Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .ipynb_checkpoints/README-checkpoint.md +15 -0
- .ipynb_checkpoints/trainer_log-checkpoint.jsonl +2 -0
- .ipynb_checkpoints/training_loss-checkpoint.png +0 -0
- README.md +15 -0
- adapter_config.json +21 -0
- adapter_model.bin +3 -0
- all_results.json +7 -0
- checkpoint-100/README.md +15 -0
- checkpoint-100/adapter_config.json +21 -0
- checkpoint-100/adapter_model.bin +3 -0
- checkpoint-100/finetuning_args.json +16 -0
- checkpoint-100/optimizer.pt +3 -0
- checkpoint-100/rng_state.pth +3 -0
- checkpoint-100/scaler.pt +3 -0
- checkpoint-100/scheduler.pt +3 -0
- checkpoint-100/trainer_state.json +136 -0
- checkpoint-100/training_args.bin +3 -0
- checkpoint-1000/README.md +15 -0
- checkpoint-1000/adapter_config.json +21 -0
- checkpoint-1000/adapter_model.bin +3 -0
- checkpoint-1000/finetuning_args.json +16 -0
- checkpoint-1000/optimizer.pt +3 -0
- checkpoint-1000/rng_state.pth +3 -0
- checkpoint-1000/scaler.pt +3 -0
- checkpoint-1000/scheduler.pt +3 -0
- checkpoint-1000/trainer_state.json +1216 -0
- checkpoint-1000/training_args.bin +3 -0
- checkpoint-1100/README.md +15 -0
- checkpoint-1100/adapter_config.json +21 -0
- checkpoint-1100/adapter_model.bin +3 -0
- checkpoint-1100/finetuning_args.json +16 -0
- checkpoint-1100/optimizer.pt +3 -0
- checkpoint-1100/rng_state.pth +3 -0
- checkpoint-1100/scaler.pt +3 -0
- checkpoint-1100/scheduler.pt +3 -0
- checkpoint-1100/trainer_state.json +1336 -0
- checkpoint-1100/training_args.bin +3 -0
- checkpoint-1200/README.md +15 -0
- checkpoint-1200/adapter_config.json +21 -0
- checkpoint-1200/adapter_model.bin +3 -0
- checkpoint-1200/finetuning_args.json +16 -0
- checkpoint-1200/optimizer.pt +3 -0
- checkpoint-1200/rng_state.pth +3 -0
- checkpoint-1200/scaler.pt +3 -0
- checkpoint-1200/scheduler.pt +3 -0
- checkpoint-1200/trainer_state.json +1456 -0
- checkpoint-1200/training_args.bin +3 -0
- checkpoint-1300/README.md +15 -0
- checkpoint-1300/adapter_config.json +21 -0
- checkpoint-1300/adapter_model.bin +3 -0
.ipynb_checkpoints/README-checkpoint.md
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
---
|
4 |
+
## Training procedure
|
5 |
+
|
6 |
+
|
7 |
+
The following `bitsandbytes` quantization config was used during training:
|
8 |
+
- load_in_8bit: True
|
9 |
+
- llm_int8_threshold: 6.0
|
10 |
+
- llm_int8_skip_modules: None
|
11 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
12 |
+
### Framework versions
|
13 |
+
|
14 |
+
|
15 |
+
- PEFT 0.5.0
|
.ipynb_checkpoints/trainer_log-checkpoint.jsonl
ADDED
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
1 |
+
{"current_steps": 5, "total_steps": 5424, "loss": 1.6349, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9999895164082156e-05, "epoch": 0.0, "percentage": 0.09, "elapsed_time": "0:00:53", "remaining_time": "16:02:24"}
|
2 |
+
{"current_steps": 10, "total_steps": 5424, "loss": 1.6199, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.999958065720787e-05, "epoch": 0.01, "percentage": 0.18, "elapsed_time": "0:01:45", "remaining_time": "15:54:15"}
|
.ipynb_checkpoints/training_loss-checkpoint.png
ADDED
README.md
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
---
|
4 |
+
## Training procedure
|
5 |
+
|
6 |
+
|
7 |
+
The following `bitsandbytes` quantization config was used during training:
|
8 |
+
- load_in_8bit: True
|
9 |
+
- llm_int8_threshold: 6.0
|
10 |
+
- llm_int8_skip_modules: None
|
11 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
12 |
+
### Framework versions
|
13 |
+
|
14 |
+
|
15 |
+
- PEFT 0.5.0
|
adapter_config.json
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"auto_mapping": null,
|
3 |
+
"base_model_name_or_path": "meta-llama/Llama-2-7b-chat-hf",
|
4 |
+
"bias": "none",
|
5 |
+
"fan_in_fan_out": false,
|
6 |
+
"inference_mode": true,
|
7 |
+
"init_lora_weights": true,
|
8 |
+
"layers_pattern": null,
|
9 |
+
"layers_to_transform": null,
|
10 |
+
"lora_alpha": 32.0,
|
11 |
+
"lora_dropout": 0.1,
|
12 |
+
"modules_to_save": null,
|
13 |
+
"peft_type": "LORA",
|
14 |
+
"r": 8,
|
15 |
+
"revision": null,
|
16 |
+
"target_modules": [
|
17 |
+
"q_proj",
|
18 |
+
"v_proj"
|
19 |
+
],
|
20 |
+
"task_type": "CAUSAL_LM"
|
21 |
+
}
|
adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b1a1ffddcaa42c5b32d83acae8d4ed797725d1955445bb62cfe0a87da0be3a0e
|
3 |
+
size 16821197
|
all_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"train_loss": 0.9648243357649947,
|
4 |
+
"train_runtime": 56978.2271,
|
5 |
+
"train_samples_per_second": 1.523,
|
6 |
+
"train_steps_per_second": 0.095
|
7 |
+
}
|
checkpoint-100/README.md
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
---
|
4 |
+
## Training procedure
|
5 |
+
|
6 |
+
|
7 |
+
The following `bitsandbytes` quantization config was used during training:
|
8 |
+
- load_in_8bit: True
|
9 |
+
- llm_int8_threshold: 6.0
|
10 |
+
- llm_int8_skip_modules: None
|
11 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
12 |
+
### Framework versions
|
13 |
+
|
14 |
+
|
15 |
+
- PEFT 0.5.0
|
checkpoint-100/adapter_config.json
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"auto_mapping": null,
|
3 |
+
"base_model_name_or_path": "meta-llama/Llama-2-7b-chat-hf",
|
4 |
+
"bias": "none",
|
5 |
+
"fan_in_fan_out": false,
|
6 |
+
"inference_mode": true,
|
7 |
+
"init_lora_weights": true,
|
8 |
+
"layers_pattern": null,
|
9 |
+
"layers_to_transform": null,
|
10 |
+
"lora_alpha": 32.0,
|
11 |
+
"lora_dropout": 0.1,
|
12 |
+
"modules_to_save": null,
|
13 |
+
"peft_type": "LORA",
|
14 |
+
"r": 8,
|
15 |
+
"revision": null,
|
16 |
+
"target_modules": [
|
17 |
+
"q_proj",
|
18 |
+
"v_proj"
|
19 |
+
],
|
20 |
+
"task_type": "CAUSAL_LM"
|
21 |
+
}
|
checkpoint-100/adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ea01c09ff608b5c7099cffa399a08b3450a36b101137f99df08de90dc686a292
|
3 |
+
size 16821197
|
checkpoint-100/finetuning_args.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"dpo_beta": 0.1,
|
3 |
+
"finetuning_type": "lora",
|
4 |
+
"lora_alpha": 32.0,
|
5 |
+
"lora_dropout": 0.1,
|
6 |
+
"lora_rank": 8,
|
7 |
+
"lora_target": [
|
8 |
+
"q_proj",
|
9 |
+
"v_proj"
|
10 |
+
],
|
11 |
+
"name_module_trainable": "mlp",
|
12 |
+
"num_hidden_layers": 32,
|
13 |
+
"num_layer_trainable": 3,
|
14 |
+
"ppo_score_norm": false,
|
15 |
+
"resume_lora_training": true
|
16 |
+
}
|
checkpoint-100/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c95c01320b9f42048cfa27aa398a98f285e7e8c6bcac04dac33ce2792a03e716
|
3 |
+
size 33629765
|
checkpoint-100/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:456575f7c97fbfb5063cd944a34e372bd839e2035bcd8de1a9f57cee31d0ed2b
|
3 |
+
size 14575
|
checkpoint-100/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfa44e8523f62833816d29aa6c576eaa7783e3bbdb3e132e248b1d8aaee6132b
|
3 |
+
size 557
|
checkpoint-100/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f315341427af6a189cf3f47ec337dfddc9476659f210947cad5a0049c84cec8b
|
3 |
+
size 627
|
checkpoint-100/trainer_state.json
ADDED
@@ -0,0 +1,136 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.055294442908487694,
|
5 |
+
"global_step": 100,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.0,
|
12 |
+
"learning_rate": 4.9999895164082156e-05,
|
13 |
+
"loss": 1.6349,
|
14 |
+
"step": 5
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.01,
|
18 |
+
"learning_rate": 4.999958065720787e-05,
|
19 |
+
"loss": 1.6199,
|
20 |
+
"step": 10
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.01,
|
24 |
+
"learning_rate": 4.999905648201487e-05,
|
25 |
+
"loss": 1.4834,
|
26 |
+
"step": 15
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.01,
|
30 |
+
"learning_rate": 4.999832264289934e-05,
|
31 |
+
"loss": 1.3882,
|
32 |
+
"step": 20
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.01,
|
36 |
+
"learning_rate": 4.999737914601591e-05,
|
37 |
+
"loss": 1.3679,
|
38 |
+
"step": 25
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.02,
|
42 |
+
"learning_rate": 4.999622599927756e-05,
|
43 |
+
"loss": 1.2396,
|
44 |
+
"step": 30
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.02,
|
48 |
+
"learning_rate": 4.999486321235559e-05,
|
49 |
+
"loss": 1.321,
|
50 |
+
"step": 35
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.02,
|
54 |
+
"learning_rate": 4.9993290796679516e-05,
|
55 |
+
"loss": 1.2874,
|
56 |
+
"step": 40
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.02,
|
60 |
+
"learning_rate": 4.999150876543699e-05,
|
61 |
+
"loss": 1.2607,
|
62 |
+
"step": 45
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.03,
|
66 |
+
"learning_rate": 4.9989517133573694e-05,
|
67 |
+
"loss": 1.2454,
|
68 |
+
"step": 50
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.03,
|
72 |
+
"learning_rate": 4.9987315917793174e-05,
|
73 |
+
"loss": 1.2799,
|
74 |
+
"step": 55
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.03,
|
78 |
+
"learning_rate": 4.998490513655676e-05,
|
79 |
+
"loss": 1.2575,
|
80 |
+
"step": 60
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.04,
|
84 |
+
"learning_rate": 4.998228481008337e-05,
|
85 |
+
"loss": 1.2404,
|
86 |
+
"step": 65
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.04,
|
90 |
+
"learning_rate": 4.997945496034934e-05,
|
91 |
+
"loss": 1.2219,
|
92 |
+
"step": 70
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.04,
|
96 |
+
"learning_rate": 4.9976415611088267e-05,
|
97 |
+
"loss": 1.2241,
|
98 |
+
"step": 75
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.04,
|
102 |
+
"learning_rate": 4.997316678779079e-05,
|
103 |
+
"loss": 1.1716,
|
104 |
+
"step": 80
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.05,
|
108 |
+
"learning_rate": 4.996970851770438e-05,
|
109 |
+
"loss": 1.1883,
|
110 |
+
"step": 85
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.05,
|
114 |
+
"learning_rate": 4.9966040829833115e-05,
|
115 |
+
"loss": 1.205,
|
116 |
+
"step": 90
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.05,
|
120 |
+
"learning_rate": 4.9962163754937426e-05,
|
121 |
+
"loss": 1.1246,
|
122 |
+
"step": 95
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.06,
|
126 |
+
"learning_rate": 4.995807732553384e-05,
|
127 |
+
"loss": 1.1636,
|
128 |
+
"step": 100
|
129 |
+
}
|
130 |
+
],
|
131 |
+
"max_steps": 5424,
|
132 |
+
"num_train_epochs": 3,
|
133 |
+
"total_flos": 3.2497031184384e+16,
|
134 |
+
"trial_name": null,
|
135 |
+
"trial_params": null
|
136 |
+
}
|
checkpoint-100/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f6a8853599a52b1f15984d75ce4b6434c335fdc67d4509d0b2ca0d8c613590a
|
3 |
+
size 3362
|
checkpoint-1000/README.md
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
---
|
4 |
+
## Training procedure
|
5 |
+
|
6 |
+
|
7 |
+
The following `bitsandbytes` quantization config was used during training:
|
8 |
+
- load_in_8bit: True
|
9 |
+
- llm_int8_threshold: 6.0
|
10 |
+
- llm_int8_skip_modules: None
|
11 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
12 |
+
### Framework versions
|
13 |
+
|
14 |
+
|
15 |
+
- PEFT 0.5.0
|
checkpoint-1000/adapter_config.json
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"auto_mapping": null,
|
3 |
+
"base_model_name_or_path": "meta-llama/Llama-2-7b-chat-hf",
|
4 |
+
"bias": "none",
|
5 |
+
"fan_in_fan_out": false,
|
6 |
+
"inference_mode": true,
|
7 |
+
"init_lora_weights": true,
|
8 |
+
"layers_pattern": null,
|
9 |
+
"layers_to_transform": null,
|
10 |
+
"lora_alpha": 32.0,
|
11 |
+
"lora_dropout": 0.1,
|
12 |
+
"modules_to_save": null,
|
13 |
+
"peft_type": "LORA",
|
14 |
+
"r": 8,
|
15 |
+
"revision": null,
|
16 |
+
"target_modules": [
|
17 |
+
"q_proj",
|
18 |
+
"v_proj"
|
19 |
+
],
|
20 |
+
"task_type": "CAUSAL_LM"
|
21 |
+
}
|
checkpoint-1000/adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d25e10111b464093549a11f134a59c4ac86510a9f7e3bb4d2127534696bfeaeb
|
3 |
+
size 16821197
|
checkpoint-1000/finetuning_args.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"dpo_beta": 0.1,
|
3 |
+
"finetuning_type": "lora",
|
4 |
+
"lora_alpha": 32.0,
|
5 |
+
"lora_dropout": 0.1,
|
6 |
+
"lora_rank": 8,
|
7 |
+
"lora_target": [
|
8 |
+
"q_proj",
|
9 |
+
"v_proj"
|
10 |
+
],
|
11 |
+
"name_module_trainable": "mlp",
|
12 |
+
"num_hidden_layers": 32,
|
13 |
+
"num_layer_trainable": 3,
|
14 |
+
"ppo_score_norm": false,
|
15 |
+
"resume_lora_training": true
|
16 |
+
}
|
checkpoint-1000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b5121f5f1c38b5973d2409a8547b2d15e2186030c767c45fb3962d1ba9a69c54
|
3 |
+
size 33629893
|
checkpoint-1000/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:73090c0dec8be67d9b176c7292edb88b14dcff706fff6020d9d9b3c02368ca19
|
3 |
+
size 14575
|
checkpoint-1000/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:68cff80b680ddf6e7abbef98b5f336b97f9b5963e2209307f639383870e8cc71
|
3 |
+
size 557
|
checkpoint-1000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:866e16a03b3e8054e079edfb5555569d68a0ca587e1d2a7c9fddcbdda27f69eb
|
3 |
+
size 627
|
checkpoint-1000/trainer_state.json
ADDED
@@ -0,0 +1,1216 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.552944429084877,
|
5 |
+
"global_step": 1000,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.0,
|
12 |
+
"learning_rate": 4.9999895164082156e-05,
|
13 |
+
"loss": 1.6349,
|
14 |
+
"step": 5
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.01,
|
18 |
+
"learning_rate": 4.999958065720787e-05,
|
19 |
+
"loss": 1.6199,
|
20 |
+
"step": 10
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.01,
|
24 |
+
"learning_rate": 4.999905648201487e-05,
|
25 |
+
"loss": 1.4834,
|
26 |
+
"step": 15
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.01,
|
30 |
+
"learning_rate": 4.999832264289934e-05,
|
31 |
+
"loss": 1.3882,
|
32 |
+
"step": 20
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.01,
|
36 |
+
"learning_rate": 4.999737914601591e-05,
|
37 |
+
"loss": 1.3679,
|
38 |
+
"step": 25
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.02,
|
42 |
+
"learning_rate": 4.999622599927756e-05,
|
43 |
+
"loss": 1.2396,
|
44 |
+
"step": 30
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.02,
|
48 |
+
"learning_rate": 4.999486321235559e-05,
|
49 |
+
"loss": 1.321,
|
50 |
+
"step": 35
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.02,
|
54 |
+
"learning_rate": 4.9993290796679516e-05,
|
55 |
+
"loss": 1.2874,
|
56 |
+
"step": 40
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.02,
|
60 |
+
"learning_rate": 4.999150876543699e-05,
|
61 |
+
"loss": 1.2607,
|
62 |
+
"step": 45
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.03,
|
66 |
+
"learning_rate": 4.9989517133573694e-05,
|
67 |
+
"loss": 1.2454,
|
68 |
+
"step": 50
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.03,
|
72 |
+
"learning_rate": 4.9987315917793174e-05,
|
73 |
+
"loss": 1.2799,
|
74 |
+
"step": 55
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.03,
|
78 |
+
"learning_rate": 4.998490513655676e-05,
|
79 |
+
"loss": 1.2575,
|
80 |
+
"step": 60
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.04,
|
84 |
+
"learning_rate": 4.998228481008337e-05,
|
85 |
+
"loss": 1.2404,
|
86 |
+
"step": 65
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.04,
|
90 |
+
"learning_rate": 4.997945496034934e-05,
|
91 |
+
"loss": 1.2219,
|
92 |
+
"step": 70
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.04,
|
96 |
+
"learning_rate": 4.9976415611088267e-05,
|
97 |
+
"loss": 1.2241,
|
98 |
+
"step": 75
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.04,
|
102 |
+
"learning_rate": 4.997316678779079e-05,
|
103 |
+
"loss": 1.1716,
|
104 |
+
"step": 80
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.05,
|
108 |
+
"learning_rate": 4.996970851770438e-05,
|
109 |
+
"loss": 1.1883,
|
110 |
+
"step": 85
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.05,
|
114 |
+
"learning_rate": 4.9966040829833115e-05,
|
115 |
+
"loss": 1.205,
|
116 |
+
"step": 90
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.05,
|
120 |
+
"learning_rate": 4.9962163754937426e-05,
|
121 |
+
"loss": 1.1246,
|
122 |
+
"step": 95
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.06,
|
126 |
+
"learning_rate": 4.995807732553384e-05,
|
127 |
+
"loss": 1.1636,
|
128 |
+
"step": 100
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.06,
|
132 |
+
"learning_rate": 4.9953781575894723e-05,
|
133 |
+
"loss": 1.158,
|
134 |
+
"step": 105
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 0.06,
|
138 |
+
"learning_rate": 4.9949276542048e-05,
|
139 |
+
"loss": 1.1477,
|
140 |
+
"step": 110
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 0.06,
|
144 |
+
"learning_rate": 4.9944562261776805e-05,
|
145 |
+
"loss": 1.1678,
|
146 |
+
"step": 115
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 0.07,
|
150 |
+
"learning_rate": 4.9939638774619216e-05,
|
151 |
+
"loss": 1.1501,
|
152 |
+
"step": 120
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 0.07,
|
156 |
+
"learning_rate": 4.99345061218679e-05,
|
157 |
+
"loss": 1.1955,
|
158 |
+
"step": 125
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 0.07,
|
162 |
+
"learning_rate": 4.9929164346569756e-05,
|
163 |
+
"loss": 1.1724,
|
164 |
+
"step": 130
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.07,
|
168 |
+
"learning_rate": 4.9923613493525576e-05,
|
169 |
+
"loss": 1.177,
|
170 |
+
"step": 135
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.08,
|
174 |
+
"learning_rate": 4.991785360928968e-05,
|
175 |
+
"loss": 1.1418,
|
176 |
+
"step": 140
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 0.08,
|
180 |
+
"learning_rate": 4.991188474216947e-05,
|
181 |
+
"loss": 1.1898,
|
182 |
+
"step": 145
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 0.08,
|
186 |
+
"learning_rate": 4.9905706942225094e-05,
|
187 |
+
"loss": 1.1479,
|
188 |
+
"step": 150
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 0.09,
|
192 |
+
"learning_rate": 4.9899320261268966e-05,
|
193 |
+
"loss": 1.1356,
|
194 |
+
"step": 155
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 0.09,
|
198 |
+
"learning_rate": 4.989272475286537e-05,
|
199 |
+
"loss": 1.1397,
|
200 |
+
"step": 160
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 0.09,
|
204 |
+
"learning_rate": 4.9885920472330004e-05,
|
205 |
+
"loss": 1.1215,
|
206 |
+
"step": 165
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 0.09,
|
210 |
+
"learning_rate": 4.9878907476729516e-05,
|
211 |
+
"loss": 1.167,
|
212 |
+
"step": 170
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.1,
|
216 |
+
"learning_rate": 4.9871685824881e-05,
|
217 |
+
"loss": 1.1219,
|
218 |
+
"step": 175
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 0.1,
|
222 |
+
"learning_rate": 4.9864255577351534e-05,
|
223 |
+
"loss": 1.0835,
|
224 |
+
"step": 180
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 0.1,
|
228 |
+
"learning_rate": 4.985661679645769e-05,
|
229 |
+
"loss": 1.0721,
|
230 |
+
"step": 185
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 0.11,
|
234 |
+
"learning_rate": 4.9848769546264915e-05,
|
235 |
+
"loss": 1.0692,
|
236 |
+
"step": 190
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 0.11,
|
240 |
+
"learning_rate": 4.9840713892587146e-05,
|
241 |
+
"loss": 1.0488,
|
242 |
+
"step": 195
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 0.11,
|
246 |
+
"learning_rate": 4.983244990298609e-05,
|
247 |
+
"loss": 1.1285,
|
248 |
+
"step": 200
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 0.11,
|
252 |
+
"learning_rate": 4.982397764677081e-05,
|
253 |
+
"loss": 1.0832,
|
254 |
+
"step": 205
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.12,
|
258 |
+
"learning_rate": 4.981529719499704e-05,
|
259 |
+
"loss": 1.0652,
|
260 |
+
"step": 210
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 0.12,
|
264 |
+
"learning_rate": 4.980640862046663e-05,
|
265 |
+
"loss": 1.1043,
|
266 |
+
"step": 215
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 0.12,
|
270 |
+
"learning_rate": 4.979731199772693e-05,
|
271 |
+
"loss": 1.112,
|
272 |
+
"step": 220
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 0.12,
|
276 |
+
"learning_rate": 4.9788007403070146e-05,
|
277 |
+
"loss": 1.1029,
|
278 |
+
"step": 225
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 0.13,
|
282 |
+
"learning_rate": 4.977849491453277e-05,
|
283 |
+
"loss": 1.0869,
|
284 |
+
"step": 230
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 0.13,
|
288 |
+
"learning_rate": 4.976877461189481e-05,
|
289 |
+
"loss": 1.0843,
|
290 |
+
"step": 235
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 0.13,
|
294 |
+
"learning_rate": 4.975884657667922e-05,
|
295 |
+
"loss": 1.0789,
|
296 |
+
"step": 240
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.14,
|
300 |
+
"learning_rate": 4.974871089215118e-05,
|
301 |
+
"loss": 1.0449,
|
302 |
+
"step": 245
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 0.14,
|
306 |
+
"learning_rate": 4.9738367643317405e-05,
|
307 |
+
"loss": 1.1053,
|
308 |
+
"step": 250
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 0.14,
|
312 |
+
"learning_rate": 4.9727816916925395e-05,
|
313 |
+
"loss": 1.0651,
|
314 |
+
"step": 255
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 0.14,
|
318 |
+
"learning_rate": 4.971705880146276e-05,
|
319 |
+
"loss": 1.0828,
|
320 |
+
"step": 260
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 0.15,
|
324 |
+
"learning_rate": 4.970609338715646e-05,
|
325 |
+
"loss": 1.0932,
|
326 |
+
"step": 265
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 0.15,
|
330 |
+
"learning_rate": 4.969492076597203e-05,
|
331 |
+
"loss": 1.0648,
|
332 |
+
"step": 270
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 0.15,
|
336 |
+
"learning_rate": 4.968354103161283e-05,
|
337 |
+
"loss": 1.0948,
|
338 |
+
"step": 275
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.15,
|
342 |
+
"learning_rate": 4.967195427951926e-05,
|
343 |
+
"loss": 1.0721,
|
344 |
+
"step": 280
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 0.16,
|
348 |
+
"learning_rate": 4.9660160606867936e-05,
|
349 |
+
"loss": 1.124,
|
350 |
+
"step": 285
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 0.16,
|
354 |
+
"learning_rate": 4.9648160112570896e-05,
|
355 |
+
"loss": 1.0963,
|
356 |
+
"step": 290
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 0.16,
|
360 |
+
"learning_rate": 4.9635952897274773e-05,
|
361 |
+
"loss": 1.1078,
|
362 |
+
"step": 295
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 0.17,
|
366 |
+
"learning_rate": 4.9623539063359925e-05,
|
367 |
+
"loss": 1.1059,
|
368 |
+
"step": 300
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 0.17,
|
372 |
+
"learning_rate": 4.961091871493962e-05,
|
373 |
+
"loss": 1.1032,
|
374 |
+
"step": 305
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 0.17,
|
378 |
+
"learning_rate": 4.959809195785912e-05,
|
379 |
+
"loss": 1.0595,
|
380 |
+
"step": 310
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.17,
|
384 |
+
"learning_rate": 4.958505889969481e-05,
|
385 |
+
"loss": 1.1096,
|
386 |
+
"step": 315
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"epoch": 0.18,
|
390 |
+
"learning_rate": 4.957181964975329e-05,
|
391 |
+
"loss": 1.0589,
|
392 |
+
"step": 320
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 0.18,
|
396 |
+
"learning_rate": 4.955837431907049e-05,
|
397 |
+
"loss": 1.0608,
|
398 |
+
"step": 325
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 0.18,
|
402 |
+
"learning_rate": 4.954472302041069e-05,
|
403 |
+
"loss": 1.0819,
|
404 |
+
"step": 330
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 0.19,
|
408 |
+
"learning_rate": 4.9530865868265605e-05,
|
409 |
+
"loss": 1.0759,
|
410 |
+
"step": 335
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 0.19,
|
414 |
+
"learning_rate": 4.951680297885342e-05,
|
415 |
+
"loss": 1.0515,
|
416 |
+
"step": 340
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 0.19,
|
420 |
+
"learning_rate": 4.950253447011779e-05,
|
421 |
+
"loss": 1.0371,
|
422 |
+
"step": 345
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.19,
|
426 |
+
"learning_rate": 4.948806046172691e-05,
|
427 |
+
"loss": 1.0619,
|
428 |
+
"step": 350
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 0.2,
|
432 |
+
"learning_rate": 4.947338107507245e-05,
|
433 |
+
"loss": 1.0757,
|
434 |
+
"step": 355
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 0.2,
|
438 |
+
"learning_rate": 4.945849643326857e-05,
|
439 |
+
"loss": 1.0686,
|
440 |
+
"step": 360
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 0.2,
|
444 |
+
"learning_rate": 4.9443406661150874e-05,
|
445 |
+
"loss": 1.0809,
|
446 |
+
"step": 365
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 0.2,
|
450 |
+
"learning_rate": 4.942811188527537e-05,
|
451 |
+
"loss": 1.0704,
|
452 |
+
"step": 370
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 0.21,
|
456 |
+
"learning_rate": 4.941261223391742e-05,
|
457 |
+
"loss": 1.0655,
|
458 |
+
"step": 375
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 0.21,
|
462 |
+
"learning_rate": 4.939690783707063e-05,
|
463 |
+
"loss": 1.1182,
|
464 |
+
"step": 380
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.21,
|
468 |
+
"learning_rate": 4.938099882644578e-05,
|
469 |
+
"loss": 1.081,
|
470 |
+
"step": 385
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 0.22,
|
474 |
+
"learning_rate": 4.9364885335469734e-05,
|
475 |
+
"loss": 1.0792,
|
476 |
+
"step": 390
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"epoch": 0.22,
|
480 |
+
"learning_rate": 4.93485674992843e-05,
|
481 |
+
"loss": 1.0244,
|
482 |
+
"step": 395
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 0.22,
|
486 |
+
"learning_rate": 4.933204545474511e-05,
|
487 |
+
"loss": 1.0531,
|
488 |
+
"step": 400
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 0.22,
|
492 |
+
"learning_rate": 4.9315319340420465e-05,
|
493 |
+
"loss": 1.048,
|
494 |
+
"step": 405
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 0.23,
|
498 |
+
"learning_rate": 4.929838929659015e-05,
|
499 |
+
"loss": 1.04,
|
500 |
+
"step": 410
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 0.23,
|
504 |
+
"learning_rate": 4.9281255465244314e-05,
|
505 |
+
"loss": 1.0686,
|
506 |
+
"step": 415
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.23,
|
510 |
+
"learning_rate": 4.926391799008223e-05,
|
511 |
+
"loss": 1.0933,
|
512 |
+
"step": 420
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"epoch": 0.24,
|
516 |
+
"learning_rate": 4.924637701651111e-05,
|
517 |
+
"loss": 1.0313,
|
518 |
+
"step": 425
|
519 |
+
},
|
520 |
+
{
|
521 |
+
"epoch": 0.24,
|
522 |
+
"learning_rate": 4.9228632691644874e-05,
|
523 |
+
"loss": 1.0811,
|
524 |
+
"step": 430
|
525 |
+
},
|
526 |
+
{
|
527 |
+
"epoch": 0.24,
|
528 |
+
"learning_rate": 4.921068516430293e-05,
|
529 |
+
"loss": 1.0617,
|
530 |
+
"step": 435
|
531 |
+
},
|
532 |
+
{
|
533 |
+
"epoch": 0.24,
|
534 |
+
"learning_rate": 4.919253458500892e-05,
|
535 |
+
"loss": 1.0482,
|
536 |
+
"step": 440
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 0.25,
|
540 |
+
"learning_rate": 4.9174181105989445e-05,
|
541 |
+
"loss": 1.0681,
|
542 |
+
"step": 445
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 0.25,
|
546 |
+
"learning_rate": 4.9155624881172834e-05,
|
547 |
+
"loss": 1.0476,
|
548 |
+
"step": 450
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 0.25,
|
552 |
+
"learning_rate": 4.913686606618777e-05,
|
553 |
+
"loss": 1.0463,
|
554 |
+
"step": 455
|
555 |
+
},
|
556 |
+
{
|
557 |
+
"epoch": 0.25,
|
558 |
+
"learning_rate": 4.911790481836208e-05,
|
559 |
+
"loss": 1.0213,
|
560 |
+
"step": 460
|
561 |
+
},
|
562 |
+
{
|
563 |
+
"epoch": 0.26,
|
564 |
+
"learning_rate": 4.909874129672133e-05,
|
565 |
+
"loss": 0.9855,
|
566 |
+
"step": 465
|
567 |
+
},
|
568 |
+
{
|
569 |
+
"epoch": 0.26,
|
570 |
+
"learning_rate": 4.907937566198757e-05,
|
571 |
+
"loss": 1.045,
|
572 |
+
"step": 470
|
573 |
+
},
|
574 |
+
{
|
575 |
+
"epoch": 0.26,
|
576 |
+
"learning_rate": 4.9059808076577914e-05,
|
577 |
+
"loss": 1.0442,
|
578 |
+
"step": 475
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 0.27,
|
582 |
+
"learning_rate": 4.904003870460323e-05,
|
583 |
+
"loss": 1.0354,
|
584 |
+
"step": 480
|
585 |
+
},
|
586 |
+
{
|
587 |
+
"epoch": 0.27,
|
588 |
+
"learning_rate": 4.9020067711866735e-05,
|
589 |
+
"loss": 1.0331,
|
590 |
+
"step": 485
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 0.27,
|
594 |
+
"learning_rate": 4.899989526586261e-05,
|
595 |
+
"loss": 1.0585,
|
596 |
+
"step": 490
|
597 |
+
},
|
598 |
+
{
|
599 |
+
"epoch": 0.27,
|
600 |
+
"learning_rate": 4.8979521535774636e-05,
|
601 |
+
"loss": 1.0223,
|
602 |
+
"step": 495
|
603 |
+
},
|
604 |
+
{
|
605 |
+
"epoch": 0.28,
|
606 |
+
"learning_rate": 4.895894669247468e-05,
|
607 |
+
"loss": 1.0118,
|
608 |
+
"step": 500
|
609 |
+
},
|
610 |
+
{
|
611 |
+
"epoch": 0.28,
|
612 |
+
"learning_rate": 4.8938170908521356e-05,
|
613 |
+
"loss": 1.0508,
|
614 |
+
"step": 505
|
615 |
+
},
|
616 |
+
{
|
617 |
+
"epoch": 0.28,
|
618 |
+
"learning_rate": 4.8917194358158534e-05,
|
619 |
+
"loss": 1.0656,
|
620 |
+
"step": 510
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 0.28,
|
624 |
+
"learning_rate": 4.8896017217313886e-05,
|
625 |
+
"loss": 1.0655,
|
626 |
+
"step": 515
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 0.29,
|
630 |
+
"learning_rate": 4.887463966359741e-05,
|
631 |
+
"loss": 1.0833,
|
632 |
+
"step": 520
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 0.29,
|
636 |
+
"learning_rate": 4.8853061876299956e-05,
|
637 |
+
"loss": 1.068,
|
638 |
+
"step": 525
|
639 |
+
},
|
640 |
+
{
|
641 |
+
"epoch": 0.29,
|
642 |
+
"learning_rate": 4.8831284036391684e-05,
|
643 |
+
"loss": 1.0487,
|
644 |
+
"step": 530
|
645 |
+
},
|
646 |
+
{
|
647 |
+
"epoch": 0.3,
|
648 |
+
"learning_rate": 4.880930632652058e-05,
|
649 |
+
"loss": 1.059,
|
650 |
+
"step": 535
|
651 |
+
},
|
652 |
+
{
|
653 |
+
"epoch": 0.3,
|
654 |
+
"learning_rate": 4.878712893101092e-05,
|
655 |
+
"loss": 1.0408,
|
656 |
+
"step": 540
|
657 |
+
},
|
658 |
+
{
|
659 |
+
"epoch": 0.3,
|
660 |
+
"learning_rate": 4.876475203586171e-05,
|
661 |
+
"loss": 0.9976,
|
662 |
+
"step": 545
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 0.3,
|
666 |
+
"learning_rate": 4.874217582874514e-05,
|
667 |
+
"loss": 1.0358,
|
668 |
+
"step": 550
|
669 |
+
},
|
670 |
+
{
|
671 |
+
"epoch": 0.31,
|
672 |
+
"learning_rate": 4.8719400499005e-05,
|
673 |
+
"loss": 1.0073,
|
674 |
+
"step": 555
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 0.31,
|
678 |
+
"learning_rate": 4.869642623765509e-05,
|
679 |
+
"loss": 1.0742,
|
680 |
+
"step": 560
|
681 |
+
},
|
682 |
+
{
|
683 |
+
"epoch": 0.31,
|
684 |
+
"learning_rate": 4.867325323737765e-05,
|
685 |
+
"loss": 1.0463,
|
686 |
+
"step": 565
|
687 |
+
},
|
688 |
+
{
|
689 |
+
"epoch": 0.32,
|
690 |
+
"learning_rate": 4.864988169252168e-05,
|
691 |
+
"loss": 1.0242,
|
692 |
+
"step": 570
|
693 |
+
},
|
694 |
+
{
|
695 |
+
"epoch": 0.32,
|
696 |
+
"learning_rate": 4.8626311799101375e-05,
|
697 |
+
"loss": 1.0773,
|
698 |
+
"step": 575
|
699 |
+
},
|
700 |
+
{
|
701 |
+
"epoch": 0.32,
|
702 |
+
"learning_rate": 4.860254375479446e-05,
|
703 |
+
"loss": 1.0371,
|
704 |
+
"step": 580
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 0.32,
|
708 |
+
"learning_rate": 4.8578577758940504e-05,
|
709 |
+
"loss": 1.0399,
|
710 |
+
"step": 585
|
711 |
+
},
|
712 |
+
{
|
713 |
+
"epoch": 0.33,
|
714 |
+
"learning_rate": 4.855441401253928e-05,
|
715 |
+
"loss": 1.0411,
|
716 |
+
"step": 590
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 0.33,
|
720 |
+
"learning_rate": 4.8530052718249076e-05,
|
721 |
+
"loss": 1.0476,
|
722 |
+
"step": 595
|
723 |
+
},
|
724 |
+
{
|
725 |
+
"epoch": 0.33,
|
726 |
+
"learning_rate": 4.850549408038498e-05,
|
727 |
+
"loss": 1.0075,
|
728 |
+
"step": 600
|
729 |
+
},
|
730 |
+
{
|
731 |
+
"epoch": 0.33,
|
732 |
+
"learning_rate": 4.848073830491717e-05,
|
733 |
+
"loss": 1.0045,
|
734 |
+
"step": 605
|
735 |
+
},
|
736 |
+
{
|
737 |
+
"epoch": 0.34,
|
738 |
+
"learning_rate": 4.845578559946923e-05,
|
739 |
+
"loss": 1.0368,
|
740 |
+
"step": 610
|
741 |
+
},
|
742 |
+
{
|
743 |
+
"epoch": 0.34,
|
744 |
+
"learning_rate": 4.8430636173316306e-05,
|
745 |
+
"loss": 1.0156,
|
746 |
+
"step": 615
|
747 |
+
},
|
748 |
+
{
|
749 |
+
"epoch": 0.34,
|
750 |
+
"learning_rate": 4.840529023738348e-05,
|
751 |
+
"loss": 1.0334,
|
752 |
+
"step": 620
|
753 |
+
},
|
754 |
+
{
|
755 |
+
"epoch": 0.35,
|
756 |
+
"learning_rate": 4.837974800424389e-05,
|
757 |
+
"loss": 0.9994,
|
758 |
+
"step": 625
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 0.35,
|
762 |
+
"learning_rate": 4.8354009688117026e-05,
|
763 |
+
"loss": 1.0467,
|
764 |
+
"step": 630
|
765 |
+
},
|
766 |
+
{
|
767 |
+
"epoch": 0.35,
|
768 |
+
"learning_rate": 4.8328075504866874e-05,
|
769 |
+
"loss": 0.9968,
|
770 |
+
"step": 635
|
771 |
+
},
|
772 |
+
{
|
773 |
+
"epoch": 0.35,
|
774 |
+
"learning_rate": 4.8301945672000164e-05,
|
775 |
+
"loss": 1.041,
|
776 |
+
"step": 640
|
777 |
+
},
|
778 |
+
{
|
779 |
+
"epoch": 0.36,
|
780 |
+
"learning_rate": 4.8275620408664487e-05,
|
781 |
+
"loss": 0.9811,
|
782 |
+
"step": 645
|
783 |
+
},
|
784 |
+
{
|
785 |
+
"epoch": 0.36,
|
786 |
+
"learning_rate": 4.8249099935646494e-05,
|
787 |
+
"loss": 1.0235,
|
788 |
+
"step": 650
|
789 |
+
},
|
790 |
+
{
|
791 |
+
"epoch": 0.36,
|
792 |
+
"learning_rate": 4.822238447537003e-05,
|
793 |
+
"loss": 1.0152,
|
794 |
+
"step": 655
|
795 |
+
},
|
796 |
+
{
|
797 |
+
"epoch": 0.36,
|
798 |
+
"learning_rate": 4.819547425189429e-05,
|
799 |
+
"loss": 1.038,
|
800 |
+
"step": 660
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 0.37,
|
804 |
+
"learning_rate": 4.81683694909119e-05,
|
805 |
+
"loss": 1.0387,
|
806 |
+
"step": 665
|
807 |
+
},
|
808 |
+
{
|
809 |
+
"epoch": 0.37,
|
810 |
+
"learning_rate": 4.814107041974707e-05,
|
811 |
+
"loss": 1.019,
|
812 |
+
"step": 670
|
813 |
+
},
|
814 |
+
{
|
815 |
+
"epoch": 0.37,
|
816 |
+
"learning_rate": 4.811357726735366e-05,
|
817 |
+
"loss": 1.0403,
|
818 |
+
"step": 675
|
819 |
+
},
|
820 |
+
{
|
821 |
+
"epoch": 0.38,
|
822 |
+
"learning_rate": 4.808589026431324e-05,
|
823 |
+
"loss": 1.0828,
|
824 |
+
"step": 680
|
825 |
+
},
|
826 |
+
{
|
827 |
+
"epoch": 0.38,
|
828 |
+
"learning_rate": 4.805800964283322e-05,
|
829 |
+
"loss": 1.0128,
|
830 |
+
"step": 685
|
831 |
+
},
|
832 |
+
{
|
833 |
+
"epoch": 0.38,
|
834 |
+
"learning_rate": 4.802993563674483e-05,
|
835 |
+
"loss": 1.0502,
|
836 |
+
"step": 690
|
837 |
+
},
|
838 |
+
{
|
839 |
+
"epoch": 0.38,
|
840 |
+
"learning_rate": 4.80016684815012e-05,
|
841 |
+
"loss": 1.0169,
|
842 |
+
"step": 695
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 0.39,
|
846 |
+
"learning_rate": 4.7973208414175406e-05,
|
847 |
+
"loss": 1.0316,
|
848 |
+
"step": 700
|
849 |
+
},
|
850 |
+
{
|
851 |
+
"epoch": 0.39,
|
852 |
+
"learning_rate": 4.794455567345842e-05,
|
853 |
+
"loss": 1.0263,
|
854 |
+
"step": 705
|
855 |
+
},
|
856 |
+
{
|
857 |
+
"epoch": 0.39,
|
858 |
+
"learning_rate": 4.791571049965714e-05,
|
859 |
+
"loss": 1.0801,
|
860 |
+
"step": 710
|
861 |
+
},
|
862 |
+
{
|
863 |
+
"epoch": 0.4,
|
864 |
+
"learning_rate": 4.7886673134692404e-05,
|
865 |
+
"loss": 1.0575,
|
866 |
+
"step": 715
|
867 |
+
},
|
868 |
+
{
|
869 |
+
"epoch": 0.4,
|
870 |
+
"learning_rate": 4.7857443822096905e-05,
|
871 |
+
"loss": 0.9767,
|
872 |
+
"step": 720
|
873 |
+
},
|
874 |
+
{
|
875 |
+
"epoch": 0.4,
|
876 |
+
"learning_rate": 4.782802280701319e-05,
|
877 |
+
"loss": 0.9666,
|
878 |
+
"step": 725
|
879 |
+
},
|
880 |
+
{
|
881 |
+
"epoch": 0.4,
|
882 |
+
"learning_rate": 4.77984103361916e-05,
|
883 |
+
"loss": 0.9983,
|
884 |
+
"step": 730
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 0.41,
|
888 |
+
"learning_rate": 4.776860665798816e-05,
|
889 |
+
"loss": 1.0219,
|
890 |
+
"step": 735
|
891 |
+
},
|
892 |
+
{
|
893 |
+
"epoch": 0.41,
|
894 |
+
"learning_rate": 4.773861202236257e-05,
|
895 |
+
"loss": 0.9963,
|
896 |
+
"step": 740
|
897 |
+
},
|
898 |
+
{
|
899 |
+
"epoch": 0.41,
|
900 |
+
"learning_rate": 4.770842668087602e-05,
|
901 |
+
"loss": 1.0219,
|
902 |
+
"step": 745
|
903 |
+
},
|
904 |
+
{
|
905 |
+
"epoch": 0.41,
|
906 |
+
"learning_rate": 4.767805088668916e-05,
|
907 |
+
"loss": 1.0029,
|
908 |
+
"step": 750
|
909 |
+
},
|
910 |
+
{
|
911 |
+
"epoch": 0.42,
|
912 |
+
"learning_rate": 4.7647484894559936e-05,
|
913 |
+
"loss": 1.0077,
|
914 |
+
"step": 755
|
915 |
+
},
|
916 |
+
{
|
917 |
+
"epoch": 0.42,
|
918 |
+
"learning_rate": 4.7616728960841444e-05,
|
919 |
+
"loss": 0.9908,
|
920 |
+
"step": 760
|
921 |
+
},
|
922 |
+
{
|
923 |
+
"epoch": 0.42,
|
924 |
+
"learning_rate": 4.758578334347981e-05,
|
925 |
+
"loss": 1.0092,
|
926 |
+
"step": 765
|
927 |
+
},
|
928 |
+
{
|
929 |
+
"epoch": 0.43,
|
930 |
+
"learning_rate": 4.7554648302012015e-05,
|
931 |
+
"loss": 0.9874,
|
932 |
+
"step": 770
|
933 |
+
},
|
934 |
+
{
|
935 |
+
"epoch": 0.43,
|
936 |
+
"learning_rate": 4.7523324097563706e-05,
|
937 |
+
"loss": 1.0185,
|
938 |
+
"step": 775
|
939 |
+
},
|
940 |
+
{
|
941 |
+
"epoch": 0.43,
|
942 |
+
"learning_rate": 4.749181099284703e-05,
|
943 |
+
"loss": 1.0533,
|
944 |
+
"step": 780
|
945 |
+
},
|
946 |
+
{
|
947 |
+
"epoch": 0.43,
|
948 |
+
"learning_rate": 4.746010925215839e-05,
|
949 |
+
"loss": 1.0083,
|
950 |
+
"step": 785
|
951 |
+
},
|
952 |
+
{
|
953 |
+
"epoch": 0.44,
|
954 |
+
"learning_rate": 4.74282191413763e-05,
|
955 |
+
"loss": 1.0191,
|
956 |
+
"step": 790
|
957 |
+
},
|
958 |
+
{
|
959 |
+
"epoch": 0.44,
|
960 |
+
"learning_rate": 4.7396140927959045e-05,
|
961 |
+
"loss": 0.9786,
|
962 |
+
"step": 795
|
963 |
+
},
|
964 |
+
{
|
965 |
+
"epoch": 0.44,
|
966 |
+
"learning_rate": 4.7363874880942574e-05,
|
967 |
+
"loss": 1.0197,
|
968 |
+
"step": 800
|
969 |
+
},
|
970 |
+
{
|
971 |
+
"epoch": 0.45,
|
972 |
+
"learning_rate": 4.733142127093813e-05,
|
973 |
+
"loss": 1.0471,
|
974 |
+
"step": 805
|
975 |
+
},
|
976 |
+
{
|
977 |
+
"epoch": 0.45,
|
978 |
+
"learning_rate": 4.7298780370130014e-05,
|
979 |
+
"loss": 1.0134,
|
980 |
+
"step": 810
|
981 |
+
},
|
982 |
+
{
|
983 |
+
"epoch": 0.45,
|
984 |
+
"learning_rate": 4.726595245227336e-05,
|
985 |
+
"loss": 0.9801,
|
986 |
+
"step": 815
|
987 |
+
},
|
988 |
+
{
|
989 |
+
"epoch": 0.45,
|
990 |
+
"learning_rate": 4.723293779269173e-05,
|
991 |
+
"loss": 0.9944,
|
992 |
+
"step": 820
|
993 |
+
},
|
994 |
+
{
|
995 |
+
"epoch": 0.46,
|
996 |
+
"learning_rate": 4.7199736668274924e-05,
|
997 |
+
"loss": 1.0358,
|
998 |
+
"step": 825
|
999 |
+
},
|
1000 |
+
{
|
1001 |
+
"epoch": 0.46,
|
1002 |
+
"learning_rate": 4.716634935747655e-05,
|
1003 |
+
"loss": 0.9907,
|
1004 |
+
"step": 830
|
1005 |
+
},
|
1006 |
+
{
|
1007 |
+
"epoch": 0.46,
|
1008 |
+
"learning_rate": 4.713277614031177e-05,
|
1009 |
+
"loss": 1.0698,
|
1010 |
+
"step": 835
|
1011 |
+
},
|
1012 |
+
{
|
1013 |
+
"epoch": 0.46,
|
1014 |
+
"learning_rate": 4.70990172983549e-05,
|
1015 |
+
"loss": 1.0466,
|
1016 |
+
"step": 840
|
1017 |
+
},
|
1018 |
+
{
|
1019 |
+
"epoch": 0.47,
|
1020 |
+
"learning_rate": 4.706507311473707e-05,
|
1021 |
+
"loss": 0.9489,
|
1022 |
+
"step": 845
|
1023 |
+
},
|
1024 |
+
{
|
1025 |
+
"epoch": 0.47,
|
1026 |
+
"learning_rate": 4.703094387414385e-05,
|
1027 |
+
"loss": 0.9936,
|
1028 |
+
"step": 850
|
1029 |
+
},
|
1030 |
+
{
|
1031 |
+
"epoch": 0.47,
|
1032 |
+
"learning_rate": 4.699662986281288e-05,
|
1033 |
+
"loss": 0.9672,
|
1034 |
+
"step": 855
|
1035 |
+
},
|
1036 |
+
{
|
1037 |
+
"epoch": 0.48,
|
1038 |
+
"learning_rate": 4.696213136853141e-05,
|
1039 |
+
"loss": 1.0164,
|
1040 |
+
"step": 860
|
1041 |
+
},
|
1042 |
+
{
|
1043 |
+
"epoch": 0.48,
|
1044 |
+
"learning_rate": 4.6927448680633954e-05,
|
1045 |
+
"loss": 0.9817,
|
1046 |
+
"step": 865
|
1047 |
+
},
|
1048 |
+
{
|
1049 |
+
"epoch": 0.48,
|
1050 |
+
"learning_rate": 4.689258208999983e-05,
|
1051 |
+
"loss": 1.028,
|
1052 |
+
"step": 870
|
1053 |
+
},
|
1054 |
+
{
|
1055 |
+
"epoch": 0.48,
|
1056 |
+
"learning_rate": 4.6857531889050716e-05,
|
1057 |
+
"loss": 1.0239,
|
1058 |
+
"step": 875
|
1059 |
+
},
|
1060 |
+
{
|
1061 |
+
"epoch": 0.49,
|
1062 |
+
"learning_rate": 4.682229837174821e-05,
|
1063 |
+
"loss": 1.0378,
|
1064 |
+
"step": 880
|
1065 |
+
},
|
1066 |
+
{
|
1067 |
+
"epoch": 0.49,
|
1068 |
+
"learning_rate": 4.678688183359135e-05,
|
1069 |
+
"loss": 0.9908,
|
1070 |
+
"step": 885
|
1071 |
+
},
|
1072 |
+
{
|
1073 |
+
"epoch": 0.49,
|
1074 |
+
"learning_rate": 4.675128257161418e-05,
|
1075 |
+
"loss": 0.9384,
|
1076 |
+
"step": 890
|
1077 |
+
},
|
1078 |
+
{
|
1079 |
+
"epoch": 0.49,
|
1080 |
+
"learning_rate": 4.671550088438319e-05,
|
1081 |
+
"loss": 0.9481,
|
1082 |
+
"step": 895
|
1083 |
+
},
|
1084 |
+
{
|
1085 |
+
"epoch": 0.5,
|
1086 |
+
"learning_rate": 4.6679537071994874e-05,
|
1087 |
+
"loss": 0.9541,
|
1088 |
+
"step": 900
|
1089 |
+
},
|
1090 |
+
{
|
1091 |
+
"epoch": 0.5,
|
1092 |
+
"learning_rate": 4.6643391436073165e-05,
|
1093 |
+
"loss": 0.9787,
|
1094 |
+
"step": 905
|
1095 |
+
},
|
1096 |
+
{
|
1097 |
+
"epoch": 0.5,
|
1098 |
+
"learning_rate": 4.660706427976693e-05,
|
1099 |
+
"loss": 0.9897,
|
1100 |
+
"step": 910
|
1101 |
+
},
|
1102 |
+
{
|
1103 |
+
"epoch": 0.51,
|
1104 |
+
"learning_rate": 4.657055590774745e-05,
|
1105 |
+
"loss": 0.9947,
|
1106 |
+
"step": 915
|
1107 |
+
},
|
1108 |
+
{
|
1109 |
+
"epoch": 0.51,
|
1110 |
+
"learning_rate": 4.6533866626205805e-05,
|
1111 |
+
"loss": 0.9614,
|
1112 |
+
"step": 920
|
1113 |
+
},
|
1114 |
+
{
|
1115 |
+
"epoch": 0.51,
|
1116 |
+
"learning_rate": 4.649699674285036e-05,
|
1117 |
+
"loss": 1.0323,
|
1118 |
+
"step": 925
|
1119 |
+
},
|
1120 |
+
{
|
1121 |
+
"epoch": 0.51,
|
1122 |
+
"learning_rate": 4.645994656690417e-05,
|
1123 |
+
"loss": 1.0345,
|
1124 |
+
"step": 930
|
1125 |
+
},
|
1126 |
+
{
|
1127 |
+
"epoch": 0.52,
|
1128 |
+
"learning_rate": 4.642271640910235e-05,
|
1129 |
+
"loss": 1.0432,
|
1130 |
+
"step": 935
|
1131 |
+
},
|
1132 |
+
{
|
1133 |
+
"epoch": 0.52,
|
1134 |
+
"learning_rate": 4.638530658168954e-05,
|
1135 |
+
"loss": 1.0102,
|
1136 |
+
"step": 940
|
1137 |
+
},
|
1138 |
+
{
|
1139 |
+
"epoch": 0.52,
|
1140 |
+
"learning_rate": 4.6347717398417203e-05,
|
1141 |
+
"loss": 1.0361,
|
1142 |
+
"step": 945
|
1143 |
+
},
|
1144 |
+
{
|
1145 |
+
"epoch": 0.53,
|
1146 |
+
"learning_rate": 4.6309949174541096e-05,
|
1147 |
+
"loss": 0.9818,
|
1148 |
+
"step": 950
|
1149 |
+
},
|
1150 |
+
{
|
1151 |
+
"epoch": 0.53,
|
1152 |
+
"learning_rate": 4.627200222681851e-05,
|
1153 |
+
"loss": 1.0293,
|
1154 |
+
"step": 955
|
1155 |
+
},
|
1156 |
+
{
|
1157 |
+
"epoch": 0.53,
|
1158 |
+
"learning_rate": 4.6233876873505694e-05,
|
1159 |
+
"loss": 1.0125,
|
1160 |
+
"step": 960
|
1161 |
+
},
|
1162 |
+
{
|
1163 |
+
"epoch": 0.53,
|
1164 |
+
"learning_rate": 4.619557343435516e-05,
|
1165 |
+
"loss": 1.0039,
|
1166 |
+
"step": 965
|
1167 |
+
},
|
1168 |
+
{
|
1169 |
+
"epoch": 0.54,
|
1170 |
+
"learning_rate": 4.615709223061302e-05,
|
1171 |
+
"loss": 1.0146,
|
1172 |
+
"step": 970
|
1173 |
+
},
|
1174 |
+
{
|
1175 |
+
"epoch": 0.54,
|
1176 |
+
"learning_rate": 4.611843358501624e-05,
|
1177 |
+
"loss": 1.0352,
|
1178 |
+
"step": 975
|
1179 |
+
},
|
1180 |
+
{
|
1181 |
+
"epoch": 0.54,
|
1182 |
+
"learning_rate": 4.6079597821789993e-05,
|
1183 |
+
"loss": 1.0405,
|
1184 |
+
"step": 980
|
1185 |
+
},
|
1186 |
+
{
|
1187 |
+
"epoch": 0.54,
|
1188 |
+
"learning_rate": 4.604058526664491e-05,
|
1189 |
+
"loss": 0.9834,
|
1190 |
+
"step": 985
|
1191 |
+
},
|
1192 |
+
{
|
1193 |
+
"epoch": 0.55,
|
1194 |
+
"learning_rate": 4.600139624677436e-05,
|
1195 |
+
"loss": 1.0252,
|
1196 |
+
"step": 990
|
1197 |
+
},
|
1198 |
+
{
|
1199 |
+
"epoch": 0.55,
|
1200 |
+
"learning_rate": 4.596203109085168e-05,
|
1201 |
+
"loss": 1.0516,
|
1202 |
+
"step": 995
|
1203 |
+
},
|
1204 |
+
{
|
1205 |
+
"epoch": 0.55,
|
1206 |
+
"learning_rate": 4.5922490129027464e-05,
|
1207 |
+
"loss": 0.9762,
|
1208 |
+
"step": 1000
|
1209 |
+
}
|
1210 |
+
],
|
1211 |
+
"max_steps": 5424,
|
1212 |
+
"num_train_epochs": 3,
|
1213 |
+
"total_flos": 3.2497031184384e+17,
|
1214 |
+
"trial_name": null,
|
1215 |
+
"trial_params": null
|
1216 |
+
}
|
checkpoint-1000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f6a8853599a52b1f15984d75ce4b6434c335fdc67d4509d0b2ca0d8c613590a
|
3 |
+
size 3362
|
checkpoint-1100/README.md
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
---
|
4 |
+
## Training procedure
|
5 |
+
|
6 |
+
|
7 |
+
The following `bitsandbytes` quantization config was used during training:
|
8 |
+
- load_in_8bit: True
|
9 |
+
- llm_int8_threshold: 6.0
|
10 |
+
- llm_int8_skip_modules: None
|
11 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
12 |
+
### Framework versions
|
13 |
+
|
14 |
+
|
15 |
+
- PEFT 0.5.0
|
checkpoint-1100/adapter_config.json
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"auto_mapping": null,
|
3 |
+
"base_model_name_or_path": "meta-llama/Llama-2-7b-chat-hf",
|
4 |
+
"bias": "none",
|
5 |
+
"fan_in_fan_out": false,
|
6 |
+
"inference_mode": true,
|
7 |
+
"init_lora_weights": true,
|
8 |
+
"layers_pattern": null,
|
9 |
+
"layers_to_transform": null,
|
10 |
+
"lora_alpha": 32.0,
|
11 |
+
"lora_dropout": 0.1,
|
12 |
+
"modules_to_save": null,
|
13 |
+
"peft_type": "LORA",
|
14 |
+
"r": 8,
|
15 |
+
"revision": null,
|
16 |
+
"target_modules": [
|
17 |
+
"q_proj",
|
18 |
+
"v_proj"
|
19 |
+
],
|
20 |
+
"task_type": "CAUSAL_LM"
|
21 |
+
}
|
checkpoint-1100/adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f1f39d2917cdf1a2e47072114abfc7e0e13b8b4a01cdb69b12330ff29dc83682
|
3 |
+
size 16821197
|
checkpoint-1100/finetuning_args.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"dpo_beta": 0.1,
|
3 |
+
"finetuning_type": "lora",
|
4 |
+
"lora_alpha": 32.0,
|
5 |
+
"lora_dropout": 0.1,
|
6 |
+
"lora_rank": 8,
|
7 |
+
"lora_target": [
|
8 |
+
"q_proj",
|
9 |
+
"v_proj"
|
10 |
+
],
|
11 |
+
"name_module_trainable": "mlp",
|
12 |
+
"num_hidden_layers": 32,
|
13 |
+
"num_layer_trainable": 3,
|
14 |
+
"ppo_score_norm": false,
|
15 |
+
"resume_lora_training": true
|
16 |
+
}
|
checkpoint-1100/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:debf4fa6b8d820fe570930c6a377cf0649a5e504a4143b130831c8de0e1ac4c9
|
3 |
+
size 33629893
|
checkpoint-1100/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e287b87acb8fc231da6ca55f911bf5ceb9342f5cb41f129c6c2476f5da07bb01
|
3 |
+
size 14575
|
checkpoint-1100/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:677eca5ad6580d3f557bbfda51765525add80f9acfd6c5ca0edf4a229f0c70eb
|
3 |
+
size 557
|
checkpoint-1100/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4eb0c259b7af56a0b5a35ca1140f6215c652a78a4d7f2762afa6896791e5af12
|
3 |
+
size 627
|
checkpoint-1100/trainer_state.json
ADDED
@@ -0,0 +1,1336 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.6082388719933647,
|
5 |
+
"global_step": 1100,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.0,
|
12 |
+
"learning_rate": 4.9999895164082156e-05,
|
13 |
+
"loss": 1.6349,
|
14 |
+
"step": 5
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.01,
|
18 |
+
"learning_rate": 4.999958065720787e-05,
|
19 |
+
"loss": 1.6199,
|
20 |
+
"step": 10
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.01,
|
24 |
+
"learning_rate": 4.999905648201487e-05,
|
25 |
+
"loss": 1.4834,
|
26 |
+
"step": 15
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.01,
|
30 |
+
"learning_rate": 4.999832264289934e-05,
|
31 |
+
"loss": 1.3882,
|
32 |
+
"step": 20
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.01,
|
36 |
+
"learning_rate": 4.999737914601591e-05,
|
37 |
+
"loss": 1.3679,
|
38 |
+
"step": 25
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.02,
|
42 |
+
"learning_rate": 4.999622599927756e-05,
|
43 |
+
"loss": 1.2396,
|
44 |
+
"step": 30
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.02,
|
48 |
+
"learning_rate": 4.999486321235559e-05,
|
49 |
+
"loss": 1.321,
|
50 |
+
"step": 35
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.02,
|
54 |
+
"learning_rate": 4.9993290796679516e-05,
|
55 |
+
"loss": 1.2874,
|
56 |
+
"step": 40
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.02,
|
60 |
+
"learning_rate": 4.999150876543699e-05,
|
61 |
+
"loss": 1.2607,
|
62 |
+
"step": 45
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.03,
|
66 |
+
"learning_rate": 4.9989517133573694e-05,
|
67 |
+
"loss": 1.2454,
|
68 |
+
"step": 50
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.03,
|
72 |
+
"learning_rate": 4.9987315917793174e-05,
|
73 |
+
"loss": 1.2799,
|
74 |
+
"step": 55
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.03,
|
78 |
+
"learning_rate": 4.998490513655676e-05,
|
79 |
+
"loss": 1.2575,
|
80 |
+
"step": 60
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.04,
|
84 |
+
"learning_rate": 4.998228481008337e-05,
|
85 |
+
"loss": 1.2404,
|
86 |
+
"step": 65
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.04,
|
90 |
+
"learning_rate": 4.997945496034934e-05,
|
91 |
+
"loss": 1.2219,
|
92 |
+
"step": 70
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.04,
|
96 |
+
"learning_rate": 4.9976415611088267e-05,
|
97 |
+
"loss": 1.2241,
|
98 |
+
"step": 75
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.04,
|
102 |
+
"learning_rate": 4.997316678779079e-05,
|
103 |
+
"loss": 1.1716,
|
104 |
+
"step": 80
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.05,
|
108 |
+
"learning_rate": 4.996970851770438e-05,
|
109 |
+
"loss": 1.1883,
|
110 |
+
"step": 85
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.05,
|
114 |
+
"learning_rate": 4.9966040829833115e-05,
|
115 |
+
"loss": 1.205,
|
116 |
+
"step": 90
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.05,
|
120 |
+
"learning_rate": 4.9962163754937426e-05,
|
121 |
+
"loss": 1.1246,
|
122 |
+
"step": 95
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.06,
|
126 |
+
"learning_rate": 4.995807732553384e-05,
|
127 |
+
"loss": 1.1636,
|
128 |
+
"step": 100
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.06,
|
132 |
+
"learning_rate": 4.9953781575894723e-05,
|
133 |
+
"loss": 1.158,
|
134 |
+
"step": 105
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 0.06,
|
138 |
+
"learning_rate": 4.9949276542048e-05,
|
139 |
+
"loss": 1.1477,
|
140 |
+
"step": 110
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 0.06,
|
144 |
+
"learning_rate": 4.9944562261776805e-05,
|
145 |
+
"loss": 1.1678,
|
146 |
+
"step": 115
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 0.07,
|
150 |
+
"learning_rate": 4.9939638774619216e-05,
|
151 |
+
"loss": 1.1501,
|
152 |
+
"step": 120
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 0.07,
|
156 |
+
"learning_rate": 4.99345061218679e-05,
|
157 |
+
"loss": 1.1955,
|
158 |
+
"step": 125
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 0.07,
|
162 |
+
"learning_rate": 4.9929164346569756e-05,
|
163 |
+
"loss": 1.1724,
|
164 |
+
"step": 130
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.07,
|
168 |
+
"learning_rate": 4.9923613493525576e-05,
|
169 |
+
"loss": 1.177,
|
170 |
+
"step": 135
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.08,
|
174 |
+
"learning_rate": 4.991785360928968e-05,
|
175 |
+
"loss": 1.1418,
|
176 |
+
"step": 140
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 0.08,
|
180 |
+
"learning_rate": 4.991188474216947e-05,
|
181 |
+
"loss": 1.1898,
|
182 |
+
"step": 145
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 0.08,
|
186 |
+
"learning_rate": 4.9905706942225094e-05,
|
187 |
+
"loss": 1.1479,
|
188 |
+
"step": 150
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 0.09,
|
192 |
+
"learning_rate": 4.9899320261268966e-05,
|
193 |
+
"loss": 1.1356,
|
194 |
+
"step": 155
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 0.09,
|
198 |
+
"learning_rate": 4.989272475286537e-05,
|
199 |
+
"loss": 1.1397,
|
200 |
+
"step": 160
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 0.09,
|
204 |
+
"learning_rate": 4.9885920472330004e-05,
|
205 |
+
"loss": 1.1215,
|
206 |
+
"step": 165
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 0.09,
|
210 |
+
"learning_rate": 4.9878907476729516e-05,
|
211 |
+
"loss": 1.167,
|
212 |
+
"step": 170
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.1,
|
216 |
+
"learning_rate": 4.9871685824881e-05,
|
217 |
+
"loss": 1.1219,
|
218 |
+
"step": 175
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 0.1,
|
222 |
+
"learning_rate": 4.9864255577351534e-05,
|
223 |
+
"loss": 1.0835,
|
224 |
+
"step": 180
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 0.1,
|
228 |
+
"learning_rate": 4.985661679645769e-05,
|
229 |
+
"loss": 1.0721,
|
230 |
+
"step": 185
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 0.11,
|
234 |
+
"learning_rate": 4.9848769546264915e-05,
|
235 |
+
"loss": 1.0692,
|
236 |
+
"step": 190
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 0.11,
|
240 |
+
"learning_rate": 4.9840713892587146e-05,
|
241 |
+
"loss": 1.0488,
|
242 |
+
"step": 195
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 0.11,
|
246 |
+
"learning_rate": 4.983244990298609e-05,
|
247 |
+
"loss": 1.1285,
|
248 |
+
"step": 200
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 0.11,
|
252 |
+
"learning_rate": 4.982397764677081e-05,
|
253 |
+
"loss": 1.0832,
|
254 |
+
"step": 205
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.12,
|
258 |
+
"learning_rate": 4.981529719499704e-05,
|
259 |
+
"loss": 1.0652,
|
260 |
+
"step": 210
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 0.12,
|
264 |
+
"learning_rate": 4.980640862046663e-05,
|
265 |
+
"loss": 1.1043,
|
266 |
+
"step": 215
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 0.12,
|
270 |
+
"learning_rate": 4.979731199772693e-05,
|
271 |
+
"loss": 1.112,
|
272 |
+
"step": 220
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 0.12,
|
276 |
+
"learning_rate": 4.9788007403070146e-05,
|
277 |
+
"loss": 1.1029,
|
278 |
+
"step": 225
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 0.13,
|
282 |
+
"learning_rate": 4.977849491453277e-05,
|
283 |
+
"loss": 1.0869,
|
284 |
+
"step": 230
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 0.13,
|
288 |
+
"learning_rate": 4.976877461189481e-05,
|
289 |
+
"loss": 1.0843,
|
290 |
+
"step": 235
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 0.13,
|
294 |
+
"learning_rate": 4.975884657667922e-05,
|
295 |
+
"loss": 1.0789,
|
296 |
+
"step": 240
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.14,
|
300 |
+
"learning_rate": 4.974871089215118e-05,
|
301 |
+
"loss": 1.0449,
|
302 |
+
"step": 245
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 0.14,
|
306 |
+
"learning_rate": 4.9738367643317405e-05,
|
307 |
+
"loss": 1.1053,
|
308 |
+
"step": 250
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 0.14,
|
312 |
+
"learning_rate": 4.9727816916925395e-05,
|
313 |
+
"loss": 1.0651,
|
314 |
+
"step": 255
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 0.14,
|
318 |
+
"learning_rate": 4.971705880146276e-05,
|
319 |
+
"loss": 1.0828,
|
320 |
+
"step": 260
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 0.15,
|
324 |
+
"learning_rate": 4.970609338715646e-05,
|
325 |
+
"loss": 1.0932,
|
326 |
+
"step": 265
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 0.15,
|
330 |
+
"learning_rate": 4.969492076597203e-05,
|
331 |
+
"loss": 1.0648,
|
332 |
+
"step": 270
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 0.15,
|
336 |
+
"learning_rate": 4.968354103161283e-05,
|
337 |
+
"loss": 1.0948,
|
338 |
+
"step": 275
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.15,
|
342 |
+
"learning_rate": 4.967195427951926e-05,
|
343 |
+
"loss": 1.0721,
|
344 |
+
"step": 280
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 0.16,
|
348 |
+
"learning_rate": 4.9660160606867936e-05,
|
349 |
+
"loss": 1.124,
|
350 |
+
"step": 285
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 0.16,
|
354 |
+
"learning_rate": 4.9648160112570896e-05,
|
355 |
+
"loss": 1.0963,
|
356 |
+
"step": 290
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 0.16,
|
360 |
+
"learning_rate": 4.9635952897274773e-05,
|
361 |
+
"loss": 1.1078,
|
362 |
+
"step": 295
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 0.17,
|
366 |
+
"learning_rate": 4.9623539063359925e-05,
|
367 |
+
"loss": 1.1059,
|
368 |
+
"step": 300
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 0.17,
|
372 |
+
"learning_rate": 4.961091871493962e-05,
|
373 |
+
"loss": 1.1032,
|
374 |
+
"step": 305
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 0.17,
|
378 |
+
"learning_rate": 4.959809195785912e-05,
|
379 |
+
"loss": 1.0595,
|
380 |
+
"step": 310
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.17,
|
384 |
+
"learning_rate": 4.958505889969481e-05,
|
385 |
+
"loss": 1.1096,
|
386 |
+
"step": 315
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"epoch": 0.18,
|
390 |
+
"learning_rate": 4.957181964975329e-05,
|
391 |
+
"loss": 1.0589,
|
392 |
+
"step": 320
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 0.18,
|
396 |
+
"learning_rate": 4.955837431907049e-05,
|
397 |
+
"loss": 1.0608,
|
398 |
+
"step": 325
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 0.18,
|
402 |
+
"learning_rate": 4.954472302041069e-05,
|
403 |
+
"loss": 1.0819,
|
404 |
+
"step": 330
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 0.19,
|
408 |
+
"learning_rate": 4.9530865868265605e-05,
|
409 |
+
"loss": 1.0759,
|
410 |
+
"step": 335
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 0.19,
|
414 |
+
"learning_rate": 4.951680297885342e-05,
|
415 |
+
"loss": 1.0515,
|
416 |
+
"step": 340
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 0.19,
|
420 |
+
"learning_rate": 4.950253447011779e-05,
|
421 |
+
"loss": 1.0371,
|
422 |
+
"step": 345
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.19,
|
426 |
+
"learning_rate": 4.948806046172691e-05,
|
427 |
+
"loss": 1.0619,
|
428 |
+
"step": 350
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 0.2,
|
432 |
+
"learning_rate": 4.947338107507245e-05,
|
433 |
+
"loss": 1.0757,
|
434 |
+
"step": 355
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 0.2,
|
438 |
+
"learning_rate": 4.945849643326857e-05,
|
439 |
+
"loss": 1.0686,
|
440 |
+
"step": 360
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 0.2,
|
444 |
+
"learning_rate": 4.9443406661150874e-05,
|
445 |
+
"loss": 1.0809,
|
446 |
+
"step": 365
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 0.2,
|
450 |
+
"learning_rate": 4.942811188527537e-05,
|
451 |
+
"loss": 1.0704,
|
452 |
+
"step": 370
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 0.21,
|
456 |
+
"learning_rate": 4.941261223391742e-05,
|
457 |
+
"loss": 1.0655,
|
458 |
+
"step": 375
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 0.21,
|
462 |
+
"learning_rate": 4.939690783707063e-05,
|
463 |
+
"loss": 1.1182,
|
464 |
+
"step": 380
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.21,
|
468 |
+
"learning_rate": 4.938099882644578e-05,
|
469 |
+
"loss": 1.081,
|
470 |
+
"step": 385
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 0.22,
|
474 |
+
"learning_rate": 4.9364885335469734e-05,
|
475 |
+
"loss": 1.0792,
|
476 |
+
"step": 390
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"epoch": 0.22,
|
480 |
+
"learning_rate": 4.93485674992843e-05,
|
481 |
+
"loss": 1.0244,
|
482 |
+
"step": 395
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 0.22,
|
486 |
+
"learning_rate": 4.933204545474511e-05,
|
487 |
+
"loss": 1.0531,
|
488 |
+
"step": 400
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 0.22,
|
492 |
+
"learning_rate": 4.9315319340420465e-05,
|
493 |
+
"loss": 1.048,
|
494 |
+
"step": 405
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 0.23,
|
498 |
+
"learning_rate": 4.929838929659015e-05,
|
499 |
+
"loss": 1.04,
|
500 |
+
"step": 410
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 0.23,
|
504 |
+
"learning_rate": 4.9281255465244314e-05,
|
505 |
+
"loss": 1.0686,
|
506 |
+
"step": 415
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.23,
|
510 |
+
"learning_rate": 4.926391799008223e-05,
|
511 |
+
"loss": 1.0933,
|
512 |
+
"step": 420
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"epoch": 0.24,
|
516 |
+
"learning_rate": 4.924637701651111e-05,
|
517 |
+
"loss": 1.0313,
|
518 |
+
"step": 425
|
519 |
+
},
|
520 |
+
{
|
521 |
+
"epoch": 0.24,
|
522 |
+
"learning_rate": 4.9228632691644874e-05,
|
523 |
+
"loss": 1.0811,
|
524 |
+
"step": 430
|
525 |
+
},
|
526 |
+
{
|
527 |
+
"epoch": 0.24,
|
528 |
+
"learning_rate": 4.921068516430293e-05,
|
529 |
+
"loss": 1.0617,
|
530 |
+
"step": 435
|
531 |
+
},
|
532 |
+
{
|
533 |
+
"epoch": 0.24,
|
534 |
+
"learning_rate": 4.919253458500892e-05,
|
535 |
+
"loss": 1.0482,
|
536 |
+
"step": 440
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 0.25,
|
540 |
+
"learning_rate": 4.9174181105989445e-05,
|
541 |
+
"loss": 1.0681,
|
542 |
+
"step": 445
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 0.25,
|
546 |
+
"learning_rate": 4.9155624881172834e-05,
|
547 |
+
"loss": 1.0476,
|
548 |
+
"step": 450
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 0.25,
|
552 |
+
"learning_rate": 4.913686606618777e-05,
|
553 |
+
"loss": 1.0463,
|
554 |
+
"step": 455
|
555 |
+
},
|
556 |
+
{
|
557 |
+
"epoch": 0.25,
|
558 |
+
"learning_rate": 4.911790481836208e-05,
|
559 |
+
"loss": 1.0213,
|
560 |
+
"step": 460
|
561 |
+
},
|
562 |
+
{
|
563 |
+
"epoch": 0.26,
|
564 |
+
"learning_rate": 4.909874129672133e-05,
|
565 |
+
"loss": 0.9855,
|
566 |
+
"step": 465
|
567 |
+
},
|
568 |
+
{
|
569 |
+
"epoch": 0.26,
|
570 |
+
"learning_rate": 4.907937566198757e-05,
|
571 |
+
"loss": 1.045,
|
572 |
+
"step": 470
|
573 |
+
},
|
574 |
+
{
|
575 |
+
"epoch": 0.26,
|
576 |
+
"learning_rate": 4.9059808076577914e-05,
|
577 |
+
"loss": 1.0442,
|
578 |
+
"step": 475
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 0.27,
|
582 |
+
"learning_rate": 4.904003870460323e-05,
|
583 |
+
"loss": 1.0354,
|
584 |
+
"step": 480
|
585 |
+
},
|
586 |
+
{
|
587 |
+
"epoch": 0.27,
|
588 |
+
"learning_rate": 4.9020067711866735e-05,
|
589 |
+
"loss": 1.0331,
|
590 |
+
"step": 485
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 0.27,
|
594 |
+
"learning_rate": 4.899989526586261e-05,
|
595 |
+
"loss": 1.0585,
|
596 |
+
"step": 490
|
597 |
+
},
|
598 |
+
{
|
599 |
+
"epoch": 0.27,
|
600 |
+
"learning_rate": 4.8979521535774636e-05,
|
601 |
+
"loss": 1.0223,
|
602 |
+
"step": 495
|
603 |
+
},
|
604 |
+
{
|
605 |
+
"epoch": 0.28,
|
606 |
+
"learning_rate": 4.895894669247468e-05,
|
607 |
+
"loss": 1.0118,
|
608 |
+
"step": 500
|
609 |
+
},
|
610 |
+
{
|
611 |
+
"epoch": 0.28,
|
612 |
+
"learning_rate": 4.8938170908521356e-05,
|
613 |
+
"loss": 1.0508,
|
614 |
+
"step": 505
|
615 |
+
},
|
616 |
+
{
|
617 |
+
"epoch": 0.28,
|
618 |
+
"learning_rate": 4.8917194358158534e-05,
|
619 |
+
"loss": 1.0656,
|
620 |
+
"step": 510
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 0.28,
|
624 |
+
"learning_rate": 4.8896017217313886e-05,
|
625 |
+
"loss": 1.0655,
|
626 |
+
"step": 515
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 0.29,
|
630 |
+
"learning_rate": 4.887463966359741e-05,
|
631 |
+
"loss": 1.0833,
|
632 |
+
"step": 520
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 0.29,
|
636 |
+
"learning_rate": 4.8853061876299956e-05,
|
637 |
+
"loss": 1.068,
|
638 |
+
"step": 525
|
639 |
+
},
|
640 |
+
{
|
641 |
+
"epoch": 0.29,
|
642 |
+
"learning_rate": 4.8831284036391684e-05,
|
643 |
+
"loss": 1.0487,
|
644 |
+
"step": 530
|
645 |
+
},
|
646 |
+
{
|
647 |
+
"epoch": 0.3,
|
648 |
+
"learning_rate": 4.880930632652058e-05,
|
649 |
+
"loss": 1.059,
|
650 |
+
"step": 535
|
651 |
+
},
|
652 |
+
{
|
653 |
+
"epoch": 0.3,
|
654 |
+
"learning_rate": 4.878712893101092e-05,
|
655 |
+
"loss": 1.0408,
|
656 |
+
"step": 540
|
657 |
+
},
|
658 |
+
{
|
659 |
+
"epoch": 0.3,
|
660 |
+
"learning_rate": 4.876475203586171e-05,
|
661 |
+
"loss": 0.9976,
|
662 |
+
"step": 545
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 0.3,
|
666 |
+
"learning_rate": 4.874217582874514e-05,
|
667 |
+
"loss": 1.0358,
|
668 |
+
"step": 550
|
669 |
+
},
|
670 |
+
{
|
671 |
+
"epoch": 0.31,
|
672 |
+
"learning_rate": 4.8719400499005e-05,
|
673 |
+
"loss": 1.0073,
|
674 |
+
"step": 555
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 0.31,
|
678 |
+
"learning_rate": 4.869642623765509e-05,
|
679 |
+
"loss": 1.0742,
|
680 |
+
"step": 560
|
681 |
+
},
|
682 |
+
{
|
683 |
+
"epoch": 0.31,
|
684 |
+
"learning_rate": 4.867325323737765e-05,
|
685 |
+
"loss": 1.0463,
|
686 |
+
"step": 565
|
687 |
+
},
|
688 |
+
{
|
689 |
+
"epoch": 0.32,
|
690 |
+
"learning_rate": 4.864988169252168e-05,
|
691 |
+
"loss": 1.0242,
|
692 |
+
"step": 570
|
693 |
+
},
|
694 |
+
{
|
695 |
+
"epoch": 0.32,
|
696 |
+
"learning_rate": 4.8626311799101375e-05,
|
697 |
+
"loss": 1.0773,
|
698 |
+
"step": 575
|
699 |
+
},
|
700 |
+
{
|
701 |
+
"epoch": 0.32,
|
702 |
+
"learning_rate": 4.860254375479446e-05,
|
703 |
+
"loss": 1.0371,
|
704 |
+
"step": 580
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 0.32,
|
708 |
+
"learning_rate": 4.8578577758940504e-05,
|
709 |
+
"loss": 1.0399,
|
710 |
+
"step": 585
|
711 |
+
},
|
712 |
+
{
|
713 |
+
"epoch": 0.33,
|
714 |
+
"learning_rate": 4.855441401253928e-05,
|
715 |
+
"loss": 1.0411,
|
716 |
+
"step": 590
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 0.33,
|
720 |
+
"learning_rate": 4.8530052718249076e-05,
|
721 |
+
"loss": 1.0476,
|
722 |
+
"step": 595
|
723 |
+
},
|
724 |
+
{
|
725 |
+
"epoch": 0.33,
|
726 |
+
"learning_rate": 4.850549408038498e-05,
|
727 |
+
"loss": 1.0075,
|
728 |
+
"step": 600
|
729 |
+
},
|
730 |
+
{
|
731 |
+
"epoch": 0.33,
|
732 |
+
"learning_rate": 4.848073830491717e-05,
|
733 |
+
"loss": 1.0045,
|
734 |
+
"step": 605
|
735 |
+
},
|
736 |
+
{
|
737 |
+
"epoch": 0.34,
|
738 |
+
"learning_rate": 4.845578559946923e-05,
|
739 |
+
"loss": 1.0368,
|
740 |
+
"step": 610
|
741 |
+
},
|
742 |
+
{
|
743 |
+
"epoch": 0.34,
|
744 |
+
"learning_rate": 4.8430636173316306e-05,
|
745 |
+
"loss": 1.0156,
|
746 |
+
"step": 615
|
747 |
+
},
|
748 |
+
{
|
749 |
+
"epoch": 0.34,
|
750 |
+
"learning_rate": 4.840529023738348e-05,
|
751 |
+
"loss": 1.0334,
|
752 |
+
"step": 620
|
753 |
+
},
|
754 |
+
{
|
755 |
+
"epoch": 0.35,
|
756 |
+
"learning_rate": 4.837974800424389e-05,
|
757 |
+
"loss": 0.9994,
|
758 |
+
"step": 625
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 0.35,
|
762 |
+
"learning_rate": 4.8354009688117026e-05,
|
763 |
+
"loss": 1.0467,
|
764 |
+
"step": 630
|
765 |
+
},
|
766 |
+
{
|
767 |
+
"epoch": 0.35,
|
768 |
+
"learning_rate": 4.8328075504866874e-05,
|
769 |
+
"loss": 0.9968,
|
770 |
+
"step": 635
|
771 |
+
},
|
772 |
+
{
|
773 |
+
"epoch": 0.35,
|
774 |
+
"learning_rate": 4.8301945672000164e-05,
|
775 |
+
"loss": 1.041,
|
776 |
+
"step": 640
|
777 |
+
},
|
778 |
+
{
|
779 |
+
"epoch": 0.36,
|
780 |
+
"learning_rate": 4.8275620408664487e-05,
|
781 |
+
"loss": 0.9811,
|
782 |
+
"step": 645
|
783 |
+
},
|
784 |
+
{
|
785 |
+
"epoch": 0.36,
|
786 |
+
"learning_rate": 4.8249099935646494e-05,
|
787 |
+
"loss": 1.0235,
|
788 |
+
"step": 650
|
789 |
+
},
|
790 |
+
{
|
791 |
+
"epoch": 0.36,
|
792 |
+
"learning_rate": 4.822238447537003e-05,
|
793 |
+
"loss": 1.0152,
|
794 |
+
"step": 655
|
795 |
+
},
|
796 |
+
{
|
797 |
+
"epoch": 0.36,
|
798 |
+
"learning_rate": 4.819547425189429e-05,
|
799 |
+
"loss": 1.038,
|
800 |
+
"step": 660
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 0.37,
|
804 |
+
"learning_rate": 4.81683694909119e-05,
|
805 |
+
"loss": 1.0387,
|
806 |
+
"step": 665
|
807 |
+
},
|
808 |
+
{
|
809 |
+
"epoch": 0.37,
|
810 |
+
"learning_rate": 4.814107041974707e-05,
|
811 |
+
"loss": 1.019,
|
812 |
+
"step": 670
|
813 |
+
},
|
814 |
+
{
|
815 |
+
"epoch": 0.37,
|
816 |
+
"learning_rate": 4.811357726735366e-05,
|
817 |
+
"loss": 1.0403,
|
818 |
+
"step": 675
|
819 |
+
},
|
820 |
+
{
|
821 |
+
"epoch": 0.38,
|
822 |
+
"learning_rate": 4.808589026431324e-05,
|
823 |
+
"loss": 1.0828,
|
824 |
+
"step": 680
|
825 |
+
},
|
826 |
+
{
|
827 |
+
"epoch": 0.38,
|
828 |
+
"learning_rate": 4.805800964283322e-05,
|
829 |
+
"loss": 1.0128,
|
830 |
+
"step": 685
|
831 |
+
},
|
832 |
+
{
|
833 |
+
"epoch": 0.38,
|
834 |
+
"learning_rate": 4.802993563674483e-05,
|
835 |
+
"loss": 1.0502,
|
836 |
+
"step": 690
|
837 |
+
},
|
838 |
+
{
|
839 |
+
"epoch": 0.38,
|
840 |
+
"learning_rate": 4.80016684815012e-05,
|
841 |
+
"loss": 1.0169,
|
842 |
+
"step": 695
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 0.39,
|
846 |
+
"learning_rate": 4.7973208414175406e-05,
|
847 |
+
"loss": 1.0316,
|
848 |
+
"step": 700
|
849 |
+
},
|
850 |
+
{
|
851 |
+
"epoch": 0.39,
|
852 |
+
"learning_rate": 4.794455567345842e-05,
|
853 |
+
"loss": 1.0263,
|
854 |
+
"step": 705
|
855 |
+
},
|
856 |
+
{
|
857 |
+
"epoch": 0.39,
|
858 |
+
"learning_rate": 4.791571049965714e-05,
|
859 |
+
"loss": 1.0801,
|
860 |
+
"step": 710
|
861 |
+
},
|
862 |
+
{
|
863 |
+
"epoch": 0.4,
|
864 |
+
"learning_rate": 4.7886673134692404e-05,
|
865 |
+
"loss": 1.0575,
|
866 |
+
"step": 715
|
867 |
+
},
|
868 |
+
{
|
869 |
+
"epoch": 0.4,
|
870 |
+
"learning_rate": 4.7857443822096905e-05,
|
871 |
+
"loss": 0.9767,
|
872 |
+
"step": 720
|
873 |
+
},
|
874 |
+
{
|
875 |
+
"epoch": 0.4,
|
876 |
+
"learning_rate": 4.782802280701319e-05,
|
877 |
+
"loss": 0.9666,
|
878 |
+
"step": 725
|
879 |
+
},
|
880 |
+
{
|
881 |
+
"epoch": 0.4,
|
882 |
+
"learning_rate": 4.77984103361916e-05,
|
883 |
+
"loss": 0.9983,
|
884 |
+
"step": 730
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 0.41,
|
888 |
+
"learning_rate": 4.776860665798816e-05,
|
889 |
+
"loss": 1.0219,
|
890 |
+
"step": 735
|
891 |
+
},
|
892 |
+
{
|
893 |
+
"epoch": 0.41,
|
894 |
+
"learning_rate": 4.773861202236257e-05,
|
895 |
+
"loss": 0.9963,
|
896 |
+
"step": 740
|
897 |
+
},
|
898 |
+
{
|
899 |
+
"epoch": 0.41,
|
900 |
+
"learning_rate": 4.770842668087602e-05,
|
901 |
+
"loss": 1.0219,
|
902 |
+
"step": 745
|
903 |
+
},
|
904 |
+
{
|
905 |
+
"epoch": 0.41,
|
906 |
+
"learning_rate": 4.767805088668916e-05,
|
907 |
+
"loss": 1.0029,
|
908 |
+
"step": 750
|
909 |
+
},
|
910 |
+
{
|
911 |
+
"epoch": 0.42,
|
912 |
+
"learning_rate": 4.7647484894559936e-05,
|
913 |
+
"loss": 1.0077,
|
914 |
+
"step": 755
|
915 |
+
},
|
916 |
+
{
|
917 |
+
"epoch": 0.42,
|
918 |
+
"learning_rate": 4.7616728960841444e-05,
|
919 |
+
"loss": 0.9908,
|
920 |
+
"step": 760
|
921 |
+
},
|
922 |
+
{
|
923 |
+
"epoch": 0.42,
|
924 |
+
"learning_rate": 4.758578334347981e-05,
|
925 |
+
"loss": 1.0092,
|
926 |
+
"step": 765
|
927 |
+
},
|
928 |
+
{
|
929 |
+
"epoch": 0.43,
|
930 |
+
"learning_rate": 4.7554648302012015e-05,
|
931 |
+
"loss": 0.9874,
|
932 |
+
"step": 770
|
933 |
+
},
|
934 |
+
{
|
935 |
+
"epoch": 0.43,
|
936 |
+
"learning_rate": 4.7523324097563706e-05,
|
937 |
+
"loss": 1.0185,
|
938 |
+
"step": 775
|
939 |
+
},
|
940 |
+
{
|
941 |
+
"epoch": 0.43,
|
942 |
+
"learning_rate": 4.749181099284703e-05,
|
943 |
+
"loss": 1.0533,
|
944 |
+
"step": 780
|
945 |
+
},
|
946 |
+
{
|
947 |
+
"epoch": 0.43,
|
948 |
+
"learning_rate": 4.746010925215839e-05,
|
949 |
+
"loss": 1.0083,
|
950 |
+
"step": 785
|
951 |
+
},
|
952 |
+
{
|
953 |
+
"epoch": 0.44,
|
954 |
+
"learning_rate": 4.74282191413763e-05,
|
955 |
+
"loss": 1.0191,
|
956 |
+
"step": 790
|
957 |
+
},
|
958 |
+
{
|
959 |
+
"epoch": 0.44,
|
960 |
+
"learning_rate": 4.7396140927959045e-05,
|
961 |
+
"loss": 0.9786,
|
962 |
+
"step": 795
|
963 |
+
},
|
964 |
+
{
|
965 |
+
"epoch": 0.44,
|
966 |
+
"learning_rate": 4.7363874880942574e-05,
|
967 |
+
"loss": 1.0197,
|
968 |
+
"step": 800
|
969 |
+
},
|
970 |
+
{
|
971 |
+
"epoch": 0.45,
|
972 |
+
"learning_rate": 4.733142127093813e-05,
|
973 |
+
"loss": 1.0471,
|
974 |
+
"step": 805
|
975 |
+
},
|
976 |
+
{
|
977 |
+
"epoch": 0.45,
|
978 |
+
"learning_rate": 4.7298780370130014e-05,
|
979 |
+
"loss": 1.0134,
|
980 |
+
"step": 810
|
981 |
+
},
|
982 |
+
{
|
983 |
+
"epoch": 0.45,
|
984 |
+
"learning_rate": 4.726595245227336e-05,
|
985 |
+
"loss": 0.9801,
|
986 |
+
"step": 815
|
987 |
+
},
|
988 |
+
{
|
989 |
+
"epoch": 0.45,
|
990 |
+
"learning_rate": 4.723293779269173e-05,
|
991 |
+
"loss": 0.9944,
|
992 |
+
"step": 820
|
993 |
+
},
|
994 |
+
{
|
995 |
+
"epoch": 0.46,
|
996 |
+
"learning_rate": 4.7199736668274924e-05,
|
997 |
+
"loss": 1.0358,
|
998 |
+
"step": 825
|
999 |
+
},
|
1000 |
+
{
|
1001 |
+
"epoch": 0.46,
|
1002 |
+
"learning_rate": 4.716634935747655e-05,
|
1003 |
+
"loss": 0.9907,
|
1004 |
+
"step": 830
|
1005 |
+
},
|
1006 |
+
{
|
1007 |
+
"epoch": 0.46,
|
1008 |
+
"learning_rate": 4.713277614031177e-05,
|
1009 |
+
"loss": 1.0698,
|
1010 |
+
"step": 835
|
1011 |
+
},
|
1012 |
+
{
|
1013 |
+
"epoch": 0.46,
|
1014 |
+
"learning_rate": 4.70990172983549e-05,
|
1015 |
+
"loss": 1.0466,
|
1016 |
+
"step": 840
|
1017 |
+
},
|
1018 |
+
{
|
1019 |
+
"epoch": 0.47,
|
1020 |
+
"learning_rate": 4.706507311473707e-05,
|
1021 |
+
"loss": 0.9489,
|
1022 |
+
"step": 845
|
1023 |
+
},
|
1024 |
+
{
|
1025 |
+
"epoch": 0.47,
|
1026 |
+
"learning_rate": 4.703094387414385e-05,
|
1027 |
+
"loss": 0.9936,
|
1028 |
+
"step": 850
|
1029 |
+
},
|
1030 |
+
{
|
1031 |
+
"epoch": 0.47,
|
1032 |
+
"learning_rate": 4.699662986281288e-05,
|
1033 |
+
"loss": 0.9672,
|
1034 |
+
"step": 855
|
1035 |
+
},
|
1036 |
+
{
|
1037 |
+
"epoch": 0.48,
|
1038 |
+
"learning_rate": 4.696213136853141e-05,
|
1039 |
+
"loss": 1.0164,
|
1040 |
+
"step": 860
|
1041 |
+
},
|
1042 |
+
{
|
1043 |
+
"epoch": 0.48,
|
1044 |
+
"learning_rate": 4.6927448680633954e-05,
|
1045 |
+
"loss": 0.9817,
|
1046 |
+
"step": 865
|
1047 |
+
},
|
1048 |
+
{
|
1049 |
+
"epoch": 0.48,
|
1050 |
+
"learning_rate": 4.689258208999983e-05,
|
1051 |
+
"loss": 1.028,
|
1052 |
+
"step": 870
|
1053 |
+
},
|
1054 |
+
{
|
1055 |
+
"epoch": 0.48,
|
1056 |
+
"learning_rate": 4.6857531889050716e-05,
|
1057 |
+
"loss": 1.0239,
|
1058 |
+
"step": 875
|
1059 |
+
},
|
1060 |
+
{
|
1061 |
+
"epoch": 0.49,
|
1062 |
+
"learning_rate": 4.682229837174821e-05,
|
1063 |
+
"loss": 1.0378,
|
1064 |
+
"step": 880
|
1065 |
+
},
|
1066 |
+
{
|
1067 |
+
"epoch": 0.49,
|
1068 |
+
"learning_rate": 4.678688183359135e-05,
|
1069 |
+
"loss": 0.9908,
|
1070 |
+
"step": 885
|
1071 |
+
},
|
1072 |
+
{
|
1073 |
+
"epoch": 0.49,
|
1074 |
+
"learning_rate": 4.675128257161418e-05,
|
1075 |
+
"loss": 0.9384,
|
1076 |
+
"step": 890
|
1077 |
+
},
|
1078 |
+
{
|
1079 |
+
"epoch": 0.49,
|
1080 |
+
"learning_rate": 4.671550088438319e-05,
|
1081 |
+
"loss": 0.9481,
|
1082 |
+
"step": 895
|
1083 |
+
},
|
1084 |
+
{
|
1085 |
+
"epoch": 0.5,
|
1086 |
+
"learning_rate": 4.6679537071994874e-05,
|
1087 |
+
"loss": 0.9541,
|
1088 |
+
"step": 900
|
1089 |
+
},
|
1090 |
+
{
|
1091 |
+
"epoch": 0.5,
|
1092 |
+
"learning_rate": 4.6643391436073165e-05,
|
1093 |
+
"loss": 0.9787,
|
1094 |
+
"step": 905
|
1095 |
+
},
|
1096 |
+
{
|
1097 |
+
"epoch": 0.5,
|
1098 |
+
"learning_rate": 4.660706427976693e-05,
|
1099 |
+
"loss": 0.9897,
|
1100 |
+
"step": 910
|
1101 |
+
},
|
1102 |
+
{
|
1103 |
+
"epoch": 0.51,
|
1104 |
+
"learning_rate": 4.657055590774745e-05,
|
1105 |
+
"loss": 0.9947,
|
1106 |
+
"step": 915
|
1107 |
+
},
|
1108 |
+
{
|
1109 |
+
"epoch": 0.51,
|
1110 |
+
"learning_rate": 4.6533866626205805e-05,
|
1111 |
+
"loss": 0.9614,
|
1112 |
+
"step": 920
|
1113 |
+
},
|
1114 |
+
{
|
1115 |
+
"epoch": 0.51,
|
1116 |
+
"learning_rate": 4.649699674285036e-05,
|
1117 |
+
"loss": 1.0323,
|
1118 |
+
"step": 925
|
1119 |
+
},
|
1120 |
+
{
|
1121 |
+
"epoch": 0.51,
|
1122 |
+
"learning_rate": 4.645994656690417e-05,
|
1123 |
+
"loss": 1.0345,
|
1124 |
+
"step": 930
|
1125 |
+
},
|
1126 |
+
{
|
1127 |
+
"epoch": 0.52,
|
1128 |
+
"learning_rate": 4.642271640910235e-05,
|
1129 |
+
"loss": 1.0432,
|
1130 |
+
"step": 935
|
1131 |
+
},
|
1132 |
+
{
|
1133 |
+
"epoch": 0.52,
|
1134 |
+
"learning_rate": 4.638530658168954e-05,
|
1135 |
+
"loss": 1.0102,
|
1136 |
+
"step": 940
|
1137 |
+
},
|
1138 |
+
{
|
1139 |
+
"epoch": 0.52,
|
1140 |
+
"learning_rate": 4.6347717398417203e-05,
|
1141 |
+
"loss": 1.0361,
|
1142 |
+
"step": 945
|
1143 |
+
},
|
1144 |
+
{
|
1145 |
+
"epoch": 0.53,
|
1146 |
+
"learning_rate": 4.6309949174541096e-05,
|
1147 |
+
"loss": 0.9818,
|
1148 |
+
"step": 950
|
1149 |
+
},
|
1150 |
+
{
|
1151 |
+
"epoch": 0.53,
|
1152 |
+
"learning_rate": 4.627200222681851e-05,
|
1153 |
+
"loss": 1.0293,
|
1154 |
+
"step": 955
|
1155 |
+
},
|
1156 |
+
{
|
1157 |
+
"epoch": 0.53,
|
1158 |
+
"learning_rate": 4.6233876873505694e-05,
|
1159 |
+
"loss": 1.0125,
|
1160 |
+
"step": 960
|
1161 |
+
},
|
1162 |
+
{
|
1163 |
+
"epoch": 0.53,
|
1164 |
+
"learning_rate": 4.619557343435516e-05,
|
1165 |
+
"loss": 1.0039,
|
1166 |
+
"step": 965
|
1167 |
+
},
|
1168 |
+
{
|
1169 |
+
"epoch": 0.54,
|
1170 |
+
"learning_rate": 4.615709223061302e-05,
|
1171 |
+
"loss": 1.0146,
|
1172 |
+
"step": 970
|
1173 |
+
},
|
1174 |
+
{
|
1175 |
+
"epoch": 0.54,
|
1176 |
+
"learning_rate": 4.611843358501624e-05,
|
1177 |
+
"loss": 1.0352,
|
1178 |
+
"step": 975
|
1179 |
+
},
|
1180 |
+
{
|
1181 |
+
"epoch": 0.54,
|
1182 |
+
"learning_rate": 4.6079597821789993e-05,
|
1183 |
+
"loss": 1.0405,
|
1184 |
+
"step": 980
|
1185 |
+
},
|
1186 |
+
{
|
1187 |
+
"epoch": 0.54,
|
1188 |
+
"learning_rate": 4.604058526664491e-05,
|
1189 |
+
"loss": 0.9834,
|
1190 |
+
"step": 985
|
1191 |
+
},
|
1192 |
+
{
|
1193 |
+
"epoch": 0.55,
|
1194 |
+
"learning_rate": 4.600139624677436e-05,
|
1195 |
+
"loss": 1.0252,
|
1196 |
+
"step": 990
|
1197 |
+
},
|
1198 |
+
{
|
1199 |
+
"epoch": 0.55,
|
1200 |
+
"learning_rate": 4.596203109085168e-05,
|
1201 |
+
"loss": 1.0516,
|
1202 |
+
"step": 995
|
1203 |
+
},
|
1204 |
+
{
|
1205 |
+
"epoch": 0.55,
|
1206 |
+
"learning_rate": 4.5922490129027464e-05,
|
1207 |
+
"loss": 0.9762,
|
1208 |
+
"step": 1000
|
1209 |
+
},
|
1210 |
+
{
|
1211 |
+
"epoch": 0.56,
|
1212 |
+
"learning_rate": 4.588277369292674e-05,
|
1213 |
+
"loss": 0.9801,
|
1214 |
+
"step": 1005
|
1215 |
+
},
|
1216 |
+
{
|
1217 |
+
"epoch": 0.56,
|
1218 |
+
"learning_rate": 4.5842882115646234e-05,
|
1219 |
+
"loss": 1.0127,
|
1220 |
+
"step": 1010
|
1221 |
+
},
|
1222 |
+
{
|
1223 |
+
"epoch": 0.56,
|
1224 |
+
"learning_rate": 4.580281573175157e-05,
|
1225 |
+
"loss": 1.0415,
|
1226 |
+
"step": 1015
|
1227 |
+
},
|
1228 |
+
{
|
1229 |
+
"epoch": 0.56,
|
1230 |
+
"learning_rate": 4.576257487727442e-05,
|
1231 |
+
"loss": 0.9974,
|
1232 |
+
"step": 1020
|
1233 |
+
},
|
1234 |
+
{
|
1235 |
+
"epoch": 0.57,
|
1236 |
+
"learning_rate": 4.572215988970974e-05,
|
1237 |
+
"loss": 1.0097,
|
1238 |
+
"step": 1025
|
1239 |
+
},
|
1240 |
+
{
|
1241 |
+
"epoch": 0.57,
|
1242 |
+
"learning_rate": 4.568157110801293e-05,
|
1243 |
+
"loss": 1.0004,
|
1244 |
+
"step": 1030
|
1245 |
+
},
|
1246 |
+
{
|
1247 |
+
"epoch": 0.57,
|
1248 |
+
"learning_rate": 4.5640808872596944e-05,
|
1249 |
+
"loss": 0.9932,
|
1250 |
+
"step": 1035
|
1251 |
+
},
|
1252 |
+
{
|
1253 |
+
"epoch": 0.58,
|
1254 |
+
"learning_rate": 4.5599873525329505e-05,
|
1255 |
+
"loss": 0.9437,
|
1256 |
+
"step": 1040
|
1257 |
+
},
|
1258 |
+
{
|
1259 |
+
"epoch": 0.58,
|
1260 |
+
"learning_rate": 4.555876540953019e-05,
|
1261 |
+
"loss": 1.0004,
|
1262 |
+
"step": 1045
|
1263 |
+
},
|
1264 |
+
{
|
1265 |
+
"epoch": 0.58,
|
1266 |
+
"learning_rate": 4.551748486996755e-05,
|
1267 |
+
"loss": 0.9743,
|
1268 |
+
"step": 1050
|
1269 |
+
},
|
1270 |
+
{
|
1271 |
+
"epoch": 0.58,
|
1272 |
+
"learning_rate": 4.547603225285626e-05,
|
1273 |
+
"loss": 1.0303,
|
1274 |
+
"step": 1055
|
1275 |
+
},
|
1276 |
+
{
|
1277 |
+
"epoch": 0.59,
|
1278 |
+
"learning_rate": 4.543440790585417e-05,
|
1279 |
+
"loss": 1.0225,
|
1280 |
+
"step": 1060
|
1281 |
+
},
|
1282 |
+
{
|
1283 |
+
"epoch": 0.59,
|
1284 |
+
"learning_rate": 4.539261217805939e-05,
|
1285 |
+
"loss": 1.0102,
|
1286 |
+
"step": 1065
|
1287 |
+
},
|
1288 |
+
{
|
1289 |
+
"epoch": 0.59,
|
1290 |
+
"learning_rate": 4.535064542000743e-05,
|
1291 |
+
"loss": 1.0087,
|
1292 |
+
"step": 1070
|
1293 |
+
},
|
1294 |
+
{
|
1295 |
+
"epoch": 0.59,
|
1296 |
+
"learning_rate": 4.5308507983668165e-05,
|
1297 |
+
"loss": 0.952,
|
1298 |
+
"step": 1075
|
1299 |
+
},
|
1300 |
+
{
|
1301 |
+
"epoch": 0.6,
|
1302 |
+
"learning_rate": 4.526620022244293e-05,
|
1303 |
+
"loss": 0.9767,
|
1304 |
+
"step": 1080
|
1305 |
+
},
|
1306 |
+
{
|
1307 |
+
"epoch": 0.6,
|
1308 |
+
"learning_rate": 4.522372249116158e-05,
|
1309 |
+
"loss": 1.0049,
|
1310 |
+
"step": 1085
|
1311 |
+
},
|
1312 |
+
{
|
1313 |
+
"epoch": 0.6,
|
1314 |
+
"learning_rate": 4.5181075146079456e-05,
|
1315 |
+
"loss": 1.0397,
|
1316 |
+
"step": 1090
|
1317 |
+
},
|
1318 |
+
{
|
1319 |
+
"epoch": 0.61,
|
1320 |
+
"learning_rate": 4.5138258544874455e-05,
|
1321 |
+
"loss": 1.0167,
|
1322 |
+
"step": 1095
|
1323 |
+
},
|
1324 |
+
{
|
1325 |
+
"epoch": 0.61,
|
1326 |
+
"learning_rate": 4.5095273046643985e-05,
|
1327 |
+
"loss": 0.9966,
|
1328 |
+
"step": 1100
|
1329 |
+
}
|
1330 |
+
],
|
1331 |
+
"max_steps": 5424,
|
1332 |
+
"num_train_epochs": 3,
|
1333 |
+
"total_flos": 3.57467343028224e+17,
|
1334 |
+
"trial_name": null,
|
1335 |
+
"trial_params": null
|
1336 |
+
}
|
checkpoint-1100/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f6a8853599a52b1f15984d75ce4b6434c335fdc67d4509d0b2ca0d8c613590a
|
3 |
+
size 3362
|
checkpoint-1200/README.md
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
---
|
4 |
+
## Training procedure
|
5 |
+
|
6 |
+
|
7 |
+
The following `bitsandbytes` quantization config was used during training:
|
8 |
+
- load_in_8bit: True
|
9 |
+
- llm_int8_threshold: 6.0
|
10 |
+
- llm_int8_skip_modules: None
|
11 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
12 |
+
### Framework versions
|
13 |
+
|
14 |
+
|
15 |
+
- PEFT 0.5.0
|
checkpoint-1200/adapter_config.json
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"auto_mapping": null,
|
3 |
+
"base_model_name_or_path": "meta-llama/Llama-2-7b-chat-hf",
|
4 |
+
"bias": "none",
|
5 |
+
"fan_in_fan_out": false,
|
6 |
+
"inference_mode": true,
|
7 |
+
"init_lora_weights": true,
|
8 |
+
"layers_pattern": null,
|
9 |
+
"layers_to_transform": null,
|
10 |
+
"lora_alpha": 32.0,
|
11 |
+
"lora_dropout": 0.1,
|
12 |
+
"modules_to_save": null,
|
13 |
+
"peft_type": "LORA",
|
14 |
+
"r": 8,
|
15 |
+
"revision": null,
|
16 |
+
"target_modules": [
|
17 |
+
"q_proj",
|
18 |
+
"v_proj"
|
19 |
+
],
|
20 |
+
"task_type": "CAUSAL_LM"
|
21 |
+
}
|
checkpoint-1200/adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:80bd175dd7a77f18c28c84219c23d01119f777040f5bde7e409e8039bbedd76a
|
3 |
+
size 16821197
|
checkpoint-1200/finetuning_args.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"dpo_beta": 0.1,
|
3 |
+
"finetuning_type": "lora",
|
4 |
+
"lora_alpha": 32.0,
|
5 |
+
"lora_dropout": 0.1,
|
6 |
+
"lora_rank": 8,
|
7 |
+
"lora_target": [
|
8 |
+
"q_proj",
|
9 |
+
"v_proj"
|
10 |
+
],
|
11 |
+
"name_module_trainable": "mlp",
|
12 |
+
"num_hidden_layers": 32,
|
13 |
+
"num_layer_trainable": 3,
|
14 |
+
"ppo_score_norm": false,
|
15 |
+
"resume_lora_training": true
|
16 |
+
}
|
checkpoint-1200/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f42cf432758369c915b3fcce4fe20934523b628260c5c73468bb131f74182b86
|
3 |
+
size 33629893
|
checkpoint-1200/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7db1919207ee367db4a2eeeb7e1593dffd38f5b98c3d92d9532ac89f6f8bf7ec
|
3 |
+
size 14575
|
checkpoint-1200/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:741cefeca9ef427f92406d2d10b81996655e2a9d50eb7aaa9614e6fdd1c9f529
|
3 |
+
size 557
|
checkpoint-1200/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:25f5fdd612399be58b9bfcc865f337638ef903ce8239ab85c889e867bd67ae64
|
3 |
+
size 627
|
checkpoint-1200/trainer_state.json
ADDED
@@ -0,0 +1,1456 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.6635333149018524,
|
5 |
+
"global_step": 1200,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.0,
|
12 |
+
"learning_rate": 4.9999895164082156e-05,
|
13 |
+
"loss": 1.6349,
|
14 |
+
"step": 5
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.01,
|
18 |
+
"learning_rate": 4.999958065720787e-05,
|
19 |
+
"loss": 1.6199,
|
20 |
+
"step": 10
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.01,
|
24 |
+
"learning_rate": 4.999905648201487e-05,
|
25 |
+
"loss": 1.4834,
|
26 |
+
"step": 15
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.01,
|
30 |
+
"learning_rate": 4.999832264289934e-05,
|
31 |
+
"loss": 1.3882,
|
32 |
+
"step": 20
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.01,
|
36 |
+
"learning_rate": 4.999737914601591e-05,
|
37 |
+
"loss": 1.3679,
|
38 |
+
"step": 25
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.02,
|
42 |
+
"learning_rate": 4.999622599927756e-05,
|
43 |
+
"loss": 1.2396,
|
44 |
+
"step": 30
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.02,
|
48 |
+
"learning_rate": 4.999486321235559e-05,
|
49 |
+
"loss": 1.321,
|
50 |
+
"step": 35
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.02,
|
54 |
+
"learning_rate": 4.9993290796679516e-05,
|
55 |
+
"loss": 1.2874,
|
56 |
+
"step": 40
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.02,
|
60 |
+
"learning_rate": 4.999150876543699e-05,
|
61 |
+
"loss": 1.2607,
|
62 |
+
"step": 45
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.03,
|
66 |
+
"learning_rate": 4.9989517133573694e-05,
|
67 |
+
"loss": 1.2454,
|
68 |
+
"step": 50
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.03,
|
72 |
+
"learning_rate": 4.9987315917793174e-05,
|
73 |
+
"loss": 1.2799,
|
74 |
+
"step": 55
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.03,
|
78 |
+
"learning_rate": 4.998490513655676e-05,
|
79 |
+
"loss": 1.2575,
|
80 |
+
"step": 60
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.04,
|
84 |
+
"learning_rate": 4.998228481008337e-05,
|
85 |
+
"loss": 1.2404,
|
86 |
+
"step": 65
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.04,
|
90 |
+
"learning_rate": 4.997945496034934e-05,
|
91 |
+
"loss": 1.2219,
|
92 |
+
"step": 70
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.04,
|
96 |
+
"learning_rate": 4.9976415611088267e-05,
|
97 |
+
"loss": 1.2241,
|
98 |
+
"step": 75
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.04,
|
102 |
+
"learning_rate": 4.997316678779079e-05,
|
103 |
+
"loss": 1.1716,
|
104 |
+
"step": 80
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.05,
|
108 |
+
"learning_rate": 4.996970851770438e-05,
|
109 |
+
"loss": 1.1883,
|
110 |
+
"step": 85
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.05,
|
114 |
+
"learning_rate": 4.9966040829833115e-05,
|
115 |
+
"loss": 1.205,
|
116 |
+
"step": 90
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.05,
|
120 |
+
"learning_rate": 4.9962163754937426e-05,
|
121 |
+
"loss": 1.1246,
|
122 |
+
"step": 95
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.06,
|
126 |
+
"learning_rate": 4.995807732553384e-05,
|
127 |
+
"loss": 1.1636,
|
128 |
+
"step": 100
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.06,
|
132 |
+
"learning_rate": 4.9953781575894723e-05,
|
133 |
+
"loss": 1.158,
|
134 |
+
"step": 105
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 0.06,
|
138 |
+
"learning_rate": 4.9949276542048e-05,
|
139 |
+
"loss": 1.1477,
|
140 |
+
"step": 110
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 0.06,
|
144 |
+
"learning_rate": 4.9944562261776805e-05,
|
145 |
+
"loss": 1.1678,
|
146 |
+
"step": 115
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 0.07,
|
150 |
+
"learning_rate": 4.9939638774619216e-05,
|
151 |
+
"loss": 1.1501,
|
152 |
+
"step": 120
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 0.07,
|
156 |
+
"learning_rate": 4.99345061218679e-05,
|
157 |
+
"loss": 1.1955,
|
158 |
+
"step": 125
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 0.07,
|
162 |
+
"learning_rate": 4.9929164346569756e-05,
|
163 |
+
"loss": 1.1724,
|
164 |
+
"step": 130
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.07,
|
168 |
+
"learning_rate": 4.9923613493525576e-05,
|
169 |
+
"loss": 1.177,
|
170 |
+
"step": 135
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.08,
|
174 |
+
"learning_rate": 4.991785360928968e-05,
|
175 |
+
"loss": 1.1418,
|
176 |
+
"step": 140
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 0.08,
|
180 |
+
"learning_rate": 4.991188474216947e-05,
|
181 |
+
"loss": 1.1898,
|
182 |
+
"step": 145
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 0.08,
|
186 |
+
"learning_rate": 4.9905706942225094e-05,
|
187 |
+
"loss": 1.1479,
|
188 |
+
"step": 150
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 0.09,
|
192 |
+
"learning_rate": 4.9899320261268966e-05,
|
193 |
+
"loss": 1.1356,
|
194 |
+
"step": 155
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 0.09,
|
198 |
+
"learning_rate": 4.989272475286537e-05,
|
199 |
+
"loss": 1.1397,
|
200 |
+
"step": 160
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 0.09,
|
204 |
+
"learning_rate": 4.9885920472330004e-05,
|
205 |
+
"loss": 1.1215,
|
206 |
+
"step": 165
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 0.09,
|
210 |
+
"learning_rate": 4.9878907476729516e-05,
|
211 |
+
"loss": 1.167,
|
212 |
+
"step": 170
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.1,
|
216 |
+
"learning_rate": 4.9871685824881e-05,
|
217 |
+
"loss": 1.1219,
|
218 |
+
"step": 175
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 0.1,
|
222 |
+
"learning_rate": 4.9864255577351534e-05,
|
223 |
+
"loss": 1.0835,
|
224 |
+
"step": 180
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 0.1,
|
228 |
+
"learning_rate": 4.985661679645769e-05,
|
229 |
+
"loss": 1.0721,
|
230 |
+
"step": 185
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 0.11,
|
234 |
+
"learning_rate": 4.9848769546264915e-05,
|
235 |
+
"loss": 1.0692,
|
236 |
+
"step": 190
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 0.11,
|
240 |
+
"learning_rate": 4.9840713892587146e-05,
|
241 |
+
"loss": 1.0488,
|
242 |
+
"step": 195
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 0.11,
|
246 |
+
"learning_rate": 4.983244990298609e-05,
|
247 |
+
"loss": 1.1285,
|
248 |
+
"step": 200
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 0.11,
|
252 |
+
"learning_rate": 4.982397764677081e-05,
|
253 |
+
"loss": 1.0832,
|
254 |
+
"step": 205
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.12,
|
258 |
+
"learning_rate": 4.981529719499704e-05,
|
259 |
+
"loss": 1.0652,
|
260 |
+
"step": 210
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 0.12,
|
264 |
+
"learning_rate": 4.980640862046663e-05,
|
265 |
+
"loss": 1.1043,
|
266 |
+
"step": 215
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 0.12,
|
270 |
+
"learning_rate": 4.979731199772693e-05,
|
271 |
+
"loss": 1.112,
|
272 |
+
"step": 220
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 0.12,
|
276 |
+
"learning_rate": 4.9788007403070146e-05,
|
277 |
+
"loss": 1.1029,
|
278 |
+
"step": 225
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 0.13,
|
282 |
+
"learning_rate": 4.977849491453277e-05,
|
283 |
+
"loss": 1.0869,
|
284 |
+
"step": 230
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 0.13,
|
288 |
+
"learning_rate": 4.976877461189481e-05,
|
289 |
+
"loss": 1.0843,
|
290 |
+
"step": 235
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 0.13,
|
294 |
+
"learning_rate": 4.975884657667922e-05,
|
295 |
+
"loss": 1.0789,
|
296 |
+
"step": 240
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.14,
|
300 |
+
"learning_rate": 4.974871089215118e-05,
|
301 |
+
"loss": 1.0449,
|
302 |
+
"step": 245
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 0.14,
|
306 |
+
"learning_rate": 4.9738367643317405e-05,
|
307 |
+
"loss": 1.1053,
|
308 |
+
"step": 250
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 0.14,
|
312 |
+
"learning_rate": 4.9727816916925395e-05,
|
313 |
+
"loss": 1.0651,
|
314 |
+
"step": 255
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 0.14,
|
318 |
+
"learning_rate": 4.971705880146276e-05,
|
319 |
+
"loss": 1.0828,
|
320 |
+
"step": 260
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 0.15,
|
324 |
+
"learning_rate": 4.970609338715646e-05,
|
325 |
+
"loss": 1.0932,
|
326 |
+
"step": 265
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 0.15,
|
330 |
+
"learning_rate": 4.969492076597203e-05,
|
331 |
+
"loss": 1.0648,
|
332 |
+
"step": 270
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 0.15,
|
336 |
+
"learning_rate": 4.968354103161283e-05,
|
337 |
+
"loss": 1.0948,
|
338 |
+
"step": 275
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.15,
|
342 |
+
"learning_rate": 4.967195427951926e-05,
|
343 |
+
"loss": 1.0721,
|
344 |
+
"step": 280
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 0.16,
|
348 |
+
"learning_rate": 4.9660160606867936e-05,
|
349 |
+
"loss": 1.124,
|
350 |
+
"step": 285
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 0.16,
|
354 |
+
"learning_rate": 4.9648160112570896e-05,
|
355 |
+
"loss": 1.0963,
|
356 |
+
"step": 290
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 0.16,
|
360 |
+
"learning_rate": 4.9635952897274773e-05,
|
361 |
+
"loss": 1.1078,
|
362 |
+
"step": 295
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 0.17,
|
366 |
+
"learning_rate": 4.9623539063359925e-05,
|
367 |
+
"loss": 1.1059,
|
368 |
+
"step": 300
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 0.17,
|
372 |
+
"learning_rate": 4.961091871493962e-05,
|
373 |
+
"loss": 1.1032,
|
374 |
+
"step": 305
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 0.17,
|
378 |
+
"learning_rate": 4.959809195785912e-05,
|
379 |
+
"loss": 1.0595,
|
380 |
+
"step": 310
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.17,
|
384 |
+
"learning_rate": 4.958505889969481e-05,
|
385 |
+
"loss": 1.1096,
|
386 |
+
"step": 315
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"epoch": 0.18,
|
390 |
+
"learning_rate": 4.957181964975329e-05,
|
391 |
+
"loss": 1.0589,
|
392 |
+
"step": 320
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 0.18,
|
396 |
+
"learning_rate": 4.955837431907049e-05,
|
397 |
+
"loss": 1.0608,
|
398 |
+
"step": 325
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 0.18,
|
402 |
+
"learning_rate": 4.954472302041069e-05,
|
403 |
+
"loss": 1.0819,
|
404 |
+
"step": 330
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 0.19,
|
408 |
+
"learning_rate": 4.9530865868265605e-05,
|
409 |
+
"loss": 1.0759,
|
410 |
+
"step": 335
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 0.19,
|
414 |
+
"learning_rate": 4.951680297885342e-05,
|
415 |
+
"loss": 1.0515,
|
416 |
+
"step": 340
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 0.19,
|
420 |
+
"learning_rate": 4.950253447011779e-05,
|
421 |
+
"loss": 1.0371,
|
422 |
+
"step": 345
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.19,
|
426 |
+
"learning_rate": 4.948806046172691e-05,
|
427 |
+
"loss": 1.0619,
|
428 |
+
"step": 350
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 0.2,
|
432 |
+
"learning_rate": 4.947338107507245e-05,
|
433 |
+
"loss": 1.0757,
|
434 |
+
"step": 355
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 0.2,
|
438 |
+
"learning_rate": 4.945849643326857e-05,
|
439 |
+
"loss": 1.0686,
|
440 |
+
"step": 360
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 0.2,
|
444 |
+
"learning_rate": 4.9443406661150874e-05,
|
445 |
+
"loss": 1.0809,
|
446 |
+
"step": 365
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 0.2,
|
450 |
+
"learning_rate": 4.942811188527537e-05,
|
451 |
+
"loss": 1.0704,
|
452 |
+
"step": 370
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 0.21,
|
456 |
+
"learning_rate": 4.941261223391742e-05,
|
457 |
+
"loss": 1.0655,
|
458 |
+
"step": 375
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 0.21,
|
462 |
+
"learning_rate": 4.939690783707063e-05,
|
463 |
+
"loss": 1.1182,
|
464 |
+
"step": 380
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.21,
|
468 |
+
"learning_rate": 4.938099882644578e-05,
|
469 |
+
"loss": 1.081,
|
470 |
+
"step": 385
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 0.22,
|
474 |
+
"learning_rate": 4.9364885335469734e-05,
|
475 |
+
"loss": 1.0792,
|
476 |
+
"step": 390
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"epoch": 0.22,
|
480 |
+
"learning_rate": 4.93485674992843e-05,
|
481 |
+
"loss": 1.0244,
|
482 |
+
"step": 395
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 0.22,
|
486 |
+
"learning_rate": 4.933204545474511e-05,
|
487 |
+
"loss": 1.0531,
|
488 |
+
"step": 400
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 0.22,
|
492 |
+
"learning_rate": 4.9315319340420465e-05,
|
493 |
+
"loss": 1.048,
|
494 |
+
"step": 405
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 0.23,
|
498 |
+
"learning_rate": 4.929838929659015e-05,
|
499 |
+
"loss": 1.04,
|
500 |
+
"step": 410
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 0.23,
|
504 |
+
"learning_rate": 4.9281255465244314e-05,
|
505 |
+
"loss": 1.0686,
|
506 |
+
"step": 415
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.23,
|
510 |
+
"learning_rate": 4.926391799008223e-05,
|
511 |
+
"loss": 1.0933,
|
512 |
+
"step": 420
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"epoch": 0.24,
|
516 |
+
"learning_rate": 4.924637701651111e-05,
|
517 |
+
"loss": 1.0313,
|
518 |
+
"step": 425
|
519 |
+
},
|
520 |
+
{
|
521 |
+
"epoch": 0.24,
|
522 |
+
"learning_rate": 4.9228632691644874e-05,
|
523 |
+
"loss": 1.0811,
|
524 |
+
"step": 430
|
525 |
+
},
|
526 |
+
{
|
527 |
+
"epoch": 0.24,
|
528 |
+
"learning_rate": 4.921068516430293e-05,
|
529 |
+
"loss": 1.0617,
|
530 |
+
"step": 435
|
531 |
+
},
|
532 |
+
{
|
533 |
+
"epoch": 0.24,
|
534 |
+
"learning_rate": 4.919253458500892e-05,
|
535 |
+
"loss": 1.0482,
|
536 |
+
"step": 440
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 0.25,
|
540 |
+
"learning_rate": 4.9174181105989445e-05,
|
541 |
+
"loss": 1.0681,
|
542 |
+
"step": 445
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 0.25,
|
546 |
+
"learning_rate": 4.9155624881172834e-05,
|
547 |
+
"loss": 1.0476,
|
548 |
+
"step": 450
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 0.25,
|
552 |
+
"learning_rate": 4.913686606618777e-05,
|
553 |
+
"loss": 1.0463,
|
554 |
+
"step": 455
|
555 |
+
},
|
556 |
+
{
|
557 |
+
"epoch": 0.25,
|
558 |
+
"learning_rate": 4.911790481836208e-05,
|
559 |
+
"loss": 1.0213,
|
560 |
+
"step": 460
|
561 |
+
},
|
562 |
+
{
|
563 |
+
"epoch": 0.26,
|
564 |
+
"learning_rate": 4.909874129672133e-05,
|
565 |
+
"loss": 0.9855,
|
566 |
+
"step": 465
|
567 |
+
},
|
568 |
+
{
|
569 |
+
"epoch": 0.26,
|
570 |
+
"learning_rate": 4.907937566198757e-05,
|
571 |
+
"loss": 1.045,
|
572 |
+
"step": 470
|
573 |
+
},
|
574 |
+
{
|
575 |
+
"epoch": 0.26,
|
576 |
+
"learning_rate": 4.9059808076577914e-05,
|
577 |
+
"loss": 1.0442,
|
578 |
+
"step": 475
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 0.27,
|
582 |
+
"learning_rate": 4.904003870460323e-05,
|
583 |
+
"loss": 1.0354,
|
584 |
+
"step": 480
|
585 |
+
},
|
586 |
+
{
|
587 |
+
"epoch": 0.27,
|
588 |
+
"learning_rate": 4.9020067711866735e-05,
|
589 |
+
"loss": 1.0331,
|
590 |
+
"step": 485
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 0.27,
|
594 |
+
"learning_rate": 4.899989526586261e-05,
|
595 |
+
"loss": 1.0585,
|
596 |
+
"step": 490
|
597 |
+
},
|
598 |
+
{
|
599 |
+
"epoch": 0.27,
|
600 |
+
"learning_rate": 4.8979521535774636e-05,
|
601 |
+
"loss": 1.0223,
|
602 |
+
"step": 495
|
603 |
+
},
|
604 |
+
{
|
605 |
+
"epoch": 0.28,
|
606 |
+
"learning_rate": 4.895894669247468e-05,
|
607 |
+
"loss": 1.0118,
|
608 |
+
"step": 500
|
609 |
+
},
|
610 |
+
{
|
611 |
+
"epoch": 0.28,
|
612 |
+
"learning_rate": 4.8938170908521356e-05,
|
613 |
+
"loss": 1.0508,
|
614 |
+
"step": 505
|
615 |
+
},
|
616 |
+
{
|
617 |
+
"epoch": 0.28,
|
618 |
+
"learning_rate": 4.8917194358158534e-05,
|
619 |
+
"loss": 1.0656,
|
620 |
+
"step": 510
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 0.28,
|
624 |
+
"learning_rate": 4.8896017217313886e-05,
|
625 |
+
"loss": 1.0655,
|
626 |
+
"step": 515
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 0.29,
|
630 |
+
"learning_rate": 4.887463966359741e-05,
|
631 |
+
"loss": 1.0833,
|
632 |
+
"step": 520
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 0.29,
|
636 |
+
"learning_rate": 4.8853061876299956e-05,
|
637 |
+
"loss": 1.068,
|
638 |
+
"step": 525
|
639 |
+
},
|
640 |
+
{
|
641 |
+
"epoch": 0.29,
|
642 |
+
"learning_rate": 4.8831284036391684e-05,
|
643 |
+
"loss": 1.0487,
|
644 |
+
"step": 530
|
645 |
+
},
|
646 |
+
{
|
647 |
+
"epoch": 0.3,
|
648 |
+
"learning_rate": 4.880930632652058e-05,
|
649 |
+
"loss": 1.059,
|
650 |
+
"step": 535
|
651 |
+
},
|
652 |
+
{
|
653 |
+
"epoch": 0.3,
|
654 |
+
"learning_rate": 4.878712893101092e-05,
|
655 |
+
"loss": 1.0408,
|
656 |
+
"step": 540
|
657 |
+
},
|
658 |
+
{
|
659 |
+
"epoch": 0.3,
|
660 |
+
"learning_rate": 4.876475203586171e-05,
|
661 |
+
"loss": 0.9976,
|
662 |
+
"step": 545
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 0.3,
|
666 |
+
"learning_rate": 4.874217582874514e-05,
|
667 |
+
"loss": 1.0358,
|
668 |
+
"step": 550
|
669 |
+
},
|
670 |
+
{
|
671 |
+
"epoch": 0.31,
|
672 |
+
"learning_rate": 4.8719400499005e-05,
|
673 |
+
"loss": 1.0073,
|
674 |
+
"step": 555
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 0.31,
|
678 |
+
"learning_rate": 4.869642623765509e-05,
|
679 |
+
"loss": 1.0742,
|
680 |
+
"step": 560
|
681 |
+
},
|
682 |
+
{
|
683 |
+
"epoch": 0.31,
|
684 |
+
"learning_rate": 4.867325323737765e-05,
|
685 |
+
"loss": 1.0463,
|
686 |
+
"step": 565
|
687 |
+
},
|
688 |
+
{
|
689 |
+
"epoch": 0.32,
|
690 |
+
"learning_rate": 4.864988169252168e-05,
|
691 |
+
"loss": 1.0242,
|
692 |
+
"step": 570
|
693 |
+
},
|
694 |
+
{
|
695 |
+
"epoch": 0.32,
|
696 |
+
"learning_rate": 4.8626311799101375e-05,
|
697 |
+
"loss": 1.0773,
|
698 |
+
"step": 575
|
699 |
+
},
|
700 |
+
{
|
701 |
+
"epoch": 0.32,
|
702 |
+
"learning_rate": 4.860254375479446e-05,
|
703 |
+
"loss": 1.0371,
|
704 |
+
"step": 580
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 0.32,
|
708 |
+
"learning_rate": 4.8578577758940504e-05,
|
709 |
+
"loss": 1.0399,
|
710 |
+
"step": 585
|
711 |
+
},
|
712 |
+
{
|
713 |
+
"epoch": 0.33,
|
714 |
+
"learning_rate": 4.855441401253928e-05,
|
715 |
+
"loss": 1.0411,
|
716 |
+
"step": 590
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 0.33,
|
720 |
+
"learning_rate": 4.8530052718249076e-05,
|
721 |
+
"loss": 1.0476,
|
722 |
+
"step": 595
|
723 |
+
},
|
724 |
+
{
|
725 |
+
"epoch": 0.33,
|
726 |
+
"learning_rate": 4.850549408038498e-05,
|
727 |
+
"loss": 1.0075,
|
728 |
+
"step": 600
|
729 |
+
},
|
730 |
+
{
|
731 |
+
"epoch": 0.33,
|
732 |
+
"learning_rate": 4.848073830491717e-05,
|
733 |
+
"loss": 1.0045,
|
734 |
+
"step": 605
|
735 |
+
},
|
736 |
+
{
|
737 |
+
"epoch": 0.34,
|
738 |
+
"learning_rate": 4.845578559946923e-05,
|
739 |
+
"loss": 1.0368,
|
740 |
+
"step": 610
|
741 |
+
},
|
742 |
+
{
|
743 |
+
"epoch": 0.34,
|
744 |
+
"learning_rate": 4.8430636173316306e-05,
|
745 |
+
"loss": 1.0156,
|
746 |
+
"step": 615
|
747 |
+
},
|
748 |
+
{
|
749 |
+
"epoch": 0.34,
|
750 |
+
"learning_rate": 4.840529023738348e-05,
|
751 |
+
"loss": 1.0334,
|
752 |
+
"step": 620
|
753 |
+
},
|
754 |
+
{
|
755 |
+
"epoch": 0.35,
|
756 |
+
"learning_rate": 4.837974800424389e-05,
|
757 |
+
"loss": 0.9994,
|
758 |
+
"step": 625
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 0.35,
|
762 |
+
"learning_rate": 4.8354009688117026e-05,
|
763 |
+
"loss": 1.0467,
|
764 |
+
"step": 630
|
765 |
+
},
|
766 |
+
{
|
767 |
+
"epoch": 0.35,
|
768 |
+
"learning_rate": 4.8328075504866874e-05,
|
769 |
+
"loss": 0.9968,
|
770 |
+
"step": 635
|
771 |
+
},
|
772 |
+
{
|
773 |
+
"epoch": 0.35,
|
774 |
+
"learning_rate": 4.8301945672000164e-05,
|
775 |
+
"loss": 1.041,
|
776 |
+
"step": 640
|
777 |
+
},
|
778 |
+
{
|
779 |
+
"epoch": 0.36,
|
780 |
+
"learning_rate": 4.8275620408664487e-05,
|
781 |
+
"loss": 0.9811,
|
782 |
+
"step": 645
|
783 |
+
},
|
784 |
+
{
|
785 |
+
"epoch": 0.36,
|
786 |
+
"learning_rate": 4.8249099935646494e-05,
|
787 |
+
"loss": 1.0235,
|
788 |
+
"step": 650
|
789 |
+
},
|
790 |
+
{
|
791 |
+
"epoch": 0.36,
|
792 |
+
"learning_rate": 4.822238447537003e-05,
|
793 |
+
"loss": 1.0152,
|
794 |
+
"step": 655
|
795 |
+
},
|
796 |
+
{
|
797 |
+
"epoch": 0.36,
|
798 |
+
"learning_rate": 4.819547425189429e-05,
|
799 |
+
"loss": 1.038,
|
800 |
+
"step": 660
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 0.37,
|
804 |
+
"learning_rate": 4.81683694909119e-05,
|
805 |
+
"loss": 1.0387,
|
806 |
+
"step": 665
|
807 |
+
},
|
808 |
+
{
|
809 |
+
"epoch": 0.37,
|
810 |
+
"learning_rate": 4.814107041974707e-05,
|
811 |
+
"loss": 1.019,
|
812 |
+
"step": 670
|
813 |
+
},
|
814 |
+
{
|
815 |
+
"epoch": 0.37,
|
816 |
+
"learning_rate": 4.811357726735366e-05,
|
817 |
+
"loss": 1.0403,
|
818 |
+
"step": 675
|
819 |
+
},
|
820 |
+
{
|
821 |
+
"epoch": 0.38,
|
822 |
+
"learning_rate": 4.808589026431324e-05,
|
823 |
+
"loss": 1.0828,
|
824 |
+
"step": 680
|
825 |
+
},
|
826 |
+
{
|
827 |
+
"epoch": 0.38,
|
828 |
+
"learning_rate": 4.805800964283322e-05,
|
829 |
+
"loss": 1.0128,
|
830 |
+
"step": 685
|
831 |
+
},
|
832 |
+
{
|
833 |
+
"epoch": 0.38,
|
834 |
+
"learning_rate": 4.802993563674483e-05,
|
835 |
+
"loss": 1.0502,
|
836 |
+
"step": 690
|
837 |
+
},
|
838 |
+
{
|
839 |
+
"epoch": 0.38,
|
840 |
+
"learning_rate": 4.80016684815012e-05,
|
841 |
+
"loss": 1.0169,
|
842 |
+
"step": 695
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 0.39,
|
846 |
+
"learning_rate": 4.7973208414175406e-05,
|
847 |
+
"loss": 1.0316,
|
848 |
+
"step": 700
|
849 |
+
},
|
850 |
+
{
|
851 |
+
"epoch": 0.39,
|
852 |
+
"learning_rate": 4.794455567345842e-05,
|
853 |
+
"loss": 1.0263,
|
854 |
+
"step": 705
|
855 |
+
},
|
856 |
+
{
|
857 |
+
"epoch": 0.39,
|
858 |
+
"learning_rate": 4.791571049965714e-05,
|
859 |
+
"loss": 1.0801,
|
860 |
+
"step": 710
|
861 |
+
},
|
862 |
+
{
|
863 |
+
"epoch": 0.4,
|
864 |
+
"learning_rate": 4.7886673134692404e-05,
|
865 |
+
"loss": 1.0575,
|
866 |
+
"step": 715
|
867 |
+
},
|
868 |
+
{
|
869 |
+
"epoch": 0.4,
|
870 |
+
"learning_rate": 4.7857443822096905e-05,
|
871 |
+
"loss": 0.9767,
|
872 |
+
"step": 720
|
873 |
+
},
|
874 |
+
{
|
875 |
+
"epoch": 0.4,
|
876 |
+
"learning_rate": 4.782802280701319e-05,
|
877 |
+
"loss": 0.9666,
|
878 |
+
"step": 725
|
879 |
+
},
|
880 |
+
{
|
881 |
+
"epoch": 0.4,
|
882 |
+
"learning_rate": 4.77984103361916e-05,
|
883 |
+
"loss": 0.9983,
|
884 |
+
"step": 730
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 0.41,
|
888 |
+
"learning_rate": 4.776860665798816e-05,
|
889 |
+
"loss": 1.0219,
|
890 |
+
"step": 735
|
891 |
+
},
|
892 |
+
{
|
893 |
+
"epoch": 0.41,
|
894 |
+
"learning_rate": 4.773861202236257e-05,
|
895 |
+
"loss": 0.9963,
|
896 |
+
"step": 740
|
897 |
+
},
|
898 |
+
{
|
899 |
+
"epoch": 0.41,
|
900 |
+
"learning_rate": 4.770842668087602e-05,
|
901 |
+
"loss": 1.0219,
|
902 |
+
"step": 745
|
903 |
+
},
|
904 |
+
{
|
905 |
+
"epoch": 0.41,
|
906 |
+
"learning_rate": 4.767805088668916e-05,
|
907 |
+
"loss": 1.0029,
|
908 |
+
"step": 750
|
909 |
+
},
|
910 |
+
{
|
911 |
+
"epoch": 0.42,
|
912 |
+
"learning_rate": 4.7647484894559936e-05,
|
913 |
+
"loss": 1.0077,
|
914 |
+
"step": 755
|
915 |
+
},
|
916 |
+
{
|
917 |
+
"epoch": 0.42,
|
918 |
+
"learning_rate": 4.7616728960841444e-05,
|
919 |
+
"loss": 0.9908,
|
920 |
+
"step": 760
|
921 |
+
},
|
922 |
+
{
|
923 |
+
"epoch": 0.42,
|
924 |
+
"learning_rate": 4.758578334347981e-05,
|
925 |
+
"loss": 1.0092,
|
926 |
+
"step": 765
|
927 |
+
},
|
928 |
+
{
|
929 |
+
"epoch": 0.43,
|
930 |
+
"learning_rate": 4.7554648302012015e-05,
|
931 |
+
"loss": 0.9874,
|
932 |
+
"step": 770
|
933 |
+
},
|
934 |
+
{
|
935 |
+
"epoch": 0.43,
|
936 |
+
"learning_rate": 4.7523324097563706e-05,
|
937 |
+
"loss": 1.0185,
|
938 |
+
"step": 775
|
939 |
+
},
|
940 |
+
{
|
941 |
+
"epoch": 0.43,
|
942 |
+
"learning_rate": 4.749181099284703e-05,
|
943 |
+
"loss": 1.0533,
|
944 |
+
"step": 780
|
945 |
+
},
|
946 |
+
{
|
947 |
+
"epoch": 0.43,
|
948 |
+
"learning_rate": 4.746010925215839e-05,
|
949 |
+
"loss": 1.0083,
|
950 |
+
"step": 785
|
951 |
+
},
|
952 |
+
{
|
953 |
+
"epoch": 0.44,
|
954 |
+
"learning_rate": 4.74282191413763e-05,
|
955 |
+
"loss": 1.0191,
|
956 |
+
"step": 790
|
957 |
+
},
|
958 |
+
{
|
959 |
+
"epoch": 0.44,
|
960 |
+
"learning_rate": 4.7396140927959045e-05,
|
961 |
+
"loss": 0.9786,
|
962 |
+
"step": 795
|
963 |
+
},
|
964 |
+
{
|
965 |
+
"epoch": 0.44,
|
966 |
+
"learning_rate": 4.7363874880942574e-05,
|
967 |
+
"loss": 1.0197,
|
968 |
+
"step": 800
|
969 |
+
},
|
970 |
+
{
|
971 |
+
"epoch": 0.45,
|
972 |
+
"learning_rate": 4.733142127093813e-05,
|
973 |
+
"loss": 1.0471,
|
974 |
+
"step": 805
|
975 |
+
},
|
976 |
+
{
|
977 |
+
"epoch": 0.45,
|
978 |
+
"learning_rate": 4.7298780370130014e-05,
|
979 |
+
"loss": 1.0134,
|
980 |
+
"step": 810
|
981 |
+
},
|
982 |
+
{
|
983 |
+
"epoch": 0.45,
|
984 |
+
"learning_rate": 4.726595245227336e-05,
|
985 |
+
"loss": 0.9801,
|
986 |
+
"step": 815
|
987 |
+
},
|
988 |
+
{
|
989 |
+
"epoch": 0.45,
|
990 |
+
"learning_rate": 4.723293779269173e-05,
|
991 |
+
"loss": 0.9944,
|
992 |
+
"step": 820
|
993 |
+
},
|
994 |
+
{
|
995 |
+
"epoch": 0.46,
|
996 |
+
"learning_rate": 4.7199736668274924e-05,
|
997 |
+
"loss": 1.0358,
|
998 |
+
"step": 825
|
999 |
+
},
|
1000 |
+
{
|
1001 |
+
"epoch": 0.46,
|
1002 |
+
"learning_rate": 4.716634935747655e-05,
|
1003 |
+
"loss": 0.9907,
|
1004 |
+
"step": 830
|
1005 |
+
},
|
1006 |
+
{
|
1007 |
+
"epoch": 0.46,
|
1008 |
+
"learning_rate": 4.713277614031177e-05,
|
1009 |
+
"loss": 1.0698,
|
1010 |
+
"step": 835
|
1011 |
+
},
|
1012 |
+
{
|
1013 |
+
"epoch": 0.46,
|
1014 |
+
"learning_rate": 4.70990172983549e-05,
|
1015 |
+
"loss": 1.0466,
|
1016 |
+
"step": 840
|
1017 |
+
},
|
1018 |
+
{
|
1019 |
+
"epoch": 0.47,
|
1020 |
+
"learning_rate": 4.706507311473707e-05,
|
1021 |
+
"loss": 0.9489,
|
1022 |
+
"step": 845
|
1023 |
+
},
|
1024 |
+
{
|
1025 |
+
"epoch": 0.47,
|
1026 |
+
"learning_rate": 4.703094387414385e-05,
|
1027 |
+
"loss": 0.9936,
|
1028 |
+
"step": 850
|
1029 |
+
},
|
1030 |
+
{
|
1031 |
+
"epoch": 0.47,
|
1032 |
+
"learning_rate": 4.699662986281288e-05,
|
1033 |
+
"loss": 0.9672,
|
1034 |
+
"step": 855
|
1035 |
+
},
|
1036 |
+
{
|
1037 |
+
"epoch": 0.48,
|
1038 |
+
"learning_rate": 4.696213136853141e-05,
|
1039 |
+
"loss": 1.0164,
|
1040 |
+
"step": 860
|
1041 |
+
},
|
1042 |
+
{
|
1043 |
+
"epoch": 0.48,
|
1044 |
+
"learning_rate": 4.6927448680633954e-05,
|
1045 |
+
"loss": 0.9817,
|
1046 |
+
"step": 865
|
1047 |
+
},
|
1048 |
+
{
|
1049 |
+
"epoch": 0.48,
|
1050 |
+
"learning_rate": 4.689258208999983e-05,
|
1051 |
+
"loss": 1.028,
|
1052 |
+
"step": 870
|
1053 |
+
},
|
1054 |
+
{
|
1055 |
+
"epoch": 0.48,
|
1056 |
+
"learning_rate": 4.6857531889050716e-05,
|
1057 |
+
"loss": 1.0239,
|
1058 |
+
"step": 875
|
1059 |
+
},
|
1060 |
+
{
|
1061 |
+
"epoch": 0.49,
|
1062 |
+
"learning_rate": 4.682229837174821e-05,
|
1063 |
+
"loss": 1.0378,
|
1064 |
+
"step": 880
|
1065 |
+
},
|
1066 |
+
{
|
1067 |
+
"epoch": 0.49,
|
1068 |
+
"learning_rate": 4.678688183359135e-05,
|
1069 |
+
"loss": 0.9908,
|
1070 |
+
"step": 885
|
1071 |
+
},
|
1072 |
+
{
|
1073 |
+
"epoch": 0.49,
|
1074 |
+
"learning_rate": 4.675128257161418e-05,
|
1075 |
+
"loss": 0.9384,
|
1076 |
+
"step": 890
|
1077 |
+
},
|
1078 |
+
{
|
1079 |
+
"epoch": 0.49,
|
1080 |
+
"learning_rate": 4.671550088438319e-05,
|
1081 |
+
"loss": 0.9481,
|
1082 |
+
"step": 895
|
1083 |
+
},
|
1084 |
+
{
|
1085 |
+
"epoch": 0.5,
|
1086 |
+
"learning_rate": 4.6679537071994874e-05,
|
1087 |
+
"loss": 0.9541,
|
1088 |
+
"step": 900
|
1089 |
+
},
|
1090 |
+
{
|
1091 |
+
"epoch": 0.5,
|
1092 |
+
"learning_rate": 4.6643391436073165e-05,
|
1093 |
+
"loss": 0.9787,
|
1094 |
+
"step": 905
|
1095 |
+
},
|
1096 |
+
{
|
1097 |
+
"epoch": 0.5,
|
1098 |
+
"learning_rate": 4.660706427976693e-05,
|
1099 |
+
"loss": 0.9897,
|
1100 |
+
"step": 910
|
1101 |
+
},
|
1102 |
+
{
|
1103 |
+
"epoch": 0.51,
|
1104 |
+
"learning_rate": 4.657055590774745e-05,
|
1105 |
+
"loss": 0.9947,
|
1106 |
+
"step": 915
|
1107 |
+
},
|
1108 |
+
{
|
1109 |
+
"epoch": 0.51,
|
1110 |
+
"learning_rate": 4.6533866626205805e-05,
|
1111 |
+
"loss": 0.9614,
|
1112 |
+
"step": 920
|
1113 |
+
},
|
1114 |
+
{
|
1115 |
+
"epoch": 0.51,
|
1116 |
+
"learning_rate": 4.649699674285036e-05,
|
1117 |
+
"loss": 1.0323,
|
1118 |
+
"step": 925
|
1119 |
+
},
|
1120 |
+
{
|
1121 |
+
"epoch": 0.51,
|
1122 |
+
"learning_rate": 4.645994656690417e-05,
|
1123 |
+
"loss": 1.0345,
|
1124 |
+
"step": 930
|
1125 |
+
},
|
1126 |
+
{
|
1127 |
+
"epoch": 0.52,
|
1128 |
+
"learning_rate": 4.642271640910235e-05,
|
1129 |
+
"loss": 1.0432,
|
1130 |
+
"step": 935
|
1131 |
+
},
|
1132 |
+
{
|
1133 |
+
"epoch": 0.52,
|
1134 |
+
"learning_rate": 4.638530658168954e-05,
|
1135 |
+
"loss": 1.0102,
|
1136 |
+
"step": 940
|
1137 |
+
},
|
1138 |
+
{
|
1139 |
+
"epoch": 0.52,
|
1140 |
+
"learning_rate": 4.6347717398417203e-05,
|
1141 |
+
"loss": 1.0361,
|
1142 |
+
"step": 945
|
1143 |
+
},
|
1144 |
+
{
|
1145 |
+
"epoch": 0.53,
|
1146 |
+
"learning_rate": 4.6309949174541096e-05,
|
1147 |
+
"loss": 0.9818,
|
1148 |
+
"step": 950
|
1149 |
+
},
|
1150 |
+
{
|
1151 |
+
"epoch": 0.53,
|
1152 |
+
"learning_rate": 4.627200222681851e-05,
|
1153 |
+
"loss": 1.0293,
|
1154 |
+
"step": 955
|
1155 |
+
},
|
1156 |
+
{
|
1157 |
+
"epoch": 0.53,
|
1158 |
+
"learning_rate": 4.6233876873505694e-05,
|
1159 |
+
"loss": 1.0125,
|
1160 |
+
"step": 960
|
1161 |
+
},
|
1162 |
+
{
|
1163 |
+
"epoch": 0.53,
|
1164 |
+
"learning_rate": 4.619557343435516e-05,
|
1165 |
+
"loss": 1.0039,
|
1166 |
+
"step": 965
|
1167 |
+
},
|
1168 |
+
{
|
1169 |
+
"epoch": 0.54,
|
1170 |
+
"learning_rate": 4.615709223061302e-05,
|
1171 |
+
"loss": 1.0146,
|
1172 |
+
"step": 970
|
1173 |
+
},
|
1174 |
+
{
|
1175 |
+
"epoch": 0.54,
|
1176 |
+
"learning_rate": 4.611843358501624e-05,
|
1177 |
+
"loss": 1.0352,
|
1178 |
+
"step": 975
|
1179 |
+
},
|
1180 |
+
{
|
1181 |
+
"epoch": 0.54,
|
1182 |
+
"learning_rate": 4.6079597821789993e-05,
|
1183 |
+
"loss": 1.0405,
|
1184 |
+
"step": 980
|
1185 |
+
},
|
1186 |
+
{
|
1187 |
+
"epoch": 0.54,
|
1188 |
+
"learning_rate": 4.604058526664491e-05,
|
1189 |
+
"loss": 0.9834,
|
1190 |
+
"step": 985
|
1191 |
+
},
|
1192 |
+
{
|
1193 |
+
"epoch": 0.55,
|
1194 |
+
"learning_rate": 4.600139624677436e-05,
|
1195 |
+
"loss": 1.0252,
|
1196 |
+
"step": 990
|
1197 |
+
},
|
1198 |
+
{
|
1199 |
+
"epoch": 0.55,
|
1200 |
+
"learning_rate": 4.596203109085168e-05,
|
1201 |
+
"loss": 1.0516,
|
1202 |
+
"step": 995
|
1203 |
+
},
|
1204 |
+
{
|
1205 |
+
"epoch": 0.55,
|
1206 |
+
"learning_rate": 4.5922490129027464e-05,
|
1207 |
+
"loss": 0.9762,
|
1208 |
+
"step": 1000
|
1209 |
+
},
|
1210 |
+
{
|
1211 |
+
"epoch": 0.56,
|
1212 |
+
"learning_rate": 4.588277369292674e-05,
|
1213 |
+
"loss": 0.9801,
|
1214 |
+
"step": 1005
|
1215 |
+
},
|
1216 |
+
{
|
1217 |
+
"epoch": 0.56,
|
1218 |
+
"learning_rate": 4.5842882115646234e-05,
|
1219 |
+
"loss": 1.0127,
|
1220 |
+
"step": 1010
|
1221 |
+
},
|
1222 |
+
{
|
1223 |
+
"epoch": 0.56,
|
1224 |
+
"learning_rate": 4.580281573175157e-05,
|
1225 |
+
"loss": 1.0415,
|
1226 |
+
"step": 1015
|
1227 |
+
},
|
1228 |
+
{
|
1229 |
+
"epoch": 0.56,
|
1230 |
+
"learning_rate": 4.576257487727442e-05,
|
1231 |
+
"loss": 0.9974,
|
1232 |
+
"step": 1020
|
1233 |
+
},
|
1234 |
+
{
|
1235 |
+
"epoch": 0.57,
|
1236 |
+
"learning_rate": 4.572215988970974e-05,
|
1237 |
+
"loss": 1.0097,
|
1238 |
+
"step": 1025
|
1239 |
+
},
|
1240 |
+
{
|
1241 |
+
"epoch": 0.57,
|
1242 |
+
"learning_rate": 4.568157110801293e-05,
|
1243 |
+
"loss": 1.0004,
|
1244 |
+
"step": 1030
|
1245 |
+
},
|
1246 |
+
{
|
1247 |
+
"epoch": 0.57,
|
1248 |
+
"learning_rate": 4.5640808872596944e-05,
|
1249 |
+
"loss": 0.9932,
|
1250 |
+
"step": 1035
|
1251 |
+
},
|
1252 |
+
{
|
1253 |
+
"epoch": 0.58,
|
1254 |
+
"learning_rate": 4.5599873525329505e-05,
|
1255 |
+
"loss": 0.9437,
|
1256 |
+
"step": 1040
|
1257 |
+
},
|
1258 |
+
{
|
1259 |
+
"epoch": 0.58,
|
1260 |
+
"learning_rate": 4.555876540953019e-05,
|
1261 |
+
"loss": 1.0004,
|
1262 |
+
"step": 1045
|
1263 |
+
},
|
1264 |
+
{
|
1265 |
+
"epoch": 0.58,
|
1266 |
+
"learning_rate": 4.551748486996755e-05,
|
1267 |
+
"loss": 0.9743,
|
1268 |
+
"step": 1050
|
1269 |
+
},
|
1270 |
+
{
|
1271 |
+
"epoch": 0.58,
|
1272 |
+
"learning_rate": 4.547603225285626e-05,
|
1273 |
+
"loss": 1.0303,
|
1274 |
+
"step": 1055
|
1275 |
+
},
|
1276 |
+
{
|
1277 |
+
"epoch": 0.59,
|
1278 |
+
"learning_rate": 4.543440790585417e-05,
|
1279 |
+
"loss": 1.0225,
|
1280 |
+
"step": 1060
|
1281 |
+
},
|
1282 |
+
{
|
1283 |
+
"epoch": 0.59,
|
1284 |
+
"learning_rate": 4.539261217805939e-05,
|
1285 |
+
"loss": 1.0102,
|
1286 |
+
"step": 1065
|
1287 |
+
},
|
1288 |
+
{
|
1289 |
+
"epoch": 0.59,
|
1290 |
+
"learning_rate": 4.535064542000743e-05,
|
1291 |
+
"loss": 1.0087,
|
1292 |
+
"step": 1070
|
1293 |
+
},
|
1294 |
+
{
|
1295 |
+
"epoch": 0.59,
|
1296 |
+
"learning_rate": 4.5308507983668165e-05,
|
1297 |
+
"loss": 0.952,
|
1298 |
+
"step": 1075
|
1299 |
+
},
|
1300 |
+
{
|
1301 |
+
"epoch": 0.6,
|
1302 |
+
"learning_rate": 4.526620022244293e-05,
|
1303 |
+
"loss": 0.9767,
|
1304 |
+
"step": 1080
|
1305 |
+
},
|
1306 |
+
{
|
1307 |
+
"epoch": 0.6,
|
1308 |
+
"learning_rate": 4.522372249116158e-05,
|
1309 |
+
"loss": 1.0049,
|
1310 |
+
"step": 1085
|
1311 |
+
},
|
1312 |
+
{
|
1313 |
+
"epoch": 0.6,
|
1314 |
+
"learning_rate": 4.5181075146079456e-05,
|
1315 |
+
"loss": 1.0397,
|
1316 |
+
"step": 1090
|
1317 |
+
},
|
1318 |
+
{
|
1319 |
+
"epoch": 0.61,
|
1320 |
+
"learning_rate": 4.5138258544874455e-05,
|
1321 |
+
"loss": 1.0167,
|
1322 |
+
"step": 1095
|
1323 |
+
},
|
1324 |
+
{
|
1325 |
+
"epoch": 0.61,
|
1326 |
+
"learning_rate": 4.5095273046643985e-05,
|
1327 |
+
"loss": 0.9966,
|
1328 |
+
"step": 1100
|
1329 |
+
},
|
1330 |
+
{
|
1331 |
+
"epoch": 0.61,
|
1332 |
+
"learning_rate": 4.5052119011901986e-05,
|
1333 |
+
"loss": 0.983,
|
1334 |
+
"step": 1105
|
1335 |
+
},
|
1336 |
+
{
|
1337 |
+
"epoch": 0.61,
|
1338 |
+
"learning_rate": 4.500879680257587e-05,
|
1339 |
+
"loss": 1.0301,
|
1340 |
+
"step": 1110
|
1341 |
+
},
|
1342 |
+
{
|
1343 |
+
"epoch": 0.62,
|
1344 |
+
"learning_rate": 4.4965306782003535e-05,
|
1345 |
+
"loss": 1.0371,
|
1346 |
+
"step": 1115
|
1347 |
+
},
|
1348 |
+
{
|
1349 |
+
"epoch": 0.62,
|
1350 |
+
"learning_rate": 4.492164931493028e-05,
|
1351 |
+
"loss": 1.0083,
|
1352 |
+
"step": 1120
|
1353 |
+
},
|
1354 |
+
{
|
1355 |
+
"epoch": 0.62,
|
1356 |
+
"learning_rate": 4.487782476750575e-05,
|
1357 |
+
"loss": 0.9728,
|
1358 |
+
"step": 1125
|
1359 |
+
},
|
1360 |
+
{
|
1361 |
+
"epoch": 0.62,
|
1362 |
+
"learning_rate": 4.4833833507280884e-05,
|
1363 |
+
"loss": 0.9892,
|
1364 |
+
"step": 1130
|
1365 |
+
},
|
1366 |
+
{
|
1367 |
+
"epoch": 0.63,
|
1368 |
+
"learning_rate": 4.4789675903204805e-05,
|
1369 |
+
"loss": 0.9847,
|
1370 |
+
"step": 1135
|
1371 |
+
},
|
1372 |
+
{
|
1373 |
+
"epoch": 0.63,
|
1374 |
+
"learning_rate": 4.474535232562176e-05,
|
1375 |
+
"loss": 1.0545,
|
1376 |
+
"step": 1140
|
1377 |
+
},
|
1378 |
+
{
|
1379 |
+
"epoch": 0.63,
|
1380 |
+
"learning_rate": 4.470086314626797e-05,
|
1381 |
+
"loss": 1.0204,
|
1382 |
+
"step": 1145
|
1383 |
+
},
|
1384 |
+
{
|
1385 |
+
"epoch": 0.64,
|
1386 |
+
"learning_rate": 4.465620873826856e-05,
|
1387 |
+
"loss": 0.9648,
|
1388 |
+
"step": 1150
|
1389 |
+
},
|
1390 |
+
{
|
1391 |
+
"epoch": 0.64,
|
1392 |
+
"learning_rate": 4.46113894761344e-05,
|
1393 |
+
"loss": 0.9545,
|
1394 |
+
"step": 1155
|
1395 |
+
},
|
1396 |
+
{
|
1397 |
+
"epoch": 0.64,
|
1398 |
+
"learning_rate": 4.456640573575896e-05,
|
1399 |
+
"loss": 1.0256,
|
1400 |
+
"step": 1160
|
1401 |
+
},
|
1402 |
+
{
|
1403 |
+
"epoch": 0.64,
|
1404 |
+
"learning_rate": 4.4521257894415183e-05,
|
1405 |
+
"loss": 0.99,
|
1406 |
+
"step": 1165
|
1407 |
+
},
|
1408 |
+
{
|
1409 |
+
"epoch": 0.65,
|
1410 |
+
"learning_rate": 4.44759463307523e-05,
|
1411 |
+
"loss": 0.9906,
|
1412 |
+
"step": 1170
|
1413 |
+
},
|
1414 |
+
{
|
1415 |
+
"epoch": 0.65,
|
1416 |
+
"learning_rate": 4.443047142479266e-05,
|
1417 |
+
"loss": 0.9876,
|
1418 |
+
"step": 1175
|
1419 |
+
},
|
1420 |
+
{
|
1421 |
+
"epoch": 0.65,
|
1422 |
+
"learning_rate": 4.4384833557928553e-05,
|
1423 |
+
"loss": 1.0495,
|
1424 |
+
"step": 1180
|
1425 |
+
},
|
1426 |
+
{
|
1427 |
+
"epoch": 0.66,
|
1428 |
+
"learning_rate": 4.4339033112918966e-05,
|
1429 |
+
"loss": 0.9869,
|
1430 |
+
"step": 1185
|
1431 |
+
},
|
1432 |
+
{
|
1433 |
+
"epoch": 0.66,
|
1434 |
+
"learning_rate": 4.4293070473886456e-05,
|
1435 |
+
"loss": 1.0299,
|
1436 |
+
"step": 1190
|
1437 |
+
},
|
1438 |
+
{
|
1439 |
+
"epoch": 0.66,
|
1440 |
+
"learning_rate": 4.424694602631385e-05,
|
1441 |
+
"loss": 1.0073,
|
1442 |
+
"step": 1195
|
1443 |
+
},
|
1444 |
+
{
|
1445 |
+
"epoch": 0.66,
|
1446 |
+
"learning_rate": 4.420066015704105e-05,
|
1447 |
+
"loss": 1.0023,
|
1448 |
+
"step": 1200
|
1449 |
+
}
|
1450 |
+
],
|
1451 |
+
"max_steps": 5424,
|
1452 |
+
"num_train_epochs": 3,
|
1453 |
+
"total_flos": 3.89964374212608e+17,
|
1454 |
+
"trial_name": null,
|
1455 |
+
"trial_params": null
|
1456 |
+
}
|
checkpoint-1200/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f6a8853599a52b1f15984d75ce4b6434c335fdc67d4509d0b2ca0d8c613590a
|
3 |
+
size 3362
|
checkpoint-1300/README.md
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
---
|
4 |
+
## Training procedure
|
5 |
+
|
6 |
+
|
7 |
+
The following `bitsandbytes` quantization config was used during training:
|
8 |
+
- load_in_8bit: True
|
9 |
+
- llm_int8_threshold: 6.0
|
10 |
+
- llm_int8_skip_modules: None
|
11 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
12 |
+
### Framework versions
|
13 |
+
|
14 |
+
|
15 |
+
- PEFT 0.5.0
|
checkpoint-1300/adapter_config.json
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"auto_mapping": null,
|
3 |
+
"base_model_name_or_path": "meta-llama/Llama-2-7b-chat-hf",
|
4 |
+
"bias": "none",
|
5 |
+
"fan_in_fan_out": false,
|
6 |
+
"inference_mode": true,
|
7 |
+
"init_lora_weights": true,
|
8 |
+
"layers_pattern": null,
|
9 |
+
"layers_to_transform": null,
|
10 |
+
"lora_alpha": 32.0,
|
11 |
+
"lora_dropout": 0.1,
|
12 |
+
"modules_to_save": null,
|
13 |
+
"peft_type": "LORA",
|
14 |
+
"r": 8,
|
15 |
+
"revision": null,
|
16 |
+
"target_modules": [
|
17 |
+
"q_proj",
|
18 |
+
"v_proj"
|
19 |
+
],
|
20 |
+
"task_type": "CAUSAL_LM"
|
21 |
+
}
|
checkpoint-1300/adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d2278e667677bfbfc7e5bc7aa88f1db8f45950b047e420960a13e2302a5cd6bf
|
3 |
+
size 16821197
|