Add files using upload-large-folder tool
Browse files- .gitattributes +1 -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 +171 -0
- trainer_state.json +1232 -0
- training_args.bin +3 -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
|
adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "Qwen/Qwen2.5-32B-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 |
+
"v_proj",
|
| 24 |
+
"up_proj",
|
| 25 |
+
"q_proj",
|
| 26 |
+
"down_proj",
|
| 27 |
+
"o_proj",
|
| 28 |
+
"k_proj",
|
| 29 |
+
"gate_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 sha256:8c92d4fb0f1a5abf21826624032963df252006ddbe9cce746ace925a00423047
|
| 3 |
+
size 134337704
|
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": 0.019414987415075302,
|
| 4 |
+
"eval_runtime": 6.422,
|
| 5 |
+
"eval_samples_per_second": 1.09,
|
| 6 |
+
"eval_steps_per_second": 0.311,
|
| 7 |
+
"total_flos": 861011422740480.0,
|
| 8 |
+
"train_loss": 0.03621660071041654,
|
| 9 |
+
"train_runtime": 2036.7134,
|
| 10 |
+
"train_samples_per_second": 0.668,
|
| 11 |
+
"train_steps_per_second": 0.083
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"eval_loss": 0.019414987415075302,
|
| 4 |
+
"eval_runtime": 6.422,
|
| 5 |
+
"eval_samples_per_second": 1.09,
|
| 6 |
+
"eval_steps_per_second": 0.311
|
| 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": 861011422740480.0,
|
| 4 |
+
"train_loss": 0.03621660071041654,
|
| 5 |
+
"train_runtime": 2036.7134,
|
| 6 |
+
"train_samples_per_second": 0.668,
|
| 7 |
+
"train_steps_per_second": 0.083
|
| 8 |
+
}
|
trainer_log.jsonl
ADDED
|
@@ -0,0 +1,171 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 1, "total_steps": 170, "loss": 0.1079, "lr": 1.6666666666666667e-05, "epoch": 0.011764705882352941, "percentage": 0.59, "elapsed_time": "0:00:16", "remaining_time": "0:46:56"}
|
| 2 |
+
{"current_steps": 2, "total_steps": 170, "loss": 0.1141, "lr": 3.3333333333333335e-05, "epoch": 0.023529411764705882, "percentage": 1.18, "elapsed_time": "0:00:28", "remaining_time": "0:39:44"}
|
| 3 |
+
{"current_steps": 3, "total_steps": 170, "loss": 0.1204, "lr": 5e-05, "epoch": 0.03529411764705882, "percentage": 1.76, "elapsed_time": "0:00:40", "remaining_time": "0:37:13"}
|
| 4 |
+
{"current_steps": 4, "total_steps": 170, "loss": 0.1276, "lr": 6.666666666666667e-05, "epoch": 0.047058823529411764, "percentage": 2.35, "elapsed_time": "0:00:51", "remaining_time": "0:35:51"}
|
| 5 |
+
{"current_steps": 5, "total_steps": 170, "loss": 0.1689, "lr": 8.333333333333334e-05, "epoch": 0.058823529411764705, "percentage": 2.94, "elapsed_time": "0:01:03", "remaining_time": "0:34:59"}
|
| 6 |
+
{"current_steps": 6, "total_steps": 170, "loss": 0.1345, "lr": 0.0001, "epoch": 0.07058823529411765, "percentage": 3.53, "elapsed_time": "0:01:15", "remaining_time": "0:34:20"}
|
| 7 |
+
{"current_steps": 7, "total_steps": 170, "loss": 0.1202, "lr": 9.999082642158973e-05, "epoch": 0.08235294117647059, "percentage": 4.12, "elapsed_time": "0:01:27", "remaining_time": "0:33:48"}
|
| 8 |
+
{"current_steps": 8, "total_steps": 170, "loss": 0.0983, "lr": 9.99633090525405e-05, "epoch": 0.09411764705882353, "percentage": 4.71, "elapsed_time": "0:01:38", "remaining_time": "0:33:21"}
|
| 9 |
+
{"current_steps": 9, "total_steps": 170, "loss": 0.0954, "lr": 9.991745799016206e-05, "epoch": 0.10588235294117647, "percentage": 5.29, "elapsed_time": "0:01:50", "remaining_time": "0:32:58"}
|
| 10 |
+
{"current_steps": 10, "total_steps": 170, "loss": 0.0977, "lr": 9.985329005918702e-05, "epoch": 0.11764705882352941, "percentage": 5.88, "elapsed_time": "0:02:02", "remaining_time": "0:32:37"}
|
| 11 |
+
{"current_steps": 11, "total_steps": 170, "loss": 0.0626, "lr": 9.977082880559725e-05, "epoch": 0.12941176470588237, "percentage": 6.47, "elapsed_time": "0:02:14", "remaining_time": "0:32:17"}
|
| 12 |
+
{"current_steps": 12, "total_steps": 170, "loss": 0.0929, "lr": 9.967010448798375e-05, "epoch": 0.1411764705882353, "percentage": 7.06, "elapsed_time": "0:02:25", "remaining_time": "0:31:59"}
|
| 13 |
+
{"current_steps": 13, "total_steps": 170, "loss": 0.0845, "lr": 9.955115406644356e-05, "epoch": 0.15294117647058825, "percentage": 7.65, "elapsed_time": "0:02:37", "remaining_time": "0:31:42"}
|
| 14 |
+
{"current_steps": 14, "total_steps": 170, "loss": 0.0659, "lr": 9.941402118901744e-05, "epoch": 0.16470588235294117, "percentage": 8.24, "elapsed_time": "0:02:49", "remaining_time": "0:31:26"}
|
| 15 |
+
{"current_steps": 15, "total_steps": 170, "loss": 0.0531, "lr": 9.92587561756735e-05, "epoch": 0.17647058823529413, "percentage": 8.82, "elapsed_time": "0:03:01", "remaining_time": "0:31:10"}
|
| 16 |
+
{"current_steps": 16, "total_steps": 170, "loss": 0.0642, "lr": 9.908541599984276e-05, "epoch": 0.18823529411764706, "percentage": 9.41, "elapsed_time": "0:03:12", "remaining_time": "0:30:55"}
|
| 17 |
+
{"current_steps": 17, "total_steps": 170, "loss": 0.0588, "lr": 9.889406426751296e-05, "epoch": 0.2, "percentage": 10.0, "elapsed_time": "0:03:24", "remaining_time": "0:30:40"}
|
| 18 |
+
{"current_steps": 18, "total_steps": 170, "loss": 0.0649, "lr": 9.868477119388896e-05, "epoch": 0.21176470588235294, "percentage": 10.59, "elapsed_time": "0:03:36", "remaining_time": "0:30:25"}
|
| 19 |
+
{"current_steps": 19, "total_steps": 170, "loss": 0.0677, "lr": 9.84576135776276e-05, "epoch": 0.2235294117647059, "percentage": 11.18, "elapsed_time": "0:03:47", "remaining_time": "0:30:11"}
|
| 20 |
+
{"current_steps": 20, "total_steps": 170, "loss": 0.0606, "lr": 9.821267477265705e-05, "epoch": 0.23529411764705882, "percentage": 11.76, "elapsed_time": "0:03:59", "remaining_time": "0:29:57"}
|
| 21 |
+
{"current_steps": 21, "total_steps": 170, "loss": 0.0609, "lr": 9.795004465759065e-05, "epoch": 0.24705882352941178, "percentage": 12.35, "elapsed_time": "0:04:11", "remaining_time": "0:29:43"}
|
| 22 |
+
{"current_steps": 22, "total_steps": 170, "loss": 0.0475, "lr": 9.766981960274653e-05, "epoch": 0.25882352941176473, "percentage": 12.94, "elapsed_time": "0:04:23", "remaining_time": "0:29:29"}
|
| 23 |
+
{"current_steps": 23, "total_steps": 170, "loss": 0.0415, "lr": 9.737210243478521e-05, "epoch": 0.27058823529411763, "percentage": 13.53, "elapsed_time": "0:04:34", "remaining_time": "0:29:16"}
|
| 24 |
+
{"current_steps": 24, "total_steps": 170, "loss": 0.0474, "lr": 9.705700239897809e-05, "epoch": 0.2823529411764706, "percentage": 14.12, "elapsed_time": "0:04:46", "remaining_time": "0:29:02"}
|
| 25 |
+
{"current_steps": 25, "total_steps": 170, "loss": 0.0422, "lr": 9.672463511912055e-05, "epoch": 0.29411764705882354, "percentage": 14.71, "elapsed_time": "0:04:58", "remaining_time": "0:28:48"}
|
| 26 |
+
{"current_steps": 26, "total_steps": 170, "loss": 0.044, "lr": 9.637512255510475e-05, "epoch": 0.3058823529411765, "percentage": 15.29, "elapsed_time": "0:05:09", "remaining_time": "0:28:35"}
|
| 27 |
+
{"current_steps": 27, "total_steps": 170, "loss": 0.0398, "lr": 9.600859295816708e-05, "epoch": 0.3176470588235294, "percentage": 15.88, "elapsed_time": "0:05:21", "remaining_time": "0:28:22"}
|
| 28 |
+
{"current_steps": 28, "total_steps": 170, "loss": 0.0386, "lr": 9.56251808238275e-05, "epoch": 0.32941176470588235, "percentage": 16.47, "elapsed_time": "0:05:33", "remaining_time": "0:28:09"}
|
| 29 |
+
{"current_steps": 29, "total_steps": 170, "loss": 0.0432, "lr": 9.522502684253709e-05, "epoch": 0.3411764705882353, "percentage": 17.06, "elapsed_time": "0:05:44", "remaining_time": "0:27:57"}
|
| 30 |
+
{"current_steps": 30, "total_steps": 170, "loss": 0.0437, "lr": 9.480827784805278e-05, "epoch": 0.35294117647058826, "percentage": 17.65, "elapsed_time": "0:05:56", "remaining_time": "0:27:44"}
|
| 31 |
+
{"current_steps": 31, "total_steps": 170, "loss": 0.0361, "lr": 9.437508676355773e-05, "epoch": 0.36470588235294116, "percentage": 18.24, "elapsed_time": "0:06:08", "remaining_time": "0:27:31"}
|
| 32 |
+
{"current_steps": 32, "total_steps": 170, "loss": 0.0418, "lr": 9.392561254554713e-05, "epoch": 0.3764705882352941, "percentage": 18.82, "elapsed_time": "0:06:19", "remaining_time": "0:27:18"}
|
| 33 |
+
{"current_steps": 33, "total_steps": 170, "loss": 0.0392, "lr": 9.346002012550027e-05, "epoch": 0.38823529411764707, "percentage": 19.41, "elapsed_time": "0:06:31", "remaining_time": "0:27:06"}
|
| 34 |
+
{"current_steps": 34, "total_steps": 170, "loss": 0.0339, "lr": 9.297848034936006e-05, "epoch": 0.4, "percentage": 20.0, "elapsed_time": "0:06:43", "remaining_time": "0:26:54"}
|
| 35 |
+
{"current_steps": 35, "total_steps": 170, "loss": 0.0342, "lr": 9.248116991484229e-05, "epoch": 0.4117647058823529, "percentage": 20.59, "elapsed_time": "0:06:55", "remaining_time": "0:26:42"}
|
| 36 |
+
{"current_steps": 36, "total_steps": 170, "loss": 0.0288, "lr": 9.19682713065975e-05, "epoch": 0.4235294117647059, "percentage": 21.18, "elapsed_time": "0:07:07", "remaining_time": "0:26:30"}
|
| 37 |
+
{"current_steps": 37, "total_steps": 170, "loss": 0.0369, "lr": 9.143997272924973e-05, "epoch": 0.43529411764705883, "percentage": 21.76, "elapsed_time": "0:07:18", "remaining_time": "0:26:17"}
|
| 38 |
+
{"current_steps": 38, "total_steps": 170, "loss": 0.0342, "lr": 9.089646803833589e-05, "epoch": 0.4470588235294118, "percentage": 22.35, "elapsed_time": "0:07:30", "remaining_time": "0:26:05"}
|
| 39 |
+
{"current_steps": 39, "total_steps": 170, "loss": 0.0388, "lr": 9.033795666917191e-05, "epoch": 0.4588235294117647, "percentage": 22.94, "elapsed_time": "0:07:42", "remaining_time": "0:25:53"}
|
| 40 |
+
{"current_steps": 40, "total_steps": 170, "loss": 0.0345, "lr": 8.976464356367134e-05, "epoch": 0.47058823529411764, "percentage": 23.53, "elapsed_time": "0:07:54", "remaining_time": "0:25:41"}
|
| 41 |
+
{"current_steps": 41, "total_steps": 170, "loss": 0.0408, "lr": 8.917673909514322e-05, "epoch": 0.4823529411764706, "percentage": 24.12, "elapsed_time": "0:08:05", "remaining_time": "0:25:28"}
|
| 42 |
+
{"current_steps": 42, "total_steps": 170, "loss": 0.0319, "lr": 8.857445899109715e-05, "epoch": 0.49411764705882355, "percentage": 24.71, "elapsed_time": "0:08:17", "remaining_time": "0:25:16"}
|
| 43 |
+
{"current_steps": 43, "total_steps": 170, "loss": 0.0285, "lr": 8.795802425408352e-05, "epoch": 0.5058823529411764, "percentage": 25.29, "elapsed_time": "0:08:29", "remaining_time": "0:25:04"}
|
| 44 |
+
{"current_steps": 44, "total_steps": 170, "loss": 0.0322, "lr": 8.732766108059813e-05, "epoch": 0.5176470588235295, "percentage": 25.88, "elapsed_time": "0:08:41", "remaining_time": "0:24:52"}
|
| 45 |
+
{"current_steps": 45, "total_steps": 170, "loss": 0.0346, "lr": 8.668360077808093e-05, "epoch": 0.5294117647058824, "percentage": 26.47, "elapsed_time": "0:08:52", "remaining_time": "0:24:40"}
|
| 46 |
+
{"current_steps": 46, "total_steps": 170, "loss": 0.0402, "lr": 8.602607968003935e-05, "epoch": 0.5411764705882353, "percentage": 27.06, "elapsed_time": "0:09:04", "remaining_time": "0:24:27"}
|
| 47 |
+
{"current_steps": 47, "total_steps": 170, "loss": 0.0262, "lr": 8.535533905932738e-05, "epoch": 0.5529411764705883, "percentage": 27.65, "elapsed_time": "0:09:16", "remaining_time": "0:24:15"}
|
| 48 |
+
{"current_steps": 48, "total_steps": 170, "loss": 0.0274, "lr": 8.467162503961208e-05, "epoch": 0.5647058823529412, "percentage": 28.24, "elapsed_time": "0:09:27", "remaining_time": "0:24:03"}
|
| 49 |
+
{"current_steps": 49, "total_steps": 170, "loss": 0.0321, "lr": 8.397518850506028e-05, "epoch": 0.5764705882352941, "percentage": 28.82, "elapsed_time": "0:09:39", "remaining_time": "0:23:51"}
|
| 50 |
+
{"current_steps": 50, "total_steps": 170, "loss": 0.0348, "lr": 8.326628500827826e-05, "epoch": 0.5882352941176471, "percentage": 29.41, "elapsed_time": "0:09:51", "remaining_time": "0:23:39"}
|
| 51 |
+
{"current_steps": 51, "total_steps": 170, "loss": 0.0286, "lr": 8.254517467653858e-05, "epoch": 0.6, "percentage": 30.0, "elapsed_time": "0:10:03", "remaining_time": "0:23:27"}
|
| 52 |
+
{"current_steps": 52, "total_steps": 170, "loss": 0.0335, "lr": 8.181212211632799e-05, "epoch": 0.611764705882353, "percentage": 30.59, "elapsed_time": "0:10:14", "remaining_time": "0:23:15"}
|
| 53 |
+
{"current_steps": 53, "total_steps": 170, "loss": 0.0351, "lr": 8.106739631625217e-05, "epoch": 0.6235294117647059, "percentage": 31.18, "elapsed_time": "0:10:26", "remaining_time": "0:23:02"}
|
| 54 |
+
{"current_steps": 54, "total_steps": 170, "loss": 0.0292, "lr": 8.03112705483319e-05, "epoch": 0.6352941176470588, "percentage": 31.76, "elapsed_time": "0:10:38", "remaining_time": "0:22:50"}
|
| 55 |
+
{"current_steps": 55, "total_steps": 170, "loss": 0.0315, "lr": 7.954402226772804e-05, "epoch": 0.6470588235294118, "percentage": 32.35, "elapsed_time": "0:10:49", "remaining_time": "0:22:38"}
|
| 56 |
+
{"current_steps": 56, "total_steps": 170, "loss": 0.0376, "lr": 7.876593301093104e-05, "epoch": 0.6588235294117647, "percentage": 32.94, "elapsed_time": "0:11:01", "remaining_time": "0:22:26"}
|
| 57 |
+
{"current_steps": 57, "total_steps": 170, "loss": 0.0298, "lr": 7.797728829245321e-05, "epoch": 0.6705882352941176, "percentage": 33.53, "elapsed_time": "0:11:13", "remaining_time": "0:22:14"}
|
| 58 |
+
{"current_steps": 58, "total_steps": 170, "loss": 0.0285, "lr": 7.717837750006106e-05, "epoch": 0.6823529411764706, "percentage": 34.12, "elapsed_time": "0:11:24", "remaining_time": "0:22:02"}
|
| 59 |
+
{"current_steps": 59, "total_steps": 170, "loss": 0.0323, "lr": 7.636949378858646e-05, "epoch": 0.6941176470588235, "percentage": 34.71, "elapsed_time": "0:11:36", "remaining_time": "0:21:50"}
|
| 60 |
+
{"current_steps": 60, "total_steps": 170, "loss": 0.0374, "lr": 7.555093397235552e-05, "epoch": 0.7058823529411765, "percentage": 35.29, "elapsed_time": "0:11:48", "remaining_time": "0:21:38"}
|
| 61 |
+
{"current_steps": 61, "total_steps": 170, "loss": 0.0305, "lr": 7.472299841627451e-05, "epoch": 0.7176470588235294, "percentage": 35.88, "elapsed_time": "0:12:00", "remaining_time": "0:21:26"}
|
| 62 |
+
{"current_steps": 62, "total_steps": 170, "loss": 0.0305, "lr": 7.388599092561315e-05, "epoch": 0.7294117647058823, "percentage": 36.47, "elapsed_time": "0:12:11", "remaining_time": "0:21:14"}
|
| 63 |
+
{"current_steps": 63, "total_steps": 170, "loss": 0.0337, "lr": 7.304021863452524e-05, "epoch": 0.7411764705882353, "percentage": 37.06, "elapsed_time": "0:12:23", "remaining_time": "0:21:02"}
|
| 64 |
+
{"current_steps": 64, "total_steps": 170, "loss": 0.0268, "lr": 7.218599189334799e-05, "epoch": 0.7529411764705882, "percentage": 37.65, "elapsed_time": "0:12:35", "remaining_time": "0:20:50"}
|
| 65 |
+
{"current_steps": 65, "total_steps": 170, "loss": 0.0333, "lr": 7.1323624154721e-05, "epoch": 0.7647058823529411, "percentage": 38.24, "elapsed_time": "0:12:46", "remaining_time": "0:20:38"}
|
| 66 |
+
{"current_steps": 66, "total_steps": 170, "loss": 0.0367, "lr": 7.045343185856701e-05, "epoch": 0.7764705882352941, "percentage": 38.82, "elapsed_time": "0:12:58", "remaining_time": "0:20:26"}
|
| 67 |
+
{"current_steps": 67, "total_steps": 170, "loss": 0.0327, "lr": 6.957573431597646e-05, "epoch": 0.788235294117647, "percentage": 39.41, "elapsed_time": "0:13:10", "remaining_time": "0:20:14"}
|
| 68 |
+
{"current_steps": 68, "total_steps": 170, "loss": 0.0309, "lr": 6.869085359203844e-05, "epoch": 0.8, "percentage": 40.0, "elapsed_time": "0:13:22", "remaining_time": "0:20:03"}
|
| 69 |
+
{"current_steps": 69, "total_steps": 170, "loss": 0.0327, "lr": 6.779911438766116e-05, "epoch": 0.8117647058823529, "percentage": 40.59, "elapsed_time": "0:13:33", "remaining_time": "0:19:50"}
|
| 70 |
+
{"current_steps": 70, "total_steps": 170, "loss": 0.0312, "lr": 6.690084392042513e-05, "epoch": 0.8235294117647058, "percentage": 41.18, "elapsed_time": "0:13:45", "remaining_time": "0:19:38"}
|
| 71 |
+
{"current_steps": 71, "total_steps": 170, "loss": 0.0348, "lr": 6.599637180451294e-05, "epoch": 0.8352941176470589, "percentage": 41.76, "elapsed_time": "0:13:56", "remaining_time": "0:19:26"}
|
| 72 |
+
{"current_steps": 72, "total_steps": 170, "loss": 0.0317, "lr": 6.508602992975963e-05, "epoch": 0.8470588235294118, "percentage": 42.35, "elapsed_time": "0:14:08", "remaining_time": "0:19:15"}
|
| 73 |
+
{"current_steps": 73, "total_steps": 170, "loss": 0.0311, "lr": 6.417015233986786e-05, "epoch": 0.8588235294117647, "percentage": 42.94, "elapsed_time": "0:14:20", "remaining_time": "0:19:03"}
|
| 74 |
+
{"current_steps": 74, "total_steps": 170, "loss": 0.0263, "lr": 6.32490751098331e-05, "epoch": 0.8705882352941177, "percentage": 43.53, "elapsed_time": "0:14:32", "remaining_time": "0:18:51"}
|
| 75 |
+
{"current_steps": 75, "total_steps": 170, "loss": 0.0343, "lr": 6.232313622262296e-05, "epoch": 0.8823529411764706, "percentage": 44.12, "elapsed_time": "0:14:43", "remaining_time": "0:18:39"}
|
| 76 |
+
{"current_steps": 76, "total_steps": 170, "loss": 0.0304, "lr": 6.139267544515689e-05, "epoch": 0.8941176470588236, "percentage": 44.71, "elapsed_time": "0:14:55", "remaining_time": "0:18:27"}
|
| 77 |
+
{"current_steps": 77, "total_steps": 170, "loss": 0.0318, "lr": 6.045803420363084e-05, "epoch": 0.9058823529411765, "percentage": 45.29, "elapsed_time": "0:15:07", "remaining_time": "0:18:15"}
|
| 78 |
+
{"current_steps": 78, "total_steps": 170, "loss": 0.0286, "lr": 5.951955545823342e-05, "epoch": 0.9176470588235294, "percentage": 45.88, "elapsed_time": "0:15:18", "remaining_time": "0:18:03"}
|
| 79 |
+
{"current_steps": 79, "total_steps": 170, "loss": 0.0297, "lr": 5.8577583577298924e-05, "epoch": 0.9294117647058824, "percentage": 46.47, "elapsed_time": "0:15:30", "remaining_time": "0:17:51"}
|
| 80 |
+
{"current_steps": 80, "total_steps": 170, "loss": 0.0261, "lr": 5.7632464210943726e-05, "epoch": 0.9411764705882353, "percentage": 47.06, "elapsed_time": "0:15:42", "remaining_time": "0:17:39"}
|
| 81 |
+
{"current_steps": 81, "total_steps": 170, "loss": 0.026, "lr": 5.668454416423242e-05, "epoch": 0.9529411764705882, "percentage": 47.65, "elapsed_time": "0:15:53", "remaining_time": "0:17:28"}
|
| 82 |
+
{"current_steps": 82, "total_steps": 170, "loss": 0.0266, "lr": 5.573417126992003e-05, "epoch": 0.9647058823529412, "percentage": 48.24, "elapsed_time": "0:16:05", "remaining_time": "0:17:16"}
|
| 83 |
+
{"current_steps": 83, "total_steps": 170, "loss": 0.0295, "lr": 5.478169426081712e-05, "epoch": 0.9764705882352941, "percentage": 48.82, "elapsed_time": "0:16:17", "remaining_time": "0:17:04"}
|
| 84 |
+
{"current_steps": 84, "total_steps": 170, "loss": 0.0292, "lr": 5.38274626418248e-05, "epoch": 0.9882352941176471, "percentage": 49.41, "elapsed_time": "0:16:28", "remaining_time": "0:16:52"}
|
| 85 |
+
{"current_steps": 85, "total_steps": 170, "loss": 0.0287, "lr": 5.287182656168618e-05, "epoch": 1.0, "percentage": 50.0, "elapsed_time": "0:16:40", "remaining_time": "0:16:40"}
|
| 86 |
+
{"current_steps": 86, "total_steps": 170, "loss": 0.0275, "lr": 5.191513668450178e-05, "epoch": 1.011764705882353, "percentage": 50.59, "elapsed_time": "0:16:52", "remaining_time": "0:16:28"}
|
| 87 |
+
{"current_steps": 87, "total_steps": 170, "loss": 0.0245, "lr": 5.095774406105571e-05, "epoch": 1.0235294117647058, "percentage": 51.18, "elapsed_time": "0:17:03", "remaining_time": "0:16:16"}
|
| 88 |
+
{"current_steps": 88, "total_steps": 170, "loss": 0.0227, "lr": 5e-05, "epoch": 1.035294117647059, "percentage": 51.76, "elapsed_time": "0:17:15", "remaining_time": "0:16:04"}
|
| 89 |
+
{"current_steps": 89, "total_steps": 170, "loss": 0.0284, "lr": 4.9042255938944296e-05, "epoch": 1.0470588235294118, "percentage": 52.35, "elapsed_time": "0:17:27", "remaining_time": "0:15:53"}
|
| 90 |
+
{"current_steps": 90, "total_steps": 170, "loss": 0.0256, "lr": 4.8084863315498234e-05, "epoch": 1.0588235294117647, "percentage": 52.94, "elapsed_time": "0:17:39", "remaining_time": "0:15:41"}
|
| 91 |
+
{"current_steps": 91, "total_steps": 170, "loss": 0.028, "lr": 4.712817343831384e-05, "epoch": 1.0705882352941176, "percentage": 53.53, "elapsed_time": "0:17:50", "remaining_time": "0:15:29"}
|
| 92 |
+
{"current_steps": 92, "total_steps": 170, "loss": 0.0269, "lr": 4.6172537358175214e-05, "epoch": 1.0823529411764705, "percentage": 54.12, "elapsed_time": "0:18:02", "remaining_time": "0:15:17"}
|
| 93 |
+
{"current_steps": 93, "total_steps": 170, "loss": 0.0268, "lr": 4.521830573918289e-05, "epoch": 1.0941176470588236, "percentage": 54.71, "elapsed_time": "0:18:14", "remaining_time": "0:15:05"}
|
| 94 |
+
{"current_steps": 94, "total_steps": 170, "loss": 0.0287, "lr": 4.4265828730079987e-05, "epoch": 1.1058823529411765, "percentage": 55.29, "elapsed_time": "0:18:25", "remaining_time": "0:14:53"}
|
| 95 |
+
{"current_steps": 95, "total_steps": 170, "loss": 0.0254, "lr": 4.331545583576758e-05, "epoch": 1.1176470588235294, "percentage": 55.88, "elapsed_time": "0:18:37", "remaining_time": "0:14:42"}
|
| 96 |
+
{"current_steps": 96, "total_steps": 170, "loss": 0.0257, "lr": 4.236753578905627e-05, "epoch": 1.1294117647058823, "percentage": 56.47, "elapsed_time": "0:18:49", "remaining_time": "0:14:30"}
|
| 97 |
+
{"current_steps": 97, "total_steps": 170, "loss": 0.023, "lr": 4.142241642270108e-05, "epoch": 1.1411764705882352, "percentage": 57.06, "elapsed_time": "0:19:00", "remaining_time": "0:14:18"}
|
| 98 |
+
{"current_steps": 98, "total_steps": 170, "loss": 0.0227, "lr": 4.0480444541766576e-05, "epoch": 1.1529411764705881, "percentage": 57.65, "elapsed_time": "0:19:12", "remaining_time": "0:14:06"}
|
| 99 |
+
{"current_steps": 99, "total_steps": 170, "loss": 0.025, "lr": 3.954196579636918e-05, "epoch": 1.1647058823529413, "percentage": 58.24, "elapsed_time": "0:19:24", "remaining_time": "0:13:55"}
|
| 100 |
+
{"current_steps": 100, "total_steps": 170, "loss": 0.0245, "lr": 3.8607324554843136e-05, "epoch": 1.1764705882352942, "percentage": 58.82, "elapsed_time": "0:19:35", "remaining_time": "0:13:43"}
|
| 101 |
+
{"current_steps": 101, "total_steps": 170, "loss": 0.0251, "lr": 3.7676863777377054e-05, "epoch": 1.188235294117647, "percentage": 59.41, "elapsed_time": "0:19:47", "remaining_time": "0:13:31"}
|
| 102 |
+
{"current_steps": 102, "total_steps": 170, "loss": 0.0258, "lr": 3.675092489016693e-05, "epoch": 1.2, "percentage": 60.0, "elapsed_time": "0:19:59", "remaining_time": "0:13:19"}
|
| 103 |
+
{"current_steps": 103, "total_steps": 170, "loss": 0.0254, "lr": 3.582984766013215e-05, "epoch": 1.2117647058823529, "percentage": 60.59, "elapsed_time": "0:20:11", "remaining_time": "0:13:07"}
|
| 104 |
+
{"current_steps": 104, "total_steps": 170, "loss": 0.0317, "lr": 3.4913970070240386e-05, "epoch": 1.223529411764706, "percentage": 61.18, "elapsed_time": "0:20:22", "remaining_time": "0:12:55"}
|
| 105 |
+
{"current_steps": 105, "total_steps": 170, "loss": 0.0272, "lr": 3.4003628195487057e-05, "epoch": 1.2352941176470589, "percentage": 61.76, "elapsed_time": "0:20:34", "remaining_time": "0:12:44"}
|
| 106 |
+
{"current_steps": 106, "total_steps": 170, "loss": 0.0256, "lr": 3.309915607957487e-05, "epoch": 1.2470588235294118, "percentage": 62.35, "elapsed_time": "0:20:46", "remaining_time": "0:12:32"}
|
| 107 |
+
{"current_steps": 107, "total_steps": 170, "loss": 0.0207, "lr": 3.2200885612338845e-05, "epoch": 1.2588235294117647, "percentage": 62.94, "elapsed_time": "0:20:57", "remaining_time": "0:12:20"}
|
| 108 |
+
{"current_steps": 108, "total_steps": 170, "loss": 0.0297, "lr": 3.130914640796157e-05, "epoch": 1.2705882352941176, "percentage": 63.53, "elapsed_time": "0:21:09", "remaining_time": "0:12:08"}
|
| 109 |
+
{"current_steps": 109, "total_steps": 170, "loss": 0.0238, "lr": 3.0424265684023558e-05, "epoch": 1.2823529411764705, "percentage": 64.12, "elapsed_time": "0:21:21", "remaining_time": "0:11:57"}
|
| 110 |
+
{"current_steps": 110, "total_steps": 170, "loss": 0.0247, "lr": 2.9546568141433006e-05, "epoch": 1.2941176470588236, "percentage": 64.71, "elapsed_time": "0:21:33", "remaining_time": "0:11:45"}
|
| 111 |
+
{"current_steps": 111, "total_steps": 170, "loss": 0.0271, "lr": 2.8676375845279013e-05, "epoch": 1.3058823529411765, "percentage": 65.29, "elapsed_time": "0:21:44", "remaining_time": "0:11:33"}
|
| 112 |
+
{"current_steps": 112, "total_steps": 170, "loss": 0.0253, "lr": 2.7814008106652012e-05, "epoch": 1.3176470588235294, "percentage": 65.88, "elapsed_time": "0:21:56", "remaining_time": "0:11:21"}
|
| 113 |
+
{"current_steps": 113, "total_steps": 170, "loss": 0.0196, "lr": 2.6959781365474758e-05, "epoch": 1.3294117647058823, "percentage": 66.47, "elapsed_time": "0:22:08", "remaining_time": "0:11:09"}
|
| 114 |
+
{"current_steps": 114, "total_steps": 170, "loss": 0.025, "lr": 2.6114009074386846e-05, "epoch": 1.3411764705882354, "percentage": 67.06, "elapsed_time": "0:22:19", "remaining_time": "0:10:58"}
|
| 115 |
+
{"current_steps": 115, "total_steps": 170, "loss": 0.0245, "lr": 2.527700158372548e-05, "epoch": 1.3529411764705883, "percentage": 67.65, "elapsed_time": "0:22:31", "remaining_time": "0:10:46"}
|
| 116 |
+
{"current_steps": 116, "total_steps": 170, "loss": 0.0202, "lr": 2.4449066027644475e-05, "epoch": 1.3647058823529412, "percentage": 68.24, "elapsed_time": "0:22:43", "remaining_time": "0:10:34"}
|
| 117 |
+
{"current_steps": 117, "total_steps": 170, "loss": 0.0269, "lr": 2.363050621141354e-05, "epoch": 1.3764705882352941, "percentage": 68.82, "elapsed_time": "0:22:54", "remaining_time": "0:10:22"}
|
| 118 |
+
{"current_steps": 118, "total_steps": 170, "loss": 0.0259, "lr": 2.282162249993895e-05, "epoch": 1.388235294117647, "percentage": 69.41, "elapsed_time": "0:23:06", "remaining_time": "0:10:11"}
|
| 119 |
+
{"current_steps": 119, "total_steps": 170, "loss": 0.0263, "lr": 2.20227117075468e-05, "epoch": 1.4, "percentage": 70.0, "elapsed_time": "0:23:18", "remaining_time": "0:09:59"}
|
| 120 |
+
{"current_steps": 120, "total_steps": 170, "loss": 0.0237, "lr": 2.1234066989068972e-05, "epoch": 1.4117647058823528, "percentage": 70.59, "elapsed_time": "0:23:30", "remaining_time": "0:09:47"}
|
| 121 |
+
{"current_steps": 121, "total_steps": 170, "loss": 0.0221, "lr": 2.0455977732271993e-05, "epoch": 1.423529411764706, "percentage": 71.18, "elapsed_time": "0:23:41", "remaining_time": "0:09:35"}
|
| 122 |
+
{"current_steps": 122, "total_steps": 170, "loss": 0.0203, "lr": 1.9688729451668114e-05, "epoch": 1.4352941176470588, "percentage": 71.76, "elapsed_time": "0:23:53", "remaining_time": "0:09:23"}
|
| 123 |
+
{"current_steps": 123, "total_steps": 170, "loss": 0.0271, "lr": 1.893260368374786e-05, "epoch": 1.4470588235294117, "percentage": 72.35, "elapsed_time": "0:24:05", "remaining_time": "0:09:12"}
|
| 124 |
+
{"current_steps": 124, "total_steps": 170, "loss": 0.0241, "lr": 1.818787788367202e-05, "epoch": 1.4588235294117646, "percentage": 72.94, "elapsed_time": "0:24:16", "remaining_time": "0:09:00"}
|
| 125 |
+
{"current_steps": 125, "total_steps": 170, "loss": 0.0227, "lr": 1.7454825323461448e-05, "epoch": 1.4705882352941178, "percentage": 73.53, "elapsed_time": "0:24:28", "remaining_time": "0:08:48"}
|
| 126 |
+
{"current_steps": 126, "total_steps": 170, "loss": 0.0282, "lr": 1.673371499172174e-05, "epoch": 1.4823529411764707, "percentage": 74.12, "elapsed_time": "0:24:40", "remaining_time": "0:08:36"}
|
| 127 |
+
{"current_steps": 127, "total_steps": 170, "loss": 0.022, "lr": 1.6024811494939724e-05, "epoch": 1.4941176470588236, "percentage": 74.71, "elapsed_time": "0:24:51", "remaining_time": "0:08:25"}
|
| 128 |
+
{"current_steps": 128, "total_steps": 170, "loss": 0.0247, "lr": 1.532837496038792e-05, "epoch": 1.5058823529411764, "percentage": 75.29, "elapsed_time": "0:25:03", "remaining_time": "0:08:13"}
|
| 129 |
+
{"current_steps": 129, "total_steps": 170, "loss": 0.0257, "lr": 1.4644660940672627e-05, "epoch": 1.5176470588235293, "percentage": 75.88, "elapsed_time": "0:25:15", "remaining_time": "0:08:01"}
|
| 130 |
+
{"current_steps": 130, "total_steps": 170, "loss": 0.0217, "lr": 1.3973920319960655e-05, "epoch": 1.5294117647058822, "percentage": 76.47, "elapsed_time": "0:25:27", "remaining_time": "0:07:49"}
|
| 131 |
+
{"current_steps": 131, "total_steps": 170, "loss": 0.0232, "lr": 1.3316399221919074e-05, "epoch": 1.5411764705882351, "percentage": 77.06, "elapsed_time": "0:25:38", "remaining_time": "0:07:38"}
|
| 132 |
+
{"current_steps": 132, "total_steps": 170, "loss": 0.0225, "lr": 1.2672338919401866e-05, "epoch": 1.5529411764705883, "percentage": 77.65, "elapsed_time": "0:25:50", "remaining_time": "0:07:26"}
|
| 133 |
+
{"current_steps": 133, "total_steps": 170, "loss": 0.0269, "lr": 1.2041975745916472e-05, "epoch": 1.5647058823529412, "percentage": 78.24, "elapsed_time": "0:26:02", "remaining_time": "0:07:14"}
|
| 134 |
+
{"current_steps": 134, "total_steps": 170, "loss": 0.0249, "lr": 1.1425541008902851e-05, "epoch": 1.576470588235294, "percentage": 78.82, "elapsed_time": "0:26:13", "remaining_time": "0:07:02"}
|
| 135 |
+
{"current_steps": 135, "total_steps": 170, "loss": 0.0255, "lr": 1.082326090485679e-05, "epoch": 1.5882352941176472, "percentage": 79.41, "elapsed_time": "0:26:25", "remaining_time": "0:06:51"}
|
| 136 |
+
{"current_steps": 136, "total_steps": 170, "loss": 0.0286, "lr": 1.0235356436328675e-05, "epoch": 1.6, "percentage": 80.0, "elapsed_time": "0:26:37", "remaining_time": "0:06:39"}
|
| 137 |
+
{"current_steps": 137, "total_steps": 170, "loss": 0.0201, "lr": 9.662043330828085e-06, "epoch": 1.611764705882353, "percentage": 80.59, "elapsed_time": "0:26:48", "remaining_time": "0:06:27"}
|
| 138 |
+
{"current_steps": 138, "total_steps": 170, "loss": 0.0212, "lr": 9.103531961664118e-06, "epoch": 1.6235294117647059, "percentage": 81.18, "elapsed_time": "0:27:00", "remaining_time": "0:06:15"}
|
| 139 |
+
{"current_steps": 139, "total_steps": 170, "loss": 0.0244, "lr": 8.560027270750277e-06, "epoch": 1.6352941176470588, "percentage": 81.76, "elapsed_time": "0:27:12", "remaining_time": "0:06:04"}
|
| 140 |
+
{"current_steps": 140, "total_steps": 170, "loss": 0.0193, "lr": 8.031728693402502e-06, "epoch": 1.6470588235294117, "percentage": 82.35, "elapsed_time": "0:27:24", "remaining_time": "0:05:52"}
|
| 141 |
+
{"current_steps": 141, "total_steps": 170, "loss": 0.0232, "lr": 7.518830085157735e-06, "epoch": 1.6588235294117646, "percentage": 82.94, "elapsed_time": "0:27:35", "remaining_time": "0:05:40"}
|
| 142 |
+
{"current_steps": 142, "total_steps": 170, "loss": 0.0217, "lr": 7.0215196506399515e-06, "epoch": 1.6705882352941175, "percentage": 83.53, "elapsed_time": "0:27:47", "remaining_time": "0:05:28"}
|
| 143 |
+
{"current_steps": 143, "total_steps": 170, "loss": 0.0213, "lr": 6.539979874499747e-06, "epoch": 1.6823529411764706, "percentage": 84.12, "elapsed_time": "0:27:59", "remaining_time": "0:05:17"}
|
| 144 |
+
{"current_steps": 144, "total_steps": 170, "loss": 0.0234, "lr": 6.07438745445289e-06, "epoch": 1.6941176470588235, "percentage": 84.71, "elapsed_time": "0:28:10", "remaining_time": "0:05:05"}
|
| 145 |
+
{"current_steps": 145, "total_steps": 170, "loss": 0.0294, "lr": 5.624913236442286e-06, "epoch": 1.7058823529411766, "percentage": 85.29, "elapsed_time": "0:28:22", "remaining_time": "0:04:53"}
|
| 146 |
+
{"current_steps": 146, "total_steps": 170, "loss": 0.0258, "lr": 5.191722151947226e-06, "epoch": 1.7176470588235295, "percentage": 85.88, "elapsed_time": "0:28:34", "remaining_time": "0:04:41"}
|
| 147 |
+
{"current_steps": 147, "total_steps": 170, "loss": 0.0224, "lr": 4.7749731574629196e-06, "epoch": 1.7294117647058824, "percentage": 86.47, "elapsed_time": "0:28:45", "remaining_time": "0:04:30"}
|
| 148 |
+
{"current_steps": 148, "total_steps": 170, "loss": 0.021, "lr": 4.374819176172501e-06, "epoch": 1.7411764705882353, "percentage": 87.06, "elapsed_time": "0:28:57", "remaining_time": "0:04:18"}
|
| 149 |
+
{"current_steps": 149, "total_steps": 170, "loss": 0.022, "lr": 3.991407041832912e-06, "epoch": 1.7529411764705882, "percentage": 87.65, "elapsed_time": "0:29:09", "remaining_time": "0:04:06"}
|
| 150 |
+
{"current_steps": 150, "total_steps": 170, "loss": 0.0265, "lr": 3.6248774448952695e-06, "epoch": 1.7647058823529411, "percentage": 88.24, "elapsed_time": "0:29:20", "remaining_time": "0:03:54"}
|
| 151 |
+
{"current_steps": 151, "total_steps": 170, "loss": 0.024, "lr": 3.2753648808794503e-06, "epoch": 1.776470588235294, "percentage": 88.82, "elapsed_time": "0:29:32", "remaining_time": "0:03:43"}
|
| 152 |
+
{"current_steps": 152, "total_steps": 170, "loss": 0.0257, "lr": 2.942997601021924e-06, "epoch": 1.788235294117647, "percentage": 89.41, "elapsed_time": "0:29:44", "remaining_time": "0:03:31"}
|
| 153 |
+
{"current_steps": 153, "total_steps": 170, "loss": 0.0232, "lr": 2.6278975652147875e-06, "epoch": 1.8, "percentage": 90.0, "elapsed_time": "0:29:55", "remaining_time": "0:03:19"}
|
| 154 |
+
{"current_steps": 154, "total_steps": 170, "loss": 0.0232, "lr": 2.330180397253473e-06, "epoch": 1.811764705882353, "percentage": 90.59, "elapsed_time": "0:30:07", "remaining_time": "0:03:07"}
|
| 155 |
+
{"current_steps": 155, "total_steps": 170, "loss": 0.0227, "lr": 2.049955342409349e-06, "epoch": 1.8235294117647058, "percentage": 91.18, "elapsed_time": "0:30:19", "remaining_time": "0:02:56"}
|
| 156 |
+
{"current_steps": 156, "total_steps": 170, "loss": 0.0224, "lr": 1.7873252273429509e-06, "epoch": 1.835294117647059, "percentage": 91.76, "elapsed_time": "0:30:31", "remaining_time": "0:02:44"}
|
| 157 |
+
{"current_steps": 157, "total_steps": 170, "loss": 0.0208, "lr": 1.542386422372405e-06, "epoch": 1.8470588235294119, "percentage": 92.35, "elapsed_time": "0:30:42", "remaining_time": "0:02:32"}
|
| 158 |
+
{"current_steps": 158, "total_steps": 170, "loss": 0.0237, "lr": 1.3152288061110518e-06, "epoch": 1.8588235294117648, "percentage": 92.94, "elapsed_time": "0:30:54", "remaining_time": "0:02:20"}
|
| 159 |
+
{"current_steps": 159, "total_steps": 170, "loss": 0.0212, "lr": 1.1059357324870455e-06, "epoch": 1.8705882352941177, "percentage": 93.53, "elapsed_time": "0:31:06", "remaining_time": "0:02:09"}
|
| 160 |
+
{"current_steps": 160, "total_steps": 170, "loss": 0.0209, "lr": 9.145840001572537e-07, "epoch": 1.8823529411764706, "percentage": 94.12, "elapsed_time": "0:31:18", "remaining_time": "0:01:57"}
|
| 161 |
+
{"current_steps": 161, "total_steps": 170, "loss": 0.0237, "lr": 7.41243824326504e-07, "epoch": 1.8941176470588235, "percentage": 94.71, "elapsed_time": "0:31:29", "remaining_time": "0:01:45"}
|
| 162 |
+
{"current_steps": 162, "total_steps": 170, "loss": 0.0263, "lr": 5.859788109825793e-07, "epoch": 1.9058823529411764, "percentage": 95.29, "elapsed_time": "0:31:41", "remaining_time": "0:01:33"}
|
| 163 |
+
{"current_steps": 163, "total_steps": 170, "loss": 0.025, "lr": 4.48845933556441e-07, "epoch": 1.9176470588235293, "percentage": 95.88, "elapsed_time": "0:31:53", "remaining_time": "0:01:22"}
|
| 164 |
+
{"current_steps": 164, "total_steps": 170, "loss": 0.0215, "lr": 3.2989551201624835e-07, "epoch": 1.9294117647058824, "percentage": 96.47, "elapsed_time": "0:32:04", "remaining_time": "0:01:10"}
|
| 165 |
+
{"current_steps": 165, "total_steps": 170, "loss": 0.0273, "lr": 2.2917119440275524e-07, "epoch": 1.9411764705882353, "percentage": 97.06, "elapsed_time": "0:32:16", "remaining_time": "0:00:58"}
|
| 166 |
+
{"current_steps": 166, "total_steps": 170, "loss": 0.0251, "lr": 1.4670994081297795e-07, "epoch": 1.9529411764705882, "percentage": 97.65, "elapsed_time": "0:32:28", "remaining_time": "0:00:46"}
|
| 167 |
+
{"current_steps": 167, "total_steps": 170, "loss": 0.0273, "lr": 8.254200983794369e-08, "epoch": 1.9647058823529413, "percentage": 98.24, "elapsed_time": "0:32:40", "remaining_time": "0:00:35"}
|
| 168 |
+
{"current_steps": 168, "total_steps": 170, "loss": 0.0239, "lr": 3.669094745950008e-08, "epoch": 1.9764705882352942, "percentage": 98.82, "elapsed_time": "0:32:51", "remaining_time": "0:00:23"}
|
| 169 |
+
{"current_steps": 169, "total_steps": 170, "loss": 0.0207, "lr": 9.17357841028199e-09, "epoch": 1.988235294117647, "percentage": 99.41, "elapsed_time": "0:33:03", "remaining_time": "0:00:11"}
|
| 170 |
+
{"current_steps": 170, "total_steps": 170, "loss": 0.0232, "lr": 0.0, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "0:33:15", "remaining_time": "0:00:00"}
|
| 171 |
+
{"current_steps": 170, "total_steps": 170, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "0:33:56", "remaining_time": "0:00:00"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1232 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"eval_steps": 200,
|
| 6 |
+
"global_step": 170,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.011764705882352941,
|
| 13 |
+
"grad_norm": 0.035323630468616266,
|
| 14 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 15 |
+
"loss": 0.1079,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.023529411764705882,
|
| 20 |
+
"grad_norm": 0.03136221824048882,
|
| 21 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 22 |
+
"loss": 0.1141,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.03529411764705882,
|
| 27 |
+
"grad_norm": 0.03804619743095702,
|
| 28 |
+
"learning_rate": 5e-05,
|
| 29 |
+
"loss": 0.1204,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.047058823529411764,
|
| 34 |
+
"grad_norm": 0.04070206833240694,
|
| 35 |
+
"learning_rate": 6.666666666666667e-05,
|
| 36 |
+
"loss": 0.1276,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.058823529411764705,
|
| 41 |
+
"grad_norm": 0.07589226019496102,
|
| 42 |
+
"learning_rate": 8.333333333333334e-05,
|
| 43 |
+
"loss": 0.1689,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.07058823529411765,
|
| 48 |
+
"grad_norm": 0.07319090807548947,
|
| 49 |
+
"learning_rate": 0.0001,
|
| 50 |
+
"loss": 0.1345,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.08235294117647059,
|
| 55 |
+
"grad_norm": 0.06996995505114396,
|
| 56 |
+
"learning_rate": 9.999082642158973e-05,
|
| 57 |
+
"loss": 0.1202,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.09411764705882353,
|
| 62 |
+
"grad_norm": 0.05248182376644038,
|
| 63 |
+
"learning_rate": 9.99633090525405e-05,
|
| 64 |
+
"loss": 0.0983,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.10588235294117647,
|
| 69 |
+
"grad_norm": 0.06219777780481942,
|
| 70 |
+
"learning_rate": 9.991745799016206e-05,
|
| 71 |
+
"loss": 0.0954,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.11764705882352941,
|
| 76 |
+
"grad_norm": 0.06595531802798588,
|
| 77 |
+
"learning_rate": 9.985329005918702e-05,
|
| 78 |
+
"loss": 0.0977,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.12941176470588237,
|
| 83 |
+
"grad_norm": 0.03606112500648923,
|
| 84 |
+
"learning_rate": 9.977082880559725e-05,
|
| 85 |
+
"loss": 0.0626,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.1411764705882353,
|
| 90 |
+
"grad_norm": 0.0722550944651642,
|
| 91 |
+
"learning_rate": 9.967010448798375e-05,
|
| 92 |
+
"loss": 0.0929,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.15294117647058825,
|
| 97 |
+
"grad_norm": 0.054771186088142604,
|
| 98 |
+
"learning_rate": 9.955115406644356e-05,
|
| 99 |
+
"loss": 0.0845,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.16470588235294117,
|
| 104 |
+
"grad_norm": 0.051628745573165394,
|
| 105 |
+
"learning_rate": 9.941402118901744e-05,
|
| 106 |
+
"loss": 0.0659,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.17647058823529413,
|
| 111 |
+
"grad_norm": 0.0486190850226073,
|
| 112 |
+
"learning_rate": 9.92587561756735e-05,
|
| 113 |
+
"loss": 0.0531,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.18823529411764706,
|
| 118 |
+
"grad_norm": 0.05588842841049585,
|
| 119 |
+
"learning_rate": 9.908541599984276e-05,
|
| 120 |
+
"loss": 0.0642,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.2,
|
| 125 |
+
"grad_norm": 0.05641046123379798,
|
| 126 |
+
"learning_rate": 9.889406426751296e-05,
|
| 127 |
+
"loss": 0.0588,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.21176470588235294,
|
| 132 |
+
"grad_norm": 0.054058284278693136,
|
| 133 |
+
"learning_rate": 9.868477119388896e-05,
|
| 134 |
+
"loss": 0.0649,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.2235294117647059,
|
| 139 |
+
"grad_norm": 0.0531804463754218,
|
| 140 |
+
"learning_rate": 9.84576135776276e-05,
|
| 141 |
+
"loss": 0.0677,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.23529411764705882,
|
| 146 |
+
"grad_norm": 0.058590111826598894,
|
| 147 |
+
"learning_rate": 9.821267477265705e-05,
|
| 148 |
+
"loss": 0.0606,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.24705882352941178,
|
| 153 |
+
"grad_norm": 0.04785785363882365,
|
| 154 |
+
"learning_rate": 9.795004465759065e-05,
|
| 155 |
+
"loss": 0.0609,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.25882352941176473,
|
| 160 |
+
"grad_norm": 0.05206751702161926,
|
| 161 |
+
"learning_rate": 9.766981960274653e-05,
|
| 162 |
+
"loss": 0.0475,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.27058823529411763,
|
| 167 |
+
"grad_norm": 0.037054145575494114,
|
| 168 |
+
"learning_rate": 9.737210243478521e-05,
|
| 169 |
+
"loss": 0.0415,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.2823529411764706,
|
| 174 |
+
"grad_norm": 0.04044144505681365,
|
| 175 |
+
"learning_rate": 9.705700239897809e-05,
|
| 176 |
+
"loss": 0.0474,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.29411764705882354,
|
| 181 |
+
"grad_norm": 0.030749676244442067,
|
| 182 |
+
"learning_rate": 9.672463511912055e-05,
|
| 183 |
+
"loss": 0.0422,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.3058823529411765,
|
| 188 |
+
"grad_norm": 0.035338570129669074,
|
| 189 |
+
"learning_rate": 9.637512255510475e-05,
|
| 190 |
+
"loss": 0.044,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.3176470588235294,
|
| 195 |
+
"grad_norm": 0.03379157572576983,
|
| 196 |
+
"learning_rate": 9.600859295816708e-05,
|
| 197 |
+
"loss": 0.0398,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.32941176470588235,
|
| 202 |
+
"grad_norm": 0.04025818097716925,
|
| 203 |
+
"learning_rate": 9.56251808238275e-05,
|
| 204 |
+
"loss": 0.0386,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.3411764705882353,
|
| 209 |
+
"grad_norm": 0.04406959077203071,
|
| 210 |
+
"learning_rate": 9.522502684253709e-05,
|
| 211 |
+
"loss": 0.0432,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.35294117647058826,
|
| 216 |
+
"grad_norm": 0.03978101147616123,
|
| 217 |
+
"learning_rate": 9.480827784805278e-05,
|
| 218 |
+
"loss": 0.0437,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.36470588235294116,
|
| 223 |
+
"grad_norm": 0.06465311190984376,
|
| 224 |
+
"learning_rate": 9.437508676355773e-05,
|
| 225 |
+
"loss": 0.0361,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.3764705882352941,
|
| 230 |
+
"grad_norm": 0.040734739666672064,
|
| 231 |
+
"learning_rate": 9.392561254554713e-05,
|
| 232 |
+
"loss": 0.0418,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.38823529411764707,
|
| 237 |
+
"grad_norm": 0.049975058896066196,
|
| 238 |
+
"learning_rate": 9.346002012550027e-05,
|
| 239 |
+
"loss": 0.0392,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.4,
|
| 244 |
+
"grad_norm": 0.035517771488692076,
|
| 245 |
+
"learning_rate": 9.297848034936006e-05,
|
| 246 |
+
"loss": 0.0339,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.4117647058823529,
|
| 251 |
+
"grad_norm": 0.03716302242601897,
|
| 252 |
+
"learning_rate": 9.248116991484229e-05,
|
| 253 |
+
"loss": 0.0342,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.4235294117647059,
|
| 258 |
+
"grad_norm": 0.025634143517022603,
|
| 259 |
+
"learning_rate": 9.19682713065975e-05,
|
| 260 |
+
"loss": 0.0288,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.43529411764705883,
|
| 265 |
+
"grad_norm": 0.03813921333883497,
|
| 266 |
+
"learning_rate": 9.143997272924973e-05,
|
| 267 |
+
"loss": 0.0369,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.4470588235294118,
|
| 272 |
+
"grad_norm": 0.035523177764954665,
|
| 273 |
+
"learning_rate": 9.089646803833589e-05,
|
| 274 |
+
"loss": 0.0342,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.4588235294117647,
|
| 279 |
+
"grad_norm": 0.04123934232531618,
|
| 280 |
+
"learning_rate": 9.033795666917191e-05,
|
| 281 |
+
"loss": 0.0388,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.47058823529411764,
|
| 286 |
+
"grad_norm": 0.03480415683019527,
|
| 287 |
+
"learning_rate": 8.976464356367134e-05,
|
| 288 |
+
"loss": 0.0345,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.4823529411764706,
|
| 293 |
+
"grad_norm": 0.04301396030731473,
|
| 294 |
+
"learning_rate": 8.917673909514322e-05,
|
| 295 |
+
"loss": 0.0408,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.49411764705882355,
|
| 300 |
+
"grad_norm": 0.04119245023494202,
|
| 301 |
+
"learning_rate": 8.857445899109715e-05,
|
| 302 |
+
"loss": 0.0319,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.5058823529411764,
|
| 307 |
+
"grad_norm": 0.03800838266272386,
|
| 308 |
+
"learning_rate": 8.795802425408352e-05,
|
| 309 |
+
"loss": 0.0285,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.5176470588235295,
|
| 314 |
+
"grad_norm": 0.026205323264901936,
|
| 315 |
+
"learning_rate": 8.732766108059813e-05,
|
| 316 |
+
"loss": 0.0322,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.5294117647058824,
|
| 321 |
+
"grad_norm": 0.03931353228016249,
|
| 322 |
+
"learning_rate": 8.668360077808093e-05,
|
| 323 |
+
"loss": 0.0346,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.5411764705882353,
|
| 328 |
+
"grad_norm": 0.047847025199635816,
|
| 329 |
+
"learning_rate": 8.602607968003935e-05,
|
| 330 |
+
"loss": 0.0402,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.5529411764705883,
|
| 335 |
+
"grad_norm": 0.03579784853738504,
|
| 336 |
+
"learning_rate": 8.535533905932738e-05,
|
| 337 |
+
"loss": 0.0262,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.5647058823529412,
|
| 342 |
+
"grad_norm": 0.06521605078365518,
|
| 343 |
+
"learning_rate": 8.467162503961208e-05,
|
| 344 |
+
"loss": 0.0274,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.5764705882352941,
|
| 349 |
+
"grad_norm": 0.027318223641263305,
|
| 350 |
+
"learning_rate": 8.397518850506028e-05,
|
| 351 |
+
"loss": 0.0321,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.5882352941176471,
|
| 356 |
+
"grad_norm": 0.03667920290649668,
|
| 357 |
+
"learning_rate": 8.326628500827826e-05,
|
| 358 |
+
"loss": 0.0348,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.6,
|
| 363 |
+
"grad_norm": 0.03841473526092613,
|
| 364 |
+
"learning_rate": 8.254517467653858e-05,
|
| 365 |
+
"loss": 0.0286,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.611764705882353,
|
| 370 |
+
"grad_norm": 0.03512510354697874,
|
| 371 |
+
"learning_rate": 8.181212211632799e-05,
|
| 372 |
+
"loss": 0.0335,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.6235294117647059,
|
| 377 |
+
"grad_norm": 0.03758958960229201,
|
| 378 |
+
"learning_rate": 8.106739631625217e-05,
|
| 379 |
+
"loss": 0.0351,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.6352941176470588,
|
| 384 |
+
"grad_norm": 0.03141384942404683,
|
| 385 |
+
"learning_rate": 8.03112705483319e-05,
|
| 386 |
+
"loss": 0.0292,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.6470588235294118,
|
| 391 |
+
"grad_norm": 0.05123314473482919,
|
| 392 |
+
"learning_rate": 7.954402226772804e-05,
|
| 393 |
+
"loss": 0.0315,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.6588235294117647,
|
| 398 |
+
"grad_norm": 0.05526844683394433,
|
| 399 |
+
"learning_rate": 7.876593301093104e-05,
|
| 400 |
+
"loss": 0.0376,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.6705882352941176,
|
| 405 |
+
"grad_norm": 0.03442418193147859,
|
| 406 |
+
"learning_rate": 7.797728829245321e-05,
|
| 407 |
+
"loss": 0.0298,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.6823529411764706,
|
| 412 |
+
"grad_norm": 0.05381333860636251,
|
| 413 |
+
"learning_rate": 7.717837750006106e-05,
|
| 414 |
+
"loss": 0.0285,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.6941176470588235,
|
| 419 |
+
"grad_norm": 0.04595131495742476,
|
| 420 |
+
"learning_rate": 7.636949378858646e-05,
|
| 421 |
+
"loss": 0.0323,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.7058823529411765,
|
| 426 |
+
"grad_norm": 0.04547237722119376,
|
| 427 |
+
"learning_rate": 7.555093397235552e-05,
|
| 428 |
+
"loss": 0.0374,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.7176470588235294,
|
| 433 |
+
"grad_norm": 0.029277787154415737,
|
| 434 |
+
"learning_rate": 7.472299841627451e-05,
|
| 435 |
+
"loss": 0.0305,
|
| 436 |
+
"step": 61
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.7294117647058823,
|
| 440 |
+
"grad_norm": 0.054416629180822844,
|
| 441 |
+
"learning_rate": 7.388599092561315e-05,
|
| 442 |
+
"loss": 0.0305,
|
| 443 |
+
"step": 62
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.7411764705882353,
|
| 447 |
+
"grad_norm": 0.07521136626264392,
|
| 448 |
+
"learning_rate": 7.304021863452524e-05,
|
| 449 |
+
"loss": 0.0337,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.7529411764705882,
|
| 454 |
+
"grad_norm": 0.027594110933489315,
|
| 455 |
+
"learning_rate": 7.218599189334799e-05,
|
| 456 |
+
"loss": 0.0268,
|
| 457 |
+
"step": 64
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.7647058823529411,
|
| 461 |
+
"grad_norm": 0.044043131009126026,
|
| 462 |
+
"learning_rate": 7.1323624154721e-05,
|
| 463 |
+
"loss": 0.0333,
|
| 464 |
+
"step": 65
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.7764705882352941,
|
| 468 |
+
"grad_norm": 0.088281551033726,
|
| 469 |
+
"learning_rate": 7.045343185856701e-05,
|
| 470 |
+
"loss": 0.0367,
|
| 471 |
+
"step": 66
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.788235294117647,
|
| 475 |
+
"grad_norm": 0.04328862177911276,
|
| 476 |
+
"learning_rate": 6.957573431597646e-05,
|
| 477 |
+
"loss": 0.0327,
|
| 478 |
+
"step": 67
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.8,
|
| 482 |
+
"grad_norm": 0.03272017374355755,
|
| 483 |
+
"learning_rate": 6.869085359203844e-05,
|
| 484 |
+
"loss": 0.0309,
|
| 485 |
+
"step": 68
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.8117647058823529,
|
| 489 |
+
"grad_norm": 0.06280711357209813,
|
| 490 |
+
"learning_rate": 6.779911438766116e-05,
|
| 491 |
+
"loss": 0.0327,
|
| 492 |
+
"step": 69
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.8235294117647058,
|
| 496 |
+
"grad_norm": 0.052927974729157626,
|
| 497 |
+
"learning_rate": 6.690084392042513e-05,
|
| 498 |
+
"loss": 0.0312,
|
| 499 |
+
"step": 70
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.8352941176470589,
|
| 503 |
+
"grad_norm": 0.05429533945696401,
|
| 504 |
+
"learning_rate": 6.599637180451294e-05,
|
| 505 |
+
"loss": 0.0348,
|
| 506 |
+
"step": 71
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.8470588235294118,
|
| 510 |
+
"grad_norm": 0.048917527979116436,
|
| 511 |
+
"learning_rate": 6.508602992975963e-05,
|
| 512 |
+
"loss": 0.0317,
|
| 513 |
+
"step": 72
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.8588235294117647,
|
| 517 |
+
"grad_norm": 0.031886426687786254,
|
| 518 |
+
"learning_rate": 6.417015233986786e-05,
|
| 519 |
+
"loss": 0.0311,
|
| 520 |
+
"step": 73
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.8705882352941177,
|
| 524 |
+
"grad_norm": 0.03376820411697015,
|
| 525 |
+
"learning_rate": 6.32490751098331e-05,
|
| 526 |
+
"loss": 0.0263,
|
| 527 |
+
"step": 74
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.8823529411764706,
|
| 531 |
+
"grad_norm": 0.03767361887537691,
|
| 532 |
+
"learning_rate": 6.232313622262296e-05,
|
| 533 |
+
"loss": 0.0343,
|
| 534 |
+
"step": 75
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.8941176470588236,
|
| 538 |
+
"grad_norm": 0.04332615343931221,
|
| 539 |
+
"learning_rate": 6.139267544515689e-05,
|
| 540 |
+
"loss": 0.0304,
|
| 541 |
+
"step": 76
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.9058823529411765,
|
| 545 |
+
"grad_norm": 0.04146445958416543,
|
| 546 |
+
"learning_rate": 6.045803420363084e-05,
|
| 547 |
+
"loss": 0.0318,
|
| 548 |
+
"step": 77
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.9176470588235294,
|
| 552 |
+
"grad_norm": 0.03675850801075872,
|
| 553 |
+
"learning_rate": 5.951955545823342e-05,
|
| 554 |
+
"loss": 0.0286,
|
| 555 |
+
"step": 78
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.9294117647058824,
|
| 559 |
+
"grad_norm": 0.03951469611584691,
|
| 560 |
+
"learning_rate": 5.8577583577298924e-05,
|
| 561 |
+
"loss": 0.0297,
|
| 562 |
+
"step": 79
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.9411764705882353,
|
| 566 |
+
"grad_norm": 0.03613565309891407,
|
| 567 |
+
"learning_rate": 5.7632464210943726e-05,
|
| 568 |
+
"loss": 0.0261,
|
| 569 |
+
"step": 80
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.9529411764705882,
|
| 573 |
+
"grad_norm": 0.031008899018911143,
|
| 574 |
+
"learning_rate": 5.668454416423242e-05,
|
| 575 |
+
"loss": 0.026,
|
| 576 |
+
"step": 81
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.9647058823529412,
|
| 580 |
+
"grad_norm": 0.0692628338321925,
|
| 581 |
+
"learning_rate": 5.573417126992003e-05,
|
| 582 |
+
"loss": 0.0266,
|
| 583 |
+
"step": 82
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.9764705882352941,
|
| 587 |
+
"grad_norm": 0.05852763315877547,
|
| 588 |
+
"learning_rate": 5.478169426081712e-05,
|
| 589 |
+
"loss": 0.0295,
|
| 590 |
+
"step": 83
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.9882352941176471,
|
| 594 |
+
"grad_norm": 0.03199303327911728,
|
| 595 |
+
"learning_rate": 5.38274626418248e-05,
|
| 596 |
+
"loss": 0.0292,
|
| 597 |
+
"step": 84
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 1.0,
|
| 601 |
+
"grad_norm": 0.03733696573812923,
|
| 602 |
+
"learning_rate": 5.287182656168618e-05,
|
| 603 |
+
"loss": 0.0287,
|
| 604 |
+
"step": 85
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 1.011764705882353,
|
| 608 |
+
"grad_norm": 0.04222433319800323,
|
| 609 |
+
"learning_rate": 5.191513668450178e-05,
|
| 610 |
+
"loss": 0.0275,
|
| 611 |
+
"step": 86
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 1.0235294117647058,
|
| 615 |
+
"grad_norm": 0.033149244513485374,
|
| 616 |
+
"learning_rate": 5.095774406105571e-05,
|
| 617 |
+
"loss": 0.0245,
|
| 618 |
+
"step": 87
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 1.035294117647059,
|
| 622 |
+
"grad_norm": 0.030866296785570155,
|
| 623 |
+
"learning_rate": 5e-05,
|
| 624 |
+
"loss": 0.0227,
|
| 625 |
+
"step": 88
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 1.0470588235294118,
|
| 629 |
+
"grad_norm": 0.029363896734282895,
|
| 630 |
+
"learning_rate": 4.9042255938944296e-05,
|
| 631 |
+
"loss": 0.0284,
|
| 632 |
+
"step": 89
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 1.0588235294117647,
|
| 636 |
+
"grad_norm": 0.03458859192281693,
|
| 637 |
+
"learning_rate": 4.8084863315498234e-05,
|
| 638 |
+
"loss": 0.0256,
|
| 639 |
+
"step": 90
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.0705882352941176,
|
| 643 |
+
"grad_norm": 0.033499852353591555,
|
| 644 |
+
"learning_rate": 4.712817343831384e-05,
|
| 645 |
+
"loss": 0.028,
|
| 646 |
+
"step": 91
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 1.0823529411764705,
|
| 650 |
+
"grad_norm": 0.03348874233244485,
|
| 651 |
+
"learning_rate": 4.6172537358175214e-05,
|
| 652 |
+
"loss": 0.0269,
|
| 653 |
+
"step": 92
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 1.0941176470588236,
|
| 657 |
+
"grad_norm": 0.03268399220561992,
|
| 658 |
+
"learning_rate": 4.521830573918289e-05,
|
| 659 |
+
"loss": 0.0268,
|
| 660 |
+
"step": 93
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 1.1058823529411765,
|
| 664 |
+
"grad_norm": 0.03535497654299178,
|
| 665 |
+
"learning_rate": 4.4265828730079987e-05,
|
| 666 |
+
"loss": 0.0287,
|
| 667 |
+
"step": 94
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 1.1176470588235294,
|
| 671 |
+
"grad_norm": 0.035249786662349535,
|
| 672 |
+
"learning_rate": 4.331545583576758e-05,
|
| 673 |
+
"loss": 0.0254,
|
| 674 |
+
"step": 95
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 1.1294117647058823,
|
| 678 |
+
"grad_norm": 0.042058533392068366,
|
| 679 |
+
"learning_rate": 4.236753578905627e-05,
|
| 680 |
+
"loss": 0.0257,
|
| 681 |
+
"step": 96
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 1.1411764705882352,
|
| 685 |
+
"grad_norm": 0.035662240284239075,
|
| 686 |
+
"learning_rate": 4.142241642270108e-05,
|
| 687 |
+
"loss": 0.023,
|
| 688 |
+
"step": 97
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 1.1529411764705881,
|
| 692 |
+
"grad_norm": 0.03205942374398337,
|
| 693 |
+
"learning_rate": 4.0480444541766576e-05,
|
| 694 |
+
"loss": 0.0227,
|
| 695 |
+
"step": 98
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 1.1647058823529413,
|
| 699 |
+
"grad_norm": 0.03410677741547236,
|
| 700 |
+
"learning_rate": 3.954196579636918e-05,
|
| 701 |
+
"loss": 0.025,
|
| 702 |
+
"step": 99
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 1.1764705882352942,
|
| 706 |
+
"grad_norm": 0.037977473156353136,
|
| 707 |
+
"learning_rate": 3.8607324554843136e-05,
|
| 708 |
+
"loss": 0.0245,
|
| 709 |
+
"step": 100
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 1.188235294117647,
|
| 713 |
+
"grad_norm": 0.034304594099498986,
|
| 714 |
+
"learning_rate": 3.7676863777377054e-05,
|
| 715 |
+
"loss": 0.0251,
|
| 716 |
+
"step": 101
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 1.2,
|
| 720 |
+
"grad_norm": 0.04024140735442772,
|
| 721 |
+
"learning_rate": 3.675092489016693e-05,
|
| 722 |
+
"loss": 0.0258,
|
| 723 |
+
"step": 102
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 1.2117647058823529,
|
| 727 |
+
"grad_norm": 0.03640815220830249,
|
| 728 |
+
"learning_rate": 3.582984766013215e-05,
|
| 729 |
+
"loss": 0.0254,
|
| 730 |
+
"step": 103
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 1.223529411764706,
|
| 734 |
+
"grad_norm": 0.05308696935770744,
|
| 735 |
+
"learning_rate": 3.4913970070240386e-05,
|
| 736 |
+
"loss": 0.0317,
|
| 737 |
+
"step": 104
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 1.2352941176470589,
|
| 741 |
+
"grad_norm": 0.03532605452768607,
|
| 742 |
+
"learning_rate": 3.4003628195487057e-05,
|
| 743 |
+
"loss": 0.0272,
|
| 744 |
+
"step": 105
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 1.2470588235294118,
|
| 748 |
+
"grad_norm": 0.03399447551991043,
|
| 749 |
+
"learning_rate": 3.309915607957487e-05,
|
| 750 |
+
"loss": 0.0256,
|
| 751 |
+
"step": 106
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 1.2588235294117647,
|
| 755 |
+
"grad_norm": 0.03154244903849424,
|
| 756 |
+
"learning_rate": 3.2200885612338845e-05,
|
| 757 |
+
"loss": 0.0207,
|
| 758 |
+
"step": 107
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 1.2705882352941176,
|
| 762 |
+
"grad_norm": 0.04861329315126559,
|
| 763 |
+
"learning_rate": 3.130914640796157e-05,
|
| 764 |
+
"loss": 0.0297,
|
| 765 |
+
"step": 108
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 1.2823529411764705,
|
| 769 |
+
"grad_norm": 0.04026826659177659,
|
| 770 |
+
"learning_rate": 3.0424265684023558e-05,
|
| 771 |
+
"loss": 0.0238,
|
| 772 |
+
"step": 109
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 1.2941176470588236,
|
| 776 |
+
"grad_norm": 0.03529433347937337,
|
| 777 |
+
"learning_rate": 2.9546568141433006e-05,
|
| 778 |
+
"loss": 0.0247,
|
| 779 |
+
"step": 110
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 1.3058823529411765,
|
| 783 |
+
"grad_norm": 0.035218945260167514,
|
| 784 |
+
"learning_rate": 2.8676375845279013e-05,
|
| 785 |
+
"loss": 0.0271,
|
| 786 |
+
"step": 111
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 1.3176470588235294,
|
| 790 |
+
"grad_norm": 0.03409897136114451,
|
| 791 |
+
"learning_rate": 2.7814008106652012e-05,
|
| 792 |
+
"loss": 0.0253,
|
| 793 |
+
"step": 112
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 1.3294117647058823,
|
| 797 |
+
"grad_norm": 0.03345892031561033,
|
| 798 |
+
"learning_rate": 2.6959781365474758e-05,
|
| 799 |
+
"loss": 0.0196,
|
| 800 |
+
"step": 113
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 1.3411764705882354,
|
| 804 |
+
"grad_norm": 0.041711810588722247,
|
| 805 |
+
"learning_rate": 2.6114009074386846e-05,
|
| 806 |
+
"loss": 0.025,
|
| 807 |
+
"step": 114
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 1.3529411764705883,
|
| 811 |
+
"grad_norm": 0.03404740591421045,
|
| 812 |
+
"learning_rate": 2.527700158372548e-05,
|
| 813 |
+
"loss": 0.0245,
|
| 814 |
+
"step": 115
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 1.3647058823529412,
|
| 818 |
+
"grad_norm": 0.03806934179838023,
|
| 819 |
+
"learning_rate": 2.4449066027644475e-05,
|
| 820 |
+
"loss": 0.0202,
|
| 821 |
+
"step": 116
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 1.3764705882352941,
|
| 825 |
+
"grad_norm": 0.037833218608223404,
|
| 826 |
+
"learning_rate": 2.363050621141354e-05,
|
| 827 |
+
"loss": 0.0269,
|
| 828 |
+
"step": 117
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 1.388235294117647,
|
| 832 |
+
"grad_norm": 0.040060220347060395,
|
| 833 |
+
"learning_rate": 2.282162249993895e-05,
|
| 834 |
+
"loss": 0.0259,
|
| 835 |
+
"step": 118
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 1.4,
|
| 839 |
+
"grad_norm": 0.039492305883863446,
|
| 840 |
+
"learning_rate": 2.20227117075468e-05,
|
| 841 |
+
"loss": 0.0263,
|
| 842 |
+
"step": 119
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 1.4117647058823528,
|
| 846 |
+
"grad_norm": 0.04146681928718736,
|
| 847 |
+
"learning_rate": 2.1234066989068972e-05,
|
| 848 |
+
"loss": 0.0237,
|
| 849 |
+
"step": 120
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 1.423529411764706,
|
| 853 |
+
"grad_norm": 0.044440473554041314,
|
| 854 |
+
"learning_rate": 2.0455977732271993e-05,
|
| 855 |
+
"loss": 0.0221,
|
| 856 |
+
"step": 121
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 1.4352941176470588,
|
| 860 |
+
"grad_norm": 0.033828391729890175,
|
| 861 |
+
"learning_rate": 1.9688729451668114e-05,
|
| 862 |
+
"loss": 0.0203,
|
| 863 |
+
"step": 122
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 1.4470588235294117,
|
| 867 |
+
"grad_norm": 0.038308578853440155,
|
| 868 |
+
"learning_rate": 1.893260368374786e-05,
|
| 869 |
+
"loss": 0.0271,
|
| 870 |
+
"step": 123
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 1.4588235294117646,
|
| 874 |
+
"grad_norm": 0.035696891554767116,
|
| 875 |
+
"learning_rate": 1.818787788367202e-05,
|
| 876 |
+
"loss": 0.0241,
|
| 877 |
+
"step": 124
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 1.4705882352941178,
|
| 881 |
+
"grad_norm": 0.03450606035436337,
|
| 882 |
+
"learning_rate": 1.7454825323461448e-05,
|
| 883 |
+
"loss": 0.0227,
|
| 884 |
+
"step": 125
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 1.4823529411764707,
|
| 888 |
+
"grad_norm": 0.04502948564553977,
|
| 889 |
+
"learning_rate": 1.673371499172174e-05,
|
| 890 |
+
"loss": 0.0282,
|
| 891 |
+
"step": 126
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 1.4941176470588236,
|
| 895 |
+
"grad_norm": 0.03775360455129196,
|
| 896 |
+
"learning_rate": 1.6024811494939724e-05,
|
| 897 |
+
"loss": 0.022,
|
| 898 |
+
"step": 127
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 1.5058823529411764,
|
| 902 |
+
"grad_norm": 0.035858486799161725,
|
| 903 |
+
"learning_rate": 1.532837496038792e-05,
|
| 904 |
+
"loss": 0.0247,
|
| 905 |
+
"step": 128
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 1.5176470588235293,
|
| 909 |
+
"grad_norm": 0.03737088577494754,
|
| 910 |
+
"learning_rate": 1.4644660940672627e-05,
|
| 911 |
+
"loss": 0.0257,
|
| 912 |
+
"step": 129
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 1.5294117647058822,
|
| 916 |
+
"grad_norm": 0.03461325321460445,
|
| 917 |
+
"learning_rate": 1.3973920319960655e-05,
|
| 918 |
+
"loss": 0.0217,
|
| 919 |
+
"step": 130
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 1.5411764705882351,
|
| 923 |
+
"grad_norm": 0.034501790257859405,
|
| 924 |
+
"learning_rate": 1.3316399221919074e-05,
|
| 925 |
+
"loss": 0.0232,
|
| 926 |
+
"step": 131
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 1.5529411764705883,
|
| 930 |
+
"grad_norm": 0.03782875214918853,
|
| 931 |
+
"learning_rate": 1.2672338919401866e-05,
|
| 932 |
+
"loss": 0.0225,
|
| 933 |
+
"step": 132
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 1.5647058823529412,
|
| 937 |
+
"grad_norm": 0.04306989405034864,
|
| 938 |
+
"learning_rate": 1.2041975745916472e-05,
|
| 939 |
+
"loss": 0.0269,
|
| 940 |
+
"step": 133
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 1.576470588235294,
|
| 944 |
+
"grad_norm": 0.037700226280294416,
|
| 945 |
+
"learning_rate": 1.1425541008902851e-05,
|
| 946 |
+
"loss": 0.0249,
|
| 947 |
+
"step": 134
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 1.5882352941176472,
|
| 951 |
+
"grad_norm": 0.03890317937719569,
|
| 952 |
+
"learning_rate": 1.082326090485679e-05,
|
| 953 |
+
"loss": 0.0255,
|
| 954 |
+
"step": 135
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 1.6,
|
| 958 |
+
"grad_norm": 0.04219733674070769,
|
| 959 |
+
"learning_rate": 1.0235356436328675e-05,
|
| 960 |
+
"loss": 0.0286,
|
| 961 |
+
"step": 136
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 1.611764705882353,
|
| 965 |
+
"grad_norm": 0.03273981321791409,
|
| 966 |
+
"learning_rate": 9.662043330828085e-06,
|
| 967 |
+
"loss": 0.0201,
|
| 968 |
+
"step": 137
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 1.6235294117647059,
|
| 972 |
+
"grad_norm": 0.03302849889769006,
|
| 973 |
+
"learning_rate": 9.103531961664118e-06,
|
| 974 |
+
"loss": 0.0212,
|
| 975 |
+
"step": 138
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 1.6352941176470588,
|
| 979 |
+
"grad_norm": 0.04021301444135266,
|
| 980 |
+
"learning_rate": 8.560027270750277e-06,
|
| 981 |
+
"loss": 0.0244,
|
| 982 |
+
"step": 139
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 1.6470588235294117,
|
| 986 |
+
"grad_norm": 0.034002953931695744,
|
| 987 |
+
"learning_rate": 8.031728693402502e-06,
|
| 988 |
+
"loss": 0.0193,
|
| 989 |
+
"step": 140
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 1.6588235294117646,
|
| 993 |
+
"grad_norm": 0.03494170057614315,
|
| 994 |
+
"learning_rate": 7.518830085157735e-06,
|
| 995 |
+
"loss": 0.0232,
|
| 996 |
+
"step": 141
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 1.6705882352941175,
|
| 1000 |
+
"grad_norm": 0.05067951397515134,
|
| 1001 |
+
"learning_rate": 7.0215196506399515e-06,
|
| 1002 |
+
"loss": 0.0217,
|
| 1003 |
+
"step": 142
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 1.6823529411764706,
|
| 1007 |
+
"grad_norm": 0.035476236926014315,
|
| 1008 |
+
"learning_rate": 6.539979874499747e-06,
|
| 1009 |
+
"loss": 0.0213,
|
| 1010 |
+
"step": 143
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 1.6941176470588235,
|
| 1014 |
+
"grad_norm": 0.036655504933770414,
|
| 1015 |
+
"learning_rate": 6.07438745445289e-06,
|
| 1016 |
+
"loss": 0.0234,
|
| 1017 |
+
"step": 144
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 1.7058823529411766,
|
| 1021 |
+
"grad_norm": 0.041657363570965146,
|
| 1022 |
+
"learning_rate": 5.624913236442286e-06,
|
| 1023 |
+
"loss": 0.0294,
|
| 1024 |
+
"step": 145
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 1.7176470588235295,
|
| 1028 |
+
"grad_norm": 0.05150076449892236,
|
| 1029 |
+
"learning_rate": 5.191722151947226e-06,
|
| 1030 |
+
"loss": 0.0258,
|
| 1031 |
+
"step": 146
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 1.7294117647058824,
|
| 1035 |
+
"grad_norm": 0.0404588183080739,
|
| 1036 |
+
"learning_rate": 4.7749731574629196e-06,
|
| 1037 |
+
"loss": 0.0224,
|
| 1038 |
+
"step": 147
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 1.7411764705882353,
|
| 1042 |
+
"grad_norm": 0.033224356486454734,
|
| 1043 |
+
"learning_rate": 4.374819176172501e-06,
|
| 1044 |
+
"loss": 0.021,
|
| 1045 |
+
"step": 148
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 1.7529411764705882,
|
| 1049 |
+
"grad_norm": 0.03795419337831155,
|
| 1050 |
+
"learning_rate": 3.991407041832912e-06,
|
| 1051 |
+
"loss": 0.022,
|
| 1052 |
+
"step": 149
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 1.7647058823529411,
|
| 1056 |
+
"grad_norm": 0.04200165421199087,
|
| 1057 |
+
"learning_rate": 3.6248774448952695e-06,
|
| 1058 |
+
"loss": 0.0265,
|
| 1059 |
+
"step": 150
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 1.776470588235294,
|
| 1063 |
+
"grad_norm": 0.03845197891559611,
|
| 1064 |
+
"learning_rate": 3.2753648808794503e-06,
|
| 1065 |
+
"loss": 0.024,
|
| 1066 |
+
"step": 151
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 1.788235294117647,
|
| 1070 |
+
"grad_norm": 0.037815699401078935,
|
| 1071 |
+
"learning_rate": 2.942997601021924e-06,
|
| 1072 |
+
"loss": 0.0257,
|
| 1073 |
+
"step": 152
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 1.8,
|
| 1077 |
+
"grad_norm": 0.03519274514771082,
|
| 1078 |
+
"learning_rate": 2.6278975652147875e-06,
|
| 1079 |
+
"loss": 0.0232,
|
| 1080 |
+
"step": 153
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 1.811764705882353,
|
| 1084 |
+
"grad_norm": 0.03706158210535721,
|
| 1085 |
+
"learning_rate": 2.330180397253473e-06,
|
| 1086 |
+
"loss": 0.0232,
|
| 1087 |
+
"step": 154
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 1.8235294117647058,
|
| 1091 |
+
"grad_norm": 0.04248155649655448,
|
| 1092 |
+
"learning_rate": 2.049955342409349e-06,
|
| 1093 |
+
"loss": 0.0227,
|
| 1094 |
+
"step": 155
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 1.835294117647059,
|
| 1098 |
+
"grad_norm": 0.0368432870786149,
|
| 1099 |
+
"learning_rate": 1.7873252273429509e-06,
|
| 1100 |
+
"loss": 0.0224,
|
| 1101 |
+
"step": 156
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 1.8470588235294119,
|
| 1105 |
+
"grad_norm": 0.03332568698884207,
|
| 1106 |
+
"learning_rate": 1.542386422372405e-06,
|
| 1107 |
+
"loss": 0.0208,
|
| 1108 |
+
"step": 157
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 1.8588235294117648,
|
| 1112 |
+
"grad_norm": 0.036213210721090155,
|
| 1113 |
+
"learning_rate": 1.3152288061110518e-06,
|
| 1114 |
+
"loss": 0.0237,
|
| 1115 |
+
"step": 158
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 1.8705882352941177,
|
| 1119 |
+
"grad_norm": 0.035507819488375524,
|
| 1120 |
+
"learning_rate": 1.1059357324870455e-06,
|
| 1121 |
+
"loss": 0.0212,
|
| 1122 |
+
"step": 159
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 1.8823529411764706,
|
| 1126 |
+
"grad_norm": 0.032773052246892385,
|
| 1127 |
+
"learning_rate": 9.145840001572537e-07,
|
| 1128 |
+
"loss": 0.0209,
|
| 1129 |
+
"step": 160
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 1.8941176470588235,
|
| 1133 |
+
"grad_norm": 0.03720092396666804,
|
| 1134 |
+
"learning_rate": 7.41243824326504e-07,
|
| 1135 |
+
"loss": 0.0237,
|
| 1136 |
+
"step": 161
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 1.9058823529411764,
|
| 1140 |
+
"grad_norm": 0.061643042263861664,
|
| 1141 |
+
"learning_rate": 5.859788109825793e-07,
|
| 1142 |
+
"loss": 0.0263,
|
| 1143 |
+
"step": 162
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 1.9176470588235293,
|
| 1147 |
+
"grad_norm": 0.037441015710064,
|
| 1148 |
+
"learning_rate": 4.48845933556441e-07,
|
| 1149 |
+
"loss": 0.025,
|
| 1150 |
+
"step": 163
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 1.9294117647058824,
|
| 1154 |
+
"grad_norm": 0.03459803638637435,
|
| 1155 |
+
"learning_rate": 3.2989551201624835e-07,
|
| 1156 |
+
"loss": 0.0215,
|
| 1157 |
+
"step": 164
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 1.9411764705882353,
|
| 1161 |
+
"grad_norm": 0.04948419428076397,
|
| 1162 |
+
"learning_rate": 2.2917119440275524e-07,
|
| 1163 |
+
"loss": 0.0273,
|
| 1164 |
+
"step": 165
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 1.9529411764705882,
|
| 1168 |
+
"grad_norm": 0.040939656098896986,
|
| 1169 |
+
"learning_rate": 1.4670994081297795e-07,
|
| 1170 |
+
"loss": 0.0251,
|
| 1171 |
+
"step": 166
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 1.9647058823529413,
|
| 1175 |
+
"grad_norm": 0.03941121437437399,
|
| 1176 |
+
"learning_rate": 8.254200983794369e-08,
|
| 1177 |
+
"loss": 0.0273,
|
| 1178 |
+
"step": 167
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 1.9764705882352942,
|
| 1182 |
+
"grad_norm": 0.04847566902018068,
|
| 1183 |
+
"learning_rate": 3.669094745950008e-08,
|
| 1184 |
+
"loss": 0.0239,
|
| 1185 |
+
"step": 168
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 1.988235294117647,
|
| 1189 |
+
"grad_norm": 0.04650396689287853,
|
| 1190 |
+
"learning_rate": 9.17357841028199e-09,
|
| 1191 |
+
"loss": 0.0207,
|
| 1192 |
+
"step": 169
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 2.0,
|
| 1196 |
+
"grad_norm": 0.04099329304128327,
|
| 1197 |
+
"learning_rate": 0.0,
|
| 1198 |
+
"loss": 0.0232,
|
| 1199 |
+
"step": 170
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 2.0,
|
| 1203 |
+
"step": 170,
|
| 1204 |
+
"total_flos": 861011422740480.0,
|
| 1205 |
+
"train_loss": 0.03621660071041654,
|
| 1206 |
+
"train_runtime": 2036.7134,
|
| 1207 |
+
"train_samples_per_second": 0.668,
|
| 1208 |
+
"train_steps_per_second": 0.083
|
| 1209 |
+
}
|
| 1210 |
+
],
|
| 1211 |
+
"logging_steps": 1,
|
| 1212 |
+
"max_steps": 170,
|
| 1213 |
+
"num_input_tokens_seen": 0,
|
| 1214 |
+
"num_train_epochs": 2,
|
| 1215 |
+
"save_steps": 50000,
|
| 1216 |
+
"stateful_callbacks": {
|
| 1217 |
+
"TrainerControl": {
|
| 1218 |
+
"args": {
|
| 1219 |
+
"should_epoch_stop": false,
|
| 1220 |
+
"should_evaluate": false,
|
| 1221 |
+
"should_log": false,
|
| 1222 |
+
"should_save": true,
|
| 1223 |
+
"should_training_stop": true
|
| 1224 |
+
},
|
| 1225 |
+
"attributes": {}
|
| 1226 |
+
}
|
| 1227 |
+
},
|
| 1228 |
+
"total_flos": 861011422740480.0,
|
| 1229 |
+
"train_batch_size": 2,
|
| 1230 |
+
"trial_name": null,
|
| 1231 |
+
"trial_params": null
|
| 1232 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d401921801c2fd7e7085d4f15064e2d97b5ebeb4e6c4340261ce884103f7e47c
|
| 3 |
+
size 7224
|
training_loss.png
ADDED
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|