Add files using upload-large-folder tool
Browse files- .gitattributes +1 -0
- README.md +66 -0
- adapter_config.json +34 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +24 -0
- all_results.json +12 -0
- eval_results.json +7 -0
- merges.txt +0 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +208 -0
- train_results.json +8 -0
- trainer_log.jsonl +290 -0
- trainer_state.json +2066 -0
- training_args.bin +3 -0
- training_eval_loss.png +0 -0
- training_loss.png +0 -0
- vocab.json +0 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
license: other
|
4 |
+
base_model: Qwen/Qwen2.5-14B-Instruct
|
5 |
+
tags:
|
6 |
+
- llama-factory
|
7 |
+
- lora
|
8 |
+
- generated_from_trainer
|
9 |
+
model-index:
|
10 |
+
- name: MATH_training_response_Qwen2.5_72B
|
11 |
+
results: []
|
12 |
+
---
|
13 |
+
|
14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
+
should probably proofread and complete it, then remove this comment. -->
|
16 |
+
|
17 |
+
# MATH_training_response_Qwen2.5_72B
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [Qwen/Qwen2.5-14B-Instruct](https://huggingface.co/Qwen/Qwen2.5-14B-Instruct) on the MATH_training_response_Qwen2.5_72B dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.0579
|
22 |
+
|
23 |
+
## Model description
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Intended uses & limitations
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training and evaluation data
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training procedure
|
36 |
+
|
37 |
+
### Training hyperparameters
|
38 |
+
|
39 |
+
The following hyperparameters were used during training:
|
40 |
+
- learning_rate: 0.0001
|
41 |
+
- train_batch_size: 1
|
42 |
+
- eval_batch_size: 1
|
43 |
+
- seed: 42
|
44 |
+
- distributed_type: multi-GPU
|
45 |
+
- num_devices: 4
|
46 |
+
- total_train_batch_size: 4
|
47 |
+
- total_eval_batch_size: 4
|
48 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
49 |
+
- lr_scheduler_type: cosine
|
50 |
+
- lr_scheduler_warmup_ratio: 0.1
|
51 |
+
- num_epochs: 2.0
|
52 |
+
|
53 |
+
### Training results
|
54 |
+
|
55 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
56 |
+
|:-------------:|:------:|:----:|:---------------:|
|
57 |
+
| 0.046 | 1.3889 | 200 | 0.0584 |
|
58 |
+
|
59 |
+
|
60 |
+
### Framework versions
|
61 |
+
|
62 |
+
- PEFT 0.12.0
|
63 |
+
- Transformers 4.46.1
|
64 |
+
- Pytorch 2.5.1+cu124
|
65 |
+
- Datasets 3.1.0
|
66 |
+
- Tokenizers 0.20.3
|
adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "Qwen/Qwen2.5-14B-Instruct",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 16,
|
14 |
+
"lora_dropout": 0.0,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 8,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"k_proj",
|
24 |
+
"down_proj",
|
25 |
+
"o_proj",
|
26 |
+
"q_proj",
|
27 |
+
"up_proj",
|
28 |
+
"gate_proj",
|
29 |
+
"v_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fea4b9066052e7677343c9fe97cb80f2f66e84669ffc4178961eb4d211cf4801
|
3 |
+
size 68902296
|
added_tokens.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</tool_call>": 151658,
|
3 |
+
"<tool_call>": 151657,
|
4 |
+
"<|box_end|>": 151649,
|
5 |
+
"<|box_start|>": 151648,
|
6 |
+
"<|endoftext|>": 151643,
|
7 |
+
"<|file_sep|>": 151664,
|
8 |
+
"<|fim_middle|>": 151660,
|
9 |
+
"<|fim_pad|>": 151662,
|
10 |
+
"<|fim_prefix|>": 151659,
|
11 |
+
"<|fim_suffix|>": 151661,
|
12 |
+
"<|im_end|>": 151645,
|
13 |
+
"<|im_start|>": 151644,
|
14 |
+
"<|image_pad|>": 151655,
|
15 |
+
"<|object_ref_end|>": 151647,
|
16 |
+
"<|object_ref_start|>": 151646,
|
17 |
+
"<|quad_end|>": 151651,
|
18 |
+
"<|quad_start|>": 151650,
|
19 |
+
"<|repo_name|>": 151663,
|
20 |
+
"<|video_pad|>": 151656,
|
21 |
+
"<|vision_end|>": 151653,
|
22 |
+
"<|vision_pad|>": 151654,
|
23 |
+
"<|vision_start|>": 151652
|
24 |
+
}
|
all_results.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.0,
|
3 |
+
"eval_loss": 0.05785840377211571,
|
4 |
+
"eval_runtime": 2.9043,
|
5 |
+
"eval_samples_per_second": 2.066,
|
6 |
+
"eval_steps_per_second": 0.689,
|
7 |
+
"total_flos": 547031730880512.0,
|
8 |
+
"train_loss": 0.056736280779457755,
|
9 |
+
"train_runtime": 1071.8886,
|
10 |
+
"train_samples_per_second": 1.069,
|
11 |
+
"train_steps_per_second": 0.269
|
12 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.0,
|
3 |
+
"eval_loss": 0.05785840377211571,
|
4 |
+
"eval_runtime": 2.9043,
|
5 |
+
"eval_samples_per_second": 2.066,
|
6 |
+
"eval_steps_per_second": 0.689
|
7 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
special_tokens_map.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>",
|
5 |
+
"<|object_ref_start|>",
|
6 |
+
"<|object_ref_end|>",
|
7 |
+
"<|box_start|>",
|
8 |
+
"<|box_end|>",
|
9 |
+
"<|quad_start|>",
|
10 |
+
"<|quad_end|>",
|
11 |
+
"<|vision_start|>",
|
12 |
+
"<|vision_end|>",
|
13 |
+
"<|vision_pad|>",
|
14 |
+
"<|image_pad|>",
|
15 |
+
"<|video_pad|>"
|
16 |
+
],
|
17 |
+
"eos_token": {
|
18 |
+
"content": "<|im_end|>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
},
|
24 |
+
"pad_token": {
|
25 |
+
"content": "<|endoftext|>",
|
26 |
+
"lstrip": false,
|
27 |
+
"normalized": false,
|
28 |
+
"rstrip": false,
|
29 |
+
"single_word": false
|
30 |
+
}
|
31 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
3 |
+
size 11421896
|
tokenizer_config.json
ADDED
@@ -0,0 +1,208 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"151643": {
|
6 |
+
"content": "<|endoftext|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"151644": {
|
14 |
+
"content": "<|im_start|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"151645": {
|
22 |
+
"content": "<|im_end|>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"151646": {
|
30 |
+
"content": "<|object_ref_start|>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"151647": {
|
38 |
+
"content": "<|object_ref_end|>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
},
|
45 |
+
"151648": {
|
46 |
+
"content": "<|box_start|>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false,
|
51 |
+
"special": true
|
52 |
+
},
|
53 |
+
"151649": {
|
54 |
+
"content": "<|box_end|>",
|
55 |
+
"lstrip": false,
|
56 |
+
"normalized": false,
|
57 |
+
"rstrip": false,
|
58 |
+
"single_word": false,
|
59 |
+
"special": true
|
60 |
+
},
|
61 |
+
"151650": {
|
62 |
+
"content": "<|quad_start|>",
|
63 |
+
"lstrip": false,
|
64 |
+
"normalized": false,
|
65 |
+
"rstrip": false,
|
66 |
+
"single_word": false,
|
67 |
+
"special": true
|
68 |
+
},
|
69 |
+
"151651": {
|
70 |
+
"content": "<|quad_end|>",
|
71 |
+
"lstrip": false,
|
72 |
+
"normalized": false,
|
73 |
+
"rstrip": false,
|
74 |
+
"single_word": false,
|
75 |
+
"special": true
|
76 |
+
},
|
77 |
+
"151652": {
|
78 |
+
"content": "<|vision_start|>",
|
79 |
+
"lstrip": false,
|
80 |
+
"normalized": false,
|
81 |
+
"rstrip": false,
|
82 |
+
"single_word": false,
|
83 |
+
"special": true
|
84 |
+
},
|
85 |
+
"151653": {
|
86 |
+
"content": "<|vision_end|>",
|
87 |
+
"lstrip": false,
|
88 |
+
"normalized": false,
|
89 |
+
"rstrip": false,
|
90 |
+
"single_word": false,
|
91 |
+
"special": true
|
92 |
+
},
|
93 |
+
"151654": {
|
94 |
+
"content": "<|vision_pad|>",
|
95 |
+
"lstrip": false,
|
96 |
+
"normalized": false,
|
97 |
+
"rstrip": false,
|
98 |
+
"single_word": false,
|
99 |
+
"special": true
|
100 |
+
},
|
101 |
+
"151655": {
|
102 |
+
"content": "<|image_pad|>",
|
103 |
+
"lstrip": false,
|
104 |
+
"normalized": false,
|
105 |
+
"rstrip": false,
|
106 |
+
"single_word": false,
|
107 |
+
"special": true
|
108 |
+
},
|
109 |
+
"151656": {
|
110 |
+
"content": "<|video_pad|>",
|
111 |
+
"lstrip": false,
|
112 |
+
"normalized": false,
|
113 |
+
"rstrip": false,
|
114 |
+
"single_word": false,
|
115 |
+
"special": true
|
116 |
+
},
|
117 |
+
"151657": {
|
118 |
+
"content": "<tool_call>",
|
119 |
+
"lstrip": false,
|
120 |
+
"normalized": false,
|
121 |
+
"rstrip": false,
|
122 |
+
"single_word": false,
|
123 |
+
"special": false
|
124 |
+
},
|
125 |
+
"151658": {
|
126 |
+
"content": "</tool_call>",
|
127 |
+
"lstrip": false,
|
128 |
+
"normalized": false,
|
129 |
+
"rstrip": false,
|
130 |
+
"single_word": false,
|
131 |
+
"special": false
|
132 |
+
},
|
133 |
+
"151659": {
|
134 |
+
"content": "<|fim_prefix|>",
|
135 |
+
"lstrip": false,
|
136 |
+
"normalized": false,
|
137 |
+
"rstrip": false,
|
138 |
+
"single_word": false,
|
139 |
+
"special": false
|
140 |
+
},
|
141 |
+
"151660": {
|
142 |
+
"content": "<|fim_middle|>",
|
143 |
+
"lstrip": false,
|
144 |
+
"normalized": false,
|
145 |
+
"rstrip": false,
|
146 |
+
"single_word": false,
|
147 |
+
"special": false
|
148 |
+
},
|
149 |
+
"151661": {
|
150 |
+
"content": "<|fim_suffix|>",
|
151 |
+
"lstrip": false,
|
152 |
+
"normalized": false,
|
153 |
+
"rstrip": false,
|
154 |
+
"single_word": false,
|
155 |
+
"special": false
|
156 |
+
},
|
157 |
+
"151662": {
|
158 |
+
"content": "<|fim_pad|>",
|
159 |
+
"lstrip": false,
|
160 |
+
"normalized": false,
|
161 |
+
"rstrip": false,
|
162 |
+
"single_word": false,
|
163 |
+
"special": false
|
164 |
+
},
|
165 |
+
"151663": {
|
166 |
+
"content": "<|repo_name|>",
|
167 |
+
"lstrip": false,
|
168 |
+
"normalized": false,
|
169 |
+
"rstrip": false,
|
170 |
+
"single_word": false,
|
171 |
+
"special": false
|
172 |
+
},
|
173 |
+
"151664": {
|
174 |
+
"content": "<|file_sep|>",
|
175 |
+
"lstrip": false,
|
176 |
+
"normalized": false,
|
177 |
+
"rstrip": false,
|
178 |
+
"single_word": false,
|
179 |
+
"special": false
|
180 |
+
}
|
181 |
+
},
|
182 |
+
"additional_special_tokens": [
|
183 |
+
"<|im_start|>",
|
184 |
+
"<|im_end|>",
|
185 |
+
"<|object_ref_start|>",
|
186 |
+
"<|object_ref_end|>",
|
187 |
+
"<|box_start|>",
|
188 |
+
"<|box_end|>",
|
189 |
+
"<|quad_start|>",
|
190 |
+
"<|quad_end|>",
|
191 |
+
"<|vision_start|>",
|
192 |
+
"<|vision_end|>",
|
193 |
+
"<|vision_pad|>",
|
194 |
+
"<|image_pad|>",
|
195 |
+
"<|video_pad|>"
|
196 |
+
],
|
197 |
+
"bos_token": null,
|
198 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
199 |
+
"clean_up_tokenization_spaces": false,
|
200 |
+
"eos_token": "<|im_end|>",
|
201 |
+
"errors": "replace",
|
202 |
+
"model_max_length": 131072,
|
203 |
+
"pad_token": "<|endoftext|>",
|
204 |
+
"padding_side": "right",
|
205 |
+
"split_special_tokens": false,
|
206 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
207 |
+
"unk_token": null
|
208 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.0,
|
3 |
+
"total_flos": 547031730880512.0,
|
4 |
+
"train_loss": 0.056736280779457755,
|
5 |
+
"train_runtime": 1071.8886,
|
6 |
+
"train_samples_per_second": 1.069,
|
7 |
+
"train_steps_per_second": 0.269
|
8 |
+
}
|
trainer_log.jsonl
ADDED
@@ -0,0 +1,290 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{"current_steps": 1, "total_steps": 288, "loss": 0.1218, "lr": 3.448275862068966e-06, "epoch": 0.006944444444444444, "percentage": 0.35, "elapsed_time": "0:00:06", "remaining_time": "0:32:10"}
|
2 |
+
{"current_steps": 2, "total_steps": 288, "loss": 0.1441, "lr": 6.896551724137932e-06, "epoch": 0.013888888888888888, "percentage": 0.69, "elapsed_time": "0:00:16", "remaining_time": "0:39:48"}
|
3 |
+
{"current_steps": 3, "total_steps": 288, "loss": 0.1517, "lr": 1.0344827586206897e-05, "epoch": 0.020833333333333332, "percentage": 1.04, "elapsed_time": "0:00:20", "remaining_time": "0:32:12"}
|
4 |
+
{"current_steps": 4, "total_steps": 288, "loss": 0.184, "lr": 1.3793103448275863e-05, "epoch": 0.027777777777777776, "percentage": 1.39, "elapsed_time": "0:00:23", "remaining_time": "0:28:19"}
|
5 |
+
{"current_steps": 5, "total_steps": 288, "loss": 0.0937, "lr": 1.7241379310344828e-05, "epoch": 0.034722222222222224, "percentage": 1.74, "elapsed_time": "0:00:27", "remaining_time": "0:25:57"}
|
6 |
+
{"current_steps": 6, "total_steps": 288, "loss": 0.1932, "lr": 2.0689655172413793e-05, "epoch": 0.041666666666666664, "percentage": 2.08, "elapsed_time": "0:00:31", "remaining_time": "0:24:20"}
|
7 |
+
{"current_steps": 7, "total_steps": 288, "loss": 0.1163, "lr": 2.413793103448276e-05, "epoch": 0.04861111111111111, "percentage": 2.43, "elapsed_time": "0:00:34", "remaining_time": "0:23:13"}
|
8 |
+
{"current_steps": 8, "total_steps": 288, "loss": 0.0997, "lr": 2.7586206896551727e-05, "epoch": 0.05555555555555555, "percentage": 2.78, "elapsed_time": "0:00:38", "remaining_time": "0:22:21"}
|
9 |
+
{"current_steps": 9, "total_steps": 288, "loss": 0.0691, "lr": 3.103448275862069e-05, "epoch": 0.0625, "percentage": 3.12, "elapsed_time": "0:00:41", "remaining_time": "0:21:39"}
|
10 |
+
{"current_steps": 10, "total_steps": 288, "loss": 0.1096, "lr": 3.4482758620689657e-05, "epoch": 0.06944444444444445, "percentage": 3.47, "elapsed_time": "0:00:45", "remaining_time": "0:21:05"}
|
11 |
+
{"current_steps": 11, "total_steps": 288, "loss": 0.0915, "lr": 3.793103448275862e-05, "epoch": 0.0763888888888889, "percentage": 3.82, "elapsed_time": "0:00:49", "remaining_time": "0:20:37"}
|
12 |
+
{"current_steps": 12, "total_steps": 288, "loss": 0.0758, "lr": 4.1379310344827587e-05, "epoch": 0.08333333333333333, "percentage": 4.17, "elapsed_time": "0:00:52", "remaining_time": "0:20:13"}
|
13 |
+
{"current_steps": 13, "total_steps": 288, "loss": 0.085, "lr": 4.482758620689655e-05, "epoch": 0.09027777777777778, "percentage": 4.51, "elapsed_time": "0:00:56", "remaining_time": "0:19:52"}
|
14 |
+
{"current_steps": 14, "total_steps": 288, "loss": 0.1039, "lr": 4.827586206896552e-05, "epoch": 0.09722222222222222, "percentage": 4.86, "elapsed_time": "0:00:59", "remaining_time": "0:19:32"}
|
15 |
+
{"current_steps": 15, "total_steps": 288, "loss": 0.1153, "lr": 5.172413793103449e-05, "epoch": 0.10416666666666667, "percentage": 5.21, "elapsed_time": "0:01:03", "remaining_time": "0:19:17"}
|
16 |
+
{"current_steps": 16, "total_steps": 288, "loss": 0.096, "lr": 5.517241379310345e-05, "epoch": 0.1111111111111111, "percentage": 5.56, "elapsed_time": "0:01:07", "remaining_time": "0:19:02"}
|
17 |
+
{"current_steps": 17, "total_steps": 288, "loss": 0.1187, "lr": 5.862068965517241e-05, "epoch": 0.11805555555555555, "percentage": 5.9, "elapsed_time": "0:01:10", "remaining_time": "0:18:48"}
|
18 |
+
{"current_steps": 18, "total_steps": 288, "loss": 0.0613, "lr": 6.206896551724138e-05, "epoch": 0.125, "percentage": 6.25, "elapsed_time": "0:01:14", "remaining_time": "0:18:35"}
|
19 |
+
{"current_steps": 19, "total_steps": 288, "loss": 0.112, "lr": 6.551724137931034e-05, "epoch": 0.13194444444444445, "percentage": 6.6, "elapsed_time": "0:01:18", "remaining_time": "0:18:24"}
|
20 |
+
{"current_steps": 20, "total_steps": 288, "loss": 0.1131, "lr": 6.896551724137931e-05, "epoch": 0.1388888888888889, "percentage": 6.94, "elapsed_time": "0:01:21", "remaining_time": "0:18:14"}
|
21 |
+
{"current_steps": 21, "total_steps": 288, "loss": 0.0754, "lr": 7.241379310344828e-05, "epoch": 0.14583333333333334, "percentage": 7.29, "elapsed_time": "0:01:25", "remaining_time": "0:18:04"}
|
22 |
+
{"current_steps": 22, "total_steps": 288, "loss": 0.0476, "lr": 7.586206896551724e-05, "epoch": 0.1527777777777778, "percentage": 7.64, "elapsed_time": "0:01:28", "remaining_time": "0:17:54"}
|
23 |
+
{"current_steps": 23, "total_steps": 288, "loss": 0.0778, "lr": 7.931034482758621e-05, "epoch": 0.1597222222222222, "percentage": 7.99, "elapsed_time": "0:01:32", "remaining_time": "0:17:46"}
|
24 |
+
{"current_steps": 24, "total_steps": 288, "loss": 0.0749, "lr": 8.275862068965517e-05, "epoch": 0.16666666666666666, "percentage": 8.33, "elapsed_time": "0:01:36", "remaining_time": "0:17:37"}
|
25 |
+
{"current_steps": 25, "total_steps": 288, "loss": 0.0692, "lr": 8.620689655172413e-05, "epoch": 0.1736111111111111, "percentage": 8.68, "elapsed_time": "0:01:39", "remaining_time": "0:17:29"}
|
26 |
+
{"current_steps": 26, "total_steps": 288, "loss": 0.1005, "lr": 8.96551724137931e-05, "epoch": 0.18055555555555555, "percentage": 9.03, "elapsed_time": "0:01:43", "remaining_time": "0:17:21"}
|
27 |
+
{"current_steps": 27, "total_steps": 288, "loss": 0.0796, "lr": 9.310344827586207e-05, "epoch": 0.1875, "percentage": 9.38, "elapsed_time": "0:01:46", "remaining_time": "0:17:14"}
|
28 |
+
{"current_steps": 28, "total_steps": 288, "loss": 0.0808, "lr": 9.655172413793105e-05, "epoch": 0.19444444444444445, "percentage": 9.72, "elapsed_time": "0:01:50", "remaining_time": "0:17:07"}
|
29 |
+
{"current_steps": 29, "total_steps": 288, "loss": 0.0589, "lr": 0.0001, "epoch": 0.2013888888888889, "percentage": 10.07, "elapsed_time": "0:01:54", "remaining_time": "0:16:59"}
|
30 |
+
{"current_steps": 30, "total_steps": 288, "loss": 0.0885, "lr": 9.999632180371776e-05, "epoch": 0.20833333333333334, "percentage": 10.42, "elapsed_time": "0:01:57", "remaining_time": "0:16:52"}
|
31 |
+
{"current_steps": 31, "total_steps": 288, "loss": 0.0859, "lr": 9.998528775603611e-05, "epoch": 0.2152777777777778, "percentage": 10.76, "elapsed_time": "0:02:01", "remaining_time": "0:16:46"}
|
32 |
+
{"current_steps": 32, "total_steps": 288, "loss": 0.0482, "lr": 9.99668994803708e-05, "epoch": 0.2222222222222222, "percentage": 11.11, "elapsed_time": "0:02:05", "remaining_time": "0:16:40"}
|
33 |
+
{"current_steps": 33, "total_steps": 288, "loss": 0.0575, "lr": 9.994115968214932e-05, "epoch": 0.22916666666666666, "percentage": 11.46, "elapsed_time": "0:02:08", "remaining_time": "0:16:34"}
|
34 |
+
{"current_steps": 34, "total_steps": 288, "loss": 0.0661, "lr": 9.990807214841287e-05, "epoch": 0.2361111111111111, "percentage": 11.81, "elapsed_time": "0:02:12", "remaining_time": "0:16:28"}
|
35 |
+
{"current_steps": 35, "total_steps": 288, "loss": 0.0556, "lr": 9.986764174725919e-05, "epoch": 0.24305555555555555, "percentage": 12.15, "elapsed_time": "0:02:15", "remaining_time": "0:16:22"}
|
36 |
+
{"current_steps": 36, "total_steps": 288, "loss": 0.0546, "lr": 9.981987442712633e-05, "epoch": 0.25, "percentage": 12.5, "elapsed_time": "0:02:19", "remaining_time": "0:16:16"}
|
37 |
+
{"current_steps": 37, "total_steps": 288, "loss": 0.0704, "lr": 9.976477721591745e-05, "epoch": 0.2569444444444444, "percentage": 12.85, "elapsed_time": "0:02:23", "remaining_time": "0:16:10"}
|
38 |
+
{"current_steps": 38, "total_steps": 288, "loss": 0.0627, "lr": 9.97023582199669e-05, "epoch": 0.2638888888888889, "percentage": 13.19, "elapsed_time": "0:02:26", "remaining_time": "0:16:05"}
|
39 |
+
{"current_steps": 39, "total_steps": 288, "loss": 0.0353, "lr": 9.963262662284736e-05, "epoch": 0.2708333333333333, "percentage": 13.54, "elapsed_time": "0:02:30", "remaining_time": "0:16:00"}
|
40 |
+
{"current_steps": 40, "total_steps": 288, "loss": 0.0562, "lr": 9.955559268401893e-05, "epoch": 0.2777777777777778, "percentage": 13.89, "elapsed_time": "0:02:34", "remaining_time": "0:15:54"}
|
41 |
+
{"current_steps": 41, "total_steps": 288, "loss": 0.0774, "lr": 9.947126773731948e-05, "epoch": 0.2847222222222222, "percentage": 14.24, "elapsed_time": "0:02:37", "remaining_time": "0:15:49"}
|
42 |
+
{"current_steps": 42, "total_steps": 288, "loss": 0.0688, "lr": 9.937966418929726e-05, "epoch": 0.2916666666666667, "percentage": 14.58, "elapsed_time": "0:02:41", "remaining_time": "0:15:43"}
|
43 |
+
{"current_steps": 43, "total_steps": 288, "loss": 0.0631, "lr": 9.928079551738543e-05, "epoch": 0.2986111111111111, "percentage": 14.93, "elapsed_time": "0:02:44", "remaining_time": "0:15:38"}
|
44 |
+
{"current_steps": 44, "total_steps": 288, "loss": 0.0602, "lr": 9.917467626791925e-05, "epoch": 0.3055555555555556, "percentage": 15.28, "elapsed_time": "0:02:48", "remaining_time": "0:15:33"}
|
45 |
+
{"current_steps": 45, "total_steps": 288, "loss": 0.0603, "lr": 9.90613220539959e-05, "epoch": 0.3125, "percentage": 15.62, "elapsed_time": "0:02:52", "remaining_time": "0:15:28"}
|
46 |
+
{"current_steps": 46, "total_steps": 288, "loss": 0.05, "lr": 9.89407495531773e-05, "epoch": 0.3194444444444444, "percentage": 15.97, "elapsed_time": "0:02:55", "remaining_time": "0:15:23"}
|
47 |
+
{"current_steps": 47, "total_steps": 288, "loss": 0.0666, "lr": 9.881297650503641e-05, "epoch": 0.3263888888888889, "percentage": 16.32, "elapsed_time": "0:02:59", "remaining_time": "0:15:18"}
|
48 |
+
{"current_steps": 48, "total_steps": 288, "loss": 0.0576, "lr": 9.867802170854724e-05, "epoch": 0.3333333333333333, "percentage": 16.67, "elapsed_time": "0:03:02", "remaining_time": "0:15:14"}
|
49 |
+
{"current_steps": 49, "total_steps": 288, "loss": 0.0714, "lr": 9.853590501931904e-05, "epoch": 0.3402777777777778, "percentage": 17.01, "elapsed_time": "0:03:06", "remaining_time": "0:15:09"}
|
50 |
+
{"current_steps": 50, "total_steps": 288, "loss": 0.0557, "lr": 9.838664734667495e-05, "epoch": 0.3472222222222222, "percentage": 17.36, "elapsed_time": "0:03:09", "remaining_time": "0:15:04"}
|
51 |
+
{"current_steps": 51, "total_steps": 288, "loss": 0.0608, "lr": 9.82302706505756e-05, "epoch": 0.3541666666666667, "percentage": 17.71, "elapsed_time": "0:03:13", "remaining_time": "0:15:01"}
|
52 |
+
{"current_steps": 52, "total_steps": 288, "loss": 0.0457, "lr": 9.806679793838829e-05, "epoch": 0.3611111111111111, "percentage": 18.06, "elapsed_time": "0:03:17", "remaining_time": "0:14:57"}
|
53 |
+
{"current_steps": 53, "total_steps": 288, "loss": 0.0538, "lr": 9.78962532615019e-05, "epoch": 0.3680555555555556, "percentage": 18.4, "elapsed_time": "0:03:21", "remaining_time": "0:14:52"}
|
54 |
+
{"current_steps": 54, "total_steps": 288, "loss": 0.0535, "lr": 9.771866171178831e-05, "epoch": 0.375, "percentage": 18.75, "elapsed_time": "0:03:24", "remaining_time": "0:14:48"}
|
55 |
+
{"current_steps": 55, "total_steps": 288, "loss": 0.0533, "lr": 9.753404941791062e-05, "epoch": 0.3819444444444444, "percentage": 19.1, "elapsed_time": "0:03:28", "remaining_time": "0:14:43"}
|
56 |
+
{"current_steps": 56, "total_steps": 288, "loss": 0.0558, "lr": 9.734244354147895e-05, "epoch": 0.3888888888888889, "percentage": 19.44, "elapsed_time": "0:03:32", "remaining_time": "0:14:39"}
|
57 |
+
{"current_steps": 57, "total_steps": 288, "loss": 0.059, "lr": 9.714387227305422e-05, "epoch": 0.3958333333333333, "percentage": 19.79, "elapsed_time": "0:03:35", "remaining_time": "0:14:34"}
|
58 |
+
{"current_steps": 58, "total_steps": 288, "loss": 0.0666, "lr": 9.693836482800044e-05, "epoch": 0.4027777777777778, "percentage": 20.14, "elapsed_time": "0:03:39", "remaining_time": "0:14:30"}
|
59 |
+
{"current_steps": 59, "total_steps": 288, "loss": 0.0553, "lr": 9.672595144218646e-05, "epoch": 0.4097222222222222, "percentage": 20.49, "elapsed_time": "0:03:43", "remaining_time": "0:14:26"}
|
60 |
+
{"current_steps": 60, "total_steps": 288, "loss": 0.0736, "lr": 9.650666336753728e-05, "epoch": 0.4166666666666667, "percentage": 20.83, "elapsed_time": "0:03:46", "remaining_time": "0:14:22"}
|
61 |
+
{"current_steps": 61, "total_steps": 288, "loss": 0.0658, "lr": 9.628053286743619e-05, "epoch": 0.4236111111111111, "percentage": 21.18, "elapsed_time": "0:03:50", "remaining_time": "0:14:17"}
|
62 |
+
{"current_steps": 62, "total_steps": 288, "loss": 0.0597, "lr": 9.604759321197773e-05, "epoch": 0.4305555555555556, "percentage": 21.53, "elapsed_time": "0:03:54", "remaining_time": "0:14:13"}
|
63 |
+
{"current_steps": 63, "total_steps": 288, "loss": 0.0661, "lr": 9.580787867307293e-05, "epoch": 0.4375, "percentage": 21.88, "elapsed_time": "0:03:57", "remaining_time": "0:14:09"}
|
64 |
+
{"current_steps": 64, "total_steps": 288, "loss": 0.0684, "lr": 9.55614245194068e-05, "epoch": 0.4444444444444444, "percentage": 22.22, "elapsed_time": "0:04:01", "remaining_time": "0:14:04"}
|
65 |
+
{"current_steps": 65, "total_steps": 288, "loss": 0.0547, "lr": 9.530826701124939e-05, "epoch": 0.4513888888888889, "percentage": 22.57, "elapsed_time": "0:04:04", "remaining_time": "0:14:00"}
|
66 |
+
{"current_steps": 66, "total_steps": 288, "loss": 0.0596, "lr": 9.504844339512095e-05, "epoch": 0.4583333333333333, "percentage": 22.92, "elapsed_time": "0:04:08", "remaining_time": "0:13:55"}
|
67 |
+
{"current_steps": 67, "total_steps": 288, "loss": 0.0411, "lr": 9.478199189831183e-05, "epoch": 0.4652777777777778, "percentage": 23.26, "elapsed_time": "0:04:12", "remaining_time": "0:13:51"}
|
68 |
+
{"current_steps": 68, "total_steps": 288, "loss": 0.0548, "lr": 9.450895172325822e-05, "epoch": 0.4722222222222222, "percentage": 23.61, "elapsed_time": "0:04:15", "remaining_time": "0:13:47"}
|
69 |
+
{"current_steps": 69, "total_steps": 288, "loss": 0.0531, "lr": 9.422936304177439e-05, "epoch": 0.4791666666666667, "percentage": 23.96, "elapsed_time": "0:04:19", "remaining_time": "0:13:43"}
|
70 |
+
{"current_steps": 70, "total_steps": 288, "loss": 0.0658, "lr": 9.39432669891423e-05, "epoch": 0.4861111111111111, "percentage": 24.31, "elapsed_time": "0:04:22", "remaining_time": "0:13:38"}
|
71 |
+
{"current_steps": 71, "total_steps": 288, "loss": 0.0511, "lr": 9.365070565805941e-05, "epoch": 0.4930555555555556, "percentage": 24.65, "elapsed_time": "0:04:26", "remaining_time": "0:13:34"}
|
72 |
+
{"current_steps": 72, "total_steps": 288, "loss": 0.0547, "lr": 9.335172209244575e-05, "epoch": 0.5, "percentage": 25.0, "elapsed_time": "0:04:30", "remaining_time": "0:13:30"}
|
73 |
+
{"current_steps": 73, "total_steps": 288, "loss": 0.0674, "lr": 9.304636028111094e-05, "epoch": 0.5069444444444444, "percentage": 25.35, "elapsed_time": "0:04:33", "remaining_time": "0:13:26"}
|
74 |
+
{"current_steps": 74, "total_steps": 288, "loss": 0.067, "lr": 9.273466515128209e-05, "epoch": 0.5138888888888888, "percentage": 25.69, "elapsed_time": "0:04:37", "remaining_time": "0:13:22"}
|
75 |
+
{"current_steps": 75, "total_steps": 288, "loss": 0.0501, "lr": 9.241668256199392e-05, "epoch": 0.5208333333333334, "percentage": 26.04, "elapsed_time": "0:04:41", "remaining_time": "0:13:18"}
|
76 |
+
{"current_steps": 76, "total_steps": 288, "loss": 0.0509, "lr": 9.209245929734156e-05, "epoch": 0.5277777777777778, "percentage": 26.39, "elapsed_time": "0:04:44", "remaining_time": "0:13:13"}
|
77 |
+
{"current_steps": 77, "total_steps": 288, "loss": 0.0465, "lr": 9.176204305959726e-05, "epoch": 0.5347222222222222, "percentage": 26.74, "elapsed_time": "0:04:48", "remaining_time": "0:13:09"}
|
78 |
+
{"current_steps": 78, "total_steps": 288, "loss": 0.0454, "lr": 9.142548246219212e-05, "epoch": 0.5416666666666666, "percentage": 27.08, "elapsed_time": "0:04:51", "remaining_time": "0:13:05"}
|
79 |
+
{"current_steps": 79, "total_steps": 288, "loss": 0.0598, "lr": 9.108282702256365e-05, "epoch": 0.5486111111111112, "percentage": 27.43, "elapsed_time": "0:04:55", "remaining_time": "0:13:01"}
|
80 |
+
{"current_steps": 80, "total_steps": 288, "loss": 0.0632, "lr": 9.073412715487044e-05, "epoch": 0.5555555555555556, "percentage": 27.78, "elapsed_time": "0:04:59", "remaining_time": "0:12:57"}
|
81 |
+
{"current_steps": 81, "total_steps": 288, "loss": 0.059, "lr": 9.037943416257474e-05, "epoch": 0.5625, "percentage": 28.12, "elapsed_time": "0:05:02", "remaining_time": "0:12:53"}
|
82 |
+
{"current_steps": 82, "total_steps": 288, "loss": 0.0578, "lr": 9.001880023089441e-05, "epoch": 0.5694444444444444, "percentage": 28.47, "elapsed_time": "0:05:06", "remaining_time": "0:12:49"}
|
83 |
+
{"current_steps": 83, "total_steps": 288, "loss": 0.0435, "lr": 8.965227841912489e-05, "epoch": 0.5763888888888888, "percentage": 28.82, "elapsed_time": "0:05:09", "remaining_time": "0:12:45"}
|
84 |
+
{"current_steps": 84, "total_steps": 288, "loss": 0.058, "lr": 8.927992265283282e-05, "epoch": 0.5833333333333334, "percentage": 29.17, "elapsed_time": "0:05:13", "remaining_time": "0:12:41"}
|
85 |
+
{"current_steps": 85, "total_steps": 288, "loss": 0.045, "lr": 8.890178771592199e-05, "epoch": 0.5902777777777778, "percentage": 29.51, "elapsed_time": "0:05:17", "remaining_time": "0:12:37"}
|
86 |
+
{"current_steps": 86, "total_steps": 288, "loss": 0.0709, "lr": 8.851792924257317e-05, "epoch": 0.5972222222222222, "percentage": 29.86, "elapsed_time": "0:05:20", "remaining_time": "0:12:33"}
|
87 |
+
{"current_steps": 87, "total_steps": 288, "loss": 0.0525, "lr": 8.812840370905873e-05, "epoch": 0.6041666666666666, "percentage": 30.21, "elapsed_time": "0:05:24", "remaining_time": "0:12:29"}
|
88 |
+
{"current_steps": 88, "total_steps": 288, "loss": 0.0464, "lr": 8.773326842543347e-05, "epoch": 0.6111111111111112, "percentage": 30.56, "elapsed_time": "0:05:27", "remaining_time": "0:12:25"}
|
89 |
+
{"current_steps": 89, "total_steps": 288, "loss": 0.0649, "lr": 8.733258152710262e-05, "epoch": 0.6180555555555556, "percentage": 30.9, "elapsed_time": "0:05:31", "remaining_time": "0:12:21"}
|
90 |
+
{"current_steps": 90, "total_steps": 288, "loss": 0.0575, "lr": 8.692640196626858e-05, "epoch": 0.625, "percentage": 31.25, "elapsed_time": "0:05:35", "remaining_time": "0:12:17"}
|
91 |
+
{"current_steps": 91, "total_steps": 288, "loss": 0.0694, "lr": 8.651478950325737e-05, "epoch": 0.6319444444444444, "percentage": 31.6, "elapsed_time": "0:05:38", "remaining_time": "0:12:13"}
|
92 |
+
{"current_steps": 92, "total_steps": 288, "loss": 0.0581, "lr": 8.609780469772623e-05, "epoch": 0.6388888888888888, "percentage": 31.94, "elapsed_time": "0:05:42", "remaining_time": "0:12:09"}
|
93 |
+
{"current_steps": 93, "total_steps": 288, "loss": 0.0489, "lr": 8.567550889975362e-05, "epoch": 0.6458333333333334, "percentage": 32.29, "elapsed_time": "0:05:45", "remaining_time": "0:12:05"}
|
94 |
+
{"current_steps": 94, "total_steps": 288, "loss": 0.0597, "lr": 8.524796424081292e-05, "epoch": 0.6527777777777778, "percentage": 32.64, "elapsed_time": "0:05:49", "remaining_time": "0:12:01"}
|
95 |
+
{"current_steps": 95, "total_steps": 288, "loss": 0.0609, "lr": 8.481523362463111e-05, "epoch": 0.6597222222222222, "percentage": 32.99, "elapsed_time": "0:05:53", "remaining_time": "0:11:57"}
|
96 |
+
{"current_steps": 96, "total_steps": 288, "loss": 0.0461, "lr": 8.437738071793394e-05, "epoch": 0.6666666666666666, "percentage": 33.33, "elapsed_time": "0:05:56", "remaining_time": "0:11:53"}
|
97 |
+
{"current_steps": 97, "total_steps": 288, "loss": 0.0675, "lr": 8.393446994107877e-05, "epoch": 0.6736111111111112, "percentage": 33.68, "elapsed_time": "0:06:00", "remaining_time": "0:11:49"}
|
98 |
+
{"current_steps": 98, "total_steps": 288, "loss": 0.0501, "lr": 8.348656645857649e-05, "epoch": 0.6805555555555556, "percentage": 34.03, "elapsed_time": "0:06:03", "remaining_time": "0:11:45"}
|
99 |
+
{"current_steps": 99, "total_steps": 288, "loss": 0.0465, "lr": 8.303373616950408e-05, "epoch": 0.6875, "percentage": 34.38, "elapsed_time": "0:06:07", "remaining_time": "0:11:41"}
|
100 |
+
{"current_steps": 100, "total_steps": 288, "loss": 0.0538, "lr": 8.257604569780897e-05, "epoch": 0.6944444444444444, "percentage": 34.72, "elapsed_time": "0:06:11", "remaining_time": "0:11:37"}
|
101 |
+
{"current_steps": 101, "total_steps": 288, "loss": 0.0532, "lr": 8.21135623825068e-05, "epoch": 0.7013888888888888, "percentage": 35.07, "elapsed_time": "0:06:14", "remaining_time": "0:11:33"}
|
102 |
+
{"current_steps": 102, "total_steps": 288, "loss": 0.0584, "lr": 8.164635426777404e-05, "epoch": 0.7083333333333334, "percentage": 35.42, "elapsed_time": "0:06:18", "remaining_time": "0:11:29"}
|
103 |
+
{"current_steps": 103, "total_steps": 288, "loss": 0.0486, "lr": 8.117449009293668e-05, "epoch": 0.7152777777777778, "percentage": 35.76, "elapsed_time": "0:06:22", "remaining_time": "0:11:26"}
|
104 |
+
{"current_steps": 104, "total_steps": 288, "loss": 0.0512, "lr": 8.069803928235689e-05, "epoch": 0.7222222222222222, "percentage": 36.11, "elapsed_time": "0:06:25", "remaining_time": "0:11:22"}
|
105 |
+
{"current_steps": 105, "total_steps": 288, "loss": 0.0466, "lr": 8.021707193521865e-05, "epoch": 0.7291666666666666, "percentage": 36.46, "elapsed_time": "0:06:29", "remaining_time": "0:11:18"}
|
106 |
+
{"current_steps": 106, "total_steps": 288, "loss": 0.0614, "lr": 7.973165881521434e-05, "epoch": 0.7361111111111112, "percentage": 36.81, "elapsed_time": "0:06:32", "remaining_time": "0:11:14"}
|
107 |
+
{"current_steps": 107, "total_steps": 288, "loss": 0.0468, "lr": 7.924187134013323e-05, "epoch": 0.7430555555555556, "percentage": 37.15, "elapsed_time": "0:06:36", "remaining_time": "0:11:10"}
|
108 |
+
{"current_steps": 108, "total_steps": 288, "loss": 0.0522, "lr": 7.874778157135415e-05, "epoch": 0.75, "percentage": 37.5, "elapsed_time": "0:06:40", "remaining_time": "0:11:06"}
|
109 |
+
{"current_steps": 109, "total_steps": 288, "loss": 0.0639, "lr": 7.824946220324312e-05, "epoch": 0.7569444444444444, "percentage": 37.85, "elapsed_time": "0:06:43", "remaining_time": "0:11:02"}
|
110 |
+
{"current_steps": 110, "total_steps": 288, "loss": 0.054, "lr": 7.774698655245802e-05, "epoch": 0.7638888888888888, "percentage": 38.19, "elapsed_time": "0:06:47", "remaining_time": "0:10:58"}
|
111 |
+
{"current_steps": 111, "total_steps": 288, "loss": 0.0492, "lr": 7.724042854716169e-05, "epoch": 0.7708333333333334, "percentage": 38.54, "elapsed_time": "0:06:50", "remaining_time": "0:10:55"}
|
112 |
+
{"current_steps": 112, "total_steps": 288, "loss": 0.0562, "lr": 7.6729862716145e-05, "epoch": 0.7777777777777778, "percentage": 38.89, "elapsed_time": "0:06:54", "remaining_time": "0:10:51"}
|
113 |
+
{"current_steps": 113, "total_steps": 288, "loss": 0.069, "lr": 7.621536417786159e-05, "epoch": 0.7847222222222222, "percentage": 39.24, "elapsed_time": "0:06:58", "remaining_time": "0:10:47"}
|
114 |
+
{"current_steps": 114, "total_steps": 288, "loss": 0.057, "lr": 7.56970086293759e-05, "epoch": 0.7916666666666666, "percentage": 39.58, "elapsed_time": "0:07:01", "remaining_time": "0:10:43"}
|
115 |
+
{"current_steps": 115, "total_steps": 288, "loss": 0.0545, "lr": 7.5174872335226e-05, "epoch": 0.7986111111111112, "percentage": 39.93, "elapsed_time": "0:07:05", "remaining_time": "0:10:39"}
|
116 |
+
{"current_steps": 116, "total_steps": 288, "loss": 0.0533, "lr": 7.464903211620291e-05, "epoch": 0.8055555555555556, "percentage": 40.28, "elapsed_time": "0:07:08", "remaining_time": "0:10:35"}
|
117 |
+
{"current_steps": 117, "total_steps": 288, "loss": 0.0567, "lr": 7.411956533804818e-05, "epoch": 0.8125, "percentage": 40.62, "elapsed_time": "0:07:12", "remaining_time": "0:10:32"}
|
118 |
+
{"current_steps": 118, "total_steps": 288, "loss": 0.0634, "lr": 7.358654990007122e-05, "epoch": 0.8194444444444444, "percentage": 40.97, "elapsed_time": "0:07:16", "remaining_time": "0:10:28"}
|
119 |
+
{"current_steps": 119, "total_steps": 288, "loss": 0.0396, "lr": 7.305006422368811e-05, "epoch": 0.8263888888888888, "percentage": 41.32, "elapsed_time": "0:07:19", "remaining_time": "0:10:24"}
|
120 |
+
{"current_steps": 120, "total_steps": 288, "loss": 0.0598, "lr": 7.251018724088367e-05, "epoch": 0.8333333333333334, "percentage": 41.67, "elapsed_time": "0:07:23", "remaining_time": "0:10:20"}
|
121 |
+
{"current_steps": 121, "total_steps": 288, "loss": 0.0542, "lr": 7.196699838259834e-05, "epoch": 0.8402777777777778, "percentage": 42.01, "elapsed_time": "0:07:26", "remaining_time": "0:10:16"}
|
122 |
+
{"current_steps": 122, "total_steps": 288, "loss": 0.064, "lr": 7.142057756704168e-05, "epoch": 0.8472222222222222, "percentage": 42.36, "elapsed_time": "0:07:30", "remaining_time": "0:10:13"}
|
123 |
+
{"current_steps": 123, "total_steps": 288, "loss": 0.0552, "lr": 7.087100518793421e-05, "epoch": 0.8541666666666666, "percentage": 42.71, "elapsed_time": "0:07:34", "remaining_time": "0:10:09"}
|
124 |
+
{"current_steps": 124, "total_steps": 288, "loss": 0.0519, "lr": 7.031836210267915e-05, "epoch": 0.8611111111111112, "percentage": 43.06, "elapsed_time": "0:07:37", "remaining_time": "0:10:05"}
|
125 |
+
{"current_steps": 125, "total_steps": 288, "loss": 0.0544, "lr": 6.976272962046619e-05, "epoch": 0.8680555555555556, "percentage": 43.4, "elapsed_time": "0:07:41", "remaining_time": "0:10:01"}
|
126 |
+
{"current_steps": 126, "total_steps": 288, "loss": 0.0684, "lr": 6.920418949030856e-05, "epoch": 0.875, "percentage": 43.75, "elapsed_time": "0:07:44", "remaining_time": "0:09:57"}
|
127 |
+
{"current_steps": 127, "total_steps": 288, "loss": 0.0737, "lr": 6.864282388901544e-05, "epoch": 0.8819444444444444, "percentage": 44.1, "elapsed_time": "0:07:48", "remaining_time": "0:09:53"}
|
128 |
+
{"current_steps": 128, "total_steps": 288, "loss": 0.0515, "lr": 6.807871540910154e-05, "epoch": 0.8888888888888888, "percentage": 44.44, "elapsed_time": "0:07:52", "remaining_time": "0:09:50"}
|
129 |
+
{"current_steps": 129, "total_steps": 288, "loss": 0.0574, "lr": 6.751194704663543e-05, "epoch": 0.8958333333333334, "percentage": 44.79, "elapsed_time": "0:07:55", "remaining_time": "0:09:46"}
|
130 |
+
{"current_steps": 130, "total_steps": 288, "loss": 0.0445, "lr": 6.694260218902844e-05, "epoch": 0.9027777777777778, "percentage": 45.14, "elapsed_time": "0:07:59", "remaining_time": "0:09:42"}
|
131 |
+
{"current_steps": 131, "total_steps": 288, "loss": 0.0569, "lr": 6.637076460276613e-05, "epoch": 0.9097222222222222, "percentage": 45.49, "elapsed_time": "0:08:02", "remaining_time": "0:09:38"}
|
132 |
+
{"current_steps": 132, "total_steps": 288, "loss": 0.0551, "lr": 6.57965184210838e-05, "epoch": 0.9166666666666666, "percentage": 45.83, "elapsed_time": "0:08:06", "remaining_time": "0:09:35"}
|
133 |
+
{"current_steps": 133, "total_steps": 288, "loss": 0.0557, "lr": 6.521994813158834e-05, "epoch": 0.9236111111111112, "percentage": 46.18, "elapsed_time": "0:08:10", "remaining_time": "0:09:31"}
|
134 |
+
{"current_steps": 134, "total_steps": 288, "loss": 0.041, "lr": 6.464113856382752e-05, "epoch": 0.9305555555555556, "percentage": 46.53, "elapsed_time": "0:08:13", "remaining_time": "0:09:27"}
|
135 |
+
{"current_steps": 135, "total_steps": 288, "loss": 0.0522, "lr": 6.406017487680937e-05, "epoch": 0.9375, "percentage": 46.88, "elapsed_time": "0:08:17", "remaining_time": "0:09:23"}
|
136 |
+
{"current_steps": 136, "total_steps": 288, "loss": 0.0486, "lr": 6.347714254647284e-05, "epoch": 0.9444444444444444, "percentage": 47.22, "elapsed_time": "0:08:21", "remaining_time": "0:09:19"}
|
137 |
+
{"current_steps": 137, "total_steps": 288, "loss": 0.0593, "lr": 6.28921273531119e-05, "epoch": 0.9513888888888888, "percentage": 47.57, "elapsed_time": "0:08:24", "remaining_time": "0:09:16"}
|
138 |
+
{"current_steps": 138, "total_steps": 288, "loss": 0.0603, "lr": 6.230521536875494e-05, "epoch": 0.9583333333333334, "percentage": 47.92, "elapsed_time": "0:08:28", "remaining_time": "0:09:12"}
|
139 |
+
{"current_steps": 139, "total_steps": 288, "loss": 0.0422, "lr": 6.171649294450113e-05, "epoch": 0.9652777777777778, "percentage": 48.26, "elapsed_time": "0:08:31", "remaining_time": "0:09:08"}
|
140 |
+
{"current_steps": 140, "total_steps": 288, "loss": 0.0628, "lr": 6.112604669781572e-05, "epoch": 0.9722222222222222, "percentage": 48.61, "elapsed_time": "0:08:35", "remaining_time": "0:09:04"}
|
141 |
+
{"current_steps": 141, "total_steps": 288, "loss": 0.0416, "lr": 6.0533963499786314e-05, "epoch": 0.9791666666666666, "percentage": 48.96, "elapsed_time": "0:08:39", "remaining_time": "0:09:01"}
|
142 |
+
{"current_steps": 142, "total_steps": 288, "loss": 0.0663, "lr": 5.994033046234162e-05, "epoch": 0.9861111111111112, "percentage": 49.31, "elapsed_time": "0:08:42", "remaining_time": "0:08:57"}
|
143 |
+
{"current_steps": 143, "total_steps": 288, "loss": 0.0598, "lr": 5.934523492543489e-05, "epoch": 0.9930555555555556, "percentage": 49.65, "elapsed_time": "0:08:46", "remaining_time": "0:08:53"}
|
144 |
+
{"current_steps": 144, "total_steps": 288, "loss": 0.0553, "lr": 5.874876444419377e-05, "epoch": 1.0, "percentage": 50.0, "elapsed_time": "0:08:49", "remaining_time": "0:08:49"}
|
145 |
+
{"current_steps": 145, "total_steps": 288, "loss": 0.0487, "lr": 5.8151006776038544e-05, "epoch": 1.0069444444444444, "percentage": 50.35, "elapsed_time": "0:08:53", "remaining_time": "0:08:46"}
|
146 |
+
{"current_steps": 146, "total_steps": 288, "loss": 0.0496, "lr": 5.75520498677705e-05, "epoch": 1.0138888888888888, "percentage": 50.69, "elapsed_time": "0:08:57", "remaining_time": "0:08:42"}
|
147 |
+
{"current_steps": 147, "total_steps": 288, "loss": 0.0447, "lr": 5.6951981842632585e-05, "epoch": 1.0208333333333333, "percentage": 51.04, "elapsed_time": "0:09:00", "remaining_time": "0:08:38"}
|
148 |
+
{"current_steps": 148, "total_steps": 288, "loss": 0.0574, "lr": 5.6350890987343944e-05, "epoch": 1.0277777777777777, "percentage": 51.39, "elapsed_time": "0:09:04", "remaining_time": "0:08:34"}
|
149 |
+
{"current_steps": 149, "total_steps": 288, "loss": 0.0484, "lr": 5.574886573911056e-05, "epoch": 1.0347222222222223, "percentage": 51.74, "elapsed_time": "0:09:07", "remaining_time": "0:08:31"}
|
150 |
+
{"current_steps": 150, "total_steps": 288, "loss": 0.0424, "lr": 5.5145994672613624e-05, "epoch": 1.0416666666666667, "percentage": 52.08, "elapsed_time": "0:09:11", "remaining_time": "0:08:27"}
|
151 |
+
{"current_steps": 151, "total_steps": 288, "loss": 0.0506, "lr": 5.4542366486977756e-05, "epoch": 1.0486111111111112, "percentage": 52.43, "elapsed_time": "0:09:15", "remaining_time": "0:08:23"}
|
152 |
+
{"current_steps": 152, "total_steps": 288, "loss": 0.0527, "lr": 5.39380699927209e-05, "epoch": 1.0555555555555556, "percentage": 52.78, "elapsed_time": "0:09:18", "remaining_time": "0:08:19"}
|
153 |
+
{"current_steps": 153, "total_steps": 288, "loss": 0.0511, "lr": 5.3333194098687764e-05, "epoch": 1.0625, "percentage": 53.12, "elapsed_time": "0:09:22", "remaining_time": "0:08:16"}
|
154 |
+
{"current_steps": 154, "total_steps": 288, "loss": 0.0543, "lr": 5.272782779896898e-05, "epoch": 1.0694444444444444, "percentage": 53.47, "elapsed_time": "0:09:25", "remaining_time": "0:08:12"}
|
155 |
+
{"current_steps": 155, "total_steps": 288, "loss": 0.0595, "lr": 5.212206015980742e-05, "epoch": 1.0763888888888888, "percentage": 53.82, "elapsed_time": "0:09:29", "remaining_time": "0:08:08"}
|
156 |
+
{"current_steps": 156, "total_steps": 288, "loss": 0.0396, "lr": 5.151598030649425e-05, "epoch": 1.0833333333333333, "percentage": 54.17, "elapsed_time": "0:09:33", "remaining_time": "0:08:05"}
|
157 |
+
{"current_steps": 157, "total_steps": 288, "loss": 0.0436, "lr": 5.0909677410255985e-05, "epoch": 1.0902777777777777, "percentage": 54.51, "elapsed_time": "0:09:36", "remaining_time": "0:08:01"}
|
158 |
+
{"current_steps": 158, "total_steps": 288, "loss": 0.0514, "lr": 5.030324067513499e-05, "epoch": 1.0972222222222223, "percentage": 54.86, "elapsed_time": "0:09:40", "remaining_time": "0:07:57"}
|
159 |
+
{"current_steps": 159, "total_steps": 288, "loss": 0.0472, "lr": 4.969675932486503e-05, "epoch": 1.1041666666666667, "percentage": 55.21, "elapsed_time": "0:09:44", "remaining_time": "0:07:53"}
|
160 |
+
{"current_steps": 160, "total_steps": 288, "loss": 0.0436, "lr": 4.9090322589744027e-05, "epoch": 1.1111111111111112, "percentage": 55.56, "elapsed_time": "0:09:47", "remaining_time": "0:07:50"}
|
161 |
+
{"current_steps": 161, "total_steps": 288, "loss": 0.0547, "lr": 4.848401969350577e-05, "epoch": 1.1180555555555556, "percentage": 55.9, "elapsed_time": "0:09:51", "remaining_time": "0:07:46"}
|
162 |
+
{"current_steps": 162, "total_steps": 288, "loss": 0.0454, "lr": 4.78779398401926e-05, "epoch": 1.125, "percentage": 56.25, "elapsed_time": "0:09:54", "remaining_time": "0:07:42"}
|
163 |
+
{"current_steps": 163, "total_steps": 288, "loss": 0.0481, "lr": 4.7272172201031054e-05, "epoch": 1.1319444444444444, "percentage": 56.6, "elapsed_time": "0:09:58", "remaining_time": "0:07:38"}
|
164 |
+
{"current_steps": 164, "total_steps": 288, "loss": 0.0463, "lr": 4.666680590131225e-05, "epoch": 1.1388888888888888, "percentage": 56.94, "elapsed_time": "0:10:02", "remaining_time": "0:07:35"}
|
165 |
+
{"current_steps": 165, "total_steps": 288, "loss": 0.0506, "lr": 4.606193000727913e-05, "epoch": 1.1458333333333333, "percentage": 57.29, "elapsed_time": "0:10:05", "remaining_time": "0:07:31"}
|
166 |
+
{"current_steps": 166, "total_steps": 288, "loss": 0.0474, "lr": 4.545763351302224e-05, "epoch": 1.1527777777777777, "percentage": 57.64, "elapsed_time": "0:10:09", "remaining_time": "0:07:27"}
|
167 |
+
{"current_steps": 167, "total_steps": 288, "loss": 0.0454, "lr": 4.485400532738638e-05, "epoch": 1.1597222222222223, "percentage": 57.99, "elapsed_time": "0:10:12", "remaining_time": "0:07:24"}
|
168 |
+
{"current_steps": 168, "total_steps": 288, "loss": 0.0517, "lr": 4.425113426088945e-05, "epoch": 1.1666666666666667, "percentage": 58.33, "elapsed_time": "0:10:16", "remaining_time": "0:07:20"}
|
169 |
+
{"current_steps": 169, "total_steps": 288, "loss": 0.0538, "lr": 4.364910901265606e-05, "epoch": 1.1736111111111112, "percentage": 58.68, "elapsed_time": "0:10:20", "remaining_time": "0:07:16"}
|
170 |
+
{"current_steps": 170, "total_steps": 288, "loss": 0.0413, "lr": 4.3048018157367433e-05, "epoch": 1.1805555555555556, "percentage": 59.03, "elapsed_time": "0:10:23", "remaining_time": "0:07:12"}
|
171 |
+
{"current_steps": 171, "total_steps": 288, "loss": 0.0571, "lr": 4.244795013222951e-05, "epoch": 1.1875, "percentage": 59.38, "elapsed_time": "0:10:27", "remaining_time": "0:07:09"}
|
172 |
+
{"current_steps": 172, "total_steps": 288, "loss": 0.0406, "lr": 4.184899322396147e-05, "epoch": 1.1944444444444444, "percentage": 59.72, "elapsed_time": "0:10:30", "remaining_time": "0:07:05"}
|
173 |
+
{"current_steps": 173, "total_steps": 288, "loss": 0.0492, "lr": 4.125123555580624e-05, "epoch": 1.2013888888888888, "percentage": 60.07, "elapsed_time": "0:10:34", "remaining_time": "0:07:01"}
|
174 |
+
{"current_steps": 174, "total_steps": 288, "loss": 0.057, "lr": 4.0654765074565124e-05, "epoch": 1.2083333333333333, "percentage": 60.42, "elapsed_time": "0:10:38", "remaining_time": "0:06:58"}
|
175 |
+
{"current_steps": 175, "total_steps": 288, "loss": 0.0479, "lr": 4.005966953765839e-05, "epoch": 1.2152777777777777, "percentage": 60.76, "elapsed_time": "0:10:41", "remaining_time": "0:06:54"}
|
176 |
+
{"current_steps": 176, "total_steps": 288, "loss": 0.0395, "lr": 3.94660365002137e-05, "epoch": 1.2222222222222223, "percentage": 61.11, "elapsed_time": "0:10:45", "remaining_time": "0:06:50"}
|
177 |
+
{"current_steps": 177, "total_steps": 288, "loss": 0.0391, "lr": 3.887395330218429e-05, "epoch": 1.2291666666666667, "percentage": 61.46, "elapsed_time": "0:10:48", "remaining_time": "0:06:46"}
|
178 |
+
{"current_steps": 178, "total_steps": 288, "loss": 0.043, "lr": 3.8283507055498886e-05, "epoch": 1.2361111111111112, "percentage": 61.81, "elapsed_time": "0:10:52", "remaining_time": "0:06:43"}
|
179 |
+
{"current_steps": 179, "total_steps": 288, "loss": 0.0449, "lr": 3.769478463124507e-05, "epoch": 1.2430555555555556, "percentage": 62.15, "elapsed_time": "0:10:56", "remaining_time": "0:06:39"}
|
180 |
+
{"current_steps": 180, "total_steps": 288, "loss": 0.0563, "lr": 3.7107872646888116e-05, "epoch": 1.25, "percentage": 62.5, "elapsed_time": "0:10:59", "remaining_time": "0:06:35"}
|
181 |
+
{"current_steps": 181, "total_steps": 288, "loss": 0.0652, "lr": 3.652285745352717e-05, "epoch": 1.2569444444444444, "percentage": 62.85, "elapsed_time": "0:11:03", "remaining_time": "0:06:32"}
|
182 |
+
{"current_steps": 182, "total_steps": 288, "loss": 0.0439, "lr": 3.5939825123190635e-05, "epoch": 1.2638888888888888, "percentage": 63.19, "elapsed_time": "0:11:06", "remaining_time": "0:06:28"}
|
183 |
+
{"current_steps": 183, "total_steps": 288, "loss": 0.0396, "lr": 3.5358861436172485e-05, "epoch": 1.2708333333333333, "percentage": 63.54, "elapsed_time": "0:11:10", "remaining_time": "0:06:24"}
|
184 |
+
{"current_steps": 184, "total_steps": 288, "loss": 0.0349, "lr": 3.4780051868411675e-05, "epoch": 1.2777777777777777, "percentage": 63.89, "elapsed_time": "0:11:14", "remaining_time": "0:06:21"}
|
185 |
+
{"current_steps": 185, "total_steps": 288, "loss": 0.045, "lr": 3.4203481578916194e-05, "epoch": 1.2847222222222223, "percentage": 64.24, "elapsed_time": "0:11:17", "remaining_time": "0:06:17"}
|
186 |
+
{"current_steps": 186, "total_steps": 288, "loss": 0.054, "lr": 3.362923539723389e-05, "epoch": 1.2916666666666667, "percentage": 64.58, "elapsed_time": "0:11:21", "remaining_time": "0:06:13"}
|
187 |
+
{"current_steps": 187, "total_steps": 288, "loss": 0.0462, "lr": 3.305739781097157e-05, "epoch": 1.2986111111111112, "percentage": 64.93, "elapsed_time": "0:11:25", "remaining_time": "0:06:09"}
|
188 |
+
{"current_steps": 188, "total_steps": 288, "loss": 0.049, "lr": 3.248805295336458e-05, "epoch": 1.3055555555555556, "percentage": 65.28, "elapsed_time": "0:11:28", "remaining_time": "0:06:06"}
|
189 |
+
{"current_steps": 189, "total_steps": 288, "loss": 0.0398, "lr": 3.1921284590898456e-05, "epoch": 1.3125, "percentage": 65.62, "elapsed_time": "0:11:32", "remaining_time": "0:06:02"}
|
190 |
+
{"current_steps": 190, "total_steps": 288, "loss": 0.0622, "lr": 3.135717611098458e-05, "epoch": 1.3194444444444444, "percentage": 65.97, "elapsed_time": "0:11:35", "remaining_time": "0:05:58"}
|
191 |
+
{"current_steps": 191, "total_steps": 288, "loss": 0.0628, "lr": 3.079581050969146e-05, "epoch": 1.3263888888888888, "percentage": 66.32, "elapsed_time": "0:11:39", "remaining_time": "0:05:55"}
|
192 |
+
{"current_steps": 192, "total_steps": 288, "loss": 0.0538, "lr": 3.023727037953382e-05, "epoch": 1.3333333333333333, "percentage": 66.67, "elapsed_time": "0:11:43", "remaining_time": "0:05:51"}
|
193 |
+
{"current_steps": 193, "total_steps": 288, "loss": 0.0494, "lr": 2.9681637897320868e-05, "epoch": 1.3402777777777777, "percentage": 67.01, "elapsed_time": "0:11:46", "remaining_time": "0:05:47"}
|
194 |
+
{"current_steps": 194, "total_steps": 288, "loss": 0.0494, "lr": 2.912899481206582e-05, "epoch": 1.3472222222222223, "percentage": 67.36, "elapsed_time": "0:11:50", "remaining_time": "0:05:44"}
|
195 |
+
{"current_steps": 195, "total_steps": 288, "loss": 0.0474, "lr": 2.8579422432958312e-05, "epoch": 1.3541666666666667, "percentage": 67.71, "elapsed_time": "0:11:54", "remaining_time": "0:05:40"}
|
196 |
+
{"current_steps": 196, "total_steps": 288, "loss": 0.0522, "lr": 2.803300161740166e-05, "epoch": 1.3611111111111112, "percentage": 68.06, "elapsed_time": "0:11:58", "remaining_time": "0:05:37"}
|
197 |
+
{"current_steps": 197, "total_steps": 288, "loss": 0.0393, "lr": 2.748981275911633e-05, "epoch": 1.3680555555555556, "percentage": 68.4, "elapsed_time": "0:12:01", "remaining_time": "0:05:33"}
|
198 |
+
{"current_steps": 198, "total_steps": 288, "loss": 0.0395, "lr": 2.6949935776311896e-05, "epoch": 1.375, "percentage": 68.75, "elapsed_time": "0:12:05", "remaining_time": "0:05:29"}
|
199 |
+
{"current_steps": 199, "total_steps": 288, "loss": 0.0445, "lr": 2.6413450099928783e-05, "epoch": 1.3819444444444444, "percentage": 69.1, "elapsed_time": "0:12:08", "remaining_time": "0:05:25"}
|
200 |
+
{"current_steps": 200, "total_steps": 288, "loss": 0.046, "lr": 2.5880434661951823e-05, "epoch": 1.3888888888888888, "percentage": 69.44, "elapsed_time": "0:12:12", "remaining_time": "0:05:22"}
|
201 |
+
{"current_steps": 200, "total_steps": 288, "eval_loss": 0.05843019485473633, "epoch": 1.3888888888888888, "percentage": 69.44, "elapsed_time": "0:12:15", "remaining_time": "0:05:23"}
|
202 |
+
{"current_steps": 201, "total_steps": 288, "loss": 0.0592, "lr": 2.5350967883797096e-05, "epoch": 1.3958333333333333, "percentage": 69.79, "elapsed_time": "0:12:18", "remaining_time": "0:05:19"}
|
203 |
+
{"current_steps": 202, "total_steps": 288, "loss": 0.0492, "lr": 2.4825127664774006e-05, "epoch": 1.4027777777777777, "percentage": 70.14, "elapsed_time": "0:12:22", "remaining_time": "0:05:16"}
|
204 |
+
{"current_steps": 203, "total_steps": 288, "loss": 0.0599, "lr": 2.4302991370624107e-05, "epoch": 1.4097222222222223, "percentage": 70.49, "elapsed_time": "0:12:26", "remaining_time": "0:05:12"}
|
205 |
+
{"current_steps": 204, "total_steps": 288, "loss": 0.0405, "lr": 2.3784635822138424e-05, "epoch": 1.4166666666666667, "percentage": 70.83, "elapsed_time": "0:12:29", "remaining_time": "0:05:08"}
|
206 |
+
{"current_steps": 205, "total_steps": 288, "loss": 0.0522, "lr": 2.327013728385502e-05, "epoch": 1.4236111111111112, "percentage": 71.18, "elapsed_time": "0:12:33", "remaining_time": "0:05:05"}
|
207 |
+
{"current_steps": 206, "total_steps": 288, "loss": 0.0498, "lr": 2.2759571452838324e-05, "epoch": 1.4305555555555556, "percentage": 71.53, "elapsed_time": "0:12:37", "remaining_time": "0:05:01"}
|
208 |
+
{"current_steps": 207, "total_steps": 288, "loss": 0.0516, "lr": 2.225301344754199e-05, "epoch": 1.4375, "percentage": 71.88, "elapsed_time": "0:12:40", "remaining_time": "0:04:57"}
|
209 |
+
{"current_steps": 208, "total_steps": 288, "loss": 0.0356, "lr": 2.17505377967569e-05, "epoch": 1.4444444444444444, "percentage": 72.22, "elapsed_time": "0:12:44", "remaining_time": "0:04:53"}
|
210 |
+
{"current_steps": 209, "total_steps": 288, "loss": 0.0553, "lr": 2.1252218428645846e-05, "epoch": 1.4513888888888888, "percentage": 72.57, "elapsed_time": "0:12:47", "remaining_time": "0:04:50"}
|
211 |
+
{"current_steps": 210, "total_steps": 288, "loss": 0.0436, "lr": 2.075812865986677e-05, "epoch": 1.4583333333333333, "percentage": 72.92, "elapsed_time": "0:12:51", "remaining_time": "0:04:46"}
|
212 |
+
{"current_steps": 211, "total_steps": 288, "loss": 0.0531, "lr": 2.026834118478567e-05, "epoch": 1.4652777777777777, "percentage": 73.26, "elapsed_time": "0:12:55", "remaining_time": "0:04:42"}
|
213 |
+
{"current_steps": 212, "total_steps": 288, "loss": 0.0529, "lr": 1.978292806478134e-05, "epoch": 1.4722222222222223, "percentage": 73.61, "elapsed_time": "0:12:58", "remaining_time": "0:04:39"}
|
214 |
+
{"current_steps": 213, "total_steps": 288, "loss": 0.0408, "lr": 1.9301960717643118e-05, "epoch": 1.4791666666666667, "percentage": 73.96, "elapsed_time": "0:13:02", "remaining_time": "0:04:35"}
|
215 |
+
{"current_steps": 214, "total_steps": 288, "loss": 0.0532, "lr": 1.8825509907063327e-05, "epoch": 1.4861111111111112, "percentage": 74.31, "elapsed_time": "0:13:05", "remaining_time": "0:04:31"}
|
216 |
+
{"current_steps": 215, "total_steps": 288, "loss": 0.0357, "lr": 1.8353645732225976e-05, "epoch": 1.4930555555555556, "percentage": 74.65, "elapsed_time": "0:13:09", "remaining_time": "0:04:28"}
|
217 |
+
{"current_steps": 216, "total_steps": 288, "loss": 0.0458, "lr": 1.7886437617493205e-05, "epoch": 1.5, "percentage": 75.0, "elapsed_time": "0:13:13", "remaining_time": "0:04:24"}
|
218 |
+
{"current_steps": 217, "total_steps": 288, "loss": 0.065, "lr": 1.7423954302191047e-05, "epoch": 1.5069444444444444, "percentage": 75.35, "elapsed_time": "0:13:16", "remaining_time": "0:04:20"}
|
219 |
+
{"current_steps": 218, "total_steps": 288, "loss": 0.0363, "lr": 1.6966263830495936e-05, "epoch": 1.5138888888888888, "percentage": 75.69, "elapsed_time": "0:13:20", "remaining_time": "0:04:17"}
|
220 |
+
{"current_steps": 219, "total_steps": 288, "loss": 0.0504, "lr": 1.6513433541423528e-05, "epoch": 1.5208333333333335, "percentage": 76.04, "elapsed_time": "0:13:24", "remaining_time": "0:04:13"}
|
221 |
+
{"current_steps": 220, "total_steps": 288, "loss": 0.0393, "lr": 1.606553005892125e-05, "epoch": 1.5277777777777777, "percentage": 76.39, "elapsed_time": "0:13:27", "remaining_time": "0:04:09"}
|
222 |
+
{"current_steps": 221, "total_steps": 288, "loss": 0.0482, "lr": 1.5622619282066082e-05, "epoch": 1.5347222222222223, "percentage": 76.74, "elapsed_time": "0:13:31", "remaining_time": "0:04:05"}
|
223 |
+
{"current_steps": 222, "total_steps": 288, "loss": 0.037, "lr": 1.5184766375368915e-05, "epoch": 1.5416666666666665, "percentage": 77.08, "elapsed_time": "0:13:34", "remaining_time": "0:04:02"}
|
224 |
+
{"current_steps": 223, "total_steps": 288, "loss": 0.0536, "lr": 1.4752035759187106e-05, "epoch": 1.5486111111111112, "percentage": 77.43, "elapsed_time": "0:13:38", "remaining_time": "0:03:58"}
|
225 |
+
{"current_steps": 224, "total_steps": 288, "loss": 0.0461, "lr": 1.4324491100246385e-05, "epoch": 1.5555555555555556, "percentage": 77.78, "elapsed_time": "0:13:42", "remaining_time": "0:03:54"}
|
226 |
+
{"current_steps": 225, "total_steps": 288, "loss": 0.0461, "lr": 1.3902195302273779e-05, "epoch": 1.5625, "percentage": 78.12, "elapsed_time": "0:13:45", "remaining_time": "0:03:51"}
|
227 |
+
{"current_steps": 226, "total_steps": 288, "loss": 0.0448, "lr": 1.348521049674264e-05, "epoch": 1.5694444444444444, "percentage": 78.47, "elapsed_time": "0:13:49", "remaining_time": "0:03:47"}
|
228 |
+
{"current_steps": 227, "total_steps": 288, "loss": 0.0475, "lr": 1.3073598033731426e-05, "epoch": 1.5763888888888888, "percentage": 78.82, "elapsed_time": "0:13:52", "remaining_time": "0:03:43"}
|
229 |
+
{"current_steps": 228, "total_steps": 288, "loss": 0.0432, "lr": 1.2667418472897386e-05, "epoch": 1.5833333333333335, "percentage": 79.17, "elapsed_time": "0:13:56", "remaining_time": "0:03:40"}
|
230 |
+
{"current_steps": 229, "total_steps": 288, "loss": 0.0446, "lr": 1.2266731574566536e-05, "epoch": 1.5902777777777777, "percentage": 79.51, "elapsed_time": "0:14:00", "remaining_time": "0:03:36"}
|
231 |
+
{"current_steps": 230, "total_steps": 288, "loss": 0.0403, "lr": 1.1871596290941278e-05, "epoch": 1.5972222222222223, "percentage": 79.86, "elapsed_time": "0:14:03", "remaining_time": "0:03:32"}
|
232 |
+
{"current_steps": 231, "total_steps": 288, "loss": 0.0424, "lr": 1.1482070757426856e-05, "epoch": 1.6041666666666665, "percentage": 80.21, "elapsed_time": "0:14:07", "remaining_time": "0:03:29"}
|
233 |
+
{"current_steps": 232, "total_steps": 288, "loss": 0.0486, "lr": 1.1098212284078036e-05, "epoch": 1.6111111111111112, "percentage": 80.56, "elapsed_time": "0:14:10", "remaining_time": "0:03:25"}
|
234 |
+
{"current_steps": 233, "total_steps": 288, "loss": 0.0452, "lr": 1.0720077347167202e-05, "epoch": 1.6180555555555556, "percentage": 80.9, "elapsed_time": "0:14:14", "remaining_time": "0:03:21"}
|
235 |
+
{"current_steps": 234, "total_steps": 288, "loss": 0.0418, "lr": 1.0347721580875126e-05, "epoch": 1.625, "percentage": 81.25, "elapsed_time": "0:14:18", "remaining_time": "0:03:18"}
|
236 |
+
{"current_steps": 235, "total_steps": 288, "loss": 0.0488, "lr": 9.981199769105604e-06, "epoch": 1.6319444444444444, "percentage": 81.6, "elapsed_time": "0:14:21", "remaining_time": "0:03:14"}
|
237 |
+
{"current_steps": 236, "total_steps": 288, "loss": 0.0544, "lr": 9.620565837425271e-06, "epoch": 1.6388888888888888, "percentage": 81.94, "elapsed_time": "0:14:25", "remaining_time": "0:03:10"}
|
238 |
+
{"current_steps": 237, "total_steps": 288, "loss": 0.0418, "lr": 9.26587284512957e-06, "epoch": 1.6458333333333335, "percentage": 82.29, "elapsed_time": "0:14:28", "remaining_time": "0:03:06"}
|
239 |
+
{"current_steps": 238, "total_steps": 288, "loss": 0.0509, "lr": 8.917172977436356e-06, "epoch": 1.6527777777777777, "percentage": 82.64, "elapsed_time": "0:14:32", "remaining_time": "0:03:03"}
|
240 |
+
{"current_steps": 239, "total_steps": 288, "loss": 0.0493, "lr": 8.574517537807897e-06, "epoch": 1.6597222222222223, "percentage": 82.99, "elapsed_time": "0:14:36", "remaining_time": "0:02:59"}
|
241 |
+
{"current_steps": 240, "total_steps": 288, "loss": 0.0538, "lr": 8.237956940402757e-06, "epoch": 1.6666666666666665, "percentage": 83.33, "elapsed_time": "0:14:39", "remaining_time": "0:02:55"}
|
242 |
+
{"current_steps": 241, "total_steps": 288, "loss": 0.0417, "lr": 7.907540702658456e-06, "epoch": 1.6736111111111112, "percentage": 83.68, "elapsed_time": "0:14:43", "remaining_time": "0:02:52"}
|
243 |
+
{"current_steps": 242, "total_steps": 288, "loss": 0.0648, "lr": 7.583317438006093e-06, "epoch": 1.6805555555555556, "percentage": 84.03, "elapsed_time": "0:14:47", "remaining_time": "0:02:48"}
|
244 |
+
{"current_steps": 243, "total_steps": 288, "loss": 0.0409, "lr": 7.265334848717931e-06, "epoch": 1.6875, "percentage": 84.38, "elapsed_time": "0:14:50", "remaining_time": "0:02:44"}
|
245 |
+
{"current_steps": 244, "total_steps": 288, "loss": 0.0425, "lr": 6.953639718889076e-06, "epoch": 1.6944444444444444, "percentage": 84.72, "elapsed_time": "0:14:54", "remaining_time": "0:02:41"}
|
246 |
+
{"current_steps": 245, "total_steps": 288, "loss": 0.0483, "lr": 6.648277907554235e-06, "epoch": 1.7013888888888888, "percentage": 85.07, "elapsed_time": "0:14:57", "remaining_time": "0:02:37"}
|
247 |
+
{"current_steps": 246, "total_steps": 288, "loss": 0.0461, "lr": 6.349294341940593e-06, "epoch": 1.7083333333333335, "percentage": 85.42, "elapsed_time": "0:15:01", "remaining_time": "0:02:33"}
|
248 |
+
{"current_steps": 247, "total_steps": 288, "loss": 0.0538, "lr": 6.056733010857712e-06, "epoch": 1.7152777777777777, "percentage": 85.76, "elapsed_time": "0:15:05", "remaining_time": "0:02:30"}
|
249 |
+
{"current_steps": 248, "total_steps": 288, "loss": 0.0455, "lr": 5.770636958225617e-06, "epoch": 1.7222222222222223, "percentage": 86.11, "elapsed_time": "0:15:08", "remaining_time": "0:02:26"}
|
250 |
+
{"current_steps": 249, "total_steps": 288, "loss": 0.0444, "lr": 5.491048276741784e-06, "epoch": 1.7291666666666665, "percentage": 86.46, "elapsed_time": "0:15:12", "remaining_time": "0:02:22"}
|
251 |
+
{"current_steps": 250, "total_steps": 288, "loss": 0.0607, "lr": 5.218008101688171e-06, "epoch": 1.7361111111111112, "percentage": 86.81, "elapsed_time": "0:15:15", "remaining_time": "0:02:19"}
|
252 |
+
{"current_steps": 251, "total_steps": 288, "loss": 0.0445, "lr": 4.951556604879048e-06, "epoch": 1.7430555555555556, "percentage": 87.15, "elapsed_time": "0:15:19", "remaining_time": "0:02:15"}
|
253 |
+
{"current_steps": 252, "total_steps": 288, "loss": 0.0388, "lr": 4.691732988750614e-06, "epoch": 1.75, "percentage": 87.5, "elapsed_time": "0:15:23", "remaining_time": "0:02:11"}
|
254 |
+
{"current_steps": 253, "total_steps": 288, "loss": 0.0391, "lr": 4.43857548059321e-06, "epoch": 1.7569444444444444, "percentage": 87.85, "elapsed_time": "0:15:26", "remaining_time": "0:02:08"}
|
255 |
+
{"current_steps": 254, "total_steps": 288, "loss": 0.0432, "lr": 4.192121326927073e-06, "epoch": 1.7638888888888888, "percentage": 88.19, "elapsed_time": "0:15:30", "remaining_time": "0:02:04"}
|
256 |
+
{"current_steps": 255, "total_steps": 288, "loss": 0.044, "lr": 3.952406788022267e-06, "epoch": 1.7708333333333335, "percentage": 88.54, "elapsed_time": "0:15:33", "remaining_time": "0:02:00"}
|
257 |
+
{"current_steps": 256, "total_steps": 288, "loss": 0.042, "lr": 3.7194671325638198e-06, "epoch": 1.7777777777777777, "percentage": 88.89, "elapsed_time": "0:15:37", "remaining_time": "0:01:57"}
|
258 |
+
{"current_steps": 257, "total_steps": 288, "loss": 0.0446, "lr": 3.493336632462718e-06, "epoch": 1.7847222222222223, "percentage": 89.24, "elapsed_time": "0:15:41", "remaining_time": "0:01:53"}
|
259 |
+
{"current_steps": 258, "total_steps": 288, "loss": 0.0375, "lr": 3.274048557813553e-06, "epoch": 1.7916666666666665, "percentage": 89.58, "elapsed_time": "0:15:44", "remaining_time": "0:01:49"}
|
260 |
+
{"current_steps": 259, "total_steps": 288, "loss": 0.0458, "lr": 3.061635171999566e-06, "epoch": 1.7986111111111112, "percentage": 89.93, "elapsed_time": "0:15:48", "remaining_time": "0:01:46"}
|
261 |
+
{"current_steps": 260, "total_steps": 288, "loss": 0.043, "lr": 2.85612772694579e-06, "epoch": 1.8055555555555556, "percentage": 90.28, "elapsed_time": "0:15:51", "remaining_time": "0:01:42"}
|
262 |
+
{"current_steps": 261, "total_steps": 288, "loss": 0.0422, "lr": 2.657556458521049e-06, "epoch": 1.8125, "percentage": 90.62, "elapsed_time": "0:15:55", "remaining_time": "0:01:38"}
|
263 |
+
{"current_steps": 262, "total_steps": 288, "loss": 0.049, "lr": 2.4659505820893826e-06, "epoch": 1.8194444444444444, "percentage": 90.97, "elapsed_time": "0:15:59", "remaining_time": "0:01:35"}
|
264 |
+
{"current_steps": 263, "total_steps": 288, "loss": 0.0437, "lr": 2.2813382882116986e-06, "epoch": 1.8263888888888888, "percentage": 91.32, "elapsed_time": "0:16:02", "remaining_time": "0:01:31"}
|
265 |
+
{"current_steps": 264, "total_steps": 288, "loss": 0.0426, "lr": 2.1037467384981026e-06, "epoch": 1.8333333333333335, "percentage": 91.67, "elapsed_time": "0:16:06", "remaining_time": "0:01:27"}
|
266 |
+
{"current_steps": 265, "total_steps": 288, "loss": 0.0458, "lr": 1.933202061611722e-06, "epoch": 1.8402777777777777, "percentage": 92.01, "elapsed_time": "0:16:09", "remaining_time": "0:01:24"}
|
267 |
+
{"current_steps": 266, "total_steps": 288, "loss": 0.0531, "lr": 1.769729349424415e-06, "epoch": 1.8472222222222223, "percentage": 92.36, "elapsed_time": "0:16:13", "remaining_time": "0:01:20"}
|
268 |
+
{"current_steps": 267, "total_steps": 288, "loss": 0.0425, "lr": 1.6133526533250565e-06, "epoch": 1.8541666666666665, "percentage": 92.71, "elapsed_time": "0:16:17", "remaining_time": "0:01:16"}
|
269 |
+
{"current_steps": 268, "total_steps": 288, "loss": 0.0492, "lr": 1.4640949806809523e-06, "epoch": 1.8611111111111112, "percentage": 93.06, "elapsed_time": "0:16:20", "remaining_time": "0:01:13"}
|
270 |
+
{"current_steps": 269, "total_steps": 288, "loss": 0.0452, "lr": 1.3219782914527634e-06, "epoch": 1.8680555555555556, "percentage": 93.4, "elapsed_time": "0:16:24", "remaining_time": "0:01:09"}
|
271 |
+
{"current_steps": 270, "total_steps": 288, "loss": 0.0549, "lr": 1.1870234949636073e-06, "epoch": 1.875, "percentage": 93.75, "elapsed_time": "0:16:27", "remaining_time": "0:01:05"}
|
272 |
+
{"current_steps": 271, "total_steps": 288, "loss": 0.0463, "lr": 1.0592504468227127e-06, "epoch": 1.8819444444444444, "percentage": 94.1, "elapsed_time": "0:16:31", "remaining_time": "0:01:02"}
|
273 |
+
{"current_steps": 272, "total_steps": 288, "loss": 0.0522, "lr": 9.386779460041017e-07, "epoch": 1.8888888888888888, "percentage": 94.44, "elapsed_time": "0:16:35", "remaining_time": "0:00:58"}
|
274 |
+
{"current_steps": 273, "total_steps": 288, "loss": 0.0475, "lr": 8.253237320807461e-07, "epoch": 1.8958333333333335, "percentage": 94.79, "elapsed_time": "0:16:38", "remaining_time": "0:00:54"}
|
275 |
+
{"current_steps": 274, "total_steps": 288, "loss": 0.0498, "lr": 7.192044826145771e-07, "epoch": 1.9027777777777777, "percentage": 95.14, "elapsed_time": "0:16:42", "remaining_time": "0:00:51"}
|
276 |
+
{"current_steps": 275, "total_steps": 288, "loss": 0.0422, "lr": 6.20335810702749e-07, "epoch": 1.9097222222222223, "percentage": 95.49, "elapsed_time": "0:16:46", "remaining_time": "0:00:47"}
|
277 |
+
{"current_steps": 276, "total_steps": 288, "loss": 0.0433, "lr": 5.287322626805202e-07, "epoch": 1.9166666666666665, "percentage": 95.83, "elapsed_time": "0:16:49", "remaining_time": "0:00:43"}
|
278 |
+
{"current_steps": 277, "total_steps": 288, "loss": 0.0499, "lr": 4.4440731598107686e-07, "epoch": 1.9236111111111112, "percentage": 96.18, "elapsed_time": "0:16:53", "remaining_time": "0:00:40"}
|
279 |
+
{"current_steps": 278, "total_steps": 288, "loss": 0.0664, "lr": 3.673733771526466e-07, "epoch": 1.9305555555555556, "percentage": 96.53, "elapsed_time": "0:16:56", "remaining_time": "0:00:36"}
|
280 |
+
{"current_steps": 279, "total_steps": 288, "loss": 0.0395, "lr": 2.976417800331144e-07, "epoch": 1.9375, "percentage": 96.88, "elapsed_time": "0:17:00", "remaining_time": "0:00:32"}
|
281 |
+
{"current_steps": 280, "total_steps": 288, "loss": 0.0456, "lr": 2.352227840825394e-07, "epoch": 1.9444444444444444, "percentage": 97.22, "elapsed_time": "0:17:04", "remaining_time": "0:00:29"}
|
282 |
+
{"current_steps": 281, "total_steps": 288, "loss": 0.0449, "lr": 1.8012557287367392e-07, "epoch": 1.9513888888888888, "percentage": 97.57, "elapsed_time": "0:17:07", "remaining_time": "0:00:25"}
|
283 |
+
{"current_steps": 282, "total_steps": 288, "loss": 0.0433, "lr": 1.3235825274081625e-07, "epoch": 1.9583333333333335, "percentage": 97.92, "elapsed_time": "0:17:11", "remaining_time": "0:00:21"}
|
284 |
+
{"current_steps": 283, "total_steps": 288, "loss": 0.0516, "lr": 9.19278515871369e-08, "epoch": 1.9652777777777777, "percentage": 98.26, "elapsed_time": "0:17:14", "remaining_time": "0:00:18"}
|
285 |
+
{"current_steps": 284, "total_steps": 288, "loss": 0.0392, "lr": 5.8840317850683555e-08, "epoch": 1.9722222222222223, "percentage": 98.61, "elapsed_time": "0:17:18", "remaining_time": "0:00:14"}
|
286 |
+
{"current_steps": 285, "total_steps": 288, "loss": 0.0471, "lr": 3.310051962920335e-08, "epoch": 1.9791666666666665, "percentage": 98.96, "elapsed_time": "0:17:22", "remaining_time": "0:00:10"}
|
287 |
+
{"current_steps": 286, "total_steps": 288, "loss": 0.0542, "lr": 1.471224396389359e-08, "epoch": 1.9861111111111112, "percentage": 99.31, "elapsed_time": "0:17:25", "remaining_time": "0:00:07"}
|
288 |
+
{"current_steps": 287, "total_steps": 288, "loss": 0.0474, "lr": 3.6781962822529657e-09, "epoch": 1.9930555555555556, "percentage": 99.65, "elapsed_time": "0:17:29", "remaining_time": "0:00:03"}
|
289 |
+
{"current_steps": 288, "total_steps": 288, "loss": 0.0448, "lr": 0.0, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "0:17:32", "remaining_time": "0:00:00"}
|
290 |
+
{"current_steps": 288, "total_steps": 288, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "0:17:51", "remaining_time": "0:00:00"}
|
trainer_state.json
ADDED
@@ -0,0 +1,2066 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.0,
|
5 |
+
"eval_steps": 200,
|
6 |
+
"global_step": 288,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.006944444444444444,
|
13 |
+
"grad_norm": 0.0634646986292456,
|
14 |
+
"learning_rate": 3.448275862068966e-06,
|
15 |
+
"loss": 0.1218,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.013888888888888888,
|
20 |
+
"grad_norm": 0.0859646592063227,
|
21 |
+
"learning_rate": 6.896551724137932e-06,
|
22 |
+
"loss": 0.1441,
|
23 |
+
"step": 2
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.020833333333333332,
|
27 |
+
"grad_norm": 0.08311493152111031,
|
28 |
+
"learning_rate": 1.0344827586206897e-05,
|
29 |
+
"loss": 0.1517,
|
30 |
+
"step": 3
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.027777777777777776,
|
34 |
+
"grad_norm": 0.14507101606184478,
|
35 |
+
"learning_rate": 1.3793103448275863e-05,
|
36 |
+
"loss": 0.184,
|
37 |
+
"step": 4
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.034722222222222224,
|
41 |
+
"grad_norm": 0.049880571226207794,
|
42 |
+
"learning_rate": 1.7241379310344828e-05,
|
43 |
+
"loss": 0.0937,
|
44 |
+
"step": 5
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.041666666666666664,
|
48 |
+
"grad_norm": 0.13472688960866697,
|
49 |
+
"learning_rate": 2.0689655172413793e-05,
|
50 |
+
"loss": 0.1932,
|
51 |
+
"step": 6
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.04861111111111111,
|
55 |
+
"grad_norm": 0.063128720217521,
|
56 |
+
"learning_rate": 2.413793103448276e-05,
|
57 |
+
"loss": 0.1163,
|
58 |
+
"step": 7
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.05555555555555555,
|
62 |
+
"grad_norm": 0.05791338456495497,
|
63 |
+
"learning_rate": 2.7586206896551727e-05,
|
64 |
+
"loss": 0.0997,
|
65 |
+
"step": 8
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.0625,
|
69 |
+
"grad_norm": 0.03814512155396182,
|
70 |
+
"learning_rate": 3.103448275862069e-05,
|
71 |
+
"loss": 0.0691,
|
72 |
+
"step": 9
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.06944444444444445,
|
76 |
+
"grad_norm": 0.07278628165772846,
|
77 |
+
"learning_rate": 3.4482758620689657e-05,
|
78 |
+
"loss": 0.1096,
|
79 |
+
"step": 10
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.0763888888888889,
|
83 |
+
"grad_norm": 0.06072973165332569,
|
84 |
+
"learning_rate": 3.793103448275862e-05,
|
85 |
+
"loss": 0.0915,
|
86 |
+
"step": 11
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.08333333333333333,
|
90 |
+
"grad_norm": 0.05086161703424197,
|
91 |
+
"learning_rate": 4.1379310344827587e-05,
|
92 |
+
"loss": 0.0758,
|
93 |
+
"step": 12
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.09027777777777778,
|
97 |
+
"grad_norm": 0.06108424147364289,
|
98 |
+
"learning_rate": 4.482758620689655e-05,
|
99 |
+
"loss": 0.085,
|
100 |
+
"step": 13
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.09722222222222222,
|
104 |
+
"grad_norm": 0.08171893276043111,
|
105 |
+
"learning_rate": 4.827586206896552e-05,
|
106 |
+
"loss": 0.1039,
|
107 |
+
"step": 14
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.10416666666666667,
|
111 |
+
"grad_norm": 0.10806188024280473,
|
112 |
+
"learning_rate": 5.172413793103449e-05,
|
113 |
+
"loss": 0.1153,
|
114 |
+
"step": 15
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.1111111111111111,
|
118 |
+
"grad_norm": 0.08264842267025586,
|
119 |
+
"learning_rate": 5.517241379310345e-05,
|
120 |
+
"loss": 0.096,
|
121 |
+
"step": 16
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.11805555555555555,
|
125 |
+
"grad_norm": 0.11707563126376766,
|
126 |
+
"learning_rate": 5.862068965517241e-05,
|
127 |
+
"loss": 0.1187,
|
128 |
+
"step": 17
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.125,
|
132 |
+
"grad_norm": 0.04624996354545763,
|
133 |
+
"learning_rate": 6.206896551724138e-05,
|
134 |
+
"loss": 0.0613,
|
135 |
+
"step": 18
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.13194444444444445,
|
139 |
+
"grad_norm": 0.12096307356119897,
|
140 |
+
"learning_rate": 6.551724137931034e-05,
|
141 |
+
"loss": 0.112,
|
142 |
+
"step": 19
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.1388888888888889,
|
146 |
+
"grad_norm": 0.11329767467249009,
|
147 |
+
"learning_rate": 6.896551724137931e-05,
|
148 |
+
"loss": 0.1131,
|
149 |
+
"step": 20
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.14583333333333334,
|
153 |
+
"grad_norm": 0.07076834653741017,
|
154 |
+
"learning_rate": 7.241379310344828e-05,
|
155 |
+
"loss": 0.0754,
|
156 |
+
"step": 21
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.1527777777777778,
|
160 |
+
"grad_norm": 0.07631833003946596,
|
161 |
+
"learning_rate": 7.586206896551724e-05,
|
162 |
+
"loss": 0.0476,
|
163 |
+
"step": 22
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.1597222222222222,
|
167 |
+
"grad_norm": 0.09111429978286256,
|
168 |
+
"learning_rate": 7.931034482758621e-05,
|
169 |
+
"loss": 0.0778,
|
170 |
+
"step": 23
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.16666666666666666,
|
174 |
+
"grad_norm": 0.09638107817903875,
|
175 |
+
"learning_rate": 8.275862068965517e-05,
|
176 |
+
"loss": 0.0749,
|
177 |
+
"step": 24
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.1736111111111111,
|
181 |
+
"grad_norm": 0.08873808756623787,
|
182 |
+
"learning_rate": 8.620689655172413e-05,
|
183 |
+
"loss": 0.0692,
|
184 |
+
"step": 25
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.18055555555555555,
|
188 |
+
"grad_norm": 0.1193395529072999,
|
189 |
+
"learning_rate": 8.96551724137931e-05,
|
190 |
+
"loss": 0.1005,
|
191 |
+
"step": 26
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.1875,
|
195 |
+
"grad_norm": 0.07825819960868853,
|
196 |
+
"learning_rate": 9.310344827586207e-05,
|
197 |
+
"loss": 0.0796,
|
198 |
+
"step": 27
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.19444444444444445,
|
202 |
+
"grad_norm": 0.09882721733405724,
|
203 |
+
"learning_rate": 9.655172413793105e-05,
|
204 |
+
"loss": 0.0808,
|
205 |
+
"step": 28
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.2013888888888889,
|
209 |
+
"grad_norm": 0.07496690540223322,
|
210 |
+
"learning_rate": 0.0001,
|
211 |
+
"loss": 0.0589,
|
212 |
+
"step": 29
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.20833333333333334,
|
216 |
+
"grad_norm": 0.06753626384871714,
|
217 |
+
"learning_rate": 9.999632180371776e-05,
|
218 |
+
"loss": 0.0885,
|
219 |
+
"step": 30
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.2152777777777778,
|
223 |
+
"grad_norm": 0.11227962647329344,
|
224 |
+
"learning_rate": 9.998528775603611e-05,
|
225 |
+
"loss": 0.0859,
|
226 |
+
"step": 31
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.2222222222222222,
|
230 |
+
"grad_norm": 0.04228956053702444,
|
231 |
+
"learning_rate": 9.99668994803708e-05,
|
232 |
+
"loss": 0.0482,
|
233 |
+
"step": 32
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.22916666666666666,
|
237 |
+
"grad_norm": 0.049938706422113184,
|
238 |
+
"learning_rate": 9.994115968214932e-05,
|
239 |
+
"loss": 0.0575,
|
240 |
+
"step": 33
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.2361111111111111,
|
244 |
+
"grad_norm": 0.054468426952476535,
|
245 |
+
"learning_rate": 9.990807214841287e-05,
|
246 |
+
"loss": 0.0661,
|
247 |
+
"step": 34
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.24305555555555555,
|
251 |
+
"grad_norm": 0.048987738819091665,
|
252 |
+
"learning_rate": 9.986764174725919e-05,
|
253 |
+
"loss": 0.0556,
|
254 |
+
"step": 35
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.25,
|
258 |
+
"grad_norm": 0.05029249306240408,
|
259 |
+
"learning_rate": 9.981987442712633e-05,
|
260 |
+
"loss": 0.0546,
|
261 |
+
"step": 36
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.2569444444444444,
|
265 |
+
"grad_norm": 0.07920414870467878,
|
266 |
+
"learning_rate": 9.976477721591745e-05,
|
267 |
+
"loss": 0.0704,
|
268 |
+
"step": 37
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.2638888888888889,
|
272 |
+
"grad_norm": 0.04856426595651698,
|
273 |
+
"learning_rate": 9.97023582199669e-05,
|
274 |
+
"loss": 0.0627,
|
275 |
+
"step": 38
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.2708333333333333,
|
279 |
+
"grad_norm": 0.03338189886854429,
|
280 |
+
"learning_rate": 9.963262662284736e-05,
|
281 |
+
"loss": 0.0353,
|
282 |
+
"step": 39
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.2777777777777778,
|
286 |
+
"grad_norm": 0.05814625123252708,
|
287 |
+
"learning_rate": 9.955559268401893e-05,
|
288 |
+
"loss": 0.0562,
|
289 |
+
"step": 40
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.2847222222222222,
|
293 |
+
"grad_norm": 0.09810680657571984,
|
294 |
+
"learning_rate": 9.947126773731948e-05,
|
295 |
+
"loss": 0.0774,
|
296 |
+
"step": 41
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.2916666666666667,
|
300 |
+
"grad_norm": 0.08137711658725671,
|
301 |
+
"learning_rate": 9.937966418929726e-05,
|
302 |
+
"loss": 0.0688,
|
303 |
+
"step": 42
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.2986111111111111,
|
307 |
+
"grad_norm": 0.04984221097640415,
|
308 |
+
"learning_rate": 9.928079551738543e-05,
|
309 |
+
"loss": 0.0631,
|
310 |
+
"step": 43
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.3055555555555556,
|
314 |
+
"grad_norm": 0.045586138765645726,
|
315 |
+
"learning_rate": 9.917467626791925e-05,
|
316 |
+
"loss": 0.0602,
|
317 |
+
"step": 44
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.3125,
|
321 |
+
"grad_norm": 0.04555416039001976,
|
322 |
+
"learning_rate": 9.90613220539959e-05,
|
323 |
+
"loss": 0.0603,
|
324 |
+
"step": 45
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.3194444444444444,
|
328 |
+
"grad_norm": 0.06929704690081513,
|
329 |
+
"learning_rate": 9.89407495531773e-05,
|
330 |
+
"loss": 0.05,
|
331 |
+
"step": 46
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.3263888888888889,
|
335 |
+
"grad_norm": 0.05071419561253368,
|
336 |
+
"learning_rate": 9.881297650503641e-05,
|
337 |
+
"loss": 0.0666,
|
338 |
+
"step": 47
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.3333333333333333,
|
342 |
+
"grad_norm": 0.05861571605506496,
|
343 |
+
"learning_rate": 9.867802170854724e-05,
|
344 |
+
"loss": 0.0576,
|
345 |
+
"step": 48
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.3402777777777778,
|
349 |
+
"grad_norm": 0.05602477728042172,
|
350 |
+
"learning_rate": 9.853590501931904e-05,
|
351 |
+
"loss": 0.0714,
|
352 |
+
"step": 49
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 0.3472222222222222,
|
356 |
+
"grad_norm": 0.0600399573347184,
|
357 |
+
"learning_rate": 9.838664734667495e-05,
|
358 |
+
"loss": 0.0557,
|
359 |
+
"step": 50
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.3541666666666667,
|
363 |
+
"grad_norm": 0.04310502477291791,
|
364 |
+
"learning_rate": 9.82302706505756e-05,
|
365 |
+
"loss": 0.0608,
|
366 |
+
"step": 51
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 0.3611111111111111,
|
370 |
+
"grad_norm": 0.04208369800984692,
|
371 |
+
"learning_rate": 9.806679793838829e-05,
|
372 |
+
"loss": 0.0457,
|
373 |
+
"step": 52
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 0.3680555555555556,
|
377 |
+
"grad_norm": 0.04390617615736525,
|
378 |
+
"learning_rate": 9.78962532615019e-05,
|
379 |
+
"loss": 0.0538,
|
380 |
+
"step": 53
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.375,
|
384 |
+
"grad_norm": 0.040829606477323165,
|
385 |
+
"learning_rate": 9.771866171178831e-05,
|
386 |
+
"loss": 0.0535,
|
387 |
+
"step": 54
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.3819444444444444,
|
391 |
+
"grad_norm": 0.04189168396894191,
|
392 |
+
"learning_rate": 9.753404941791062e-05,
|
393 |
+
"loss": 0.0533,
|
394 |
+
"step": 55
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 0.3888888888888889,
|
398 |
+
"grad_norm": 0.048795880713950655,
|
399 |
+
"learning_rate": 9.734244354147895e-05,
|
400 |
+
"loss": 0.0558,
|
401 |
+
"step": 56
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 0.3958333333333333,
|
405 |
+
"grad_norm": 0.04594331706981098,
|
406 |
+
"learning_rate": 9.714387227305422e-05,
|
407 |
+
"loss": 0.059,
|
408 |
+
"step": 57
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 0.4027777777777778,
|
412 |
+
"grad_norm": 0.059333907325760896,
|
413 |
+
"learning_rate": 9.693836482800044e-05,
|
414 |
+
"loss": 0.0666,
|
415 |
+
"step": 58
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 0.4097222222222222,
|
419 |
+
"grad_norm": 0.04504422858266263,
|
420 |
+
"learning_rate": 9.672595144218646e-05,
|
421 |
+
"loss": 0.0553,
|
422 |
+
"step": 59
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.4166666666666667,
|
426 |
+
"grad_norm": 0.06138639267675264,
|
427 |
+
"learning_rate": 9.650666336753728e-05,
|
428 |
+
"loss": 0.0736,
|
429 |
+
"step": 60
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.4236111111111111,
|
433 |
+
"grad_norm": 0.054120807804378494,
|
434 |
+
"learning_rate": 9.628053286743619e-05,
|
435 |
+
"loss": 0.0658,
|
436 |
+
"step": 61
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 0.4305555555555556,
|
440 |
+
"grad_norm": 0.05215983401668381,
|
441 |
+
"learning_rate": 9.604759321197773e-05,
|
442 |
+
"loss": 0.0597,
|
443 |
+
"step": 62
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 0.4375,
|
447 |
+
"grad_norm": 0.05923618865174348,
|
448 |
+
"learning_rate": 9.580787867307293e-05,
|
449 |
+
"loss": 0.0661,
|
450 |
+
"step": 63
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 0.4444444444444444,
|
454 |
+
"grad_norm": 0.06697666067838456,
|
455 |
+
"learning_rate": 9.55614245194068e-05,
|
456 |
+
"loss": 0.0684,
|
457 |
+
"step": 64
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 0.4513888888888889,
|
461 |
+
"grad_norm": 0.04541593572547064,
|
462 |
+
"learning_rate": 9.530826701124939e-05,
|
463 |
+
"loss": 0.0547,
|
464 |
+
"step": 65
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.4583333333333333,
|
468 |
+
"grad_norm": 0.05700134510715612,
|
469 |
+
"learning_rate": 9.504844339512095e-05,
|
470 |
+
"loss": 0.0596,
|
471 |
+
"step": 66
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.4652777777777778,
|
475 |
+
"grad_norm": 0.041366318222701697,
|
476 |
+
"learning_rate": 9.478199189831183e-05,
|
477 |
+
"loss": 0.0411,
|
478 |
+
"step": 67
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 0.4722222222222222,
|
482 |
+
"grad_norm": 0.043353520617435734,
|
483 |
+
"learning_rate": 9.450895172325822e-05,
|
484 |
+
"loss": 0.0548,
|
485 |
+
"step": 68
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 0.4791666666666667,
|
489 |
+
"grad_norm": 0.05496280723006238,
|
490 |
+
"learning_rate": 9.422936304177439e-05,
|
491 |
+
"loss": 0.0531,
|
492 |
+
"step": 69
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 0.4861111111111111,
|
496 |
+
"grad_norm": 0.057292146852494466,
|
497 |
+
"learning_rate": 9.39432669891423e-05,
|
498 |
+
"loss": 0.0658,
|
499 |
+
"step": 70
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 0.4930555555555556,
|
503 |
+
"grad_norm": 0.044098969405188045,
|
504 |
+
"learning_rate": 9.365070565805941e-05,
|
505 |
+
"loss": 0.0511,
|
506 |
+
"step": 71
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.5,
|
510 |
+
"grad_norm": 0.10907567767546891,
|
511 |
+
"learning_rate": 9.335172209244575e-05,
|
512 |
+
"loss": 0.0547,
|
513 |
+
"step": 72
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.5069444444444444,
|
517 |
+
"grad_norm": 0.05193284317496665,
|
518 |
+
"learning_rate": 9.304636028111094e-05,
|
519 |
+
"loss": 0.0674,
|
520 |
+
"step": 73
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 0.5138888888888888,
|
524 |
+
"grad_norm": 0.06799161021928798,
|
525 |
+
"learning_rate": 9.273466515128209e-05,
|
526 |
+
"loss": 0.067,
|
527 |
+
"step": 74
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 0.5208333333333334,
|
531 |
+
"grad_norm": 0.05626247552701963,
|
532 |
+
"learning_rate": 9.241668256199392e-05,
|
533 |
+
"loss": 0.0501,
|
534 |
+
"step": 75
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 0.5277777777777778,
|
538 |
+
"grad_norm": 0.04578630890465305,
|
539 |
+
"learning_rate": 9.209245929734156e-05,
|
540 |
+
"loss": 0.0509,
|
541 |
+
"step": 76
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 0.5347222222222222,
|
545 |
+
"grad_norm": 0.0451951125591856,
|
546 |
+
"learning_rate": 9.176204305959726e-05,
|
547 |
+
"loss": 0.0465,
|
548 |
+
"step": 77
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 0.5416666666666666,
|
552 |
+
"grad_norm": 0.04052385478349237,
|
553 |
+
"learning_rate": 9.142548246219212e-05,
|
554 |
+
"loss": 0.0454,
|
555 |
+
"step": 78
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.5486111111111112,
|
559 |
+
"grad_norm": 0.04695475481560532,
|
560 |
+
"learning_rate": 9.108282702256365e-05,
|
561 |
+
"loss": 0.0598,
|
562 |
+
"step": 79
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 0.5555555555555556,
|
566 |
+
"grad_norm": 0.05974716728603661,
|
567 |
+
"learning_rate": 9.073412715487044e-05,
|
568 |
+
"loss": 0.0632,
|
569 |
+
"step": 80
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 0.5625,
|
573 |
+
"grad_norm": 0.04594564477538813,
|
574 |
+
"learning_rate": 9.037943416257474e-05,
|
575 |
+
"loss": 0.059,
|
576 |
+
"step": 81
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 0.5694444444444444,
|
580 |
+
"grad_norm": 0.04581771185786344,
|
581 |
+
"learning_rate": 9.001880023089441e-05,
|
582 |
+
"loss": 0.0578,
|
583 |
+
"step": 82
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 0.5763888888888888,
|
587 |
+
"grad_norm": 0.03808060898920002,
|
588 |
+
"learning_rate": 8.965227841912489e-05,
|
589 |
+
"loss": 0.0435,
|
590 |
+
"step": 83
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 0.5833333333333334,
|
594 |
+
"grad_norm": 0.06582783981663642,
|
595 |
+
"learning_rate": 8.927992265283282e-05,
|
596 |
+
"loss": 0.058,
|
597 |
+
"step": 84
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 0.5902777777777778,
|
601 |
+
"grad_norm": 0.0409049374684989,
|
602 |
+
"learning_rate": 8.890178771592199e-05,
|
603 |
+
"loss": 0.045,
|
604 |
+
"step": 85
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 0.5972222222222222,
|
608 |
+
"grad_norm": 0.056258831948584206,
|
609 |
+
"learning_rate": 8.851792924257317e-05,
|
610 |
+
"loss": 0.0709,
|
611 |
+
"step": 86
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 0.6041666666666666,
|
615 |
+
"grad_norm": 0.04580764978743741,
|
616 |
+
"learning_rate": 8.812840370905873e-05,
|
617 |
+
"loss": 0.0525,
|
618 |
+
"step": 87
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 0.6111111111111112,
|
622 |
+
"grad_norm": 0.043263482428543644,
|
623 |
+
"learning_rate": 8.773326842543347e-05,
|
624 |
+
"loss": 0.0464,
|
625 |
+
"step": 88
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 0.6180555555555556,
|
629 |
+
"grad_norm": 0.059777623657141676,
|
630 |
+
"learning_rate": 8.733258152710262e-05,
|
631 |
+
"loss": 0.0649,
|
632 |
+
"step": 89
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 0.625,
|
636 |
+
"grad_norm": 0.049405025547198826,
|
637 |
+
"learning_rate": 8.692640196626858e-05,
|
638 |
+
"loss": 0.0575,
|
639 |
+
"step": 90
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.6319444444444444,
|
643 |
+
"grad_norm": 0.054678965104638884,
|
644 |
+
"learning_rate": 8.651478950325737e-05,
|
645 |
+
"loss": 0.0694,
|
646 |
+
"step": 91
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 0.6388888888888888,
|
650 |
+
"grad_norm": 0.05031387124367363,
|
651 |
+
"learning_rate": 8.609780469772623e-05,
|
652 |
+
"loss": 0.0581,
|
653 |
+
"step": 92
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 0.6458333333333334,
|
657 |
+
"grad_norm": 0.043219919789406584,
|
658 |
+
"learning_rate": 8.567550889975362e-05,
|
659 |
+
"loss": 0.0489,
|
660 |
+
"step": 93
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 0.6527777777777778,
|
664 |
+
"grad_norm": 0.04843201217718916,
|
665 |
+
"learning_rate": 8.524796424081292e-05,
|
666 |
+
"loss": 0.0597,
|
667 |
+
"step": 94
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 0.6597222222222222,
|
671 |
+
"grad_norm": 0.0522833112433358,
|
672 |
+
"learning_rate": 8.481523362463111e-05,
|
673 |
+
"loss": 0.0609,
|
674 |
+
"step": 95
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 0.6666666666666666,
|
678 |
+
"grad_norm": 0.04658288241167051,
|
679 |
+
"learning_rate": 8.437738071793394e-05,
|
680 |
+
"loss": 0.0461,
|
681 |
+
"step": 96
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 0.6736111111111112,
|
685 |
+
"grad_norm": 0.05192918762269953,
|
686 |
+
"learning_rate": 8.393446994107877e-05,
|
687 |
+
"loss": 0.0675,
|
688 |
+
"step": 97
|
689 |
+
},
|
690 |
+
{
|
691 |
+
"epoch": 0.6805555555555556,
|
692 |
+
"grad_norm": 0.04625340723515702,
|
693 |
+
"learning_rate": 8.348656645857649e-05,
|
694 |
+
"loss": 0.0501,
|
695 |
+
"step": 98
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"epoch": 0.6875,
|
699 |
+
"grad_norm": 0.04545506022482319,
|
700 |
+
"learning_rate": 8.303373616950408e-05,
|
701 |
+
"loss": 0.0465,
|
702 |
+
"step": 99
|
703 |
+
},
|
704 |
+
{
|
705 |
+
"epoch": 0.6944444444444444,
|
706 |
+
"grad_norm": 0.048499611503797835,
|
707 |
+
"learning_rate": 8.257604569780897e-05,
|
708 |
+
"loss": 0.0538,
|
709 |
+
"step": 100
|
710 |
+
},
|
711 |
+
{
|
712 |
+
"epoch": 0.7013888888888888,
|
713 |
+
"grad_norm": 0.04849174145205094,
|
714 |
+
"learning_rate": 8.21135623825068e-05,
|
715 |
+
"loss": 0.0532,
|
716 |
+
"step": 101
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 0.7083333333333334,
|
720 |
+
"grad_norm": 0.046809029835309476,
|
721 |
+
"learning_rate": 8.164635426777404e-05,
|
722 |
+
"loss": 0.0584,
|
723 |
+
"step": 102
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 0.7152777777777778,
|
727 |
+
"grad_norm": 0.04338551366678789,
|
728 |
+
"learning_rate": 8.117449009293668e-05,
|
729 |
+
"loss": 0.0486,
|
730 |
+
"step": 103
|
731 |
+
},
|
732 |
+
{
|
733 |
+
"epoch": 0.7222222222222222,
|
734 |
+
"grad_norm": 0.04288423757366809,
|
735 |
+
"learning_rate": 8.069803928235689e-05,
|
736 |
+
"loss": 0.0512,
|
737 |
+
"step": 104
|
738 |
+
},
|
739 |
+
{
|
740 |
+
"epoch": 0.7291666666666666,
|
741 |
+
"grad_norm": 0.04297925782588076,
|
742 |
+
"learning_rate": 8.021707193521865e-05,
|
743 |
+
"loss": 0.0466,
|
744 |
+
"step": 105
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 0.7361111111111112,
|
748 |
+
"grad_norm": 0.04840548556064357,
|
749 |
+
"learning_rate": 7.973165881521434e-05,
|
750 |
+
"loss": 0.0614,
|
751 |
+
"step": 106
|
752 |
+
},
|
753 |
+
{
|
754 |
+
"epoch": 0.7430555555555556,
|
755 |
+
"grad_norm": 0.05089661493349612,
|
756 |
+
"learning_rate": 7.924187134013323e-05,
|
757 |
+
"loss": 0.0468,
|
758 |
+
"step": 107
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 0.75,
|
762 |
+
"grad_norm": 0.043594180551687345,
|
763 |
+
"learning_rate": 7.874778157135415e-05,
|
764 |
+
"loss": 0.0522,
|
765 |
+
"step": 108
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 0.7569444444444444,
|
769 |
+
"grad_norm": 0.07921359503782698,
|
770 |
+
"learning_rate": 7.824946220324312e-05,
|
771 |
+
"loss": 0.0639,
|
772 |
+
"step": 109
|
773 |
+
},
|
774 |
+
{
|
775 |
+
"epoch": 0.7638888888888888,
|
776 |
+
"grad_norm": 0.046303003192425585,
|
777 |
+
"learning_rate": 7.774698655245802e-05,
|
778 |
+
"loss": 0.054,
|
779 |
+
"step": 110
|
780 |
+
},
|
781 |
+
{
|
782 |
+
"epoch": 0.7708333333333334,
|
783 |
+
"grad_norm": 0.0443323814040479,
|
784 |
+
"learning_rate": 7.724042854716169e-05,
|
785 |
+
"loss": 0.0492,
|
786 |
+
"step": 111
|
787 |
+
},
|
788 |
+
{
|
789 |
+
"epoch": 0.7777777777777778,
|
790 |
+
"grad_norm": 0.04970508540718419,
|
791 |
+
"learning_rate": 7.6729862716145e-05,
|
792 |
+
"loss": 0.0562,
|
793 |
+
"step": 112
|
794 |
+
},
|
795 |
+
{
|
796 |
+
"epoch": 0.7847222222222222,
|
797 |
+
"grad_norm": 0.09180702014526151,
|
798 |
+
"learning_rate": 7.621536417786159e-05,
|
799 |
+
"loss": 0.069,
|
800 |
+
"step": 113
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 0.7916666666666666,
|
804 |
+
"grad_norm": 0.047409146676109855,
|
805 |
+
"learning_rate": 7.56970086293759e-05,
|
806 |
+
"loss": 0.057,
|
807 |
+
"step": 114
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 0.7986111111111112,
|
811 |
+
"grad_norm": 0.05564719359814639,
|
812 |
+
"learning_rate": 7.5174872335226e-05,
|
813 |
+
"loss": 0.0545,
|
814 |
+
"step": 115
|
815 |
+
},
|
816 |
+
{
|
817 |
+
"epoch": 0.8055555555555556,
|
818 |
+
"grad_norm": 0.044385293233721056,
|
819 |
+
"learning_rate": 7.464903211620291e-05,
|
820 |
+
"loss": 0.0533,
|
821 |
+
"step": 116
|
822 |
+
},
|
823 |
+
{
|
824 |
+
"epoch": 0.8125,
|
825 |
+
"grad_norm": 0.048373968528083365,
|
826 |
+
"learning_rate": 7.411956533804818e-05,
|
827 |
+
"loss": 0.0567,
|
828 |
+
"step": 117
|
829 |
+
},
|
830 |
+
{
|
831 |
+
"epoch": 0.8194444444444444,
|
832 |
+
"grad_norm": 0.06631096530721073,
|
833 |
+
"learning_rate": 7.358654990007122e-05,
|
834 |
+
"loss": 0.0634,
|
835 |
+
"step": 118
|
836 |
+
},
|
837 |
+
{
|
838 |
+
"epoch": 0.8263888888888888,
|
839 |
+
"grad_norm": 0.03919679279316613,
|
840 |
+
"learning_rate": 7.305006422368811e-05,
|
841 |
+
"loss": 0.0396,
|
842 |
+
"step": 119
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 0.8333333333333334,
|
846 |
+
"grad_norm": 0.0612342230223103,
|
847 |
+
"learning_rate": 7.251018724088367e-05,
|
848 |
+
"loss": 0.0598,
|
849 |
+
"step": 120
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 0.8402777777777778,
|
853 |
+
"grad_norm": 0.04761240051837147,
|
854 |
+
"learning_rate": 7.196699838259834e-05,
|
855 |
+
"loss": 0.0542,
|
856 |
+
"step": 121
|
857 |
+
},
|
858 |
+
{
|
859 |
+
"epoch": 0.8472222222222222,
|
860 |
+
"grad_norm": 0.055239940867233474,
|
861 |
+
"learning_rate": 7.142057756704168e-05,
|
862 |
+
"loss": 0.064,
|
863 |
+
"step": 122
|
864 |
+
},
|
865 |
+
{
|
866 |
+
"epoch": 0.8541666666666666,
|
867 |
+
"grad_norm": 0.05625030436845944,
|
868 |
+
"learning_rate": 7.087100518793421e-05,
|
869 |
+
"loss": 0.0552,
|
870 |
+
"step": 123
|
871 |
+
},
|
872 |
+
{
|
873 |
+
"epoch": 0.8611111111111112,
|
874 |
+
"grad_norm": 0.04917209401012176,
|
875 |
+
"learning_rate": 7.031836210267915e-05,
|
876 |
+
"loss": 0.0519,
|
877 |
+
"step": 124
|
878 |
+
},
|
879 |
+
{
|
880 |
+
"epoch": 0.8680555555555556,
|
881 |
+
"grad_norm": 0.045923821351934915,
|
882 |
+
"learning_rate": 6.976272962046619e-05,
|
883 |
+
"loss": 0.0544,
|
884 |
+
"step": 125
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 0.875,
|
888 |
+
"grad_norm": 0.055983725032457854,
|
889 |
+
"learning_rate": 6.920418949030856e-05,
|
890 |
+
"loss": 0.0684,
|
891 |
+
"step": 126
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 0.8819444444444444,
|
895 |
+
"grad_norm": 0.09704535662409224,
|
896 |
+
"learning_rate": 6.864282388901544e-05,
|
897 |
+
"loss": 0.0737,
|
898 |
+
"step": 127
|
899 |
+
},
|
900 |
+
{
|
901 |
+
"epoch": 0.8888888888888888,
|
902 |
+
"grad_norm": 0.044657916384289814,
|
903 |
+
"learning_rate": 6.807871540910154e-05,
|
904 |
+
"loss": 0.0515,
|
905 |
+
"step": 128
|
906 |
+
},
|
907 |
+
{
|
908 |
+
"epoch": 0.8958333333333334,
|
909 |
+
"grad_norm": 0.07059390531279443,
|
910 |
+
"learning_rate": 6.751194704663543e-05,
|
911 |
+
"loss": 0.0574,
|
912 |
+
"step": 129
|
913 |
+
},
|
914 |
+
{
|
915 |
+
"epoch": 0.9027777777777778,
|
916 |
+
"grad_norm": 0.04502070349330495,
|
917 |
+
"learning_rate": 6.694260218902844e-05,
|
918 |
+
"loss": 0.0445,
|
919 |
+
"step": 130
|
920 |
+
},
|
921 |
+
{
|
922 |
+
"epoch": 0.9097222222222222,
|
923 |
+
"grad_norm": 0.06605902723986466,
|
924 |
+
"learning_rate": 6.637076460276613e-05,
|
925 |
+
"loss": 0.0569,
|
926 |
+
"step": 131
|
927 |
+
},
|
928 |
+
{
|
929 |
+
"epoch": 0.9166666666666666,
|
930 |
+
"grad_norm": 0.051118257758994964,
|
931 |
+
"learning_rate": 6.57965184210838e-05,
|
932 |
+
"loss": 0.0551,
|
933 |
+
"step": 132
|
934 |
+
},
|
935 |
+
{
|
936 |
+
"epoch": 0.9236111111111112,
|
937 |
+
"grad_norm": 0.04518774034822205,
|
938 |
+
"learning_rate": 6.521994813158834e-05,
|
939 |
+
"loss": 0.0557,
|
940 |
+
"step": 133
|
941 |
+
},
|
942 |
+
{
|
943 |
+
"epoch": 0.9305555555555556,
|
944 |
+
"grad_norm": 0.04284945779426791,
|
945 |
+
"learning_rate": 6.464113856382752e-05,
|
946 |
+
"loss": 0.041,
|
947 |
+
"step": 134
|
948 |
+
},
|
949 |
+
{
|
950 |
+
"epoch": 0.9375,
|
951 |
+
"grad_norm": 0.04754862748835347,
|
952 |
+
"learning_rate": 6.406017487680937e-05,
|
953 |
+
"loss": 0.0522,
|
954 |
+
"step": 135
|
955 |
+
},
|
956 |
+
{
|
957 |
+
"epoch": 0.9444444444444444,
|
958 |
+
"grad_norm": 0.04459511286211968,
|
959 |
+
"learning_rate": 6.347714254647284e-05,
|
960 |
+
"loss": 0.0486,
|
961 |
+
"step": 136
|
962 |
+
},
|
963 |
+
{
|
964 |
+
"epoch": 0.9513888888888888,
|
965 |
+
"grad_norm": 0.06113290499228477,
|
966 |
+
"learning_rate": 6.28921273531119e-05,
|
967 |
+
"loss": 0.0593,
|
968 |
+
"step": 137
|
969 |
+
},
|
970 |
+
{
|
971 |
+
"epoch": 0.9583333333333334,
|
972 |
+
"grad_norm": 0.056574006950422875,
|
973 |
+
"learning_rate": 6.230521536875494e-05,
|
974 |
+
"loss": 0.0603,
|
975 |
+
"step": 138
|
976 |
+
},
|
977 |
+
{
|
978 |
+
"epoch": 0.9652777777777778,
|
979 |
+
"grad_norm": 0.04419993037171285,
|
980 |
+
"learning_rate": 6.171649294450113e-05,
|
981 |
+
"loss": 0.0422,
|
982 |
+
"step": 139
|
983 |
+
},
|
984 |
+
{
|
985 |
+
"epoch": 0.9722222222222222,
|
986 |
+
"grad_norm": 0.058933736730721914,
|
987 |
+
"learning_rate": 6.112604669781572e-05,
|
988 |
+
"loss": 0.0628,
|
989 |
+
"step": 140
|
990 |
+
},
|
991 |
+
{
|
992 |
+
"epoch": 0.9791666666666666,
|
993 |
+
"grad_norm": 0.043997579067719075,
|
994 |
+
"learning_rate": 6.0533963499786314e-05,
|
995 |
+
"loss": 0.0416,
|
996 |
+
"step": 141
|
997 |
+
},
|
998 |
+
{
|
999 |
+
"epoch": 0.9861111111111112,
|
1000 |
+
"grad_norm": 0.0787901330317747,
|
1001 |
+
"learning_rate": 5.994033046234162e-05,
|
1002 |
+
"loss": 0.0663,
|
1003 |
+
"step": 142
|
1004 |
+
},
|
1005 |
+
{
|
1006 |
+
"epoch": 0.9930555555555556,
|
1007 |
+
"grad_norm": 0.056572258685848587,
|
1008 |
+
"learning_rate": 5.934523492543489e-05,
|
1009 |
+
"loss": 0.0598,
|
1010 |
+
"step": 143
|
1011 |
+
},
|
1012 |
+
{
|
1013 |
+
"epoch": 1.0,
|
1014 |
+
"grad_norm": 0.06836555724673425,
|
1015 |
+
"learning_rate": 5.874876444419377e-05,
|
1016 |
+
"loss": 0.0553,
|
1017 |
+
"step": 144
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"epoch": 1.0069444444444444,
|
1021 |
+
"grad_norm": 0.05528468814497019,
|
1022 |
+
"learning_rate": 5.8151006776038544e-05,
|
1023 |
+
"loss": 0.0487,
|
1024 |
+
"step": 145
|
1025 |
+
},
|
1026 |
+
{
|
1027 |
+
"epoch": 1.0138888888888888,
|
1028 |
+
"grad_norm": 0.04442209097541711,
|
1029 |
+
"learning_rate": 5.75520498677705e-05,
|
1030 |
+
"loss": 0.0496,
|
1031 |
+
"step": 146
|
1032 |
+
},
|
1033 |
+
{
|
1034 |
+
"epoch": 1.0208333333333333,
|
1035 |
+
"grad_norm": 0.04265736671883575,
|
1036 |
+
"learning_rate": 5.6951981842632585e-05,
|
1037 |
+
"loss": 0.0447,
|
1038 |
+
"step": 147
|
1039 |
+
},
|
1040 |
+
{
|
1041 |
+
"epoch": 1.0277777777777777,
|
1042 |
+
"grad_norm": 0.06716393769395008,
|
1043 |
+
"learning_rate": 5.6350890987343944e-05,
|
1044 |
+
"loss": 0.0574,
|
1045 |
+
"step": 148
|
1046 |
+
},
|
1047 |
+
{
|
1048 |
+
"epoch": 1.0347222222222223,
|
1049 |
+
"grad_norm": 0.04619919754230532,
|
1050 |
+
"learning_rate": 5.574886573911056e-05,
|
1051 |
+
"loss": 0.0484,
|
1052 |
+
"step": 149
|
1053 |
+
},
|
1054 |
+
{
|
1055 |
+
"epoch": 1.0416666666666667,
|
1056 |
+
"grad_norm": 0.04088308722298511,
|
1057 |
+
"learning_rate": 5.5145994672613624e-05,
|
1058 |
+
"loss": 0.0424,
|
1059 |
+
"step": 150
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 1.0486111111111112,
|
1063 |
+
"grad_norm": 0.07106013370406222,
|
1064 |
+
"learning_rate": 5.4542366486977756e-05,
|
1065 |
+
"loss": 0.0506,
|
1066 |
+
"step": 151
|
1067 |
+
},
|
1068 |
+
{
|
1069 |
+
"epoch": 1.0555555555555556,
|
1070 |
+
"grad_norm": 0.06544088043365288,
|
1071 |
+
"learning_rate": 5.39380699927209e-05,
|
1072 |
+
"loss": 0.0527,
|
1073 |
+
"step": 152
|
1074 |
+
},
|
1075 |
+
{
|
1076 |
+
"epoch": 1.0625,
|
1077 |
+
"grad_norm": 0.055005258429162714,
|
1078 |
+
"learning_rate": 5.3333194098687764e-05,
|
1079 |
+
"loss": 0.0511,
|
1080 |
+
"step": 153
|
1081 |
+
},
|
1082 |
+
{
|
1083 |
+
"epoch": 1.0694444444444444,
|
1084 |
+
"grad_norm": 0.05657332977154827,
|
1085 |
+
"learning_rate": 5.272782779896898e-05,
|
1086 |
+
"loss": 0.0543,
|
1087 |
+
"step": 154
|
1088 |
+
},
|
1089 |
+
{
|
1090 |
+
"epoch": 1.0763888888888888,
|
1091 |
+
"grad_norm": 0.08633216171192509,
|
1092 |
+
"learning_rate": 5.212206015980742e-05,
|
1093 |
+
"loss": 0.0595,
|
1094 |
+
"step": 155
|
1095 |
+
},
|
1096 |
+
{
|
1097 |
+
"epoch": 1.0833333333333333,
|
1098 |
+
"grad_norm": 0.04344217768745669,
|
1099 |
+
"learning_rate": 5.151598030649425e-05,
|
1100 |
+
"loss": 0.0396,
|
1101 |
+
"step": 156
|
1102 |
+
},
|
1103 |
+
{
|
1104 |
+
"epoch": 1.0902777777777777,
|
1105 |
+
"grad_norm": 0.04446718541450083,
|
1106 |
+
"learning_rate": 5.0909677410255985e-05,
|
1107 |
+
"loss": 0.0436,
|
1108 |
+
"step": 157
|
1109 |
+
},
|
1110 |
+
{
|
1111 |
+
"epoch": 1.0972222222222223,
|
1112 |
+
"grad_norm": 0.05936952558342409,
|
1113 |
+
"learning_rate": 5.030324067513499e-05,
|
1114 |
+
"loss": 0.0514,
|
1115 |
+
"step": 158
|
1116 |
+
},
|
1117 |
+
{
|
1118 |
+
"epoch": 1.1041666666666667,
|
1119 |
+
"grad_norm": 0.06506431319350331,
|
1120 |
+
"learning_rate": 4.969675932486503e-05,
|
1121 |
+
"loss": 0.0472,
|
1122 |
+
"step": 159
|
1123 |
+
},
|
1124 |
+
{
|
1125 |
+
"epoch": 1.1111111111111112,
|
1126 |
+
"grad_norm": 0.04763084580847737,
|
1127 |
+
"learning_rate": 4.9090322589744027e-05,
|
1128 |
+
"loss": 0.0436,
|
1129 |
+
"step": 160
|
1130 |
+
},
|
1131 |
+
{
|
1132 |
+
"epoch": 1.1180555555555556,
|
1133 |
+
"grad_norm": 0.06531630358906274,
|
1134 |
+
"learning_rate": 4.848401969350577e-05,
|
1135 |
+
"loss": 0.0547,
|
1136 |
+
"step": 161
|
1137 |
+
},
|
1138 |
+
{
|
1139 |
+
"epoch": 1.125,
|
1140 |
+
"grad_norm": 0.06486635891777948,
|
1141 |
+
"learning_rate": 4.78779398401926e-05,
|
1142 |
+
"loss": 0.0454,
|
1143 |
+
"step": 162
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 1.1319444444444444,
|
1147 |
+
"grad_norm": 0.06325850216814397,
|
1148 |
+
"learning_rate": 4.7272172201031054e-05,
|
1149 |
+
"loss": 0.0481,
|
1150 |
+
"step": 163
|
1151 |
+
},
|
1152 |
+
{
|
1153 |
+
"epoch": 1.1388888888888888,
|
1154 |
+
"grad_norm": 0.05964254119159708,
|
1155 |
+
"learning_rate": 4.666680590131225e-05,
|
1156 |
+
"loss": 0.0463,
|
1157 |
+
"step": 164
|
1158 |
+
},
|
1159 |
+
{
|
1160 |
+
"epoch": 1.1458333333333333,
|
1161 |
+
"grad_norm": 0.05342845760927094,
|
1162 |
+
"learning_rate": 4.606193000727913e-05,
|
1163 |
+
"loss": 0.0506,
|
1164 |
+
"step": 165
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 1.1527777777777777,
|
1168 |
+
"grad_norm": 0.05377115554688926,
|
1169 |
+
"learning_rate": 4.545763351302224e-05,
|
1170 |
+
"loss": 0.0474,
|
1171 |
+
"step": 166
|
1172 |
+
},
|
1173 |
+
{
|
1174 |
+
"epoch": 1.1597222222222223,
|
1175 |
+
"grad_norm": 0.05055891815765679,
|
1176 |
+
"learning_rate": 4.485400532738638e-05,
|
1177 |
+
"loss": 0.0454,
|
1178 |
+
"step": 167
|
1179 |
+
},
|
1180 |
+
{
|
1181 |
+
"epoch": 1.1666666666666667,
|
1182 |
+
"grad_norm": 0.05497839217223033,
|
1183 |
+
"learning_rate": 4.425113426088945e-05,
|
1184 |
+
"loss": 0.0517,
|
1185 |
+
"step": 168
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"epoch": 1.1736111111111112,
|
1189 |
+
"grad_norm": 0.07316550289620528,
|
1190 |
+
"learning_rate": 4.364910901265606e-05,
|
1191 |
+
"loss": 0.0538,
|
1192 |
+
"step": 169
|
1193 |
+
},
|
1194 |
+
{
|
1195 |
+
"epoch": 1.1805555555555556,
|
1196 |
+
"grad_norm": 0.047990097455734924,
|
1197 |
+
"learning_rate": 4.3048018157367433e-05,
|
1198 |
+
"loss": 0.0413,
|
1199 |
+
"step": 170
|
1200 |
+
},
|
1201 |
+
{
|
1202 |
+
"epoch": 1.1875,
|
1203 |
+
"grad_norm": 0.060217032523026584,
|
1204 |
+
"learning_rate": 4.244795013222951e-05,
|
1205 |
+
"loss": 0.0571,
|
1206 |
+
"step": 171
|
1207 |
+
},
|
1208 |
+
{
|
1209 |
+
"epoch": 1.1944444444444444,
|
1210 |
+
"grad_norm": 0.04698866045082108,
|
1211 |
+
"learning_rate": 4.184899322396147e-05,
|
1212 |
+
"loss": 0.0406,
|
1213 |
+
"step": 172
|
1214 |
+
},
|
1215 |
+
{
|
1216 |
+
"epoch": 1.2013888888888888,
|
1217 |
+
"grad_norm": 0.048369004985907946,
|
1218 |
+
"learning_rate": 4.125123555580624e-05,
|
1219 |
+
"loss": 0.0492,
|
1220 |
+
"step": 173
|
1221 |
+
},
|
1222 |
+
{
|
1223 |
+
"epoch": 1.2083333333333333,
|
1224 |
+
"grad_norm": 0.05659619196658486,
|
1225 |
+
"learning_rate": 4.0654765074565124e-05,
|
1226 |
+
"loss": 0.057,
|
1227 |
+
"step": 174
|
1228 |
+
},
|
1229 |
+
{
|
1230 |
+
"epoch": 1.2152777777777777,
|
1231 |
+
"grad_norm": 0.057459855223361965,
|
1232 |
+
"learning_rate": 4.005966953765839e-05,
|
1233 |
+
"loss": 0.0479,
|
1234 |
+
"step": 175
|
1235 |
+
},
|
1236 |
+
{
|
1237 |
+
"epoch": 1.2222222222222223,
|
1238 |
+
"grad_norm": 0.04572437211261691,
|
1239 |
+
"learning_rate": 3.94660365002137e-05,
|
1240 |
+
"loss": 0.0395,
|
1241 |
+
"step": 176
|
1242 |
+
},
|
1243 |
+
{
|
1244 |
+
"epoch": 1.2291666666666667,
|
1245 |
+
"grad_norm": 0.048219072573456936,
|
1246 |
+
"learning_rate": 3.887395330218429e-05,
|
1247 |
+
"loss": 0.0391,
|
1248 |
+
"step": 177
|
1249 |
+
},
|
1250 |
+
{
|
1251 |
+
"epoch": 1.2361111111111112,
|
1252 |
+
"grad_norm": 0.06136131829899375,
|
1253 |
+
"learning_rate": 3.8283507055498886e-05,
|
1254 |
+
"loss": 0.043,
|
1255 |
+
"step": 178
|
1256 |
+
},
|
1257 |
+
{
|
1258 |
+
"epoch": 1.2430555555555556,
|
1259 |
+
"grad_norm": 0.059005391153620405,
|
1260 |
+
"learning_rate": 3.769478463124507e-05,
|
1261 |
+
"loss": 0.0449,
|
1262 |
+
"step": 179
|
1263 |
+
},
|
1264 |
+
{
|
1265 |
+
"epoch": 1.25,
|
1266 |
+
"grad_norm": 0.0746524056732719,
|
1267 |
+
"learning_rate": 3.7107872646888116e-05,
|
1268 |
+
"loss": 0.0563,
|
1269 |
+
"step": 180
|
1270 |
+
},
|
1271 |
+
{
|
1272 |
+
"epoch": 1.2569444444444444,
|
1273 |
+
"grad_norm": 0.06512798583168254,
|
1274 |
+
"learning_rate": 3.652285745352717e-05,
|
1275 |
+
"loss": 0.0652,
|
1276 |
+
"step": 181
|
1277 |
+
},
|
1278 |
+
{
|
1279 |
+
"epoch": 1.2638888888888888,
|
1280 |
+
"grad_norm": 0.05118809031893748,
|
1281 |
+
"learning_rate": 3.5939825123190635e-05,
|
1282 |
+
"loss": 0.0439,
|
1283 |
+
"step": 182
|
1284 |
+
},
|
1285 |
+
{
|
1286 |
+
"epoch": 1.2708333333333333,
|
1287 |
+
"grad_norm": 0.0491373328570806,
|
1288 |
+
"learning_rate": 3.5358861436172485e-05,
|
1289 |
+
"loss": 0.0396,
|
1290 |
+
"step": 183
|
1291 |
+
},
|
1292 |
+
{
|
1293 |
+
"epoch": 1.2777777777777777,
|
1294 |
+
"grad_norm": 0.045715529417524076,
|
1295 |
+
"learning_rate": 3.4780051868411675e-05,
|
1296 |
+
"loss": 0.0349,
|
1297 |
+
"step": 184
|
1298 |
+
},
|
1299 |
+
{
|
1300 |
+
"epoch": 1.2847222222222223,
|
1301 |
+
"grad_norm": 0.05499812650132431,
|
1302 |
+
"learning_rate": 3.4203481578916194e-05,
|
1303 |
+
"loss": 0.045,
|
1304 |
+
"step": 185
|
1305 |
+
},
|
1306 |
+
{
|
1307 |
+
"epoch": 1.2916666666666667,
|
1308 |
+
"grad_norm": 0.05444819130310788,
|
1309 |
+
"learning_rate": 3.362923539723389e-05,
|
1310 |
+
"loss": 0.054,
|
1311 |
+
"step": 186
|
1312 |
+
},
|
1313 |
+
{
|
1314 |
+
"epoch": 1.2986111111111112,
|
1315 |
+
"grad_norm": 0.05755054434891386,
|
1316 |
+
"learning_rate": 3.305739781097157e-05,
|
1317 |
+
"loss": 0.0462,
|
1318 |
+
"step": 187
|
1319 |
+
},
|
1320 |
+
{
|
1321 |
+
"epoch": 1.3055555555555556,
|
1322 |
+
"grad_norm": 0.056782562230561044,
|
1323 |
+
"learning_rate": 3.248805295336458e-05,
|
1324 |
+
"loss": 0.049,
|
1325 |
+
"step": 188
|
1326 |
+
},
|
1327 |
+
{
|
1328 |
+
"epoch": 1.3125,
|
1329 |
+
"grad_norm": 0.05059433419507378,
|
1330 |
+
"learning_rate": 3.1921284590898456e-05,
|
1331 |
+
"loss": 0.0398,
|
1332 |
+
"step": 189
|
1333 |
+
},
|
1334 |
+
{
|
1335 |
+
"epoch": 1.3194444444444444,
|
1336 |
+
"grad_norm": 0.06312033575652291,
|
1337 |
+
"learning_rate": 3.135717611098458e-05,
|
1338 |
+
"loss": 0.0622,
|
1339 |
+
"step": 190
|
1340 |
+
},
|
1341 |
+
{
|
1342 |
+
"epoch": 1.3263888888888888,
|
1343 |
+
"grad_norm": 0.06684980111755691,
|
1344 |
+
"learning_rate": 3.079581050969146e-05,
|
1345 |
+
"loss": 0.0628,
|
1346 |
+
"step": 191
|
1347 |
+
},
|
1348 |
+
{
|
1349 |
+
"epoch": 1.3333333333333333,
|
1350 |
+
"grad_norm": 0.09404520793015296,
|
1351 |
+
"learning_rate": 3.023727037953382e-05,
|
1352 |
+
"loss": 0.0538,
|
1353 |
+
"step": 192
|
1354 |
+
},
|
1355 |
+
{
|
1356 |
+
"epoch": 1.3402777777777777,
|
1357 |
+
"grad_norm": 0.055119231303708986,
|
1358 |
+
"learning_rate": 2.9681637897320868e-05,
|
1359 |
+
"loss": 0.0494,
|
1360 |
+
"step": 193
|
1361 |
+
},
|
1362 |
+
{
|
1363 |
+
"epoch": 1.3472222222222223,
|
1364 |
+
"grad_norm": 0.06806024002262281,
|
1365 |
+
"learning_rate": 2.912899481206582e-05,
|
1366 |
+
"loss": 0.0494,
|
1367 |
+
"step": 194
|
1368 |
+
},
|
1369 |
+
{
|
1370 |
+
"epoch": 1.3541666666666667,
|
1371 |
+
"grad_norm": 0.05634926402516711,
|
1372 |
+
"learning_rate": 2.8579422432958312e-05,
|
1373 |
+
"loss": 0.0474,
|
1374 |
+
"step": 195
|
1375 |
+
},
|
1376 |
+
{
|
1377 |
+
"epoch": 1.3611111111111112,
|
1378 |
+
"grad_norm": 0.062090271560473254,
|
1379 |
+
"learning_rate": 2.803300161740166e-05,
|
1380 |
+
"loss": 0.0522,
|
1381 |
+
"step": 196
|
1382 |
+
},
|
1383 |
+
{
|
1384 |
+
"epoch": 1.3680555555555556,
|
1385 |
+
"grad_norm": 0.05050749410112152,
|
1386 |
+
"learning_rate": 2.748981275911633e-05,
|
1387 |
+
"loss": 0.0393,
|
1388 |
+
"step": 197
|
1389 |
+
},
|
1390 |
+
{
|
1391 |
+
"epoch": 1.375,
|
1392 |
+
"grad_norm": 0.05546645285466708,
|
1393 |
+
"learning_rate": 2.6949935776311896e-05,
|
1394 |
+
"loss": 0.0395,
|
1395 |
+
"step": 198
|
1396 |
+
},
|
1397 |
+
{
|
1398 |
+
"epoch": 1.3819444444444444,
|
1399 |
+
"grad_norm": 0.05531341419035151,
|
1400 |
+
"learning_rate": 2.6413450099928783e-05,
|
1401 |
+
"loss": 0.0445,
|
1402 |
+
"step": 199
|
1403 |
+
},
|
1404 |
+
{
|
1405 |
+
"epoch": 1.3888888888888888,
|
1406 |
+
"grad_norm": 0.057587022878495084,
|
1407 |
+
"learning_rate": 2.5880434661951823e-05,
|
1408 |
+
"loss": 0.046,
|
1409 |
+
"step": 200
|
1410 |
+
},
|
1411 |
+
{
|
1412 |
+
"epoch": 1.3888888888888888,
|
1413 |
+
"eval_loss": 0.05843019485473633,
|
1414 |
+
"eval_runtime": 2.8965,
|
1415 |
+
"eval_samples_per_second": 2.071,
|
1416 |
+
"eval_steps_per_second": 0.69,
|
1417 |
+
"step": 200
|
1418 |
+
},
|
1419 |
+
{
|
1420 |
+
"epoch": 1.3958333333333333,
|
1421 |
+
"grad_norm": 0.06587462746896457,
|
1422 |
+
"learning_rate": 2.5350967883797096e-05,
|
1423 |
+
"loss": 0.0592,
|
1424 |
+
"step": 201
|
1425 |
+
},
|
1426 |
+
{
|
1427 |
+
"epoch": 1.4027777777777777,
|
1428 |
+
"grad_norm": 0.05623019516285661,
|
1429 |
+
"learning_rate": 2.4825127664774006e-05,
|
1430 |
+
"loss": 0.0492,
|
1431 |
+
"step": 202
|
1432 |
+
},
|
1433 |
+
{
|
1434 |
+
"epoch": 1.4097222222222223,
|
1435 |
+
"grad_norm": 0.06970774002767344,
|
1436 |
+
"learning_rate": 2.4302991370624107e-05,
|
1437 |
+
"loss": 0.0599,
|
1438 |
+
"step": 203
|
1439 |
+
},
|
1440 |
+
{
|
1441 |
+
"epoch": 1.4166666666666667,
|
1442 |
+
"grad_norm": 0.050591438460209116,
|
1443 |
+
"learning_rate": 2.3784635822138424e-05,
|
1444 |
+
"loss": 0.0405,
|
1445 |
+
"step": 204
|
1446 |
+
},
|
1447 |
+
{
|
1448 |
+
"epoch": 1.4236111111111112,
|
1449 |
+
"grad_norm": 0.06087979461292365,
|
1450 |
+
"learning_rate": 2.327013728385502e-05,
|
1451 |
+
"loss": 0.0522,
|
1452 |
+
"step": 205
|
1453 |
+
},
|
1454 |
+
{
|
1455 |
+
"epoch": 1.4305555555555556,
|
1456 |
+
"grad_norm": 0.05750045979367977,
|
1457 |
+
"learning_rate": 2.2759571452838324e-05,
|
1458 |
+
"loss": 0.0498,
|
1459 |
+
"step": 206
|
1460 |
+
},
|
1461 |
+
{
|
1462 |
+
"epoch": 1.4375,
|
1463 |
+
"grad_norm": 0.06261633186118712,
|
1464 |
+
"learning_rate": 2.225301344754199e-05,
|
1465 |
+
"loss": 0.0516,
|
1466 |
+
"step": 207
|
1467 |
+
},
|
1468 |
+
{
|
1469 |
+
"epoch": 1.4444444444444444,
|
1470 |
+
"grad_norm": 0.04778739915939838,
|
1471 |
+
"learning_rate": 2.17505377967569e-05,
|
1472 |
+
"loss": 0.0356,
|
1473 |
+
"step": 208
|
1474 |
+
},
|
1475 |
+
{
|
1476 |
+
"epoch": 1.4513888888888888,
|
1477 |
+
"grad_norm": 0.06838727020740598,
|
1478 |
+
"learning_rate": 2.1252218428645846e-05,
|
1479 |
+
"loss": 0.0553,
|
1480 |
+
"step": 209
|
1481 |
+
},
|
1482 |
+
{
|
1483 |
+
"epoch": 1.4583333333333333,
|
1484 |
+
"grad_norm": 0.05699327263249455,
|
1485 |
+
"learning_rate": 2.075812865986677e-05,
|
1486 |
+
"loss": 0.0436,
|
1487 |
+
"step": 210
|
1488 |
+
},
|
1489 |
+
{
|
1490 |
+
"epoch": 1.4652777777777777,
|
1491 |
+
"grad_norm": 0.05755232280782536,
|
1492 |
+
"learning_rate": 2.026834118478567e-05,
|
1493 |
+
"loss": 0.0531,
|
1494 |
+
"step": 211
|
1495 |
+
},
|
1496 |
+
{
|
1497 |
+
"epoch": 1.4722222222222223,
|
1498 |
+
"grad_norm": 0.06672702654987289,
|
1499 |
+
"learning_rate": 1.978292806478134e-05,
|
1500 |
+
"loss": 0.0529,
|
1501 |
+
"step": 212
|
1502 |
+
},
|
1503 |
+
{
|
1504 |
+
"epoch": 1.4791666666666667,
|
1505 |
+
"grad_norm": 0.05318360817731425,
|
1506 |
+
"learning_rate": 1.9301960717643118e-05,
|
1507 |
+
"loss": 0.0408,
|
1508 |
+
"step": 213
|
1509 |
+
},
|
1510 |
+
{
|
1511 |
+
"epoch": 1.4861111111111112,
|
1512 |
+
"grad_norm": 0.05852145674739832,
|
1513 |
+
"learning_rate": 1.8825509907063327e-05,
|
1514 |
+
"loss": 0.0532,
|
1515 |
+
"step": 214
|
1516 |
+
},
|
1517 |
+
{
|
1518 |
+
"epoch": 1.4930555555555556,
|
1519 |
+
"grad_norm": 0.04695844857372584,
|
1520 |
+
"learning_rate": 1.8353645732225976e-05,
|
1521 |
+
"loss": 0.0357,
|
1522 |
+
"step": 215
|
1523 |
+
},
|
1524 |
+
{
|
1525 |
+
"epoch": 1.5,
|
1526 |
+
"grad_norm": 0.06015704770880845,
|
1527 |
+
"learning_rate": 1.7886437617493205e-05,
|
1528 |
+
"loss": 0.0458,
|
1529 |
+
"step": 216
|
1530 |
+
},
|
1531 |
+
{
|
1532 |
+
"epoch": 1.5069444444444444,
|
1533 |
+
"grad_norm": 0.06607871507117989,
|
1534 |
+
"learning_rate": 1.7423954302191047e-05,
|
1535 |
+
"loss": 0.065,
|
1536 |
+
"step": 217
|
1537 |
+
},
|
1538 |
+
{
|
1539 |
+
"epoch": 1.5138888888888888,
|
1540 |
+
"grad_norm": 0.07091336376792805,
|
1541 |
+
"learning_rate": 1.6966263830495936e-05,
|
1542 |
+
"loss": 0.0363,
|
1543 |
+
"step": 218
|
1544 |
+
},
|
1545 |
+
{
|
1546 |
+
"epoch": 1.5208333333333335,
|
1547 |
+
"grad_norm": 0.05916059675448067,
|
1548 |
+
"learning_rate": 1.6513433541423528e-05,
|
1549 |
+
"loss": 0.0504,
|
1550 |
+
"step": 219
|
1551 |
+
},
|
1552 |
+
{
|
1553 |
+
"epoch": 1.5277777777777777,
|
1554 |
+
"grad_norm": 0.06409972590419019,
|
1555 |
+
"learning_rate": 1.606553005892125e-05,
|
1556 |
+
"loss": 0.0393,
|
1557 |
+
"step": 220
|
1558 |
+
},
|
1559 |
+
{
|
1560 |
+
"epoch": 1.5347222222222223,
|
1561 |
+
"grad_norm": 0.06555802647292505,
|
1562 |
+
"learning_rate": 1.5622619282066082e-05,
|
1563 |
+
"loss": 0.0482,
|
1564 |
+
"step": 221
|
1565 |
+
},
|
1566 |
+
{
|
1567 |
+
"epoch": 1.5416666666666665,
|
1568 |
+
"grad_norm": 0.05144622081409977,
|
1569 |
+
"learning_rate": 1.5184766375368915e-05,
|
1570 |
+
"loss": 0.037,
|
1571 |
+
"step": 222
|
1572 |
+
},
|
1573 |
+
{
|
1574 |
+
"epoch": 1.5486111111111112,
|
1575 |
+
"grad_norm": 0.06265878609345442,
|
1576 |
+
"learning_rate": 1.4752035759187106e-05,
|
1577 |
+
"loss": 0.0536,
|
1578 |
+
"step": 223
|
1579 |
+
},
|
1580 |
+
{
|
1581 |
+
"epoch": 1.5555555555555556,
|
1582 |
+
"grad_norm": 0.05834542354430463,
|
1583 |
+
"learning_rate": 1.4324491100246385e-05,
|
1584 |
+
"loss": 0.0461,
|
1585 |
+
"step": 224
|
1586 |
+
},
|
1587 |
+
{
|
1588 |
+
"epoch": 1.5625,
|
1589 |
+
"grad_norm": 0.059108211105270696,
|
1590 |
+
"learning_rate": 1.3902195302273779e-05,
|
1591 |
+
"loss": 0.0461,
|
1592 |
+
"step": 225
|
1593 |
+
},
|
1594 |
+
{
|
1595 |
+
"epoch": 1.5694444444444444,
|
1596 |
+
"grad_norm": 0.06072177930930135,
|
1597 |
+
"learning_rate": 1.348521049674264e-05,
|
1598 |
+
"loss": 0.0448,
|
1599 |
+
"step": 226
|
1600 |
+
},
|
1601 |
+
{
|
1602 |
+
"epoch": 1.5763888888888888,
|
1603 |
+
"grad_norm": 0.06147140484331682,
|
1604 |
+
"learning_rate": 1.3073598033731426e-05,
|
1605 |
+
"loss": 0.0475,
|
1606 |
+
"step": 227
|
1607 |
+
},
|
1608 |
+
{
|
1609 |
+
"epoch": 1.5833333333333335,
|
1610 |
+
"grad_norm": 0.05617171004497398,
|
1611 |
+
"learning_rate": 1.2667418472897386e-05,
|
1612 |
+
"loss": 0.0432,
|
1613 |
+
"step": 228
|
1614 |
+
},
|
1615 |
+
{
|
1616 |
+
"epoch": 1.5902777777777777,
|
1617 |
+
"grad_norm": 0.06266225996920342,
|
1618 |
+
"learning_rate": 1.2266731574566536e-05,
|
1619 |
+
"loss": 0.0446,
|
1620 |
+
"step": 229
|
1621 |
+
},
|
1622 |
+
{
|
1623 |
+
"epoch": 1.5972222222222223,
|
1624 |
+
"grad_norm": 0.054440007451986294,
|
1625 |
+
"learning_rate": 1.1871596290941278e-05,
|
1626 |
+
"loss": 0.0403,
|
1627 |
+
"step": 230
|
1628 |
+
},
|
1629 |
+
{
|
1630 |
+
"epoch": 1.6041666666666665,
|
1631 |
+
"grad_norm": 0.05771513928537823,
|
1632 |
+
"learning_rate": 1.1482070757426856e-05,
|
1633 |
+
"loss": 0.0424,
|
1634 |
+
"step": 231
|
1635 |
+
},
|
1636 |
+
{
|
1637 |
+
"epoch": 1.6111111111111112,
|
1638 |
+
"grad_norm": 0.07317554509540891,
|
1639 |
+
"learning_rate": 1.1098212284078036e-05,
|
1640 |
+
"loss": 0.0486,
|
1641 |
+
"step": 232
|
1642 |
+
},
|
1643 |
+
{
|
1644 |
+
"epoch": 1.6180555555555556,
|
1645 |
+
"grad_norm": 0.0592998028315768,
|
1646 |
+
"learning_rate": 1.0720077347167202e-05,
|
1647 |
+
"loss": 0.0452,
|
1648 |
+
"step": 233
|
1649 |
+
},
|
1650 |
+
{
|
1651 |
+
"epoch": 1.625,
|
1652 |
+
"grad_norm": 0.05734391978777635,
|
1653 |
+
"learning_rate": 1.0347721580875126e-05,
|
1654 |
+
"loss": 0.0418,
|
1655 |
+
"step": 234
|
1656 |
+
},
|
1657 |
+
{
|
1658 |
+
"epoch": 1.6319444444444444,
|
1659 |
+
"grad_norm": 0.05781410001692482,
|
1660 |
+
"learning_rate": 9.981199769105604e-06,
|
1661 |
+
"loss": 0.0488,
|
1662 |
+
"step": 235
|
1663 |
+
},
|
1664 |
+
{
|
1665 |
+
"epoch": 1.6388888888888888,
|
1666 |
+
"grad_norm": 0.06084611217062411,
|
1667 |
+
"learning_rate": 9.620565837425271e-06,
|
1668 |
+
"loss": 0.0544,
|
1669 |
+
"step": 236
|
1670 |
+
},
|
1671 |
+
{
|
1672 |
+
"epoch": 1.6458333333333335,
|
1673 |
+
"grad_norm": 0.05484483522551538,
|
1674 |
+
"learning_rate": 9.26587284512957e-06,
|
1675 |
+
"loss": 0.0418,
|
1676 |
+
"step": 237
|
1677 |
+
},
|
1678 |
+
{
|
1679 |
+
"epoch": 1.6527777777777777,
|
1680 |
+
"grad_norm": 0.061075107734742555,
|
1681 |
+
"learning_rate": 8.917172977436356e-06,
|
1682 |
+
"loss": 0.0509,
|
1683 |
+
"step": 238
|
1684 |
+
},
|
1685 |
+
{
|
1686 |
+
"epoch": 1.6597222222222223,
|
1687 |
+
"grad_norm": 0.056522690917951715,
|
1688 |
+
"learning_rate": 8.574517537807897e-06,
|
1689 |
+
"loss": 0.0493,
|
1690 |
+
"step": 239
|
1691 |
+
},
|
1692 |
+
{
|
1693 |
+
"epoch": 1.6666666666666665,
|
1694 |
+
"grad_norm": 0.06145420768545982,
|
1695 |
+
"learning_rate": 8.237956940402757e-06,
|
1696 |
+
"loss": 0.0538,
|
1697 |
+
"step": 240
|
1698 |
+
},
|
1699 |
+
{
|
1700 |
+
"epoch": 1.6736111111111112,
|
1701 |
+
"grad_norm": 0.07712832225863908,
|
1702 |
+
"learning_rate": 7.907540702658456e-06,
|
1703 |
+
"loss": 0.0417,
|
1704 |
+
"step": 241
|
1705 |
+
},
|
1706 |
+
{
|
1707 |
+
"epoch": 1.6805555555555556,
|
1708 |
+
"grad_norm": 0.1210354286083926,
|
1709 |
+
"learning_rate": 7.583317438006093e-06,
|
1710 |
+
"loss": 0.0648,
|
1711 |
+
"step": 242
|
1712 |
+
},
|
1713 |
+
{
|
1714 |
+
"epoch": 1.6875,
|
1715 |
+
"grad_norm": 0.056155382622722974,
|
1716 |
+
"learning_rate": 7.265334848717931e-06,
|
1717 |
+
"loss": 0.0409,
|
1718 |
+
"step": 243
|
1719 |
+
},
|
1720 |
+
{
|
1721 |
+
"epoch": 1.6944444444444444,
|
1722 |
+
"grad_norm": 0.06052338165886097,
|
1723 |
+
"learning_rate": 6.953639718889076e-06,
|
1724 |
+
"loss": 0.0425,
|
1725 |
+
"step": 244
|
1726 |
+
},
|
1727 |
+
{
|
1728 |
+
"epoch": 1.7013888888888888,
|
1729 |
+
"grad_norm": 0.06942550868803853,
|
1730 |
+
"learning_rate": 6.648277907554235e-06,
|
1731 |
+
"loss": 0.0483,
|
1732 |
+
"step": 245
|
1733 |
+
},
|
1734 |
+
{
|
1735 |
+
"epoch": 1.7083333333333335,
|
1736 |
+
"grad_norm": 0.06102534205447137,
|
1737 |
+
"learning_rate": 6.349294341940593e-06,
|
1738 |
+
"loss": 0.0461,
|
1739 |
+
"step": 246
|
1740 |
+
},
|
1741 |
+
{
|
1742 |
+
"epoch": 1.7152777777777777,
|
1743 |
+
"grad_norm": 0.06664766533657307,
|
1744 |
+
"learning_rate": 6.056733010857712e-06,
|
1745 |
+
"loss": 0.0538,
|
1746 |
+
"step": 247
|
1747 |
+
},
|
1748 |
+
{
|
1749 |
+
"epoch": 1.7222222222222223,
|
1750 |
+
"grad_norm": 0.055246592628772316,
|
1751 |
+
"learning_rate": 5.770636958225617e-06,
|
1752 |
+
"loss": 0.0455,
|
1753 |
+
"step": 248
|
1754 |
+
},
|
1755 |
+
{
|
1756 |
+
"epoch": 1.7291666666666665,
|
1757 |
+
"grad_norm": 0.061169981220161505,
|
1758 |
+
"learning_rate": 5.491048276741784e-06,
|
1759 |
+
"loss": 0.0444,
|
1760 |
+
"step": 249
|
1761 |
+
},
|
1762 |
+
{
|
1763 |
+
"epoch": 1.7361111111111112,
|
1764 |
+
"grad_norm": 0.07327155244232343,
|
1765 |
+
"learning_rate": 5.218008101688171e-06,
|
1766 |
+
"loss": 0.0607,
|
1767 |
+
"step": 250
|
1768 |
+
},
|
1769 |
+
{
|
1770 |
+
"epoch": 1.7430555555555556,
|
1771 |
+
"grad_norm": 0.06145818807633177,
|
1772 |
+
"learning_rate": 4.951556604879048e-06,
|
1773 |
+
"loss": 0.0445,
|
1774 |
+
"step": 251
|
1775 |
+
},
|
1776 |
+
{
|
1777 |
+
"epoch": 1.75,
|
1778 |
+
"grad_norm": 0.05297976039230036,
|
1779 |
+
"learning_rate": 4.691732988750614e-06,
|
1780 |
+
"loss": 0.0388,
|
1781 |
+
"step": 252
|
1782 |
+
},
|
1783 |
+
{
|
1784 |
+
"epoch": 1.7569444444444444,
|
1785 |
+
"grad_norm": 0.054054619462972,
|
1786 |
+
"learning_rate": 4.43857548059321e-06,
|
1787 |
+
"loss": 0.0391,
|
1788 |
+
"step": 253
|
1789 |
+
},
|
1790 |
+
{
|
1791 |
+
"epoch": 1.7638888888888888,
|
1792 |
+
"grad_norm": 0.05798999532961248,
|
1793 |
+
"learning_rate": 4.192121326927073e-06,
|
1794 |
+
"loss": 0.0432,
|
1795 |
+
"step": 254
|
1796 |
+
},
|
1797 |
+
{
|
1798 |
+
"epoch": 1.7708333333333335,
|
1799 |
+
"grad_norm": 0.05728064735233047,
|
1800 |
+
"learning_rate": 3.952406788022267e-06,
|
1801 |
+
"loss": 0.044,
|
1802 |
+
"step": 255
|
1803 |
+
},
|
1804 |
+
{
|
1805 |
+
"epoch": 1.7777777777777777,
|
1806 |
+
"grad_norm": 0.05548812892517234,
|
1807 |
+
"learning_rate": 3.7194671325638198e-06,
|
1808 |
+
"loss": 0.042,
|
1809 |
+
"step": 256
|
1810 |
+
},
|
1811 |
+
{
|
1812 |
+
"epoch": 1.7847222222222223,
|
1813 |
+
"grad_norm": 0.05776655459801612,
|
1814 |
+
"learning_rate": 3.493336632462718e-06,
|
1815 |
+
"loss": 0.0446,
|
1816 |
+
"step": 257
|
1817 |
+
},
|
1818 |
+
{
|
1819 |
+
"epoch": 1.7916666666666665,
|
1820 |
+
"grad_norm": 0.06297495738200812,
|
1821 |
+
"learning_rate": 3.274048557813553e-06,
|
1822 |
+
"loss": 0.0375,
|
1823 |
+
"step": 258
|
1824 |
+
},
|
1825 |
+
{
|
1826 |
+
"epoch": 1.7986111111111112,
|
1827 |
+
"grad_norm": 0.0571294673264027,
|
1828 |
+
"learning_rate": 3.061635171999566e-06,
|
1829 |
+
"loss": 0.0458,
|
1830 |
+
"step": 259
|
1831 |
+
},
|
1832 |
+
{
|
1833 |
+
"epoch": 1.8055555555555556,
|
1834 |
+
"grad_norm": 0.05711653877850546,
|
1835 |
+
"learning_rate": 2.85612772694579e-06,
|
1836 |
+
"loss": 0.043,
|
1837 |
+
"step": 260
|
1838 |
+
},
|
1839 |
+
{
|
1840 |
+
"epoch": 1.8125,
|
1841 |
+
"grad_norm": 0.056535662892683275,
|
1842 |
+
"learning_rate": 2.657556458521049e-06,
|
1843 |
+
"loss": 0.0422,
|
1844 |
+
"step": 261
|
1845 |
+
},
|
1846 |
+
{
|
1847 |
+
"epoch": 1.8194444444444444,
|
1848 |
+
"grad_norm": 0.05861262152488929,
|
1849 |
+
"learning_rate": 2.4659505820893826e-06,
|
1850 |
+
"loss": 0.049,
|
1851 |
+
"step": 262
|
1852 |
+
},
|
1853 |
+
{
|
1854 |
+
"epoch": 1.8263888888888888,
|
1855 |
+
"grad_norm": 0.057433042780234714,
|
1856 |
+
"learning_rate": 2.2813382882116986e-06,
|
1857 |
+
"loss": 0.0437,
|
1858 |
+
"step": 263
|
1859 |
+
},
|
1860 |
+
{
|
1861 |
+
"epoch": 1.8333333333333335,
|
1862 |
+
"grad_norm": 0.05389278487965654,
|
1863 |
+
"learning_rate": 2.1037467384981026e-06,
|
1864 |
+
"loss": 0.0426,
|
1865 |
+
"step": 264
|
1866 |
+
},
|
1867 |
+
{
|
1868 |
+
"epoch": 1.8402777777777777,
|
1869 |
+
"grad_norm": 0.05557228450230491,
|
1870 |
+
"learning_rate": 1.933202061611722e-06,
|
1871 |
+
"loss": 0.0458,
|
1872 |
+
"step": 265
|
1873 |
+
},
|
1874 |
+
{
|
1875 |
+
"epoch": 1.8472222222222223,
|
1876 |
+
"grad_norm": 0.05917014990003017,
|
1877 |
+
"learning_rate": 1.769729349424415e-06,
|
1878 |
+
"loss": 0.0531,
|
1879 |
+
"step": 266
|
1880 |
+
},
|
1881 |
+
{
|
1882 |
+
"epoch": 1.8541666666666665,
|
1883 |
+
"grad_norm": 0.057944432503720486,
|
1884 |
+
"learning_rate": 1.6133526533250565e-06,
|
1885 |
+
"loss": 0.0425,
|
1886 |
+
"step": 267
|
1887 |
+
},
|
1888 |
+
{
|
1889 |
+
"epoch": 1.8611111111111112,
|
1890 |
+
"grad_norm": 0.06092440732902568,
|
1891 |
+
"learning_rate": 1.4640949806809523e-06,
|
1892 |
+
"loss": 0.0492,
|
1893 |
+
"step": 268
|
1894 |
+
},
|
1895 |
+
{
|
1896 |
+
"epoch": 1.8680555555555556,
|
1897 |
+
"grad_norm": 0.05900717359821016,
|
1898 |
+
"learning_rate": 1.3219782914527634e-06,
|
1899 |
+
"loss": 0.0452,
|
1900 |
+
"step": 269
|
1901 |
+
},
|
1902 |
+
{
|
1903 |
+
"epoch": 1.875,
|
1904 |
+
"grad_norm": 0.06389890797796334,
|
1905 |
+
"learning_rate": 1.1870234949636073e-06,
|
1906 |
+
"loss": 0.0549,
|
1907 |
+
"step": 270
|
1908 |
+
},
|
1909 |
+
{
|
1910 |
+
"epoch": 1.8819444444444444,
|
1911 |
+
"grad_norm": 0.05962740065521039,
|
1912 |
+
"learning_rate": 1.0592504468227127e-06,
|
1913 |
+
"loss": 0.0463,
|
1914 |
+
"step": 271
|
1915 |
+
},
|
1916 |
+
{
|
1917 |
+
"epoch": 1.8888888888888888,
|
1918 |
+
"grad_norm": 0.07174635089821045,
|
1919 |
+
"learning_rate": 9.386779460041017e-07,
|
1920 |
+
"loss": 0.0522,
|
1921 |
+
"step": 272
|
1922 |
+
},
|
1923 |
+
{
|
1924 |
+
"epoch": 1.8958333333333335,
|
1925 |
+
"grad_norm": 0.06082782248412747,
|
1926 |
+
"learning_rate": 8.253237320807461e-07,
|
1927 |
+
"loss": 0.0475,
|
1928 |
+
"step": 273
|
1929 |
+
},
|
1930 |
+
{
|
1931 |
+
"epoch": 1.9027777777777777,
|
1932 |
+
"grad_norm": 0.0601520271544199,
|
1933 |
+
"learning_rate": 7.192044826145771e-07,
|
1934 |
+
"loss": 0.0498,
|
1935 |
+
"step": 274
|
1936 |
+
},
|
1937 |
+
{
|
1938 |
+
"epoch": 1.9097222222222223,
|
1939 |
+
"grad_norm": 0.05825976235647901,
|
1940 |
+
"learning_rate": 6.20335810702749e-07,
|
1941 |
+
"loss": 0.0422,
|
1942 |
+
"step": 275
|
1943 |
+
},
|
1944 |
+
{
|
1945 |
+
"epoch": 1.9166666666666665,
|
1946 |
+
"grad_norm": 0.05517949333399056,
|
1947 |
+
"learning_rate": 5.287322626805202e-07,
|
1948 |
+
"loss": 0.0433,
|
1949 |
+
"step": 276
|
1950 |
+
},
|
1951 |
+
{
|
1952 |
+
"epoch": 1.9236111111111112,
|
1953 |
+
"grad_norm": 0.06763262497028635,
|
1954 |
+
"learning_rate": 4.4440731598107686e-07,
|
1955 |
+
"loss": 0.0499,
|
1956 |
+
"step": 277
|
1957 |
+
},
|
1958 |
+
{
|
1959 |
+
"epoch": 1.9305555555555556,
|
1960 |
+
"grad_norm": 0.16139138859406038,
|
1961 |
+
"learning_rate": 3.673733771526466e-07,
|
1962 |
+
"loss": 0.0664,
|
1963 |
+
"step": 278
|
1964 |
+
},
|
1965 |
+
{
|
1966 |
+
"epoch": 1.9375,
|
1967 |
+
"grad_norm": 0.056764953267334266,
|
1968 |
+
"learning_rate": 2.976417800331144e-07,
|
1969 |
+
"loss": 0.0395,
|
1970 |
+
"step": 279
|
1971 |
+
},
|
1972 |
+
{
|
1973 |
+
"epoch": 1.9444444444444444,
|
1974 |
+
"grad_norm": 0.06087509888868891,
|
1975 |
+
"learning_rate": 2.352227840825394e-07,
|
1976 |
+
"loss": 0.0456,
|
1977 |
+
"step": 280
|
1978 |
+
},
|
1979 |
+
{
|
1980 |
+
"epoch": 1.9513888888888888,
|
1981 |
+
"grad_norm": 0.07013826621193169,
|
1982 |
+
"learning_rate": 1.8012557287367392e-07,
|
1983 |
+
"loss": 0.0449,
|
1984 |
+
"step": 281
|
1985 |
+
},
|
1986 |
+
{
|
1987 |
+
"epoch": 1.9583333333333335,
|
1988 |
+
"grad_norm": 0.06122401225786666,
|
1989 |
+
"learning_rate": 1.3235825274081625e-07,
|
1990 |
+
"loss": 0.0433,
|
1991 |
+
"step": 282
|
1992 |
+
},
|
1993 |
+
{
|
1994 |
+
"epoch": 1.9652777777777777,
|
1995 |
+
"grad_norm": 0.062035625059352666,
|
1996 |
+
"learning_rate": 9.19278515871369e-08,
|
1997 |
+
"loss": 0.0516,
|
1998 |
+
"step": 283
|
1999 |
+
},
|
2000 |
+
{
|
2001 |
+
"epoch": 1.9722222222222223,
|
2002 |
+
"grad_norm": 0.05458425287261523,
|
2003 |
+
"learning_rate": 5.8840317850683555e-08,
|
2004 |
+
"loss": 0.0392,
|
2005 |
+
"step": 284
|
2006 |
+
},
|
2007 |
+
{
|
2008 |
+
"epoch": 1.9791666666666665,
|
2009 |
+
"grad_norm": 0.0574212811670188,
|
2010 |
+
"learning_rate": 3.310051962920335e-08,
|
2011 |
+
"loss": 0.0471,
|
2012 |
+
"step": 285
|
2013 |
+
},
|
2014 |
+
{
|
2015 |
+
"epoch": 1.9861111111111112,
|
2016 |
+
"grad_norm": 0.05924979972086086,
|
2017 |
+
"learning_rate": 1.471224396389359e-08,
|
2018 |
+
"loss": 0.0542,
|
2019 |
+
"step": 286
|
2020 |
+
},
|
2021 |
+
{
|
2022 |
+
"epoch": 1.9930555555555556,
|
2023 |
+
"grad_norm": 0.05752784210946029,
|
2024 |
+
"learning_rate": 3.6781962822529657e-09,
|
2025 |
+
"loss": 0.0474,
|
2026 |
+
"step": 287
|
2027 |
+
},
|
2028 |
+
{
|
2029 |
+
"epoch": 2.0,
|
2030 |
+
"grad_norm": 0.0627018913384721,
|
2031 |
+
"learning_rate": 0.0,
|
2032 |
+
"loss": 0.0448,
|
2033 |
+
"step": 288
|
2034 |
+
},
|
2035 |
+
{
|
2036 |
+
"epoch": 2.0,
|
2037 |
+
"step": 288,
|
2038 |
+
"total_flos": 547031730880512.0,
|
2039 |
+
"train_loss": 0.056736280779457755,
|
2040 |
+
"train_runtime": 1071.8886,
|
2041 |
+
"train_samples_per_second": 1.069,
|
2042 |
+
"train_steps_per_second": 0.269
|
2043 |
+
}
|
2044 |
+
],
|
2045 |
+
"logging_steps": 1,
|
2046 |
+
"max_steps": 288,
|
2047 |
+
"num_input_tokens_seen": 0,
|
2048 |
+
"num_train_epochs": 2,
|
2049 |
+
"save_steps": 300,
|
2050 |
+
"stateful_callbacks": {
|
2051 |
+
"TrainerControl": {
|
2052 |
+
"args": {
|
2053 |
+
"should_epoch_stop": false,
|
2054 |
+
"should_evaluate": false,
|
2055 |
+
"should_log": false,
|
2056 |
+
"should_save": true,
|
2057 |
+
"should_training_stop": true
|
2058 |
+
},
|
2059 |
+
"attributes": {}
|
2060 |
+
}
|
2061 |
+
},
|
2062 |
+
"total_flos": 547031730880512.0,
|
2063 |
+
"train_batch_size": 1,
|
2064 |
+
"trial_name": null,
|
2065 |
+
"trial_params": null
|
2066 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d1d59aab1b457e8b9fd7de0c37304956819c20c31aa1763bdf88eee33e8deac7
|
3 |
+
size 7224
|
training_eval_loss.png
ADDED
![]() |
training_loss.png
ADDED
![]() |
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|