Training in progress, step 400, checkpoint
Browse files- checkpoint-400/README.md +202 -0
- checkpoint-400/adapter_config.json +34 -0
- checkpoint-400/adapter_model.safetensors +3 -0
- checkpoint-400/optimizer.pt +3 -0
- checkpoint-400/rng_state.pth +3 -0
- checkpoint-400/scheduler.pt +3 -0
- checkpoint-400/special_tokens_map.json +23 -0
- checkpoint-400/tokenizer.json +3 -0
- checkpoint-400/tokenizer_config.json +2063 -0
- checkpoint-400/trainer_state.json +2961 -0
- checkpoint-400/training_args.bin +3 -0
checkpoint-400/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: unsloth/meta-llama-3.1-8b-bnb-4bit
|
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 0.13.2
|
checkpoint-400/adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "unsloth/meta-llama-3.1-8b-bnb-4bit",
|
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": 64,
|
14 |
+
"lora_dropout": 0,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 64,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"up_proj",
|
24 |
+
"down_proj",
|
25 |
+
"o_proj",
|
26 |
+
"gate_proj",
|
27 |
+
"k_proj",
|
28 |
+
"q_proj",
|
29 |
+
"v_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": true
|
34 |
+
}
|
checkpoint-400/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d0f49fc70e352edeef3e4b9ba438fbe5cf15c63dd5c93f9394fd04aacf8f1422
|
3 |
+
size 671149168
|
checkpoint-400/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:17b18e8d7ba59db39d77b21df740db352a66ecf6ecba105de01de0bc95d0900e
|
3 |
+
size 342480402
|
checkpoint-400/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bbd2538a5e54612197f39eb0afba0fd2ab8e287430c142a53bf88973ca778f06
|
3 |
+
size 14244
|
checkpoint-400/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c86883d1e90c754248621aa39dc6a8e5584ab14310a9e3d85e99b7b28842cbb1
|
3 |
+
size 1064
|
checkpoint-400/special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "<|end_of_text|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|finetune_right_pad_id|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
checkpoint-400/tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
|
3 |
+
size 17209920
|
checkpoint-400/tokenizer_config.json
ADDED
@@ -0,0 +1,2063 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"clean_up_tokenization_spaces": true,
|
2054 |
+
"eos_token": "<|end_of_text|>",
|
2055 |
+
"model_input_names": [
|
2056 |
+
"input_ids",
|
2057 |
+
"attention_mask"
|
2058 |
+
],
|
2059 |
+
"model_max_length": 131072,
|
2060 |
+
"pad_token": "<|finetune_right_pad_id|>",
|
2061 |
+
"padding_side": "right",
|
2062 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
2063 |
+
}
|
checkpoint-400/trainer_state.json
ADDED
@@ -0,0 +1,2961 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.7404398322105408,
|
3 |
+
"best_model_checkpoint": "outputs/checkpoint-400",
|
4 |
+
"epoch": 0.25023459493274947,
|
5 |
+
"eval_steps": 25,
|
6 |
+
"global_step": 400,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0006255864873318737,
|
13 |
+
"grad_norm": 3.302262783050537,
|
14 |
+
"learning_rate": 4e-05,
|
15 |
+
"loss": 1.7639,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.0012511729746637473,
|
20 |
+
"grad_norm": 3.7728819847106934,
|
21 |
+
"learning_rate": 8e-05,
|
22 |
+
"loss": 2.3471,
|
23 |
+
"step": 2
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.001876759461995621,
|
27 |
+
"grad_norm": 3.575211763381958,
|
28 |
+
"learning_rate": 0.00012,
|
29 |
+
"loss": 1.274,
|
30 |
+
"step": 3
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.0025023459493274947,
|
34 |
+
"grad_norm": 4.3921918869018555,
|
35 |
+
"learning_rate": 0.00016,
|
36 |
+
"loss": 1.8361,
|
37 |
+
"step": 4
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.0031279324366593683,
|
41 |
+
"grad_norm": 3.215696096420288,
|
42 |
+
"learning_rate": 0.0002,
|
43 |
+
"loss": 2.8766,
|
44 |
+
"step": 5
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.003753518923991242,
|
48 |
+
"grad_norm": 4.060017108917236,
|
49 |
+
"learning_rate": 0.0001996638655462185,
|
50 |
+
"loss": 1.4329,
|
51 |
+
"step": 6
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.004379105411323116,
|
55 |
+
"grad_norm": 2.7935523986816406,
|
56 |
+
"learning_rate": 0.00019932773109243698,
|
57 |
+
"loss": 1.2844,
|
58 |
+
"step": 7
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.005004691898654989,
|
62 |
+
"grad_norm": 2.312218189239502,
|
63 |
+
"learning_rate": 0.00019899159663865548,
|
64 |
+
"loss": 1.8112,
|
65 |
+
"step": 8
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.005630278385986863,
|
69 |
+
"grad_norm": 3.5389914512634277,
|
70 |
+
"learning_rate": 0.00019865546218487395,
|
71 |
+
"loss": 2.0504,
|
72 |
+
"step": 9
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.006255864873318737,
|
76 |
+
"grad_norm": 2.913029432296753,
|
77 |
+
"learning_rate": 0.00019831932773109245,
|
78 |
+
"loss": 1.9101,
|
79 |
+
"step": 10
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.00688145136065061,
|
83 |
+
"grad_norm": 3.6916606426239014,
|
84 |
+
"learning_rate": 0.00019798319327731095,
|
85 |
+
"loss": 1.9899,
|
86 |
+
"step": 11
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.007507037847982484,
|
90 |
+
"grad_norm": 3.002810478210449,
|
91 |
+
"learning_rate": 0.00019764705882352942,
|
92 |
+
"loss": 1.3224,
|
93 |
+
"step": 12
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.008132624335314358,
|
97 |
+
"grad_norm": 1.657835602760315,
|
98 |
+
"learning_rate": 0.00019731092436974792,
|
99 |
+
"loss": 1.2208,
|
100 |
+
"step": 13
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.008758210822646231,
|
104 |
+
"grad_norm": 2.414161443710327,
|
105 |
+
"learning_rate": 0.00019697478991596642,
|
106 |
+
"loss": 1.5375,
|
107 |
+
"step": 14
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.009383797309978105,
|
111 |
+
"grad_norm": 1.9695100784301758,
|
112 |
+
"learning_rate": 0.00019663865546218486,
|
113 |
+
"loss": 0.9218,
|
114 |
+
"step": 15
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.010009383797309979,
|
118 |
+
"grad_norm": 3.9755845069885254,
|
119 |
+
"learning_rate": 0.00019630252100840336,
|
120 |
+
"loss": 1.3608,
|
121 |
+
"step": 16
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.010634970284641852,
|
125 |
+
"grad_norm": 6.843455791473389,
|
126 |
+
"learning_rate": 0.00019596638655462186,
|
127 |
+
"loss": 1.2168,
|
128 |
+
"step": 17
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.011260556771973726,
|
132 |
+
"grad_norm": 3.8736443519592285,
|
133 |
+
"learning_rate": 0.00019563025210084033,
|
134 |
+
"loss": 0.7392,
|
135 |
+
"step": 18
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.0118861432593056,
|
139 |
+
"grad_norm": 1.7369539737701416,
|
140 |
+
"learning_rate": 0.00019529411764705883,
|
141 |
+
"loss": 1.0495,
|
142 |
+
"step": 19
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.012511729746637473,
|
146 |
+
"grad_norm": 1.1708225011825562,
|
147 |
+
"learning_rate": 0.0001949579831932773,
|
148 |
+
"loss": 1.2266,
|
149 |
+
"step": 20
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.013137316233969347,
|
153 |
+
"grad_norm": 1.4693603515625,
|
154 |
+
"learning_rate": 0.0001946218487394958,
|
155 |
+
"loss": 1.1364,
|
156 |
+
"step": 21
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.01376290272130122,
|
160 |
+
"grad_norm": 0.8484959602355957,
|
161 |
+
"learning_rate": 0.0001942857142857143,
|
162 |
+
"loss": 0.6253,
|
163 |
+
"step": 22
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.014388489208633094,
|
167 |
+
"grad_norm": 2.7237887382507324,
|
168 |
+
"learning_rate": 0.00019394957983193278,
|
169 |
+
"loss": 1.2932,
|
170 |
+
"step": 23
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.015014075695964968,
|
174 |
+
"grad_norm": 1.1654947996139526,
|
175 |
+
"learning_rate": 0.00019361344537815127,
|
176 |
+
"loss": 0.5659,
|
177 |
+
"step": 24
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.01563966218329684,
|
181 |
+
"grad_norm": 1.7193485498428345,
|
182 |
+
"learning_rate": 0.00019327731092436975,
|
183 |
+
"loss": 1.3627,
|
184 |
+
"step": 25
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.01563966218329684,
|
188 |
+
"eval_loss": 1.0974555015563965,
|
189 |
+
"eval_runtime": 46.8133,
|
190 |
+
"eval_samples_per_second": 5.469,
|
191 |
+
"eval_steps_per_second": 2.734,
|
192 |
+
"step": 25
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"epoch": 0.016265248670628715,
|
196 |
+
"grad_norm": 2.883988380432129,
|
197 |
+
"learning_rate": 0.00019294117647058825,
|
198 |
+
"loss": 0.6257,
|
199 |
+
"step": 26
|
200 |
+
},
|
201 |
+
{
|
202 |
+
"epoch": 0.01689083515796059,
|
203 |
+
"grad_norm": 1.4707483053207397,
|
204 |
+
"learning_rate": 0.00019260504201680674,
|
205 |
+
"loss": 0.879,
|
206 |
+
"step": 27
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 0.017516421645292463,
|
210 |
+
"grad_norm": 1.3346422910690308,
|
211 |
+
"learning_rate": 0.00019226890756302522,
|
212 |
+
"loss": 1.0058,
|
213 |
+
"step": 28
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.018142008132624336,
|
217 |
+
"grad_norm": 0.5815519094467163,
|
218 |
+
"learning_rate": 0.00019193277310924372,
|
219 |
+
"loss": 0.3475,
|
220 |
+
"step": 29
|
221 |
+
},
|
222 |
+
{
|
223 |
+
"epoch": 0.01876759461995621,
|
224 |
+
"grad_norm": 0.8800593018531799,
|
225 |
+
"learning_rate": 0.00019159663865546221,
|
226 |
+
"loss": 0.5426,
|
227 |
+
"step": 30
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 0.019393181107288084,
|
231 |
+
"grad_norm": 8.196944236755371,
|
232 |
+
"learning_rate": 0.0001912605042016807,
|
233 |
+
"loss": 1.0088,
|
234 |
+
"step": 31
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 0.020018767594619957,
|
238 |
+
"grad_norm": 3.264193296432495,
|
239 |
+
"learning_rate": 0.00019092436974789919,
|
240 |
+
"loss": 0.9319,
|
241 |
+
"step": 32
|
242 |
+
},
|
243 |
+
{
|
244 |
+
"epoch": 0.02064435408195183,
|
245 |
+
"grad_norm": 1.1047834157943726,
|
246 |
+
"learning_rate": 0.00019058823529411766,
|
247 |
+
"loss": 0.9262,
|
248 |
+
"step": 33
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 0.021269940569283705,
|
252 |
+
"grad_norm": 1.982783555984497,
|
253 |
+
"learning_rate": 0.00019025210084033613,
|
254 |
+
"loss": 1.2904,
|
255 |
+
"step": 34
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 0.021895527056615578,
|
259 |
+
"grad_norm": 2.6765289306640625,
|
260 |
+
"learning_rate": 0.00018991596638655463,
|
261 |
+
"loss": 1.0785,
|
262 |
+
"step": 35
|
263 |
+
},
|
264 |
+
{
|
265 |
+
"epoch": 0.022521113543947452,
|
266 |
+
"grad_norm": 4.674818992614746,
|
267 |
+
"learning_rate": 0.0001895798319327731,
|
268 |
+
"loss": 0.9822,
|
269 |
+
"step": 36
|
270 |
+
},
|
271 |
+
{
|
272 |
+
"epoch": 0.023146700031279326,
|
273 |
+
"grad_norm": 1.6232353448867798,
|
274 |
+
"learning_rate": 0.0001892436974789916,
|
275 |
+
"loss": 0.6441,
|
276 |
+
"step": 37
|
277 |
+
},
|
278 |
+
{
|
279 |
+
"epoch": 0.0237722865186112,
|
280 |
+
"grad_norm": 2.623237371444702,
|
281 |
+
"learning_rate": 0.0001889075630252101,
|
282 |
+
"loss": 0.8874,
|
283 |
+
"step": 38
|
284 |
+
},
|
285 |
+
{
|
286 |
+
"epoch": 0.024397873005943073,
|
287 |
+
"grad_norm": 1.4366761445999146,
|
288 |
+
"learning_rate": 0.00018857142857142857,
|
289 |
+
"loss": 0.4596,
|
290 |
+
"step": 39
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 0.025023459493274947,
|
294 |
+
"grad_norm": 1.8809682130813599,
|
295 |
+
"learning_rate": 0.00018823529411764707,
|
296 |
+
"loss": 0.887,
|
297 |
+
"step": 40
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 0.02564904598060682,
|
301 |
+
"grad_norm": 1.081438660621643,
|
302 |
+
"learning_rate": 0.00018789915966386554,
|
303 |
+
"loss": 0.4735,
|
304 |
+
"step": 41
|
305 |
+
},
|
306 |
+
{
|
307 |
+
"epoch": 0.026274632467938694,
|
308 |
+
"grad_norm": 2.1302649974823,
|
309 |
+
"learning_rate": 0.00018756302521008404,
|
310 |
+
"loss": 0.795,
|
311 |
+
"step": 42
|
312 |
+
},
|
313 |
+
{
|
314 |
+
"epoch": 0.026900218955270568,
|
315 |
+
"grad_norm": 2.005425453186035,
|
316 |
+
"learning_rate": 0.00018722689075630254,
|
317 |
+
"loss": 0.8891,
|
318 |
+
"step": 43
|
319 |
+
},
|
320 |
+
{
|
321 |
+
"epoch": 0.02752580544260244,
|
322 |
+
"grad_norm": 1.7256505489349365,
|
323 |
+
"learning_rate": 0.000186890756302521,
|
324 |
+
"loss": 0.5993,
|
325 |
+
"step": 44
|
326 |
+
},
|
327 |
+
{
|
328 |
+
"epoch": 0.028151391929934315,
|
329 |
+
"grad_norm": 0.927653968334198,
|
330 |
+
"learning_rate": 0.0001865546218487395,
|
331 |
+
"loss": 0.6185,
|
332 |
+
"step": 45
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 0.02877697841726619,
|
336 |
+
"grad_norm": 1.5710850954055786,
|
337 |
+
"learning_rate": 0.000186218487394958,
|
338 |
+
"loss": 0.5258,
|
339 |
+
"step": 46
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.029402564904598062,
|
343 |
+
"grad_norm": 1.8794296979904175,
|
344 |
+
"learning_rate": 0.00018588235294117648,
|
345 |
+
"loss": 0.8168,
|
346 |
+
"step": 47
|
347 |
+
},
|
348 |
+
{
|
349 |
+
"epoch": 0.030028151391929936,
|
350 |
+
"grad_norm": 0.9695333242416382,
|
351 |
+
"learning_rate": 0.00018554621848739498,
|
352 |
+
"loss": 0.5458,
|
353 |
+
"step": 48
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 0.03065373787926181,
|
357 |
+
"grad_norm": 3.7846665382385254,
|
358 |
+
"learning_rate": 0.00018521008403361345,
|
359 |
+
"loss": 0.943,
|
360 |
+
"step": 49
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 0.03127932436659368,
|
364 |
+
"grad_norm": 1.9213052988052368,
|
365 |
+
"learning_rate": 0.00018487394957983195,
|
366 |
+
"loss": 0.5069,
|
367 |
+
"step": 50
|
368 |
+
},
|
369 |
+
{
|
370 |
+
"epoch": 0.03127932436659368,
|
371 |
+
"eval_loss": 0.9765783548355103,
|
372 |
+
"eval_runtime": 43.502,
|
373 |
+
"eval_samples_per_second": 5.885,
|
374 |
+
"eval_steps_per_second": 2.942,
|
375 |
+
"step": 50
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 0.03190491085392556,
|
379 |
+
"grad_norm": 2.0580382347106934,
|
380 |
+
"learning_rate": 0.00018453781512605045,
|
381 |
+
"loss": 0.9423,
|
382 |
+
"step": 51
|
383 |
+
},
|
384 |
+
{
|
385 |
+
"epoch": 0.03253049734125743,
|
386 |
+
"grad_norm": 2.063591957092285,
|
387 |
+
"learning_rate": 0.0001842016806722689,
|
388 |
+
"loss": 0.7054,
|
389 |
+
"step": 52
|
390 |
+
},
|
391 |
+
{
|
392 |
+
"epoch": 0.033156083828589304,
|
393 |
+
"grad_norm": 1.2656595706939697,
|
394 |
+
"learning_rate": 0.0001838655462184874,
|
395 |
+
"loss": 0.401,
|
396 |
+
"step": 53
|
397 |
+
},
|
398 |
+
{
|
399 |
+
"epoch": 0.03378167031592118,
|
400 |
+
"grad_norm": 1.2392399311065674,
|
401 |
+
"learning_rate": 0.0001835294117647059,
|
402 |
+
"loss": 0.6077,
|
403 |
+
"step": 54
|
404 |
+
},
|
405 |
+
{
|
406 |
+
"epoch": 0.03440725680325305,
|
407 |
+
"grad_norm": 0.99504154920578,
|
408 |
+
"learning_rate": 0.00018319327731092437,
|
409 |
+
"loss": 0.6313,
|
410 |
+
"step": 55
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 0.035032843290584925,
|
414 |
+
"grad_norm": 2.0478012561798096,
|
415 |
+
"learning_rate": 0.00018285714285714286,
|
416 |
+
"loss": 1.2652,
|
417 |
+
"step": 56
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 0.0356584297779168,
|
421 |
+
"grad_norm": 0.9636131525039673,
|
422 |
+
"learning_rate": 0.00018252100840336134,
|
423 |
+
"loss": 0.7561,
|
424 |
+
"step": 57
|
425 |
+
},
|
426 |
+
{
|
427 |
+
"epoch": 0.03628401626524867,
|
428 |
+
"grad_norm": 0.874576210975647,
|
429 |
+
"learning_rate": 0.00018218487394957984,
|
430 |
+
"loss": 0.7461,
|
431 |
+
"step": 58
|
432 |
+
},
|
433 |
+
{
|
434 |
+
"epoch": 0.036909602752580546,
|
435 |
+
"grad_norm": 1.3745896816253662,
|
436 |
+
"learning_rate": 0.00018184873949579833,
|
437 |
+
"loss": 1.2856,
|
438 |
+
"step": 59
|
439 |
+
},
|
440 |
+
{
|
441 |
+
"epoch": 0.03753518923991242,
|
442 |
+
"grad_norm": 2.4839162826538086,
|
443 |
+
"learning_rate": 0.0001815126050420168,
|
444 |
+
"loss": 1.0574,
|
445 |
+
"step": 60
|
446 |
+
},
|
447 |
+
{
|
448 |
+
"epoch": 0.038160775727244294,
|
449 |
+
"grad_norm": 1.2671383619308472,
|
450 |
+
"learning_rate": 0.0001811764705882353,
|
451 |
+
"loss": 0.6177,
|
452 |
+
"step": 61
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 0.03878636221457617,
|
456 |
+
"grad_norm": 1.1862553358078003,
|
457 |
+
"learning_rate": 0.0001808403361344538,
|
458 |
+
"loss": 1.1169,
|
459 |
+
"step": 62
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.03941194870190804,
|
463 |
+
"grad_norm": 1.1347297430038452,
|
464 |
+
"learning_rate": 0.00018050420168067228,
|
465 |
+
"loss": 1.3303,
|
466 |
+
"step": 63
|
467 |
+
},
|
468 |
+
{
|
469 |
+
"epoch": 0.040037535189239915,
|
470 |
+
"grad_norm": 2.1583523750305176,
|
471 |
+
"learning_rate": 0.00018016806722689078,
|
472 |
+
"loss": 0.7941,
|
473 |
+
"step": 64
|
474 |
+
},
|
475 |
+
{
|
476 |
+
"epoch": 0.04066312167657179,
|
477 |
+
"grad_norm": 1.2432655096054077,
|
478 |
+
"learning_rate": 0.00017983193277310925,
|
479 |
+
"loss": 0.7848,
|
480 |
+
"step": 65
|
481 |
+
},
|
482 |
+
{
|
483 |
+
"epoch": 0.04128870816390366,
|
484 |
+
"grad_norm": 1.3345468044281006,
|
485 |
+
"learning_rate": 0.00017949579831932775,
|
486 |
+
"loss": 0.8953,
|
487 |
+
"step": 66
|
488 |
+
},
|
489 |
+
{
|
490 |
+
"epoch": 0.041914294651235535,
|
491 |
+
"grad_norm": 0.6861767768859863,
|
492 |
+
"learning_rate": 0.00017915966386554625,
|
493 |
+
"loss": 0.4162,
|
494 |
+
"step": 67
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 0.04253988113856741,
|
498 |
+
"grad_norm": 0.85309898853302,
|
499 |
+
"learning_rate": 0.00017882352941176472,
|
500 |
+
"loss": 0.6606,
|
501 |
+
"step": 68
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 0.04316546762589928,
|
505 |
+
"grad_norm": 1.0247780084609985,
|
506 |
+
"learning_rate": 0.00017848739495798322,
|
507 |
+
"loss": 0.5271,
|
508 |
+
"step": 69
|
509 |
+
},
|
510 |
+
{
|
511 |
+
"epoch": 0.043791054113231156,
|
512 |
+
"grad_norm": 1.3019441366195679,
|
513 |
+
"learning_rate": 0.0001781512605042017,
|
514 |
+
"loss": 0.5605,
|
515 |
+
"step": 70
|
516 |
+
},
|
517 |
+
{
|
518 |
+
"epoch": 0.04441664060056303,
|
519 |
+
"grad_norm": 1.1024900674819946,
|
520 |
+
"learning_rate": 0.00017781512605042016,
|
521 |
+
"loss": 0.9303,
|
522 |
+
"step": 71
|
523 |
+
},
|
524 |
+
{
|
525 |
+
"epoch": 0.045042227087894904,
|
526 |
+
"grad_norm": 1.079655408859253,
|
527 |
+
"learning_rate": 0.00017747899159663866,
|
528 |
+
"loss": 1.0138,
|
529 |
+
"step": 72
|
530 |
+
},
|
531 |
+
{
|
532 |
+
"epoch": 0.04566781357522678,
|
533 |
+
"grad_norm": 1.1078468561172485,
|
534 |
+
"learning_rate": 0.00017714285714285713,
|
535 |
+
"loss": 0.9861,
|
536 |
+
"step": 73
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 0.04629340006255865,
|
540 |
+
"grad_norm": 1.8648931980133057,
|
541 |
+
"learning_rate": 0.00017680672268907563,
|
542 |
+
"loss": 0.6756,
|
543 |
+
"step": 74
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 0.046918986549890525,
|
547 |
+
"grad_norm": 0.8588104248046875,
|
548 |
+
"learning_rate": 0.00017647058823529413,
|
549 |
+
"loss": 0.4867,
|
550 |
+
"step": 75
|
551 |
+
},
|
552 |
+
{
|
553 |
+
"epoch": 0.046918986549890525,
|
554 |
+
"eval_loss": 0.9139823913574219,
|
555 |
+
"eval_runtime": 43.5635,
|
556 |
+
"eval_samples_per_second": 5.876,
|
557 |
+
"eval_steps_per_second": 2.938,
|
558 |
+
"step": 75
|
559 |
+
},
|
560 |
+
{
|
561 |
+
"epoch": 0.0475445730372224,
|
562 |
+
"grad_norm": 1.6970480680465698,
|
563 |
+
"learning_rate": 0.0001761344537815126,
|
564 |
+
"loss": 0.5523,
|
565 |
+
"step": 76
|
566 |
+
},
|
567 |
+
{
|
568 |
+
"epoch": 0.04817015952455427,
|
569 |
+
"grad_norm": 0.8562026023864746,
|
570 |
+
"learning_rate": 0.0001757983193277311,
|
571 |
+
"loss": 0.4084,
|
572 |
+
"step": 77
|
573 |
+
},
|
574 |
+
{
|
575 |
+
"epoch": 0.048795746011886146,
|
576 |
+
"grad_norm": 0.9487925171852112,
|
577 |
+
"learning_rate": 0.0001754621848739496,
|
578 |
+
"loss": 0.6204,
|
579 |
+
"step": 78
|
580 |
+
},
|
581 |
+
{
|
582 |
+
"epoch": 0.04942133249921802,
|
583 |
+
"grad_norm": 11.929024696350098,
|
584 |
+
"learning_rate": 0.00017512605042016807,
|
585 |
+
"loss": 1.1662,
|
586 |
+
"step": 79
|
587 |
+
},
|
588 |
+
{
|
589 |
+
"epoch": 0.05004691898654989,
|
590 |
+
"grad_norm": 1.3468140363693237,
|
591 |
+
"learning_rate": 0.00017478991596638657,
|
592 |
+
"loss": 0.8037,
|
593 |
+
"step": 80
|
594 |
+
},
|
595 |
+
{
|
596 |
+
"epoch": 0.05067250547388177,
|
597 |
+
"grad_norm": 0.7379503846168518,
|
598 |
+
"learning_rate": 0.00017445378151260504,
|
599 |
+
"loss": 0.6564,
|
600 |
+
"step": 81
|
601 |
+
},
|
602 |
+
{
|
603 |
+
"epoch": 0.05129809196121364,
|
604 |
+
"grad_norm": 1.0315027236938477,
|
605 |
+
"learning_rate": 0.00017411764705882354,
|
606 |
+
"loss": 0.6377,
|
607 |
+
"step": 82
|
608 |
+
},
|
609 |
+
{
|
610 |
+
"epoch": 0.051923678448545514,
|
611 |
+
"grad_norm": 0.5900093913078308,
|
612 |
+
"learning_rate": 0.00017378151260504204,
|
613 |
+
"loss": 0.5122,
|
614 |
+
"step": 83
|
615 |
+
},
|
616 |
+
{
|
617 |
+
"epoch": 0.05254926493587739,
|
618 |
+
"grad_norm": 1.5138239860534668,
|
619 |
+
"learning_rate": 0.0001734453781512605,
|
620 |
+
"loss": 0.4769,
|
621 |
+
"step": 84
|
622 |
+
},
|
623 |
+
{
|
624 |
+
"epoch": 0.05317485142320926,
|
625 |
+
"grad_norm": 1.016790747642517,
|
626 |
+
"learning_rate": 0.000173109243697479,
|
627 |
+
"loss": 0.6654,
|
628 |
+
"step": 85
|
629 |
+
},
|
630 |
+
{
|
631 |
+
"epoch": 0.053800437910541135,
|
632 |
+
"grad_norm": 1.1964718103408813,
|
633 |
+
"learning_rate": 0.00017277310924369748,
|
634 |
+
"loss": 0.6334,
|
635 |
+
"step": 86
|
636 |
+
},
|
637 |
+
{
|
638 |
+
"epoch": 0.05442602439787301,
|
639 |
+
"grad_norm": 1.102842092514038,
|
640 |
+
"learning_rate": 0.00017243697478991598,
|
641 |
+
"loss": 0.832,
|
642 |
+
"step": 87
|
643 |
+
},
|
644 |
+
{
|
645 |
+
"epoch": 0.05505161088520488,
|
646 |
+
"grad_norm": 6.609305381774902,
|
647 |
+
"learning_rate": 0.00017210084033613448,
|
648 |
+
"loss": 0.6112,
|
649 |
+
"step": 88
|
650 |
+
},
|
651 |
+
{
|
652 |
+
"epoch": 0.055677197372536756,
|
653 |
+
"grad_norm": 2.6627745628356934,
|
654 |
+
"learning_rate": 0.00017176470588235293,
|
655 |
+
"loss": 1.032,
|
656 |
+
"step": 89
|
657 |
+
},
|
658 |
+
{
|
659 |
+
"epoch": 0.05630278385986863,
|
660 |
+
"grad_norm": 2.114955425262451,
|
661 |
+
"learning_rate": 0.00017142857142857143,
|
662 |
+
"loss": 0.6116,
|
663 |
+
"step": 90
|
664 |
+
},
|
665 |
+
{
|
666 |
+
"epoch": 0.0569283703472005,
|
667 |
+
"grad_norm": 1.7707552909851074,
|
668 |
+
"learning_rate": 0.00017109243697478992,
|
669 |
+
"loss": 0.4766,
|
670 |
+
"step": 91
|
671 |
+
},
|
672 |
+
{
|
673 |
+
"epoch": 0.05755395683453238,
|
674 |
+
"grad_norm": 0.9983264803886414,
|
675 |
+
"learning_rate": 0.0001707563025210084,
|
676 |
+
"loss": 0.5397,
|
677 |
+
"step": 92
|
678 |
+
},
|
679 |
+
{
|
680 |
+
"epoch": 0.05817954332186425,
|
681 |
+
"grad_norm": 8.190524101257324,
|
682 |
+
"learning_rate": 0.0001704201680672269,
|
683 |
+
"loss": 0.9531,
|
684 |
+
"step": 93
|
685 |
+
},
|
686 |
+
{
|
687 |
+
"epoch": 0.058805129809196124,
|
688 |
+
"grad_norm": 1.9920661449432373,
|
689 |
+
"learning_rate": 0.0001700840336134454,
|
690 |
+
"loss": 1.3801,
|
691 |
+
"step": 94
|
692 |
+
},
|
693 |
+
{
|
694 |
+
"epoch": 0.059430716296528,
|
695 |
+
"grad_norm": 0.8791856169700623,
|
696 |
+
"learning_rate": 0.00016974789915966387,
|
697 |
+
"loss": 0.6218,
|
698 |
+
"step": 95
|
699 |
+
},
|
700 |
+
{
|
701 |
+
"epoch": 0.06005630278385987,
|
702 |
+
"grad_norm": 1.0745537281036377,
|
703 |
+
"learning_rate": 0.00016941176470588237,
|
704 |
+
"loss": 0.5578,
|
705 |
+
"step": 96
|
706 |
+
},
|
707 |
+
{
|
708 |
+
"epoch": 0.060681889271191745,
|
709 |
+
"grad_norm": 1.4266705513000488,
|
710 |
+
"learning_rate": 0.00016907563025210084,
|
711 |
+
"loss": 1.5821,
|
712 |
+
"step": 97
|
713 |
+
},
|
714 |
+
{
|
715 |
+
"epoch": 0.06130747575852362,
|
716 |
+
"grad_norm": 1.1001832485198975,
|
717 |
+
"learning_rate": 0.00016873949579831934,
|
718 |
+
"loss": 0.5972,
|
719 |
+
"step": 98
|
720 |
+
},
|
721 |
+
{
|
722 |
+
"epoch": 0.06193306224585549,
|
723 |
+
"grad_norm": 1.3168463706970215,
|
724 |
+
"learning_rate": 0.00016840336134453784,
|
725 |
+
"loss": 0.5794,
|
726 |
+
"step": 99
|
727 |
+
},
|
728 |
+
{
|
729 |
+
"epoch": 0.06255864873318737,
|
730 |
+
"grad_norm": 1.0342196226119995,
|
731 |
+
"learning_rate": 0.0001680672268907563,
|
732 |
+
"loss": 0.6827,
|
733 |
+
"step": 100
|
734 |
+
},
|
735 |
+
{
|
736 |
+
"epoch": 0.06255864873318737,
|
737 |
+
"eval_loss": 0.8885337114334106,
|
738 |
+
"eval_runtime": 43.4886,
|
739 |
+
"eval_samples_per_second": 5.887,
|
740 |
+
"eval_steps_per_second": 2.943,
|
741 |
+
"step": 100
|
742 |
+
},
|
743 |
+
{
|
744 |
+
"epoch": 0.06318423522051923,
|
745 |
+
"grad_norm": 2.2497031688690186,
|
746 |
+
"learning_rate": 0.0001677310924369748,
|
747 |
+
"loss": 0.6468,
|
748 |
+
"step": 101
|
749 |
+
},
|
750 |
+
{
|
751 |
+
"epoch": 0.06380982170785111,
|
752 |
+
"grad_norm": 0.8061516284942627,
|
753 |
+
"learning_rate": 0.00016739495798319328,
|
754 |
+
"loss": 0.5388,
|
755 |
+
"step": 102
|
756 |
+
},
|
757 |
+
{
|
758 |
+
"epoch": 0.06443540819518298,
|
759 |
+
"grad_norm": 0.6954531669616699,
|
760 |
+
"learning_rate": 0.00016705882352941178,
|
761 |
+
"loss": 0.3191,
|
762 |
+
"step": 103
|
763 |
+
},
|
764 |
+
{
|
765 |
+
"epoch": 0.06506099468251486,
|
766 |
+
"grad_norm": 1.3721911907196045,
|
767 |
+
"learning_rate": 0.00016672268907563028,
|
768 |
+
"loss": 0.9,
|
769 |
+
"step": 104
|
770 |
+
},
|
771 |
+
{
|
772 |
+
"epoch": 0.06568658116984673,
|
773 |
+
"grad_norm": 1.084492564201355,
|
774 |
+
"learning_rate": 0.00016638655462184875,
|
775 |
+
"loss": 0.6144,
|
776 |
+
"step": 105
|
777 |
+
},
|
778 |
+
{
|
779 |
+
"epoch": 0.06631216765717861,
|
780 |
+
"grad_norm": 3.317697525024414,
|
781 |
+
"learning_rate": 0.00016605042016806725,
|
782 |
+
"loss": 0.634,
|
783 |
+
"step": 106
|
784 |
+
},
|
785 |
+
{
|
786 |
+
"epoch": 0.06693775414451048,
|
787 |
+
"grad_norm": 2.5598530769348145,
|
788 |
+
"learning_rate": 0.00016571428571428575,
|
789 |
+
"loss": 0.8931,
|
790 |
+
"step": 107
|
791 |
+
},
|
792 |
+
{
|
793 |
+
"epoch": 0.06756334063184236,
|
794 |
+
"grad_norm": 3.6414177417755127,
|
795 |
+
"learning_rate": 0.0001653781512605042,
|
796 |
+
"loss": 0.7226,
|
797 |
+
"step": 108
|
798 |
+
},
|
799 |
+
{
|
800 |
+
"epoch": 0.06818892711917422,
|
801 |
+
"grad_norm": 2.2443768978118896,
|
802 |
+
"learning_rate": 0.0001650420168067227,
|
803 |
+
"loss": 0.8862,
|
804 |
+
"step": 109
|
805 |
+
},
|
806 |
+
{
|
807 |
+
"epoch": 0.0688145136065061,
|
808 |
+
"grad_norm": 0.6285691857337952,
|
809 |
+
"learning_rate": 0.0001647058823529412,
|
810 |
+
"loss": 0.3766,
|
811 |
+
"step": 110
|
812 |
+
},
|
813 |
+
{
|
814 |
+
"epoch": 0.06944010009383797,
|
815 |
+
"grad_norm": 0.6171959042549133,
|
816 |
+
"learning_rate": 0.00016436974789915966,
|
817 |
+
"loss": 0.2821,
|
818 |
+
"step": 111
|
819 |
+
},
|
820 |
+
{
|
821 |
+
"epoch": 0.07006568658116985,
|
822 |
+
"grad_norm": 1.0057804584503174,
|
823 |
+
"learning_rate": 0.00016403361344537816,
|
824 |
+
"loss": 0.6293,
|
825 |
+
"step": 112
|
826 |
+
},
|
827 |
+
{
|
828 |
+
"epoch": 0.07069127306850172,
|
829 |
+
"grad_norm": 1.3190034627914429,
|
830 |
+
"learning_rate": 0.00016369747899159663,
|
831 |
+
"loss": 0.5547,
|
832 |
+
"step": 113
|
833 |
+
},
|
834 |
+
{
|
835 |
+
"epoch": 0.0713168595558336,
|
836 |
+
"grad_norm": 0.518517017364502,
|
837 |
+
"learning_rate": 0.00016336134453781513,
|
838 |
+
"loss": 0.1951,
|
839 |
+
"step": 114
|
840 |
+
},
|
841 |
+
{
|
842 |
+
"epoch": 0.07194244604316546,
|
843 |
+
"grad_norm": 0.848175048828125,
|
844 |
+
"learning_rate": 0.00016302521008403363,
|
845 |
+
"loss": 0.5091,
|
846 |
+
"step": 115
|
847 |
+
},
|
848 |
+
{
|
849 |
+
"epoch": 0.07256803253049735,
|
850 |
+
"grad_norm": 0.7387409806251526,
|
851 |
+
"learning_rate": 0.0001626890756302521,
|
852 |
+
"loss": 0.3872,
|
853 |
+
"step": 116
|
854 |
+
},
|
855 |
+
{
|
856 |
+
"epoch": 0.07319361901782921,
|
857 |
+
"grad_norm": 2.828091859817505,
|
858 |
+
"learning_rate": 0.0001623529411764706,
|
859 |
+
"loss": 1.2046,
|
860 |
+
"step": 117
|
861 |
+
},
|
862 |
+
{
|
863 |
+
"epoch": 0.07381920550516109,
|
864 |
+
"grad_norm": 1.7653822898864746,
|
865 |
+
"learning_rate": 0.00016201680672268907,
|
866 |
+
"loss": 1.8133,
|
867 |
+
"step": 118
|
868 |
+
},
|
869 |
+
{
|
870 |
+
"epoch": 0.07444479199249296,
|
871 |
+
"grad_norm": 3.5097360610961914,
|
872 |
+
"learning_rate": 0.00016168067226890757,
|
873 |
+
"loss": 0.6837,
|
874 |
+
"step": 119
|
875 |
+
},
|
876 |
+
{
|
877 |
+
"epoch": 0.07507037847982484,
|
878 |
+
"grad_norm": 1.3884797096252441,
|
879 |
+
"learning_rate": 0.00016134453781512607,
|
880 |
+
"loss": 0.8846,
|
881 |
+
"step": 120
|
882 |
+
},
|
883 |
+
{
|
884 |
+
"epoch": 0.0756959649671567,
|
885 |
+
"grad_norm": 22.705190658569336,
|
886 |
+
"learning_rate": 0.00016100840336134454,
|
887 |
+
"loss": 0.7281,
|
888 |
+
"step": 121
|
889 |
+
},
|
890 |
+
{
|
891 |
+
"epoch": 0.07632155145448859,
|
892 |
+
"grad_norm": 3.1223599910736084,
|
893 |
+
"learning_rate": 0.00016067226890756304,
|
894 |
+
"loss": 0.6254,
|
895 |
+
"step": 122
|
896 |
+
},
|
897 |
+
{
|
898 |
+
"epoch": 0.07694713794182045,
|
899 |
+
"grad_norm": 0.530583381652832,
|
900 |
+
"learning_rate": 0.00016033613445378154,
|
901 |
+
"loss": 0.3292,
|
902 |
+
"step": 123
|
903 |
+
},
|
904 |
+
{
|
905 |
+
"epoch": 0.07757272442915233,
|
906 |
+
"grad_norm": 1.4720183610916138,
|
907 |
+
"learning_rate": 0.00016,
|
908 |
+
"loss": 0.8192,
|
909 |
+
"step": 124
|
910 |
+
},
|
911 |
+
{
|
912 |
+
"epoch": 0.0781983109164842,
|
913 |
+
"grad_norm": 0.6448870301246643,
|
914 |
+
"learning_rate": 0.0001596638655462185,
|
915 |
+
"loss": 0.2431,
|
916 |
+
"step": 125
|
917 |
+
},
|
918 |
+
{
|
919 |
+
"epoch": 0.0781983109164842,
|
920 |
+
"eval_loss": 0.890012800693512,
|
921 |
+
"eval_runtime": 43.5059,
|
922 |
+
"eval_samples_per_second": 5.884,
|
923 |
+
"eval_steps_per_second": 2.942,
|
924 |
+
"step": 125
|
925 |
+
},
|
926 |
+
{
|
927 |
+
"epoch": 0.07882389740381608,
|
928 |
+
"grad_norm": 1.803906798362732,
|
929 |
+
"learning_rate": 0.00015932773109243698,
|
930 |
+
"loss": 0.8937,
|
931 |
+
"step": 126
|
932 |
+
},
|
933 |
+
{
|
934 |
+
"epoch": 0.07944948389114795,
|
935 |
+
"grad_norm": 2.2447054386138916,
|
936 |
+
"learning_rate": 0.00015899159663865546,
|
937 |
+
"loss": 0.6993,
|
938 |
+
"step": 127
|
939 |
+
},
|
940 |
+
{
|
941 |
+
"epoch": 0.08007507037847983,
|
942 |
+
"grad_norm": 0.6667381525039673,
|
943 |
+
"learning_rate": 0.00015865546218487396,
|
944 |
+
"loss": 0.4266,
|
945 |
+
"step": 128
|
946 |
+
},
|
947 |
+
{
|
948 |
+
"epoch": 0.0807006568658117,
|
949 |
+
"grad_norm": 1.1449408531188965,
|
950 |
+
"learning_rate": 0.00015831932773109243,
|
951 |
+
"loss": 0.5557,
|
952 |
+
"step": 129
|
953 |
+
},
|
954 |
+
{
|
955 |
+
"epoch": 0.08132624335314358,
|
956 |
+
"grad_norm": 1.399849534034729,
|
957 |
+
"learning_rate": 0.00015798319327731093,
|
958 |
+
"loss": 0.6761,
|
959 |
+
"step": 130
|
960 |
+
},
|
961 |
+
{
|
962 |
+
"epoch": 0.08195182984047544,
|
963 |
+
"grad_norm": 0.745627760887146,
|
964 |
+
"learning_rate": 0.00015764705882352943,
|
965 |
+
"loss": 0.5323,
|
966 |
+
"step": 131
|
967 |
+
},
|
968 |
+
{
|
969 |
+
"epoch": 0.08257741632780732,
|
970 |
+
"grad_norm": 1.162428379058838,
|
971 |
+
"learning_rate": 0.0001573109243697479,
|
972 |
+
"loss": 0.8231,
|
973 |
+
"step": 132
|
974 |
+
},
|
975 |
+
{
|
976 |
+
"epoch": 0.08320300281513919,
|
977 |
+
"grad_norm": 1.0329734086990356,
|
978 |
+
"learning_rate": 0.0001569747899159664,
|
979 |
+
"loss": 0.6179,
|
980 |
+
"step": 133
|
981 |
+
},
|
982 |
+
{
|
983 |
+
"epoch": 0.08382858930247107,
|
984 |
+
"grad_norm": 0.5739912986755371,
|
985 |
+
"learning_rate": 0.00015663865546218487,
|
986 |
+
"loss": 0.2515,
|
987 |
+
"step": 134
|
988 |
+
},
|
989 |
+
{
|
990 |
+
"epoch": 0.08445417578980294,
|
991 |
+
"grad_norm": 1.2065409421920776,
|
992 |
+
"learning_rate": 0.00015630252100840337,
|
993 |
+
"loss": 0.6161,
|
994 |
+
"step": 135
|
995 |
+
},
|
996 |
+
{
|
997 |
+
"epoch": 0.08507976227713482,
|
998 |
+
"grad_norm": 1.1025582551956177,
|
999 |
+
"learning_rate": 0.00015596638655462187,
|
1000 |
+
"loss": 0.5926,
|
1001 |
+
"step": 136
|
1002 |
+
},
|
1003 |
+
{
|
1004 |
+
"epoch": 0.08570534876446669,
|
1005 |
+
"grad_norm": 0.78680020570755,
|
1006 |
+
"learning_rate": 0.00015563025210084034,
|
1007 |
+
"loss": 0.9987,
|
1008 |
+
"step": 137
|
1009 |
+
},
|
1010 |
+
{
|
1011 |
+
"epoch": 0.08633093525179857,
|
1012 |
+
"grad_norm": 0.6232782006263733,
|
1013 |
+
"learning_rate": 0.00015529411764705884,
|
1014 |
+
"loss": 0.4952,
|
1015 |
+
"step": 138
|
1016 |
+
},
|
1017 |
+
{
|
1018 |
+
"epoch": 0.08695652173913043,
|
1019 |
+
"grad_norm": 3.347989559173584,
|
1020 |
+
"learning_rate": 0.00015495798319327734,
|
1021 |
+
"loss": 1.0787,
|
1022 |
+
"step": 139
|
1023 |
+
},
|
1024 |
+
{
|
1025 |
+
"epoch": 0.08758210822646231,
|
1026 |
+
"grad_norm": 0.9020625352859497,
|
1027 |
+
"learning_rate": 0.0001546218487394958,
|
1028 |
+
"loss": 0.354,
|
1029 |
+
"step": 140
|
1030 |
+
},
|
1031 |
+
{
|
1032 |
+
"epoch": 0.08820769471379418,
|
1033 |
+
"grad_norm": 1.8955539464950562,
|
1034 |
+
"learning_rate": 0.0001542857142857143,
|
1035 |
+
"loss": 0.5515,
|
1036 |
+
"step": 141
|
1037 |
+
},
|
1038 |
+
{
|
1039 |
+
"epoch": 0.08883328120112606,
|
1040 |
+
"grad_norm": 5.194116115570068,
|
1041 |
+
"learning_rate": 0.00015394957983193278,
|
1042 |
+
"loss": 0.6843,
|
1043 |
+
"step": 142
|
1044 |
+
},
|
1045 |
+
{
|
1046 |
+
"epoch": 0.08945886768845793,
|
1047 |
+
"grad_norm": 1.4467953443527222,
|
1048 |
+
"learning_rate": 0.00015361344537815128,
|
1049 |
+
"loss": 0.4236,
|
1050 |
+
"step": 143
|
1051 |
+
},
|
1052 |
+
{
|
1053 |
+
"epoch": 0.09008445417578981,
|
1054 |
+
"grad_norm": 0.523921012878418,
|
1055 |
+
"learning_rate": 0.00015327731092436978,
|
1056 |
+
"loss": 0.2165,
|
1057 |
+
"step": 144
|
1058 |
+
},
|
1059 |
+
{
|
1060 |
+
"epoch": 0.09071004066312167,
|
1061 |
+
"grad_norm": 1.653648018836975,
|
1062 |
+
"learning_rate": 0.00015294117647058822,
|
1063 |
+
"loss": 1.0643,
|
1064 |
+
"step": 145
|
1065 |
+
},
|
1066 |
+
{
|
1067 |
+
"epoch": 0.09133562715045355,
|
1068 |
+
"grad_norm": 0.6991509199142456,
|
1069 |
+
"learning_rate": 0.00015260504201680672,
|
1070 |
+
"loss": 0.4398,
|
1071 |
+
"step": 146
|
1072 |
+
},
|
1073 |
+
{
|
1074 |
+
"epoch": 0.09196121363778542,
|
1075 |
+
"grad_norm": 1.3986660242080688,
|
1076 |
+
"learning_rate": 0.00015226890756302522,
|
1077 |
+
"loss": 0.8488,
|
1078 |
+
"step": 147
|
1079 |
+
},
|
1080 |
+
{
|
1081 |
+
"epoch": 0.0925868001251173,
|
1082 |
+
"grad_norm": 1.2424954175949097,
|
1083 |
+
"learning_rate": 0.0001519327731092437,
|
1084 |
+
"loss": 0.9516,
|
1085 |
+
"step": 148
|
1086 |
+
},
|
1087 |
+
{
|
1088 |
+
"epoch": 0.09321238661244917,
|
1089 |
+
"grad_norm": 0.8900560140609741,
|
1090 |
+
"learning_rate": 0.0001515966386554622,
|
1091 |
+
"loss": 0.767,
|
1092 |
+
"step": 149
|
1093 |
+
},
|
1094 |
+
{
|
1095 |
+
"epoch": 0.09383797309978105,
|
1096 |
+
"grad_norm": 40.042503356933594,
|
1097 |
+
"learning_rate": 0.00015126050420168066,
|
1098 |
+
"loss": 0.9691,
|
1099 |
+
"step": 150
|
1100 |
+
},
|
1101 |
+
{
|
1102 |
+
"epoch": 0.09383797309978105,
|
1103 |
+
"eval_loss": 0.8660734295845032,
|
1104 |
+
"eval_runtime": 43.5102,
|
1105 |
+
"eval_samples_per_second": 5.884,
|
1106 |
+
"eval_steps_per_second": 2.942,
|
1107 |
+
"step": 150
|
1108 |
+
},
|
1109 |
+
{
|
1110 |
+
"epoch": 0.09446355958711292,
|
1111 |
+
"grad_norm": 2.816359519958496,
|
1112 |
+
"learning_rate": 0.00015092436974789916,
|
1113 |
+
"loss": 1.4959,
|
1114 |
+
"step": 151
|
1115 |
+
},
|
1116 |
+
{
|
1117 |
+
"epoch": 0.0950891460744448,
|
1118 |
+
"grad_norm": 1.9332157373428345,
|
1119 |
+
"learning_rate": 0.00015058823529411766,
|
1120 |
+
"loss": 0.6786,
|
1121 |
+
"step": 152
|
1122 |
+
},
|
1123 |
+
{
|
1124 |
+
"epoch": 0.09571473256177666,
|
1125 |
+
"grad_norm": 1.2608965635299683,
|
1126 |
+
"learning_rate": 0.00015025210084033613,
|
1127 |
+
"loss": 1.1282,
|
1128 |
+
"step": 153
|
1129 |
+
},
|
1130 |
+
{
|
1131 |
+
"epoch": 0.09634031904910854,
|
1132 |
+
"grad_norm": 1.0167793035507202,
|
1133 |
+
"learning_rate": 0.00014991596638655463,
|
1134 |
+
"loss": 0.4932,
|
1135 |
+
"step": 154
|
1136 |
+
},
|
1137 |
+
{
|
1138 |
+
"epoch": 0.09696590553644041,
|
1139 |
+
"grad_norm": 1.6121408939361572,
|
1140 |
+
"learning_rate": 0.00014957983193277313,
|
1141 |
+
"loss": 0.7193,
|
1142 |
+
"step": 155
|
1143 |
+
},
|
1144 |
+
{
|
1145 |
+
"epoch": 0.09759149202377229,
|
1146 |
+
"grad_norm": 2.4104394912719727,
|
1147 |
+
"learning_rate": 0.0001492436974789916,
|
1148 |
+
"loss": 0.4472,
|
1149 |
+
"step": 156
|
1150 |
+
},
|
1151 |
+
{
|
1152 |
+
"epoch": 0.09821707851110416,
|
1153 |
+
"grad_norm": 1.1095707416534424,
|
1154 |
+
"learning_rate": 0.0001489075630252101,
|
1155 |
+
"loss": 0.7595,
|
1156 |
+
"step": 157
|
1157 |
+
},
|
1158 |
+
{
|
1159 |
+
"epoch": 0.09884266499843604,
|
1160 |
+
"grad_norm": 1.686458945274353,
|
1161 |
+
"learning_rate": 0.00014857142857142857,
|
1162 |
+
"loss": 0.5686,
|
1163 |
+
"step": 158
|
1164 |
+
},
|
1165 |
+
{
|
1166 |
+
"epoch": 0.0994682514857679,
|
1167 |
+
"grad_norm": 3.2238378524780273,
|
1168 |
+
"learning_rate": 0.00014823529411764707,
|
1169 |
+
"loss": 0.4236,
|
1170 |
+
"step": 159
|
1171 |
+
},
|
1172 |
+
{
|
1173 |
+
"epoch": 0.10009383797309979,
|
1174 |
+
"grad_norm": 1.800552248954773,
|
1175 |
+
"learning_rate": 0.00014789915966386557,
|
1176 |
+
"loss": 0.9519,
|
1177 |
+
"step": 160
|
1178 |
+
},
|
1179 |
+
{
|
1180 |
+
"epoch": 0.10071942446043165,
|
1181 |
+
"grad_norm": 0.6441445350646973,
|
1182 |
+
"learning_rate": 0.00014756302521008404,
|
1183 |
+
"loss": 0.4119,
|
1184 |
+
"step": 161
|
1185 |
+
},
|
1186 |
+
{
|
1187 |
+
"epoch": 0.10134501094776353,
|
1188 |
+
"grad_norm": 0.5892903804779053,
|
1189 |
+
"learning_rate": 0.00014722689075630254,
|
1190 |
+
"loss": 0.2956,
|
1191 |
+
"step": 162
|
1192 |
+
},
|
1193 |
+
{
|
1194 |
+
"epoch": 0.1019705974350954,
|
1195 |
+
"grad_norm": 0.8733301758766174,
|
1196 |
+
"learning_rate": 0.00014689075630252101,
|
1197 |
+
"loss": 0.5749,
|
1198 |
+
"step": 163
|
1199 |
+
},
|
1200 |
+
{
|
1201 |
+
"epoch": 0.10259618392242728,
|
1202 |
+
"grad_norm": 1.0460662841796875,
|
1203 |
+
"learning_rate": 0.0001465546218487395,
|
1204 |
+
"loss": 0.8167,
|
1205 |
+
"step": 164
|
1206 |
+
},
|
1207 |
+
{
|
1208 |
+
"epoch": 0.10322177040975915,
|
1209 |
+
"grad_norm": 0.8178017735481262,
|
1210 |
+
"learning_rate": 0.00014621848739495799,
|
1211 |
+
"loss": 0.9027,
|
1212 |
+
"step": 165
|
1213 |
+
},
|
1214 |
+
{
|
1215 |
+
"epoch": 0.10384735689709103,
|
1216 |
+
"grad_norm": 0.5698068737983704,
|
1217 |
+
"learning_rate": 0.00014588235294117646,
|
1218 |
+
"loss": 0.1829,
|
1219 |
+
"step": 166
|
1220 |
+
},
|
1221 |
+
{
|
1222 |
+
"epoch": 0.1044729433844229,
|
1223 |
+
"grad_norm": 1.0011018514633179,
|
1224 |
+
"learning_rate": 0.00014554621848739496,
|
1225 |
+
"loss": 0.8985,
|
1226 |
+
"step": 167
|
1227 |
+
},
|
1228 |
+
{
|
1229 |
+
"epoch": 0.10509852987175478,
|
1230 |
+
"grad_norm": 1.189772367477417,
|
1231 |
+
"learning_rate": 0.00014521008403361346,
|
1232 |
+
"loss": 0.5547,
|
1233 |
+
"step": 168
|
1234 |
+
},
|
1235 |
+
{
|
1236 |
+
"epoch": 0.10572411635908664,
|
1237 |
+
"grad_norm": 0.7990069389343262,
|
1238 |
+
"learning_rate": 0.00014487394957983193,
|
1239 |
+
"loss": 0.6222,
|
1240 |
+
"step": 169
|
1241 |
+
},
|
1242 |
+
{
|
1243 |
+
"epoch": 0.10634970284641852,
|
1244 |
+
"grad_norm": 0.6419771313667297,
|
1245 |
+
"learning_rate": 0.00014453781512605043,
|
1246 |
+
"loss": 0.3225,
|
1247 |
+
"step": 170
|
1248 |
+
},
|
1249 |
+
{
|
1250 |
+
"epoch": 0.10697528933375039,
|
1251 |
+
"grad_norm": 0.8978354930877686,
|
1252 |
+
"learning_rate": 0.00014420168067226893,
|
1253 |
+
"loss": 0.4567,
|
1254 |
+
"step": 171
|
1255 |
+
},
|
1256 |
+
{
|
1257 |
+
"epoch": 0.10760087582108227,
|
1258 |
+
"grad_norm": 0.7193794250488281,
|
1259 |
+
"learning_rate": 0.0001438655462184874,
|
1260 |
+
"loss": 0.4793,
|
1261 |
+
"step": 172
|
1262 |
+
},
|
1263 |
+
{
|
1264 |
+
"epoch": 0.10822646230841414,
|
1265 |
+
"grad_norm": 0.9533759355545044,
|
1266 |
+
"learning_rate": 0.0001435294117647059,
|
1267 |
+
"loss": 1.4397,
|
1268 |
+
"step": 173
|
1269 |
+
},
|
1270 |
+
{
|
1271 |
+
"epoch": 0.10885204879574602,
|
1272 |
+
"grad_norm": 0.48348739743232727,
|
1273 |
+
"learning_rate": 0.00014319327731092437,
|
1274 |
+
"loss": 0.3398,
|
1275 |
+
"step": 174
|
1276 |
+
},
|
1277 |
+
{
|
1278 |
+
"epoch": 0.10947763528307788,
|
1279 |
+
"grad_norm": 0.7699019312858582,
|
1280 |
+
"learning_rate": 0.00014285714285714287,
|
1281 |
+
"loss": 0.7491,
|
1282 |
+
"step": 175
|
1283 |
+
},
|
1284 |
+
{
|
1285 |
+
"epoch": 0.10947763528307788,
|
1286 |
+
"eval_loss": 0.8425782322883606,
|
1287 |
+
"eval_runtime": 43.5013,
|
1288 |
+
"eval_samples_per_second": 5.885,
|
1289 |
+
"eval_steps_per_second": 2.942,
|
1290 |
+
"step": 175
|
1291 |
+
},
|
1292 |
+
{
|
1293 |
+
"epoch": 0.11010322177040976,
|
1294 |
+
"grad_norm": 0.9201186895370483,
|
1295 |
+
"learning_rate": 0.00014252100840336137,
|
1296 |
+
"loss": 0.6919,
|
1297 |
+
"step": 176
|
1298 |
+
},
|
1299 |
+
{
|
1300 |
+
"epoch": 0.11072880825774163,
|
1301 |
+
"grad_norm": 0.8190593123435974,
|
1302 |
+
"learning_rate": 0.00014218487394957984,
|
1303 |
+
"loss": 0.6262,
|
1304 |
+
"step": 177
|
1305 |
+
},
|
1306 |
+
{
|
1307 |
+
"epoch": 0.11135439474507351,
|
1308 |
+
"grad_norm": 0.9715782403945923,
|
1309 |
+
"learning_rate": 0.00014184873949579834,
|
1310 |
+
"loss": 0.8364,
|
1311 |
+
"step": 178
|
1312 |
+
},
|
1313 |
+
{
|
1314 |
+
"epoch": 0.11197998123240538,
|
1315 |
+
"grad_norm": 0.6699782609939575,
|
1316 |
+
"learning_rate": 0.0001415126050420168,
|
1317 |
+
"loss": 0.4898,
|
1318 |
+
"step": 179
|
1319 |
+
},
|
1320 |
+
{
|
1321 |
+
"epoch": 0.11260556771973726,
|
1322 |
+
"grad_norm": 1.8386518955230713,
|
1323 |
+
"learning_rate": 0.0001411764705882353,
|
1324 |
+
"loss": 0.7812,
|
1325 |
+
"step": 180
|
1326 |
+
},
|
1327 |
+
{
|
1328 |
+
"epoch": 0.11323115420706913,
|
1329 |
+
"grad_norm": 0.7240263819694519,
|
1330 |
+
"learning_rate": 0.0001408403361344538,
|
1331 |
+
"loss": 0.5508,
|
1332 |
+
"step": 181
|
1333 |
+
},
|
1334 |
+
{
|
1335 |
+
"epoch": 0.113856740694401,
|
1336 |
+
"grad_norm": 0.6068630814552307,
|
1337 |
+
"learning_rate": 0.00014050420168067225,
|
1338 |
+
"loss": 0.5151,
|
1339 |
+
"step": 182
|
1340 |
+
},
|
1341 |
+
{
|
1342 |
+
"epoch": 0.11448232718173287,
|
1343 |
+
"grad_norm": 1.6705517768859863,
|
1344 |
+
"learning_rate": 0.00014016806722689075,
|
1345 |
+
"loss": 1.2281,
|
1346 |
+
"step": 183
|
1347 |
+
},
|
1348 |
+
{
|
1349 |
+
"epoch": 0.11510791366906475,
|
1350 |
+
"grad_norm": 1.6179956197738647,
|
1351 |
+
"learning_rate": 0.00013983193277310925,
|
1352 |
+
"loss": 0.7365,
|
1353 |
+
"step": 184
|
1354 |
+
},
|
1355 |
+
{
|
1356 |
+
"epoch": 0.11573350015639662,
|
1357 |
+
"grad_norm": 1.5741758346557617,
|
1358 |
+
"learning_rate": 0.00013949579831932772,
|
1359 |
+
"loss": 1.0039,
|
1360 |
+
"step": 185
|
1361 |
+
},
|
1362 |
+
{
|
1363 |
+
"epoch": 0.1163590866437285,
|
1364 |
+
"grad_norm": 0.9270511865615845,
|
1365 |
+
"learning_rate": 0.00013915966386554622,
|
1366 |
+
"loss": 0.5768,
|
1367 |
+
"step": 186
|
1368 |
+
},
|
1369 |
+
{
|
1370 |
+
"epoch": 0.11698467313106037,
|
1371 |
+
"grad_norm": 1.3651914596557617,
|
1372 |
+
"learning_rate": 0.00013882352941176472,
|
1373 |
+
"loss": 0.7715,
|
1374 |
+
"step": 187
|
1375 |
+
},
|
1376 |
+
{
|
1377 |
+
"epoch": 0.11761025961839225,
|
1378 |
+
"grad_norm": 1.4330601692199707,
|
1379 |
+
"learning_rate": 0.0001384873949579832,
|
1380 |
+
"loss": 0.4462,
|
1381 |
+
"step": 188
|
1382 |
+
},
|
1383 |
+
{
|
1384 |
+
"epoch": 0.11823584610572412,
|
1385 |
+
"grad_norm": 0.9181672930717468,
|
1386 |
+
"learning_rate": 0.0001381512605042017,
|
1387 |
+
"loss": 0.3901,
|
1388 |
+
"step": 189
|
1389 |
+
},
|
1390 |
+
{
|
1391 |
+
"epoch": 0.118861432593056,
|
1392 |
+
"grad_norm": 0.5304622650146484,
|
1393 |
+
"learning_rate": 0.00013781512605042016,
|
1394 |
+
"loss": 0.1718,
|
1395 |
+
"step": 190
|
1396 |
+
},
|
1397 |
+
{
|
1398 |
+
"epoch": 0.11948701908038786,
|
1399 |
+
"grad_norm": 0.7475191354751587,
|
1400 |
+
"learning_rate": 0.00013747899159663866,
|
1401 |
+
"loss": 0.3602,
|
1402 |
+
"step": 191
|
1403 |
+
},
|
1404 |
+
{
|
1405 |
+
"epoch": 0.12011260556771974,
|
1406 |
+
"grad_norm": 1.2558002471923828,
|
1407 |
+
"learning_rate": 0.00013714285714285716,
|
1408 |
+
"loss": 0.8558,
|
1409 |
+
"step": 192
|
1410 |
+
},
|
1411 |
+
{
|
1412 |
+
"epoch": 0.12073819205505161,
|
1413 |
+
"grad_norm": 0.9859037399291992,
|
1414 |
+
"learning_rate": 0.00013680672268907563,
|
1415 |
+
"loss": 0.7155,
|
1416 |
+
"step": 193
|
1417 |
+
},
|
1418 |
+
{
|
1419 |
+
"epoch": 0.12136377854238349,
|
1420 |
+
"grad_norm": 0.6028466820716858,
|
1421 |
+
"learning_rate": 0.00013647058823529413,
|
1422 |
+
"loss": 0.9596,
|
1423 |
+
"step": 194
|
1424 |
+
},
|
1425 |
+
{
|
1426 |
+
"epoch": 0.12198936502971536,
|
1427 |
+
"grad_norm": 0.5713469386100769,
|
1428 |
+
"learning_rate": 0.0001361344537815126,
|
1429 |
+
"loss": 0.3442,
|
1430 |
+
"step": 195
|
1431 |
+
},
|
1432 |
+
{
|
1433 |
+
"epoch": 0.12261495151704724,
|
1434 |
+
"grad_norm": 1.0781211853027344,
|
1435 |
+
"learning_rate": 0.0001357983193277311,
|
1436 |
+
"loss": 0.5569,
|
1437 |
+
"step": 196
|
1438 |
+
},
|
1439 |
+
{
|
1440 |
+
"epoch": 0.1232405380043791,
|
1441 |
+
"grad_norm": 0.7850176095962524,
|
1442 |
+
"learning_rate": 0.0001354621848739496,
|
1443 |
+
"loss": 0.5853,
|
1444 |
+
"step": 197
|
1445 |
+
},
|
1446 |
+
{
|
1447 |
+
"epoch": 0.12386612449171099,
|
1448 |
+
"grad_norm": 0.8100555539131165,
|
1449 |
+
"learning_rate": 0.00013512605042016807,
|
1450 |
+
"loss": 0.8285,
|
1451 |
+
"step": 198
|
1452 |
+
},
|
1453 |
+
{
|
1454 |
+
"epoch": 0.12449171097904285,
|
1455 |
+
"grad_norm": 1.106834888458252,
|
1456 |
+
"learning_rate": 0.00013478991596638657,
|
1457 |
+
"loss": 0.9521,
|
1458 |
+
"step": 199
|
1459 |
+
},
|
1460 |
+
{
|
1461 |
+
"epoch": 0.12511729746637473,
|
1462 |
+
"grad_norm": 1.4412230253219604,
|
1463 |
+
"learning_rate": 0.00013445378151260507,
|
1464 |
+
"loss": 0.6478,
|
1465 |
+
"step": 200
|
1466 |
+
},
|
1467 |
+
{
|
1468 |
+
"epoch": 0.12511729746637473,
|
1469 |
+
"eval_loss": 0.8300326466560364,
|
1470 |
+
"eval_runtime": 43.5102,
|
1471 |
+
"eval_samples_per_second": 5.884,
|
1472 |
+
"eval_steps_per_second": 2.942,
|
1473 |
+
"step": 200
|
1474 |
+
},
|
1475 |
+
{
|
1476 |
+
"epoch": 0.1257428839537066,
|
1477 |
+
"grad_norm": 1.7852795124053955,
|
1478 |
+
"learning_rate": 0.00013411764705882352,
|
1479 |
+
"loss": 0.5687,
|
1480 |
+
"step": 201
|
1481 |
+
},
|
1482 |
+
{
|
1483 |
+
"epoch": 0.12636847044103847,
|
1484 |
+
"grad_norm": 2.423583745956421,
|
1485 |
+
"learning_rate": 0.00013378151260504202,
|
1486 |
+
"loss": 0.9082,
|
1487 |
+
"step": 202
|
1488 |
+
},
|
1489 |
+
{
|
1490 |
+
"epoch": 0.12699405692837035,
|
1491 |
+
"grad_norm": 1.538001298904419,
|
1492 |
+
"learning_rate": 0.00013344537815126052,
|
1493 |
+
"loss": 0.7143,
|
1494 |
+
"step": 203
|
1495 |
+
},
|
1496 |
+
{
|
1497 |
+
"epoch": 0.12761964341570223,
|
1498 |
+
"grad_norm": 1.7380592823028564,
|
1499 |
+
"learning_rate": 0.000133109243697479,
|
1500 |
+
"loss": 0.8296,
|
1501 |
+
"step": 204
|
1502 |
+
},
|
1503 |
+
{
|
1504 |
+
"epoch": 0.1282452299030341,
|
1505 |
+
"grad_norm": 0.8279218673706055,
|
1506 |
+
"learning_rate": 0.0001327731092436975,
|
1507 |
+
"loss": 0.6719,
|
1508 |
+
"step": 205
|
1509 |
+
},
|
1510 |
+
{
|
1511 |
+
"epoch": 0.12887081639036596,
|
1512 |
+
"grad_norm": 0.7059926986694336,
|
1513 |
+
"learning_rate": 0.00013243697478991596,
|
1514 |
+
"loss": 0.4785,
|
1515 |
+
"step": 206
|
1516 |
+
},
|
1517 |
+
{
|
1518 |
+
"epoch": 0.12949640287769784,
|
1519 |
+
"grad_norm": 0.6946935653686523,
|
1520 |
+
"learning_rate": 0.00013210084033613446,
|
1521 |
+
"loss": 0.4578,
|
1522 |
+
"step": 207
|
1523 |
+
},
|
1524 |
+
{
|
1525 |
+
"epoch": 0.13012198936502972,
|
1526 |
+
"grad_norm": 0.9800712466239929,
|
1527 |
+
"learning_rate": 0.00013176470588235296,
|
1528 |
+
"loss": 1.4369,
|
1529 |
+
"step": 208
|
1530 |
+
},
|
1531 |
+
{
|
1532 |
+
"epoch": 0.1307475758523616,
|
1533 |
+
"grad_norm": 0.708831787109375,
|
1534 |
+
"learning_rate": 0.00013142857142857143,
|
1535 |
+
"loss": 0.5071,
|
1536 |
+
"step": 209
|
1537 |
+
},
|
1538 |
+
{
|
1539 |
+
"epoch": 0.13137316233969346,
|
1540 |
+
"grad_norm": 1.0098780393600464,
|
1541 |
+
"learning_rate": 0.00013109243697478993,
|
1542 |
+
"loss": 0.9155,
|
1543 |
+
"step": 210
|
1544 |
+
},
|
1545 |
+
{
|
1546 |
+
"epoch": 0.13199874882702534,
|
1547 |
+
"grad_norm": 1.1598243713378906,
|
1548 |
+
"learning_rate": 0.0001307563025210084,
|
1549 |
+
"loss": 0.3757,
|
1550 |
+
"step": 211
|
1551 |
+
},
|
1552 |
+
{
|
1553 |
+
"epoch": 0.13262433531435722,
|
1554 |
+
"grad_norm": 0.7583935260772705,
|
1555 |
+
"learning_rate": 0.0001304201680672269,
|
1556 |
+
"loss": 0.3365,
|
1557 |
+
"step": 212
|
1558 |
+
},
|
1559 |
+
{
|
1560 |
+
"epoch": 0.1332499218016891,
|
1561 |
+
"grad_norm": 1.0866564512252808,
|
1562 |
+
"learning_rate": 0.0001300840336134454,
|
1563 |
+
"loss": 0.6398,
|
1564 |
+
"step": 213
|
1565 |
+
},
|
1566 |
+
{
|
1567 |
+
"epoch": 0.13387550828902095,
|
1568 |
+
"grad_norm": 1.4322006702423096,
|
1569 |
+
"learning_rate": 0.00012974789915966387,
|
1570 |
+
"loss": 0.6427,
|
1571 |
+
"step": 214
|
1572 |
+
},
|
1573 |
+
{
|
1574 |
+
"epoch": 0.13450109477635283,
|
1575 |
+
"grad_norm": 1.600325345993042,
|
1576 |
+
"learning_rate": 0.00012941176470588237,
|
1577 |
+
"loss": 0.6884,
|
1578 |
+
"step": 215
|
1579 |
+
},
|
1580 |
+
{
|
1581 |
+
"epoch": 0.1351266812636847,
|
1582 |
+
"grad_norm": 1.0634167194366455,
|
1583 |
+
"learning_rate": 0.00012907563025210087,
|
1584 |
+
"loss": 1.0343,
|
1585 |
+
"step": 216
|
1586 |
+
},
|
1587 |
+
{
|
1588 |
+
"epoch": 0.13575226775101656,
|
1589 |
+
"grad_norm": 0.9889366626739502,
|
1590 |
+
"learning_rate": 0.00012873949579831934,
|
1591 |
+
"loss": 0.717,
|
1592 |
+
"step": 217
|
1593 |
+
},
|
1594 |
+
{
|
1595 |
+
"epoch": 0.13637785423834844,
|
1596 |
+
"grad_norm": 2.0635392665863037,
|
1597 |
+
"learning_rate": 0.00012840336134453784,
|
1598 |
+
"loss": 0.5965,
|
1599 |
+
"step": 218
|
1600 |
+
},
|
1601 |
+
{
|
1602 |
+
"epoch": 0.13700344072568033,
|
1603 |
+
"grad_norm": 0.8937773704528809,
|
1604 |
+
"learning_rate": 0.0001280672268907563,
|
1605 |
+
"loss": 0.7281,
|
1606 |
+
"step": 219
|
1607 |
+
},
|
1608 |
+
{
|
1609 |
+
"epoch": 0.1376290272130122,
|
1610 |
+
"grad_norm": 0.9768427014350891,
|
1611 |
+
"learning_rate": 0.00012773109243697478,
|
1612 |
+
"loss": 0.5687,
|
1613 |
+
"step": 220
|
1614 |
+
},
|
1615 |
+
{
|
1616 |
+
"epoch": 0.13825461370034406,
|
1617 |
+
"grad_norm": 1.3913767337799072,
|
1618 |
+
"learning_rate": 0.00012739495798319328,
|
1619 |
+
"loss": 0.3984,
|
1620 |
+
"step": 221
|
1621 |
+
},
|
1622 |
+
{
|
1623 |
+
"epoch": 0.13888020018767594,
|
1624 |
+
"grad_norm": 1.4933342933654785,
|
1625 |
+
"learning_rate": 0.00012705882352941175,
|
1626 |
+
"loss": 1.2441,
|
1627 |
+
"step": 222
|
1628 |
+
},
|
1629 |
+
{
|
1630 |
+
"epoch": 0.13950578667500782,
|
1631 |
+
"grad_norm": 1.0846196413040161,
|
1632 |
+
"learning_rate": 0.00012672268907563025,
|
1633 |
+
"loss": 0.9013,
|
1634 |
+
"step": 223
|
1635 |
+
},
|
1636 |
+
{
|
1637 |
+
"epoch": 0.1401313731623397,
|
1638 |
+
"grad_norm": 0.7788563370704651,
|
1639 |
+
"learning_rate": 0.00012638655462184875,
|
1640 |
+
"loss": 0.4674,
|
1641 |
+
"step": 224
|
1642 |
+
},
|
1643 |
+
{
|
1644 |
+
"epoch": 0.14075695964967155,
|
1645 |
+
"grad_norm": 0.7341142296791077,
|
1646 |
+
"learning_rate": 0.00012605042016806722,
|
1647 |
+
"loss": 1.3271,
|
1648 |
+
"step": 225
|
1649 |
+
},
|
1650 |
+
{
|
1651 |
+
"epoch": 0.14075695964967155,
|
1652 |
+
"eval_loss": 0.8179877996444702,
|
1653 |
+
"eval_runtime": 43.5514,
|
1654 |
+
"eval_samples_per_second": 5.878,
|
1655 |
+
"eval_steps_per_second": 2.939,
|
1656 |
+
"step": 225
|
1657 |
+
},
|
1658 |
+
{
|
1659 |
+
"epoch": 0.14138254613700343,
|
1660 |
+
"grad_norm": 6.473598480224609,
|
1661 |
+
"learning_rate": 0.00012571428571428572,
|
1662 |
+
"loss": 0.6219,
|
1663 |
+
"step": 226
|
1664 |
+
},
|
1665 |
+
{
|
1666 |
+
"epoch": 0.14200813262433531,
|
1667 |
+
"grad_norm": 0.9846400022506714,
|
1668 |
+
"learning_rate": 0.0001253781512605042,
|
1669 |
+
"loss": 0.4407,
|
1670 |
+
"step": 227
|
1671 |
+
},
|
1672 |
+
{
|
1673 |
+
"epoch": 0.1426337191116672,
|
1674 |
+
"grad_norm": 0.7880604267120361,
|
1675 |
+
"learning_rate": 0.0001250420168067227,
|
1676 |
+
"loss": 0.3927,
|
1677 |
+
"step": 228
|
1678 |
+
},
|
1679 |
+
{
|
1680 |
+
"epoch": 0.14325930559899905,
|
1681 |
+
"grad_norm": 1.5999399423599243,
|
1682 |
+
"learning_rate": 0.0001247058823529412,
|
1683 |
+
"loss": 0.6917,
|
1684 |
+
"step": 229
|
1685 |
+
},
|
1686 |
+
{
|
1687 |
+
"epoch": 0.14388489208633093,
|
1688 |
+
"grad_norm": 0.8072729110717773,
|
1689 |
+
"learning_rate": 0.00012436974789915966,
|
1690 |
+
"loss": 0.4909,
|
1691 |
+
"step": 230
|
1692 |
+
},
|
1693 |
+
{
|
1694 |
+
"epoch": 0.1445104785736628,
|
1695 |
+
"grad_norm": 2.2560601234436035,
|
1696 |
+
"learning_rate": 0.00012403361344537816,
|
1697 |
+
"loss": 0.3355,
|
1698 |
+
"step": 231
|
1699 |
+
},
|
1700 |
+
{
|
1701 |
+
"epoch": 0.1451360650609947,
|
1702 |
+
"grad_norm": 0.9964832663536072,
|
1703 |
+
"learning_rate": 0.00012369747899159666,
|
1704 |
+
"loss": 0.4436,
|
1705 |
+
"step": 232
|
1706 |
+
},
|
1707 |
+
{
|
1708 |
+
"epoch": 0.14576165154832654,
|
1709 |
+
"grad_norm": 1.1081007719039917,
|
1710 |
+
"learning_rate": 0.00012336134453781513,
|
1711 |
+
"loss": 0.6582,
|
1712 |
+
"step": 233
|
1713 |
+
},
|
1714 |
+
{
|
1715 |
+
"epoch": 0.14638723803565842,
|
1716 |
+
"grad_norm": 0.9722908735275269,
|
1717 |
+
"learning_rate": 0.00012302521008403363,
|
1718 |
+
"loss": 0.7412,
|
1719 |
+
"step": 234
|
1720 |
+
},
|
1721 |
+
{
|
1722 |
+
"epoch": 0.1470128245229903,
|
1723 |
+
"grad_norm": 0.7456592917442322,
|
1724 |
+
"learning_rate": 0.0001226890756302521,
|
1725 |
+
"loss": 0.4303,
|
1726 |
+
"step": 235
|
1727 |
+
},
|
1728 |
+
{
|
1729 |
+
"epoch": 0.14763841101032218,
|
1730 |
+
"grad_norm": 1.0428457260131836,
|
1731 |
+
"learning_rate": 0.0001223529411764706,
|
1732 |
+
"loss": 1.0538,
|
1733 |
+
"step": 236
|
1734 |
+
},
|
1735 |
+
{
|
1736 |
+
"epoch": 0.14826399749765404,
|
1737 |
+
"grad_norm": 0.9209719896316528,
|
1738 |
+
"learning_rate": 0.00012201680672268909,
|
1739 |
+
"loss": 0.5864,
|
1740 |
+
"step": 237
|
1741 |
+
},
|
1742 |
+
{
|
1743 |
+
"epoch": 0.14888958398498592,
|
1744 |
+
"grad_norm": 0.990292489528656,
|
1745 |
+
"learning_rate": 0.00012168067226890756,
|
1746 |
+
"loss": 0.5929,
|
1747 |
+
"step": 238
|
1748 |
+
},
|
1749 |
+
{
|
1750 |
+
"epoch": 0.1495151704723178,
|
1751 |
+
"grad_norm": 0.6086494326591492,
|
1752 |
+
"learning_rate": 0.00012134453781512605,
|
1753 |
+
"loss": 0.4436,
|
1754 |
+
"step": 239
|
1755 |
+
},
|
1756 |
+
{
|
1757 |
+
"epoch": 0.15014075695964968,
|
1758 |
+
"grad_norm": 1.429149866104126,
|
1759 |
+
"learning_rate": 0.00012100840336134453,
|
1760 |
+
"loss": 0.246,
|
1761 |
+
"step": 240
|
1762 |
+
},
|
1763 |
+
{
|
1764 |
+
"epoch": 0.15076634344698153,
|
1765 |
+
"grad_norm": 1.8170491456985474,
|
1766 |
+
"learning_rate": 0.00012067226890756302,
|
1767 |
+
"loss": 0.6574,
|
1768 |
+
"step": 241
|
1769 |
+
},
|
1770 |
+
{
|
1771 |
+
"epoch": 0.1513919299343134,
|
1772 |
+
"grad_norm": 1.1577768325805664,
|
1773 |
+
"learning_rate": 0.00012033613445378152,
|
1774 |
+
"loss": 0.5706,
|
1775 |
+
"step": 242
|
1776 |
+
},
|
1777 |
+
{
|
1778 |
+
"epoch": 0.1520175164216453,
|
1779 |
+
"grad_norm": 0.7442137598991394,
|
1780 |
+
"learning_rate": 0.00012,
|
1781 |
+
"loss": 0.2772,
|
1782 |
+
"step": 243
|
1783 |
+
},
|
1784 |
+
{
|
1785 |
+
"epoch": 0.15264310290897717,
|
1786 |
+
"grad_norm": 1.1375997066497803,
|
1787 |
+
"learning_rate": 0.00011966386554621849,
|
1788 |
+
"loss": 0.397,
|
1789 |
+
"step": 244
|
1790 |
+
},
|
1791 |
+
{
|
1792 |
+
"epoch": 0.15326868939630903,
|
1793 |
+
"grad_norm": 0.8451513648033142,
|
1794 |
+
"learning_rate": 0.00011932773109243697,
|
1795 |
+
"loss": 0.5425,
|
1796 |
+
"step": 245
|
1797 |
+
},
|
1798 |
+
{
|
1799 |
+
"epoch": 0.1538942758836409,
|
1800 |
+
"grad_norm": 0.7176560163497925,
|
1801 |
+
"learning_rate": 0.00011899159663865547,
|
1802 |
+
"loss": 0.4398,
|
1803 |
+
"step": 246
|
1804 |
+
},
|
1805 |
+
{
|
1806 |
+
"epoch": 0.1545198623709728,
|
1807 |
+
"grad_norm": 1.049872875213623,
|
1808 |
+
"learning_rate": 0.00011865546218487396,
|
1809 |
+
"loss": 0.6479,
|
1810 |
+
"step": 247
|
1811 |
+
},
|
1812 |
+
{
|
1813 |
+
"epoch": 0.15514544885830467,
|
1814 |
+
"grad_norm": 0.6093642115592957,
|
1815 |
+
"learning_rate": 0.00011831932773109244,
|
1816 |
+
"loss": 0.6125,
|
1817 |
+
"step": 248
|
1818 |
+
},
|
1819 |
+
{
|
1820 |
+
"epoch": 0.15577103534563652,
|
1821 |
+
"grad_norm": 0.9963379502296448,
|
1822 |
+
"learning_rate": 0.00011798319327731093,
|
1823 |
+
"loss": 0.3768,
|
1824 |
+
"step": 249
|
1825 |
+
},
|
1826 |
+
{
|
1827 |
+
"epoch": 0.1563966218329684,
|
1828 |
+
"grad_norm": 3.4668896198272705,
|
1829 |
+
"learning_rate": 0.00011764705882352942,
|
1830 |
+
"loss": 0.3744,
|
1831 |
+
"step": 250
|
1832 |
+
},
|
1833 |
+
{
|
1834 |
+
"epoch": 0.1563966218329684,
|
1835 |
+
"eval_loss": 0.8456696271896362,
|
1836 |
+
"eval_runtime": 43.5223,
|
1837 |
+
"eval_samples_per_second": 5.882,
|
1838 |
+
"eval_steps_per_second": 2.941,
|
1839 |
+
"step": 250
|
1840 |
+
},
|
1841 |
+
{
|
1842 |
+
"epoch": 0.15702220832030028,
|
1843 |
+
"grad_norm": 0.6826130747795105,
|
1844 |
+
"learning_rate": 0.00011731092436974791,
|
1845 |
+
"loss": 0.4877,
|
1846 |
+
"step": 251
|
1847 |
+
},
|
1848 |
+
{
|
1849 |
+
"epoch": 0.15764779480763216,
|
1850 |
+
"grad_norm": 1.8045300245285034,
|
1851 |
+
"learning_rate": 0.0001169747899159664,
|
1852 |
+
"loss": 0.9699,
|
1853 |
+
"step": 252
|
1854 |
+
},
|
1855 |
+
{
|
1856 |
+
"epoch": 0.15827338129496402,
|
1857 |
+
"grad_norm": 0.7311923503875732,
|
1858 |
+
"learning_rate": 0.00011663865546218489,
|
1859 |
+
"loss": 0.4648,
|
1860 |
+
"step": 253
|
1861 |
+
},
|
1862 |
+
{
|
1863 |
+
"epoch": 0.1588989677822959,
|
1864 |
+
"grad_norm": 1.7481943368911743,
|
1865 |
+
"learning_rate": 0.00011630252100840337,
|
1866 |
+
"loss": 0.8871,
|
1867 |
+
"step": 254
|
1868 |
+
},
|
1869 |
+
{
|
1870 |
+
"epoch": 0.15952455426962778,
|
1871 |
+
"grad_norm": 2.6331326961517334,
|
1872 |
+
"learning_rate": 0.00011596638655462187,
|
1873 |
+
"loss": 0.8109,
|
1874 |
+
"step": 255
|
1875 |
+
},
|
1876 |
+
{
|
1877 |
+
"epoch": 0.16015014075695966,
|
1878 |
+
"grad_norm": 0.899364709854126,
|
1879 |
+
"learning_rate": 0.00011563025210084036,
|
1880 |
+
"loss": 0.5021,
|
1881 |
+
"step": 256
|
1882 |
+
},
|
1883 |
+
{
|
1884 |
+
"epoch": 0.1607757272442915,
|
1885 |
+
"grad_norm": 0.922218918800354,
|
1886 |
+
"learning_rate": 0.00011529411764705881,
|
1887 |
+
"loss": 0.5741,
|
1888 |
+
"step": 257
|
1889 |
+
},
|
1890 |
+
{
|
1891 |
+
"epoch": 0.1614013137316234,
|
1892 |
+
"grad_norm": 5.335756301879883,
|
1893 |
+
"learning_rate": 0.00011495798319327731,
|
1894 |
+
"loss": 0.842,
|
1895 |
+
"step": 258
|
1896 |
+
},
|
1897 |
+
{
|
1898 |
+
"epoch": 0.16202690021895527,
|
1899 |
+
"grad_norm": 0.8632665872573853,
|
1900 |
+
"learning_rate": 0.0001146218487394958,
|
1901 |
+
"loss": 0.4208,
|
1902 |
+
"step": 259
|
1903 |
+
},
|
1904 |
+
{
|
1905 |
+
"epoch": 0.16265248670628715,
|
1906 |
+
"grad_norm": 4.576591968536377,
|
1907 |
+
"learning_rate": 0.00011428571428571428,
|
1908 |
+
"loss": 0.8813,
|
1909 |
+
"step": 260
|
1910 |
+
},
|
1911 |
+
{
|
1912 |
+
"epoch": 0.163278073193619,
|
1913 |
+
"grad_norm": 0.907714307308197,
|
1914 |
+
"learning_rate": 0.00011394957983193277,
|
1915 |
+
"loss": 0.7204,
|
1916 |
+
"step": 261
|
1917 |
+
},
|
1918 |
+
{
|
1919 |
+
"epoch": 0.16390365968095089,
|
1920 |
+
"grad_norm": 0.8328534960746765,
|
1921 |
+
"learning_rate": 0.00011361344537815127,
|
1922 |
+
"loss": 0.7552,
|
1923 |
+
"step": 262
|
1924 |
+
},
|
1925 |
+
{
|
1926 |
+
"epoch": 0.16452924616828277,
|
1927 |
+
"grad_norm": 1.0882028341293335,
|
1928 |
+
"learning_rate": 0.00011327731092436975,
|
1929 |
+
"loss": 0.9079,
|
1930 |
+
"step": 263
|
1931 |
+
},
|
1932 |
+
{
|
1933 |
+
"epoch": 0.16515483265561465,
|
1934 |
+
"grad_norm": 1.0093358755111694,
|
1935 |
+
"learning_rate": 0.00011294117647058824,
|
1936 |
+
"loss": 0.6284,
|
1937 |
+
"step": 264
|
1938 |
+
},
|
1939 |
+
{
|
1940 |
+
"epoch": 0.1657804191429465,
|
1941 |
+
"grad_norm": 0.853907585144043,
|
1942 |
+
"learning_rate": 0.00011260504201680672,
|
1943 |
+
"loss": 0.508,
|
1944 |
+
"step": 265
|
1945 |
+
},
|
1946 |
+
{
|
1947 |
+
"epoch": 0.16640600563027838,
|
1948 |
+
"grad_norm": 1.0016460418701172,
|
1949 |
+
"learning_rate": 0.00011226890756302521,
|
1950 |
+
"loss": 0.597,
|
1951 |
+
"step": 266
|
1952 |
+
},
|
1953 |
+
{
|
1954 |
+
"epoch": 0.16703159211761026,
|
1955 |
+
"grad_norm": 1.0138968229293823,
|
1956 |
+
"learning_rate": 0.00011193277310924371,
|
1957 |
+
"loss": 0.9238,
|
1958 |
+
"step": 267
|
1959 |
+
},
|
1960 |
+
{
|
1961 |
+
"epoch": 0.16765717860494214,
|
1962 |
+
"grad_norm": 1.1728049516677856,
|
1963 |
+
"learning_rate": 0.0001115966386554622,
|
1964 |
+
"loss": 0.9152,
|
1965 |
+
"step": 268
|
1966 |
+
},
|
1967 |
+
{
|
1968 |
+
"epoch": 0.168282765092274,
|
1969 |
+
"grad_norm": 1.2228264808654785,
|
1970 |
+
"learning_rate": 0.00011126050420168068,
|
1971 |
+
"loss": 0.7483,
|
1972 |
+
"step": 269
|
1973 |
+
},
|
1974 |
+
{
|
1975 |
+
"epoch": 0.16890835157960588,
|
1976 |
+
"grad_norm": 0.6260212659835815,
|
1977 |
+
"learning_rate": 0.00011092436974789917,
|
1978 |
+
"loss": 0.5566,
|
1979 |
+
"step": 270
|
1980 |
+
},
|
1981 |
+
{
|
1982 |
+
"epoch": 0.16953393806693776,
|
1983 |
+
"grad_norm": 0.7589625716209412,
|
1984 |
+
"learning_rate": 0.00011058823529411766,
|
1985 |
+
"loss": 0.6242,
|
1986 |
+
"step": 271
|
1987 |
+
},
|
1988 |
+
{
|
1989 |
+
"epoch": 0.17015952455426964,
|
1990 |
+
"grad_norm": 1.1016935110092163,
|
1991 |
+
"learning_rate": 0.00011025210084033615,
|
1992 |
+
"loss": 0.4419,
|
1993 |
+
"step": 272
|
1994 |
+
},
|
1995 |
+
{
|
1996 |
+
"epoch": 0.1707851110416015,
|
1997 |
+
"grad_norm": 0.8092851042747498,
|
1998 |
+
"learning_rate": 0.00010991596638655464,
|
1999 |
+
"loss": 0.5168,
|
2000 |
+
"step": 273
|
2001 |
+
},
|
2002 |
+
{
|
2003 |
+
"epoch": 0.17141069752893337,
|
2004 |
+
"grad_norm": 1.012885332107544,
|
2005 |
+
"learning_rate": 0.00010957983193277312,
|
2006 |
+
"loss": 0.4334,
|
2007 |
+
"step": 274
|
2008 |
+
},
|
2009 |
+
{
|
2010 |
+
"epoch": 0.17203628401626525,
|
2011 |
+
"grad_norm": 2.6073336601257324,
|
2012 |
+
"learning_rate": 0.00010924369747899159,
|
2013 |
+
"loss": 0.5262,
|
2014 |
+
"step": 275
|
2015 |
+
},
|
2016 |
+
{
|
2017 |
+
"epoch": 0.17203628401626525,
|
2018 |
+
"eval_loss": 0.8115787506103516,
|
2019 |
+
"eval_runtime": 43.4931,
|
2020 |
+
"eval_samples_per_second": 5.886,
|
2021 |
+
"eval_steps_per_second": 2.943,
|
2022 |
+
"step": 275
|
2023 |
+
},
|
2024 |
+
{
|
2025 |
+
"epoch": 0.17266187050359713,
|
2026 |
+
"grad_norm": 5.577237606048584,
|
2027 |
+
"learning_rate": 0.00010890756302521008,
|
2028 |
+
"loss": 1.0595,
|
2029 |
+
"step": 276
|
2030 |
+
},
|
2031 |
+
{
|
2032 |
+
"epoch": 0.17328745699092898,
|
2033 |
+
"grad_norm": 1.1434190273284912,
|
2034 |
+
"learning_rate": 0.00010857142857142856,
|
2035 |
+
"loss": 0.4401,
|
2036 |
+
"step": 277
|
2037 |
+
},
|
2038 |
+
{
|
2039 |
+
"epoch": 0.17391304347826086,
|
2040 |
+
"grad_norm": 0.951992928981781,
|
2041 |
+
"learning_rate": 0.00010823529411764706,
|
2042 |
+
"loss": 0.4393,
|
2043 |
+
"step": 278
|
2044 |
+
},
|
2045 |
+
{
|
2046 |
+
"epoch": 0.17453862996559275,
|
2047 |
+
"grad_norm": 0.6695138216018677,
|
2048 |
+
"learning_rate": 0.00010789915966386555,
|
2049 |
+
"loss": 0.314,
|
2050 |
+
"step": 279
|
2051 |
+
},
|
2052 |
+
{
|
2053 |
+
"epoch": 0.17516421645292463,
|
2054 |
+
"grad_norm": 0.40990278124809265,
|
2055 |
+
"learning_rate": 0.00010756302521008403,
|
2056 |
+
"loss": 0.192,
|
2057 |
+
"step": 280
|
2058 |
+
},
|
2059 |
+
{
|
2060 |
+
"epoch": 0.17578980294025648,
|
2061 |
+
"grad_norm": 0.9555610418319702,
|
2062 |
+
"learning_rate": 0.00010722689075630252,
|
2063 |
+
"loss": 0.3646,
|
2064 |
+
"step": 281
|
2065 |
+
},
|
2066 |
+
{
|
2067 |
+
"epoch": 0.17641538942758836,
|
2068 |
+
"grad_norm": 0.7370548844337463,
|
2069 |
+
"learning_rate": 0.000106890756302521,
|
2070 |
+
"loss": 0.8997,
|
2071 |
+
"step": 282
|
2072 |
+
},
|
2073 |
+
{
|
2074 |
+
"epoch": 0.17704097591492024,
|
2075 |
+
"grad_norm": 1.0178982019424438,
|
2076 |
+
"learning_rate": 0.0001065546218487395,
|
2077 |
+
"loss": 0.986,
|
2078 |
+
"step": 283
|
2079 |
+
},
|
2080 |
+
{
|
2081 |
+
"epoch": 0.17766656240225212,
|
2082 |
+
"grad_norm": 0.41388389468193054,
|
2083 |
+
"learning_rate": 0.00010621848739495799,
|
2084 |
+
"loss": 0.2069,
|
2085 |
+
"step": 284
|
2086 |
+
},
|
2087 |
+
{
|
2088 |
+
"epoch": 0.17829214888958397,
|
2089 |
+
"grad_norm": 0.7140624523162842,
|
2090 |
+
"learning_rate": 0.00010588235294117647,
|
2091 |
+
"loss": 0.4852,
|
2092 |
+
"step": 285
|
2093 |
+
},
|
2094 |
+
{
|
2095 |
+
"epoch": 0.17891773537691585,
|
2096 |
+
"grad_norm": 0.7758356332778931,
|
2097 |
+
"learning_rate": 0.00010554621848739496,
|
2098 |
+
"loss": 0.3943,
|
2099 |
+
"step": 286
|
2100 |
+
},
|
2101 |
+
{
|
2102 |
+
"epoch": 0.17954332186424773,
|
2103 |
+
"grad_norm": 1.4193260669708252,
|
2104 |
+
"learning_rate": 0.00010521008403361346,
|
2105 |
+
"loss": 0.6412,
|
2106 |
+
"step": 287
|
2107 |
+
},
|
2108 |
+
{
|
2109 |
+
"epoch": 0.18016890835157962,
|
2110 |
+
"grad_norm": 0.7264838814735413,
|
2111 |
+
"learning_rate": 0.00010487394957983194,
|
2112 |
+
"loss": 0.7834,
|
2113 |
+
"step": 288
|
2114 |
+
},
|
2115 |
+
{
|
2116 |
+
"epoch": 0.18079449483891147,
|
2117 |
+
"grad_norm": 2.4300973415374756,
|
2118 |
+
"learning_rate": 0.00010453781512605043,
|
2119 |
+
"loss": 0.7462,
|
2120 |
+
"step": 289
|
2121 |
+
},
|
2122 |
+
{
|
2123 |
+
"epoch": 0.18142008132624335,
|
2124 |
+
"grad_norm": 1.033916711807251,
|
2125 |
+
"learning_rate": 0.00010420168067226892,
|
2126 |
+
"loss": 0.5241,
|
2127 |
+
"step": 290
|
2128 |
+
},
|
2129 |
+
{
|
2130 |
+
"epoch": 0.18204566781357523,
|
2131 |
+
"grad_norm": 0.5583767294883728,
|
2132 |
+
"learning_rate": 0.00010386554621848741,
|
2133 |
+
"loss": 0.7815,
|
2134 |
+
"step": 291
|
2135 |
+
},
|
2136 |
+
{
|
2137 |
+
"epoch": 0.1826712543009071,
|
2138 |
+
"grad_norm": 0.7440481781959534,
|
2139 |
+
"learning_rate": 0.0001035294117647059,
|
2140 |
+
"loss": 0.4674,
|
2141 |
+
"step": 292
|
2142 |
+
},
|
2143 |
+
{
|
2144 |
+
"epoch": 0.18329684078823896,
|
2145 |
+
"grad_norm": 4.230656147003174,
|
2146 |
+
"learning_rate": 0.00010319327731092439,
|
2147 |
+
"loss": 0.5219,
|
2148 |
+
"step": 293
|
2149 |
+
},
|
2150 |
+
{
|
2151 |
+
"epoch": 0.18392242727557084,
|
2152 |
+
"grad_norm": 0.6165269017219543,
|
2153 |
+
"learning_rate": 0.00010285714285714286,
|
2154 |
+
"loss": 0.3274,
|
2155 |
+
"step": 294
|
2156 |
+
},
|
2157 |
+
{
|
2158 |
+
"epoch": 0.18454801376290272,
|
2159 |
+
"grad_norm": 0.5844498872756958,
|
2160 |
+
"learning_rate": 0.00010252100840336134,
|
2161 |
+
"loss": 0.3719,
|
2162 |
+
"step": 295
|
2163 |
+
},
|
2164 |
+
{
|
2165 |
+
"epoch": 0.1851736002502346,
|
2166 |
+
"grad_norm": 0.9936206936836243,
|
2167 |
+
"learning_rate": 0.00010218487394957983,
|
2168 |
+
"loss": 1.0453,
|
2169 |
+
"step": 296
|
2170 |
+
},
|
2171 |
+
{
|
2172 |
+
"epoch": 0.18579918673756646,
|
2173 |
+
"grad_norm": 1.749831199645996,
|
2174 |
+
"learning_rate": 0.00010184873949579831,
|
2175 |
+
"loss": 0.6634,
|
2176 |
+
"step": 297
|
2177 |
+
},
|
2178 |
+
{
|
2179 |
+
"epoch": 0.18642477322489834,
|
2180 |
+
"grad_norm": 0.4740132689476013,
|
2181 |
+
"learning_rate": 0.0001015126050420168,
|
2182 |
+
"loss": 0.2901,
|
2183 |
+
"step": 298
|
2184 |
+
},
|
2185 |
+
{
|
2186 |
+
"epoch": 0.18705035971223022,
|
2187 |
+
"grad_norm": 0.664300262928009,
|
2188 |
+
"learning_rate": 0.0001011764705882353,
|
2189 |
+
"loss": 0.5869,
|
2190 |
+
"step": 299
|
2191 |
+
},
|
2192 |
+
{
|
2193 |
+
"epoch": 0.1876759461995621,
|
2194 |
+
"grad_norm": 0.7400941252708435,
|
2195 |
+
"learning_rate": 0.00010084033613445378,
|
2196 |
+
"loss": 0.7881,
|
2197 |
+
"step": 300
|
2198 |
+
},
|
2199 |
+
{
|
2200 |
+
"epoch": 0.1876759461995621,
|
2201 |
+
"eval_loss": 0.7877693772315979,
|
2202 |
+
"eval_runtime": 43.5162,
|
2203 |
+
"eval_samples_per_second": 5.883,
|
2204 |
+
"eval_steps_per_second": 2.941,
|
2205 |
+
"step": 300
|
2206 |
+
},
|
2207 |
+
{
|
2208 |
+
"epoch": 0.18830153268689395,
|
2209 |
+
"grad_norm": 0.6142858862876892,
|
2210 |
+
"learning_rate": 0.00010050420168067227,
|
2211 |
+
"loss": 0.3808,
|
2212 |
+
"step": 301
|
2213 |
+
},
|
2214 |
+
{
|
2215 |
+
"epoch": 0.18892711917422583,
|
2216 |
+
"grad_norm": 1.991969347000122,
|
2217 |
+
"learning_rate": 0.00010016806722689076,
|
2218 |
+
"loss": 0.7035,
|
2219 |
+
"step": 302
|
2220 |
+
},
|
2221 |
+
{
|
2222 |
+
"epoch": 0.1895527056615577,
|
2223 |
+
"grad_norm": 0.6220730543136597,
|
2224 |
+
"learning_rate": 9.983193277310925e-05,
|
2225 |
+
"loss": 0.2548,
|
2226 |
+
"step": 303
|
2227 |
+
},
|
2228 |
+
{
|
2229 |
+
"epoch": 0.1901782921488896,
|
2230 |
+
"grad_norm": 0.6476833820343018,
|
2231 |
+
"learning_rate": 9.949579831932774e-05,
|
2232 |
+
"loss": 0.3569,
|
2233 |
+
"step": 304
|
2234 |
+
},
|
2235 |
+
{
|
2236 |
+
"epoch": 0.19080387863622145,
|
2237 |
+
"grad_norm": 0.7133951783180237,
|
2238 |
+
"learning_rate": 9.915966386554623e-05,
|
2239 |
+
"loss": 0.4744,
|
2240 |
+
"step": 305
|
2241 |
+
},
|
2242 |
+
{
|
2243 |
+
"epoch": 0.19142946512355333,
|
2244 |
+
"grad_norm": 0.6500736474990845,
|
2245 |
+
"learning_rate": 9.882352941176471e-05,
|
2246 |
+
"loss": 0.4653,
|
2247 |
+
"step": 306
|
2248 |
+
},
|
2249 |
+
{
|
2250 |
+
"epoch": 0.1920550516108852,
|
2251 |
+
"grad_norm": 1.1231927871704102,
|
2252 |
+
"learning_rate": 9.848739495798321e-05,
|
2253 |
+
"loss": 0.818,
|
2254 |
+
"step": 307
|
2255 |
+
},
|
2256 |
+
{
|
2257 |
+
"epoch": 0.1926806380982171,
|
2258 |
+
"grad_norm": 0.8654798865318298,
|
2259 |
+
"learning_rate": 9.815126050420168e-05,
|
2260 |
+
"loss": 0.7065,
|
2261 |
+
"step": 308
|
2262 |
+
},
|
2263 |
+
{
|
2264 |
+
"epoch": 0.19330622458554894,
|
2265 |
+
"grad_norm": 0.45660969614982605,
|
2266 |
+
"learning_rate": 9.781512605042017e-05,
|
2267 |
+
"loss": 0.2412,
|
2268 |
+
"step": 309
|
2269 |
+
},
|
2270 |
+
{
|
2271 |
+
"epoch": 0.19393181107288082,
|
2272 |
+
"grad_norm": 0.9538519978523254,
|
2273 |
+
"learning_rate": 9.747899159663865e-05,
|
2274 |
+
"loss": 1.3428,
|
2275 |
+
"step": 310
|
2276 |
+
},
|
2277 |
+
{
|
2278 |
+
"epoch": 0.1945573975602127,
|
2279 |
+
"grad_norm": 0.596633791923523,
|
2280 |
+
"learning_rate": 9.714285714285715e-05,
|
2281 |
+
"loss": 0.5119,
|
2282 |
+
"step": 311
|
2283 |
+
},
|
2284 |
+
{
|
2285 |
+
"epoch": 0.19518298404754458,
|
2286 |
+
"grad_norm": 0.5247074365615845,
|
2287 |
+
"learning_rate": 9.680672268907564e-05,
|
2288 |
+
"loss": 0.6413,
|
2289 |
+
"step": 312
|
2290 |
+
},
|
2291 |
+
{
|
2292 |
+
"epoch": 0.19580857053487644,
|
2293 |
+
"grad_norm": 0.7713050246238708,
|
2294 |
+
"learning_rate": 9.647058823529412e-05,
|
2295 |
+
"loss": 0.49,
|
2296 |
+
"step": 313
|
2297 |
+
},
|
2298 |
+
{
|
2299 |
+
"epoch": 0.19643415702220832,
|
2300 |
+
"grad_norm": 0.6971513628959656,
|
2301 |
+
"learning_rate": 9.613445378151261e-05,
|
2302 |
+
"loss": 0.6505,
|
2303 |
+
"step": 314
|
2304 |
+
},
|
2305 |
+
{
|
2306 |
+
"epoch": 0.1970597435095402,
|
2307 |
+
"grad_norm": 0.5454917550086975,
|
2308 |
+
"learning_rate": 9.579831932773111e-05,
|
2309 |
+
"loss": 0.7018,
|
2310 |
+
"step": 315
|
2311 |
+
},
|
2312 |
+
{
|
2313 |
+
"epoch": 0.19768532999687208,
|
2314 |
+
"grad_norm": 0.8349499702453613,
|
2315 |
+
"learning_rate": 9.546218487394959e-05,
|
2316 |
+
"loss": 0.3179,
|
2317 |
+
"step": 316
|
2318 |
+
},
|
2319 |
+
{
|
2320 |
+
"epoch": 0.19831091648420393,
|
2321 |
+
"grad_norm": 0.5682560801506042,
|
2322 |
+
"learning_rate": 9.512605042016806e-05,
|
2323 |
+
"loss": 0.4003,
|
2324 |
+
"step": 317
|
2325 |
+
},
|
2326 |
+
{
|
2327 |
+
"epoch": 0.1989365029715358,
|
2328 |
+
"grad_norm": 0.5094739198684692,
|
2329 |
+
"learning_rate": 9.478991596638655e-05,
|
2330 |
+
"loss": 0.313,
|
2331 |
+
"step": 318
|
2332 |
+
},
|
2333 |
+
{
|
2334 |
+
"epoch": 0.1995620894588677,
|
2335 |
+
"grad_norm": 1.7074236869812012,
|
2336 |
+
"learning_rate": 9.445378151260505e-05,
|
2337 |
+
"loss": 0.9912,
|
2338 |
+
"step": 319
|
2339 |
+
},
|
2340 |
+
{
|
2341 |
+
"epoch": 0.20018767594619957,
|
2342 |
+
"grad_norm": 1.1477283239364624,
|
2343 |
+
"learning_rate": 9.411764705882353e-05,
|
2344 |
+
"loss": 0.851,
|
2345 |
+
"step": 320
|
2346 |
+
},
|
2347 |
+
{
|
2348 |
+
"epoch": 0.20081326243353143,
|
2349 |
+
"grad_norm": 0.6616579294204712,
|
2350 |
+
"learning_rate": 9.378151260504202e-05,
|
2351 |
+
"loss": 0.4844,
|
2352 |
+
"step": 321
|
2353 |
+
},
|
2354 |
+
{
|
2355 |
+
"epoch": 0.2014388489208633,
|
2356 |
+
"grad_norm": 1.0401920080184937,
|
2357 |
+
"learning_rate": 9.34453781512605e-05,
|
2358 |
+
"loss": 0.5421,
|
2359 |
+
"step": 322
|
2360 |
+
},
|
2361 |
+
{
|
2362 |
+
"epoch": 0.2020644354081952,
|
2363 |
+
"grad_norm": 0.729664146900177,
|
2364 |
+
"learning_rate": 9.3109243697479e-05,
|
2365 |
+
"loss": 0.6632,
|
2366 |
+
"step": 323
|
2367 |
+
},
|
2368 |
+
{
|
2369 |
+
"epoch": 0.20269002189552707,
|
2370 |
+
"grad_norm": 0.6752575635910034,
|
2371 |
+
"learning_rate": 9.277310924369749e-05,
|
2372 |
+
"loss": 0.4352,
|
2373 |
+
"step": 324
|
2374 |
+
},
|
2375 |
+
{
|
2376 |
+
"epoch": 0.20331560838285892,
|
2377 |
+
"grad_norm": 0.7963948249816895,
|
2378 |
+
"learning_rate": 9.243697478991598e-05,
|
2379 |
+
"loss": 0.7614,
|
2380 |
+
"step": 325
|
2381 |
+
},
|
2382 |
+
{
|
2383 |
+
"epoch": 0.20331560838285892,
|
2384 |
+
"eval_loss": 0.771190881729126,
|
2385 |
+
"eval_runtime": 43.551,
|
2386 |
+
"eval_samples_per_second": 5.878,
|
2387 |
+
"eval_steps_per_second": 2.939,
|
2388 |
+
"step": 325
|
2389 |
+
},
|
2390 |
+
{
|
2391 |
+
"epoch": 0.2039411948701908,
|
2392 |
+
"grad_norm": 0.7778791189193726,
|
2393 |
+
"learning_rate": 9.210084033613445e-05,
|
2394 |
+
"loss": 0.7251,
|
2395 |
+
"step": 326
|
2396 |
+
},
|
2397 |
+
{
|
2398 |
+
"epoch": 0.20456678135752268,
|
2399 |
+
"grad_norm": 3.0929737091064453,
|
2400 |
+
"learning_rate": 9.176470588235295e-05,
|
2401 |
+
"loss": 0.5375,
|
2402 |
+
"step": 327
|
2403 |
+
},
|
2404 |
+
{
|
2405 |
+
"epoch": 0.20519236784485456,
|
2406 |
+
"grad_norm": 0.6188391447067261,
|
2407 |
+
"learning_rate": 9.142857142857143e-05,
|
2408 |
+
"loss": 0.4007,
|
2409 |
+
"step": 328
|
2410 |
+
},
|
2411 |
+
{
|
2412 |
+
"epoch": 0.20581795433218641,
|
2413 |
+
"grad_norm": 0.9423925876617432,
|
2414 |
+
"learning_rate": 9.109243697478992e-05,
|
2415 |
+
"loss": 0.5059,
|
2416 |
+
"step": 329
|
2417 |
+
},
|
2418 |
+
{
|
2419 |
+
"epoch": 0.2064435408195183,
|
2420 |
+
"grad_norm": 0.506572425365448,
|
2421 |
+
"learning_rate": 9.07563025210084e-05,
|
2422 |
+
"loss": 0.2794,
|
2423 |
+
"step": 330
|
2424 |
+
},
|
2425 |
+
{
|
2426 |
+
"epoch": 0.20706912730685018,
|
2427 |
+
"grad_norm": 1.7139545679092407,
|
2428 |
+
"learning_rate": 9.04201680672269e-05,
|
2429 |
+
"loss": 0.5984,
|
2430 |
+
"step": 331
|
2431 |
+
},
|
2432 |
+
{
|
2433 |
+
"epoch": 0.20769471379418206,
|
2434 |
+
"grad_norm": 0.5540574789047241,
|
2435 |
+
"learning_rate": 9.008403361344539e-05,
|
2436 |
+
"loss": 0.323,
|
2437 |
+
"step": 332
|
2438 |
+
},
|
2439 |
+
{
|
2440 |
+
"epoch": 0.2083203002815139,
|
2441 |
+
"grad_norm": 0.6909454464912415,
|
2442 |
+
"learning_rate": 8.974789915966387e-05,
|
2443 |
+
"loss": 0.5399,
|
2444 |
+
"step": 333
|
2445 |
+
},
|
2446 |
+
{
|
2447 |
+
"epoch": 0.2089458867688458,
|
2448 |
+
"grad_norm": 0.7409022450447083,
|
2449 |
+
"learning_rate": 8.941176470588236e-05,
|
2450 |
+
"loss": 0.4251,
|
2451 |
+
"step": 334
|
2452 |
+
},
|
2453 |
+
{
|
2454 |
+
"epoch": 0.20957147325617767,
|
2455 |
+
"grad_norm": 0.6636312007904053,
|
2456 |
+
"learning_rate": 8.907563025210084e-05,
|
2457 |
+
"loss": 0.4021,
|
2458 |
+
"step": 335
|
2459 |
+
},
|
2460 |
+
{
|
2461 |
+
"epoch": 0.21019705974350955,
|
2462 |
+
"grad_norm": 0.5426271557807922,
|
2463 |
+
"learning_rate": 8.873949579831933e-05,
|
2464 |
+
"loss": 0.2095,
|
2465 |
+
"step": 336
|
2466 |
+
},
|
2467 |
+
{
|
2468 |
+
"epoch": 0.2108226462308414,
|
2469 |
+
"grad_norm": 0.8870647549629211,
|
2470 |
+
"learning_rate": 8.840336134453782e-05,
|
2471 |
+
"loss": 0.5773,
|
2472 |
+
"step": 337
|
2473 |
+
},
|
2474 |
+
{
|
2475 |
+
"epoch": 0.21144823271817328,
|
2476 |
+
"grad_norm": 0.5508524179458618,
|
2477 |
+
"learning_rate": 8.80672268907563e-05,
|
2478 |
+
"loss": 0.6744,
|
2479 |
+
"step": 338
|
2480 |
+
},
|
2481 |
+
{
|
2482 |
+
"epoch": 0.21207381920550517,
|
2483 |
+
"grad_norm": 1.6577738523483276,
|
2484 |
+
"learning_rate": 8.77310924369748e-05,
|
2485 |
+
"loss": 1.1134,
|
2486 |
+
"step": 339
|
2487 |
+
},
|
2488 |
+
{
|
2489 |
+
"epoch": 0.21269940569283705,
|
2490 |
+
"grad_norm": 3.218395233154297,
|
2491 |
+
"learning_rate": 8.739495798319329e-05,
|
2492 |
+
"loss": 0.5932,
|
2493 |
+
"step": 340
|
2494 |
+
},
|
2495 |
+
{
|
2496 |
+
"epoch": 0.2133249921801689,
|
2497 |
+
"grad_norm": 0.5119672417640686,
|
2498 |
+
"learning_rate": 8.705882352941177e-05,
|
2499 |
+
"loss": 0.1831,
|
2500 |
+
"step": 341
|
2501 |
+
},
|
2502 |
+
{
|
2503 |
+
"epoch": 0.21395057866750078,
|
2504 |
+
"grad_norm": 0.4874535799026489,
|
2505 |
+
"learning_rate": 8.672268907563026e-05,
|
2506 |
+
"loss": 0.485,
|
2507 |
+
"step": 342
|
2508 |
+
},
|
2509 |
+
{
|
2510 |
+
"epoch": 0.21457616515483266,
|
2511 |
+
"grad_norm": 0.6597093939781189,
|
2512 |
+
"learning_rate": 8.638655462184874e-05,
|
2513 |
+
"loss": 0.3588,
|
2514 |
+
"step": 343
|
2515 |
+
},
|
2516 |
+
{
|
2517 |
+
"epoch": 0.21520175164216454,
|
2518 |
+
"grad_norm": 1.1764620542526245,
|
2519 |
+
"learning_rate": 8.605042016806724e-05,
|
2520 |
+
"loss": 1.8765,
|
2521 |
+
"step": 344
|
2522 |
+
},
|
2523 |
+
{
|
2524 |
+
"epoch": 0.2158273381294964,
|
2525 |
+
"grad_norm": 0.6894935369491577,
|
2526 |
+
"learning_rate": 8.571428571428571e-05,
|
2527 |
+
"loss": 0.5355,
|
2528 |
+
"step": 345
|
2529 |
+
},
|
2530 |
+
{
|
2531 |
+
"epoch": 0.21645292461682827,
|
2532 |
+
"grad_norm": 0.5896294116973877,
|
2533 |
+
"learning_rate": 8.53781512605042e-05,
|
2534 |
+
"loss": 0.494,
|
2535 |
+
"step": 346
|
2536 |
+
},
|
2537 |
+
{
|
2538 |
+
"epoch": 0.21707851110416015,
|
2539 |
+
"grad_norm": 0.6212694048881531,
|
2540 |
+
"learning_rate": 8.50420168067227e-05,
|
2541 |
+
"loss": 0.5721,
|
2542 |
+
"step": 347
|
2543 |
+
},
|
2544 |
+
{
|
2545 |
+
"epoch": 0.21770409759149204,
|
2546 |
+
"grad_norm": 0.5058571100234985,
|
2547 |
+
"learning_rate": 8.470588235294118e-05,
|
2548 |
+
"loss": 0.5051,
|
2549 |
+
"step": 348
|
2550 |
+
},
|
2551 |
+
{
|
2552 |
+
"epoch": 0.2183296840788239,
|
2553 |
+
"grad_norm": 0.5089401006698608,
|
2554 |
+
"learning_rate": 8.436974789915967e-05,
|
2555 |
+
"loss": 0.3794,
|
2556 |
+
"step": 349
|
2557 |
+
},
|
2558 |
+
{
|
2559 |
+
"epoch": 0.21895527056615577,
|
2560 |
+
"grad_norm": 6.416032314300537,
|
2561 |
+
"learning_rate": 8.403361344537815e-05,
|
2562 |
+
"loss": 0.5026,
|
2563 |
+
"step": 350
|
2564 |
+
},
|
2565 |
+
{
|
2566 |
+
"epoch": 0.21895527056615577,
|
2567 |
+
"eval_loss": 0.7647964954376221,
|
2568 |
+
"eval_runtime": 43.4854,
|
2569 |
+
"eval_samples_per_second": 5.887,
|
2570 |
+
"eval_steps_per_second": 2.944,
|
2571 |
+
"step": 350
|
2572 |
+
},
|
2573 |
+
{
|
2574 |
+
"epoch": 0.21958085705348765,
|
2575 |
+
"grad_norm": 0.8862031698226929,
|
2576 |
+
"learning_rate": 8.369747899159664e-05,
|
2577 |
+
"loss": 0.5003,
|
2578 |
+
"step": 351
|
2579 |
+
},
|
2580 |
+
{
|
2581 |
+
"epoch": 0.22020644354081953,
|
2582 |
+
"grad_norm": 1.3196977376937866,
|
2583 |
+
"learning_rate": 8.336134453781514e-05,
|
2584 |
+
"loss": 0.4573,
|
2585 |
+
"step": 352
|
2586 |
+
},
|
2587 |
+
{
|
2588 |
+
"epoch": 0.22083203002815138,
|
2589 |
+
"grad_norm": 0.4763634204864502,
|
2590 |
+
"learning_rate": 8.302521008403362e-05,
|
2591 |
+
"loss": 0.3987,
|
2592 |
+
"step": 353
|
2593 |
+
},
|
2594 |
+
{
|
2595 |
+
"epoch": 0.22145761651548326,
|
2596 |
+
"grad_norm": 0.45634883642196655,
|
2597 |
+
"learning_rate": 8.26890756302521e-05,
|
2598 |
+
"loss": 0.2064,
|
2599 |
+
"step": 354
|
2600 |
+
},
|
2601 |
+
{
|
2602 |
+
"epoch": 0.22208320300281514,
|
2603 |
+
"grad_norm": 0.443393737077713,
|
2604 |
+
"learning_rate": 8.23529411764706e-05,
|
2605 |
+
"loss": 0.2308,
|
2606 |
+
"step": 355
|
2607 |
+
},
|
2608 |
+
{
|
2609 |
+
"epoch": 0.22270878949014702,
|
2610 |
+
"grad_norm": 1.135941505432129,
|
2611 |
+
"learning_rate": 8.201680672268908e-05,
|
2612 |
+
"loss": 0.8731,
|
2613 |
+
"step": 356
|
2614 |
+
},
|
2615 |
+
{
|
2616 |
+
"epoch": 0.22333437597747888,
|
2617 |
+
"grad_norm": 0.6853610873222351,
|
2618 |
+
"learning_rate": 8.168067226890757e-05,
|
2619 |
+
"loss": 0.5563,
|
2620 |
+
"step": 357
|
2621 |
+
},
|
2622 |
+
{
|
2623 |
+
"epoch": 0.22395996246481076,
|
2624 |
+
"grad_norm": 0.6356902718544006,
|
2625 |
+
"learning_rate": 8.134453781512605e-05,
|
2626 |
+
"loss": 0.4265,
|
2627 |
+
"step": 358
|
2628 |
+
},
|
2629 |
+
{
|
2630 |
+
"epoch": 0.22458554895214264,
|
2631 |
+
"grad_norm": 0.6331340074539185,
|
2632 |
+
"learning_rate": 8.100840336134454e-05,
|
2633 |
+
"loss": 0.3293,
|
2634 |
+
"step": 359
|
2635 |
+
},
|
2636 |
+
{
|
2637 |
+
"epoch": 0.22521113543947452,
|
2638 |
+
"grad_norm": 0.8068905472755432,
|
2639 |
+
"learning_rate": 8.067226890756304e-05,
|
2640 |
+
"loss": 1.2136,
|
2641 |
+
"step": 360
|
2642 |
+
},
|
2643 |
+
{
|
2644 |
+
"epoch": 0.22583672192680637,
|
2645 |
+
"grad_norm": 0.6827020049095154,
|
2646 |
+
"learning_rate": 8.033613445378152e-05,
|
2647 |
+
"loss": 0.8519,
|
2648 |
+
"step": 361
|
2649 |
+
},
|
2650 |
+
{
|
2651 |
+
"epoch": 0.22646230841413825,
|
2652 |
+
"grad_norm": 0.829730749130249,
|
2653 |
+
"learning_rate": 8e-05,
|
2654 |
+
"loss": 0.6237,
|
2655 |
+
"step": 362
|
2656 |
+
},
|
2657 |
+
{
|
2658 |
+
"epoch": 0.22708789490147013,
|
2659 |
+
"grad_norm": 0.5221096873283386,
|
2660 |
+
"learning_rate": 7.966386554621849e-05,
|
2661 |
+
"loss": 0.3099,
|
2662 |
+
"step": 363
|
2663 |
+
},
|
2664 |
+
{
|
2665 |
+
"epoch": 0.227713481388802,
|
2666 |
+
"grad_norm": 0.6234191060066223,
|
2667 |
+
"learning_rate": 7.932773109243698e-05,
|
2668 |
+
"loss": 0.9356,
|
2669 |
+
"step": 364
|
2670 |
+
},
|
2671 |
+
{
|
2672 |
+
"epoch": 0.22833906787613387,
|
2673 |
+
"grad_norm": 0.5766564607620239,
|
2674 |
+
"learning_rate": 7.899159663865546e-05,
|
2675 |
+
"loss": 0.2529,
|
2676 |
+
"step": 365
|
2677 |
+
},
|
2678 |
+
{
|
2679 |
+
"epoch": 0.22896465436346575,
|
2680 |
+
"grad_norm": 0.758171558380127,
|
2681 |
+
"learning_rate": 7.865546218487395e-05,
|
2682 |
+
"loss": 0.7577,
|
2683 |
+
"step": 366
|
2684 |
+
},
|
2685 |
+
{
|
2686 |
+
"epoch": 0.22959024085079763,
|
2687 |
+
"grad_norm": 0.6313957571983337,
|
2688 |
+
"learning_rate": 7.831932773109243e-05,
|
2689 |
+
"loss": 0.6219,
|
2690 |
+
"step": 367
|
2691 |
+
},
|
2692 |
+
{
|
2693 |
+
"epoch": 0.2302158273381295,
|
2694 |
+
"grad_norm": 0.7843011617660522,
|
2695 |
+
"learning_rate": 7.798319327731093e-05,
|
2696 |
+
"loss": 0.6617,
|
2697 |
+
"step": 368
|
2698 |
+
},
|
2699 |
+
{
|
2700 |
+
"epoch": 0.23084141382546136,
|
2701 |
+
"grad_norm": 0.9671229124069214,
|
2702 |
+
"learning_rate": 7.764705882352942e-05,
|
2703 |
+
"loss": 0.7156,
|
2704 |
+
"step": 369
|
2705 |
+
},
|
2706 |
+
{
|
2707 |
+
"epoch": 0.23146700031279324,
|
2708 |
+
"grad_norm": 0.663546085357666,
|
2709 |
+
"learning_rate": 7.73109243697479e-05,
|
2710 |
+
"loss": 0.4462,
|
2711 |
+
"step": 370
|
2712 |
+
},
|
2713 |
+
{
|
2714 |
+
"epoch": 0.23209258680012512,
|
2715 |
+
"grad_norm": 0.6233255863189697,
|
2716 |
+
"learning_rate": 7.697478991596639e-05,
|
2717 |
+
"loss": 0.5534,
|
2718 |
+
"step": 371
|
2719 |
+
},
|
2720 |
+
{
|
2721 |
+
"epoch": 0.232718173287457,
|
2722 |
+
"grad_norm": 2.0895440578460693,
|
2723 |
+
"learning_rate": 7.663865546218489e-05,
|
2724 |
+
"loss": 0.7289,
|
2725 |
+
"step": 372
|
2726 |
+
},
|
2727 |
+
{
|
2728 |
+
"epoch": 0.23334375977478886,
|
2729 |
+
"grad_norm": 0.6122156381607056,
|
2730 |
+
"learning_rate": 7.630252100840336e-05,
|
2731 |
+
"loss": 0.3891,
|
2732 |
+
"step": 373
|
2733 |
+
},
|
2734 |
+
{
|
2735 |
+
"epoch": 0.23396934626212074,
|
2736 |
+
"grad_norm": 0.5940058827400208,
|
2737 |
+
"learning_rate": 7.596638655462185e-05,
|
2738 |
+
"loss": 0.3038,
|
2739 |
+
"step": 374
|
2740 |
+
},
|
2741 |
+
{
|
2742 |
+
"epoch": 0.23459493274945262,
|
2743 |
+
"grad_norm": 0.35755977034568787,
|
2744 |
+
"learning_rate": 7.563025210084033e-05,
|
2745 |
+
"loss": 0.2848,
|
2746 |
+
"step": 375
|
2747 |
+
},
|
2748 |
+
{
|
2749 |
+
"epoch": 0.23459493274945262,
|
2750 |
+
"eval_loss": 0.7521110773086548,
|
2751 |
+
"eval_runtime": 43.5299,
|
2752 |
+
"eval_samples_per_second": 5.881,
|
2753 |
+
"eval_steps_per_second": 2.941,
|
2754 |
+
"step": 375
|
2755 |
+
},
|
2756 |
+
{
|
2757 |
+
"epoch": 0.2352205192367845,
|
2758 |
+
"grad_norm": 0.8450719118118286,
|
2759 |
+
"learning_rate": 7.529411764705883e-05,
|
2760 |
+
"loss": 0.5348,
|
2761 |
+
"step": 376
|
2762 |
+
},
|
2763 |
+
{
|
2764 |
+
"epoch": 0.23584610572411635,
|
2765 |
+
"grad_norm": 0.9100202918052673,
|
2766 |
+
"learning_rate": 7.495798319327732e-05,
|
2767 |
+
"loss": 0.8178,
|
2768 |
+
"step": 377
|
2769 |
+
},
|
2770 |
+
{
|
2771 |
+
"epoch": 0.23647169221144823,
|
2772 |
+
"grad_norm": 0.5748711228370667,
|
2773 |
+
"learning_rate": 7.46218487394958e-05,
|
2774 |
+
"loss": 0.778,
|
2775 |
+
"step": 378
|
2776 |
+
},
|
2777 |
+
{
|
2778 |
+
"epoch": 0.2370972786987801,
|
2779 |
+
"grad_norm": 0.5675060153007507,
|
2780 |
+
"learning_rate": 7.428571428571429e-05,
|
2781 |
+
"loss": 0.8042,
|
2782 |
+
"step": 379
|
2783 |
+
},
|
2784 |
+
{
|
2785 |
+
"epoch": 0.237722865186112,
|
2786 |
+
"grad_norm": 6.2747392654418945,
|
2787 |
+
"learning_rate": 7.394957983193279e-05,
|
2788 |
+
"loss": 1.4173,
|
2789 |
+
"step": 380
|
2790 |
+
},
|
2791 |
+
{
|
2792 |
+
"epoch": 0.23834845167344385,
|
2793 |
+
"grad_norm": 0.6252509355545044,
|
2794 |
+
"learning_rate": 7.361344537815127e-05,
|
2795 |
+
"loss": 0.5095,
|
2796 |
+
"step": 381
|
2797 |
+
},
|
2798 |
+
{
|
2799 |
+
"epoch": 0.23897403816077573,
|
2800 |
+
"grad_norm": 1.0525410175323486,
|
2801 |
+
"learning_rate": 7.327731092436974e-05,
|
2802 |
+
"loss": 1.1774,
|
2803 |
+
"step": 382
|
2804 |
+
},
|
2805 |
+
{
|
2806 |
+
"epoch": 0.2395996246481076,
|
2807 |
+
"grad_norm": 0.505670428276062,
|
2808 |
+
"learning_rate": 7.294117647058823e-05,
|
2809 |
+
"loss": 0.7603,
|
2810 |
+
"step": 383
|
2811 |
+
},
|
2812 |
+
{
|
2813 |
+
"epoch": 0.2402252111354395,
|
2814 |
+
"grad_norm": 0.5476568341255188,
|
2815 |
+
"learning_rate": 7.260504201680673e-05,
|
2816 |
+
"loss": 0.3354,
|
2817 |
+
"step": 384
|
2818 |
+
},
|
2819 |
+
{
|
2820 |
+
"epoch": 0.24085079762277134,
|
2821 |
+
"grad_norm": 0.687854528427124,
|
2822 |
+
"learning_rate": 7.226890756302521e-05,
|
2823 |
+
"loss": 0.6306,
|
2824 |
+
"step": 385
|
2825 |
+
},
|
2826 |
+
{
|
2827 |
+
"epoch": 0.24147638411010322,
|
2828 |
+
"grad_norm": 1.3373991250991821,
|
2829 |
+
"learning_rate": 7.19327731092437e-05,
|
2830 |
+
"loss": 0.5736,
|
2831 |
+
"step": 386
|
2832 |
+
},
|
2833 |
+
{
|
2834 |
+
"epoch": 0.2421019705974351,
|
2835 |
+
"grad_norm": 0.5465985536575317,
|
2836 |
+
"learning_rate": 7.159663865546218e-05,
|
2837 |
+
"loss": 0.2859,
|
2838 |
+
"step": 387
|
2839 |
+
},
|
2840 |
+
{
|
2841 |
+
"epoch": 0.24272755708476698,
|
2842 |
+
"grad_norm": 0.6637946963310242,
|
2843 |
+
"learning_rate": 7.126050420168068e-05,
|
2844 |
+
"loss": 0.5948,
|
2845 |
+
"step": 388
|
2846 |
+
},
|
2847 |
+
{
|
2848 |
+
"epoch": 0.24335314357209883,
|
2849 |
+
"grad_norm": 0.637915313243866,
|
2850 |
+
"learning_rate": 7.092436974789917e-05,
|
2851 |
+
"loss": 0.3947,
|
2852 |
+
"step": 389
|
2853 |
+
},
|
2854 |
+
{
|
2855 |
+
"epoch": 0.24397873005943072,
|
2856 |
+
"grad_norm": 0.8073198795318604,
|
2857 |
+
"learning_rate": 7.058823529411765e-05,
|
2858 |
+
"loss": 0.5006,
|
2859 |
+
"step": 390
|
2860 |
+
},
|
2861 |
+
{
|
2862 |
+
"epoch": 0.2446043165467626,
|
2863 |
+
"grad_norm": 0.7423315644264221,
|
2864 |
+
"learning_rate": 7.025210084033613e-05,
|
2865 |
+
"loss": 0.5209,
|
2866 |
+
"step": 391
|
2867 |
+
},
|
2868 |
+
{
|
2869 |
+
"epoch": 0.24522990303409448,
|
2870 |
+
"grad_norm": 0.6418082118034363,
|
2871 |
+
"learning_rate": 6.991596638655463e-05,
|
2872 |
+
"loss": 0.3793,
|
2873 |
+
"step": 392
|
2874 |
+
},
|
2875 |
+
{
|
2876 |
+
"epoch": 0.24585548952142633,
|
2877 |
+
"grad_norm": 1.072240948677063,
|
2878 |
+
"learning_rate": 6.957983193277311e-05,
|
2879 |
+
"loss": 0.3656,
|
2880 |
+
"step": 393
|
2881 |
+
},
|
2882 |
+
{
|
2883 |
+
"epoch": 0.2464810760087582,
|
2884 |
+
"grad_norm": 1.3167545795440674,
|
2885 |
+
"learning_rate": 6.92436974789916e-05,
|
2886 |
+
"loss": 0.9145,
|
2887 |
+
"step": 394
|
2888 |
+
},
|
2889 |
+
{
|
2890 |
+
"epoch": 0.2471066624960901,
|
2891 |
+
"grad_norm": 0.6734040379524231,
|
2892 |
+
"learning_rate": 6.890756302521008e-05,
|
2893 |
+
"loss": 0.4063,
|
2894 |
+
"step": 395
|
2895 |
+
},
|
2896 |
+
{
|
2897 |
+
"epoch": 0.24773224898342197,
|
2898 |
+
"grad_norm": 0.48195910453796387,
|
2899 |
+
"learning_rate": 6.857142857142858e-05,
|
2900 |
+
"loss": 0.4146,
|
2901 |
+
"step": 396
|
2902 |
+
},
|
2903 |
+
{
|
2904 |
+
"epoch": 0.24835783547075382,
|
2905 |
+
"grad_norm": 1.2620956897735596,
|
2906 |
+
"learning_rate": 6.823529411764707e-05,
|
2907 |
+
"loss": 0.4289,
|
2908 |
+
"step": 397
|
2909 |
+
},
|
2910 |
+
{
|
2911 |
+
"epoch": 0.2489834219580857,
|
2912 |
+
"grad_norm": 0.6438835859298706,
|
2913 |
+
"learning_rate": 6.789915966386555e-05,
|
2914 |
+
"loss": 0.6204,
|
2915 |
+
"step": 398
|
2916 |
+
},
|
2917 |
+
{
|
2918 |
+
"epoch": 0.24960900844541759,
|
2919 |
+
"grad_norm": 1.6006457805633545,
|
2920 |
+
"learning_rate": 6.756302521008404e-05,
|
2921 |
+
"loss": 0.8828,
|
2922 |
+
"step": 399
|
2923 |
+
},
|
2924 |
+
{
|
2925 |
+
"epoch": 0.25023459493274947,
|
2926 |
+
"grad_norm": 3.7350921630859375,
|
2927 |
+
"learning_rate": 6.722689075630254e-05,
|
2928 |
+
"loss": 0.5608,
|
2929 |
+
"step": 400
|
2930 |
+
},
|
2931 |
+
{
|
2932 |
+
"epoch": 0.25023459493274947,
|
2933 |
+
"eval_loss": 0.7404398322105408,
|
2934 |
+
"eval_runtime": 43.5267,
|
2935 |
+
"eval_samples_per_second": 5.881,
|
2936 |
+
"eval_steps_per_second": 2.941,
|
2937 |
+
"step": 400
|
2938 |
+
}
|
2939 |
+
],
|
2940 |
+
"logging_steps": 1,
|
2941 |
+
"max_steps": 600,
|
2942 |
+
"num_input_tokens_seen": 0,
|
2943 |
+
"num_train_epochs": 1,
|
2944 |
+
"save_steps": 50,
|
2945 |
+
"stateful_callbacks": {
|
2946 |
+
"TrainerControl": {
|
2947 |
+
"args": {
|
2948 |
+
"should_epoch_stop": false,
|
2949 |
+
"should_evaluate": false,
|
2950 |
+
"should_log": false,
|
2951 |
+
"should_save": true,
|
2952 |
+
"should_training_stop": false
|
2953 |
+
},
|
2954 |
+
"attributes": {}
|
2955 |
+
}
|
2956 |
+
},
|
2957 |
+
"total_flos": 5.1975161385998746e+17,
|
2958 |
+
"train_batch_size": 2,
|
2959 |
+
"trial_name": null,
|
2960 |
+
"trial_params": null
|
2961 |
+
}
|
checkpoint-400/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:42cfa62640183f75adb5fdf5d0b72d17709e311ac177000b5647d8cf4ce53d8a
|
3 |
+
size 5496
|