": true
|
1962 |
+
},
|
1963 |
+
"128245": {
|
1964 |
+
"content": "<|reserved_special_token_237|>",
|
1965 |
+
"lstrip": false,
|
1966 |
+
"normalized": false,
|
1967 |
+
"rstrip": false,
|
1968 |
+
"single_word": false,
|
1969 |
+
"special": true
|
1970 |
+
},
|
1971 |
+
"128246": {
|
1972 |
+
"content": "<|reserved_special_token_238|>",
|
1973 |
+
"lstrip": false,
|
1974 |
+
"normalized": false,
|
1975 |
+
"rstrip": false,
|
1976 |
+
"single_word": false,
|
1977 |
+
"special": true
|
1978 |
+
},
|
1979 |
+
"128247": {
|
1980 |
+
"content": "<|reserved_special_token_239|>",
|
1981 |
+
"lstrip": false,
|
1982 |
+
"normalized": false,
|
1983 |
+
"rstrip": false,
|
1984 |
+
"single_word": false,
|
1985 |
+
"special": true
|
1986 |
+
},
|
1987 |
+
"128248": {
|
1988 |
+
"content": "<|reserved_special_token_240|>",
|
1989 |
+
"lstrip": false,
|
1990 |
+
"normalized": false,
|
1991 |
+
"rstrip": false,
|
1992 |
+
"single_word": false,
|
1993 |
+
"special": true
|
1994 |
+
},
|
1995 |
+
"128249": {
|
1996 |
+
"content": "<|reserved_special_token_241|>",
|
1997 |
+
"lstrip": false,
|
1998 |
+
"normalized": false,
|
1999 |
+
"rstrip": false,
|
2000 |
+
"single_word": false,
|
2001 |
+
"special": true
|
2002 |
+
},
|
2003 |
+
"128250": {
|
2004 |
+
"content": "<|reserved_special_token_242|>",
|
2005 |
+
"lstrip": false,
|
2006 |
+
"normalized": false,
|
2007 |
+
"rstrip": false,
|
2008 |
+
"single_word": false,
|
2009 |
+
"special": true
|
2010 |
+
},
|
2011 |
+
"128251": {
|
2012 |
+
"content": "<|reserved_special_token_243|>",
|
2013 |
+
"lstrip": false,
|
2014 |
+
"normalized": false,
|
2015 |
+
"rstrip": false,
|
2016 |
+
"single_word": false,
|
2017 |
+
"special": true
|
2018 |
+
},
|
2019 |
+
"128252": {
|
2020 |
+
"content": "<|reserved_special_token_244|>",
|
2021 |
+
"lstrip": false,
|
2022 |
+
"normalized": false,
|
2023 |
+
"rstrip": false,
|
2024 |
+
"single_word": false,
|
2025 |
+
"special": true
|
2026 |
+
},
|
2027 |
+
"128253": {
|
2028 |
+
"content": "<|reserved_special_token_245|>",
|
2029 |
+
"lstrip": false,
|
2030 |
+
"normalized": false,
|
2031 |
+
"rstrip": false,
|
2032 |
+
"single_word": false,
|
2033 |
+
"special": true
|
2034 |
+
},
|
2035 |
+
"128254": {
|
2036 |
+
"content": "<|reserved_special_token_246|>",
|
2037 |
+
"lstrip": false,
|
2038 |
+
"normalized": false,
|
2039 |
+
"rstrip": false,
|
2040 |
+
"single_word": false,
|
2041 |
+
"special": true
|
2042 |
+
},
|
2043 |
+
"128255": {
|
2044 |
+
"content": "<|reserved_special_token_247|>",
|
2045 |
+
"lstrip": false,
|
2046 |
+
"normalized": false,
|
2047 |
+
"rstrip": false,
|
2048 |
+
"single_word": false,
|
2049 |
+
"special": true
|
2050 |
+
}
|
2051 |
+
},
|
2052 |
+
"bos_token": "<|begin_of_text|>",
|
2053 |
+
"chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- if strftime_now is defined %}\n {%- set date_string = strftime_now(\"%d %b %Y\") %}\n {%- else %}\n {%- set date_string = \"26 Jul 2024\" %}\n {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {{- \"<|eot_id|>\" }}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
|
2054 |
+
"clean_up_tokenization_spaces": true,
|
2055 |
+
"eos_token": "<|eot_id|>",
|
2056 |
+
"model_input_names": [
|
2057 |
+
"input_ids",
|
2058 |
+
"attention_mask"
|
2059 |
+
],
|
2060 |
+
"model_max_length": 131072,
|
2061 |
+
"pad_token": "<|eot_id|>",
|
2062 |
+
"padding_side": "right",
|
2063 |
+
"split_special_tokens": false,
|
2064 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
2065 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 4.97907949790795,
|
3 |
+
"total_flos": 1.199536935920124e+18,
|
4 |
+
"train_loss": 0.012196063881880846,
|
5 |
+
"train_runtime": 9595.7495,
|
6 |
+
"train_samples_per_second": 1.991,
|
7 |
+
"train_steps_per_second": 0.062
|
8 |
+
}
|
trainer_log.jsonl
ADDED
The diff for this file is too large to render.
See raw diff
|
|
trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e665038fe922eed5452cc8aa2677ba331714cf00575ebbdd2bb83108b97f4bd3
|
3 |
+
size 5496
|
training_eval_loss.png
ADDED
![]() |
training_loss.png
ADDED
![]() |