Training in progress, step 1200
Browse files- .gitattributes +1 -0
- adapter_config.json +39 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +24 -0
- merges.txt +0 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +209 -0
- trainer_log.jsonl +159 -0
- training_args.bin +3 -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 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "Qwen/Qwen2.5-1.5B-Instruct",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 128,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.0,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 64,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": [
|
| 27 |
+
"down_proj",
|
| 28 |
+
"o_proj",
|
| 29 |
+
"v_proj",
|
| 30 |
+
"q_proj",
|
| 31 |
+
"up_proj",
|
| 32 |
+
"k_proj",
|
| 33 |
+
"gate_proj"
|
| 34 |
+
],
|
| 35 |
+
"task_type": "CAUSAL_LM",
|
| 36 |
+
"trainable_token_indices": null,
|
| 37 |
+
"use_dora": false,
|
| 38 |
+
"use_rslora": false
|
| 39 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cfe074a3c1ce9b797ca713228dca3f84df3dd9814fe88396bdf182a8daa1f314
|
| 3 |
+
size 295488936
|
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 |
+
}
|
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 +1,209 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"extra_special_tokens": {},
|
| 203 |
+
"model_max_length": 131072,
|
| 204 |
+
"pad_token": "<|endoftext|>",
|
| 205 |
+
"padding_side": "right",
|
| 206 |
+
"split_special_tokens": false,
|
| 207 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 208 |
+
"unk_token": null
|
| 209 |
+
}
|
trainer_log.jsonl
ADDED
|
@@ -0,0 +1,159 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 10, "total_steps": 1455, "loss": 0.3919, "lr": 6.1643835616438354e-06, "epoch": 0.020607934054611025, "percentage": 0.69, "elapsed_time": "0:05:34", "remaining_time": "13:26:01"}
|
| 2 |
+
{"current_steps": 20, "total_steps": 1455, "loss": 0.3437, "lr": 1.3013698630136986e-05, "epoch": 0.04121586810922205, "percentage": 1.37, "elapsed_time": "0:11:06", "remaining_time": "13:16:30"}
|
| 3 |
+
{"current_steps": 30, "total_steps": 1455, "loss": 0.3129, "lr": 1.9863013698630137e-05, "epoch": 0.061823802163833076, "percentage": 2.06, "elapsed_time": "0:16:58", "remaining_time": "13:26:11"}
|
| 4 |
+
{"current_steps": 40, "total_steps": 1455, "loss": 0.2943, "lr": 2.671232876712329e-05, "epoch": 0.0824317362184441, "percentage": 2.75, "elapsed_time": "0:22:47", "remaining_time": "13:26:29"}
|
| 5 |
+
{"current_steps": 50, "total_steps": 1455, "loss": 0.2838, "lr": 3.356164383561644e-05, "epoch": 0.10303967027305512, "percentage": 3.44, "elapsed_time": "0:28:49", "remaining_time": "13:30:05"}
|
| 6 |
+
{"current_steps": 60, "total_steps": 1455, "loss": 0.2776, "lr": 4.041095890410959e-05, "epoch": 0.12364760432766615, "percentage": 4.12, "elapsed_time": "0:35:01", "remaining_time": "13:34:21"}
|
| 7 |
+
{"current_steps": 70, "total_steps": 1455, "loss": 0.2653, "lr": 4.726027397260274e-05, "epoch": 0.14425553838227717, "percentage": 4.81, "elapsed_time": "0:40:49", "remaining_time": "13:27:44"}
|
| 8 |
+
{"current_steps": 80, "total_steps": 1455, "loss": 0.2705, "lr": 5.4109589041095895e-05, "epoch": 0.1648634724368882, "percentage": 5.5, "elapsed_time": "0:46:03", "remaining_time": "13:11:41"}
|
| 9 |
+
{"current_steps": 90, "total_steps": 1455, "loss": 0.2418, "lr": 6.095890410958904e-05, "epoch": 0.18547140649149924, "percentage": 6.19, "elapsed_time": "0:51:50", "remaining_time": "13:06:17"}
|
| 10 |
+
{"current_steps": 100, "total_steps": 1455, "loss": 0.2435, "lr": 6.78082191780822e-05, "epoch": 0.20607934054611024, "percentage": 6.87, "elapsed_time": "0:56:54", "remaining_time": "12:51:09"}
|
| 11 |
+
{"current_steps": 100, "total_steps": 1455, "eval_loss": 0.23216360807418823, "epoch": 0.20607934054611024, "percentage": 6.87, "elapsed_time": "0:59:28", "remaining_time": "13:25:51"}
|
| 12 |
+
{"current_steps": 110, "total_steps": 1455, "loss": 0.2408, "lr": 7.465753424657535e-05, "epoch": 0.22668727460072127, "percentage": 7.56, "elapsed_time": "1:04:47", "remaining_time": "13:12:07"}
|
| 13 |
+
{"current_steps": 120, "total_steps": 1455, "loss": 0.2336, "lr": 8.15068493150685e-05, "epoch": 0.2472952086553323, "percentage": 8.25, "elapsed_time": "1:09:52", "remaining_time": "12:57:23"}
|
| 14 |
+
{"current_steps": 130, "total_steps": 1455, "loss": 0.2388, "lr": 8.835616438356165e-05, "epoch": 0.2679031427099433, "percentage": 8.93, "elapsed_time": "1:15:40", "remaining_time": "12:51:21"}
|
| 15 |
+
{"current_steps": 140, "total_steps": 1455, "loss": 0.2218, "lr": 9.520547945205481e-05, "epoch": 0.28851107676455434, "percentage": 9.62, "elapsed_time": "1:20:58", "remaining_time": "12:40:39"}
|
| 16 |
+
{"current_steps": 150, "total_steps": 1455, "loss": 0.2356, "lr": 9.999870401165987e-05, "epoch": 0.3091190108191654, "percentage": 10.31, "elapsed_time": "1:26:21", "remaining_time": "12:31:18"}
|
| 17 |
+
{"current_steps": 160, "total_steps": 1455, "loss": 0.2323, "lr": 9.99756660878697e-05, "epoch": 0.3297269448737764, "percentage": 11.0, "elapsed_time": "1:31:39", "remaining_time": "12:21:53"}
|
| 18 |
+
{"current_steps": 170, "total_steps": 1455, "loss": 0.2362, "lr": 9.992384369672854e-05, "epoch": 0.35033487892838744, "percentage": 11.68, "elapsed_time": "1:37:48", "remaining_time": "12:19:19"}
|
| 19 |
+
{"current_steps": 180, "total_steps": 1455, "loss": 0.2277, "lr": 9.984326668636131e-05, "epoch": 0.37094281298299847, "percentage": 12.37, "elapsed_time": "1:43:29", "remaining_time": "12:13:03"}
|
| 20 |
+
{"current_steps": 190, "total_steps": 1455, "loss": 0.2348, "lr": 9.973398146668118e-05, "epoch": 0.3915507470376095, "percentage": 13.06, "elapsed_time": "1:49:00", "remaining_time": "12:05:46"}
|
| 21 |
+
{"current_steps": 200, "total_steps": 1455, "loss": 0.2341, "lr": 9.959605098265886e-05, "epoch": 0.4121586810922205, "percentage": 13.75, "elapsed_time": "1:54:06", "remaining_time": "11:56:03"}
|
| 22 |
+
{"current_steps": 200, "total_steps": 1455, "eval_loss": 0.21873560547828674, "epoch": 0.4121586810922205, "percentage": 13.75, "elapsed_time": "1:56:40", "remaining_time": "12:12:08"}
|
| 23 |
+
{"current_steps": 210, "total_steps": 1455, "loss": 0.2367, "lr": 9.94295546780682e-05, "epoch": 0.4327666151468315, "percentage": 14.43, "elapsed_time": "2:02:34", "remaining_time": "12:06:44"}
|
| 24 |
+
{"current_steps": 220, "total_steps": 1455, "loss": 0.2222, "lr": 9.923458844972895e-05, "epoch": 0.45337454920144254, "percentage": 15.12, "elapsed_time": "2:08:04", "remaining_time": "11:58:55"}
|
| 25 |
+
{"current_steps": 230, "total_steps": 1455, "loss": 0.2082, "lr": 9.901126459227316e-05, "epoch": 0.4739824832560536, "percentage": 15.81, "elapsed_time": "2:13:32", "remaining_time": "11:51:17"}
|
| 26 |
+
{"current_steps": 240, "total_steps": 1455, "loss": 0.2202, "lr": 9.875971173346683e-05, "epoch": 0.4945904173106646, "percentage": 16.49, "elapsed_time": "2:19:45", "remaining_time": "11:47:33"}
|
| 27 |
+
{"current_steps": 250, "total_steps": 1455, "loss": 0.2277, "lr": 9.848007476012426e-05, "epoch": 0.5151983513652756, "percentage": 17.18, "elapsed_time": "2:25:01", "remaining_time": "11:38:58"}
|
| 28 |
+
{"current_steps": 260, "total_steps": 1455, "loss": 0.2195, "lr": 9.817251473465759e-05, "epoch": 0.5358062854198866, "percentage": 17.87, "elapsed_time": "2:30:14", "remaining_time": "11:30:33"}
|
| 29 |
+
{"current_steps": 270, "total_steps": 1455, "loss": 0.2236, "lr": 9.78372088023098e-05, "epoch": 0.5564142194744977, "percentage": 18.56, "elapsed_time": "2:35:18", "remaining_time": "11:21:38"}
|
| 30 |
+
{"current_steps": 280, "total_steps": 1455, "loss": 0.2414, "lr": 9.747435008912438e-05, "epoch": 0.5770221535291087, "percentage": 19.24, "elapsed_time": "2:40:59", "remaining_time": "11:15:33"}
|
| 31 |
+
{"current_steps": 290, "total_steps": 1455, "loss": 0.213, "lr": 9.708414759071059e-05, "epoch": 0.5976300875837197, "percentage": 19.93, "elapsed_time": "2:46:29", "remaining_time": "11:08:48"}
|
| 32 |
+
{"current_steps": 300, "total_steps": 1455, "loss": 0.2136, "lr": 9.666682605186835e-05, "epoch": 0.6182380216383307, "percentage": 20.62, "elapsed_time": "2:52:09", "remaining_time": "11:02:50"}
|
| 33 |
+
{"current_steps": 300, "total_steps": 1455, "eval_loss": 0.20567402243614197, "epoch": 0.6182380216383307, "percentage": 20.62, "elapsed_time": "2:54:43", "remaining_time": "11:12:41"}
|
| 34 |
+
{"current_steps": 310, "total_steps": 1455, "loss": 0.2293, "lr": 9.622262583714205e-05, "epoch": 0.6388459556929418, "percentage": 21.31, "elapsed_time": "3:00:12", "remaining_time": "11:05:35"}
|
| 35 |
+
{"current_steps": 320, "total_steps": 1455, "loss": 0.2264, "lr": 9.575180279237787e-05, "epoch": 0.6594538897475528, "percentage": 21.99, "elapsed_time": "3:05:56", "remaining_time": "10:59:30"}
|
| 36 |
+
{"current_steps": 330, "total_steps": 1455, "loss": 0.2235, "lr": 9.52546280973643e-05, "epoch": 0.6800618238021638, "percentage": 22.68, "elapsed_time": "3:11:50", "remaining_time": "10:54:01"}
|
| 37 |
+
{"current_steps": 340, "total_steps": 1455, "loss": 0.2289, "lr": 9.473138810964087e-05, "epoch": 0.7006697578567749, "percentage": 23.37, "elapsed_time": "3:17:31", "remaining_time": "10:47:46"}
|
| 38 |
+
{"current_steps": 350, "total_steps": 1455, "loss": 0.1932, "lr": 9.418238419956484e-05, "epoch": 0.7212776919113859, "percentage": 24.05, "elapsed_time": "3:23:33", "remaining_time": "10:42:40"}
|
| 39 |
+
{"current_steps": 360, "total_steps": 1455, "loss": 0.2299, "lr": 9.360793257673102e-05, "epoch": 0.7418856259659969, "percentage": 24.74, "elapsed_time": "3:29:09", "remaining_time": "10:36:11"}
|
| 40 |
+
{"current_steps": 370, "total_steps": 1455, "loss": 0.2067, "lr": 9.30083641078447e-05, "epoch": 0.762493560020608, "percentage": 25.43, "elapsed_time": "3:34:55", "remaining_time": "10:30:16"}
|
| 41 |
+
{"current_steps": 380, "total_steps": 1455, "loss": 0.2077, "lr": 9.23840241261524e-05, "epoch": 0.783101494075219, "percentage": 26.12, "elapsed_time": "3:40:41", "remaining_time": "10:24:18"}
|
| 42 |
+
{"current_steps": 390, "total_steps": 1455, "loss": 0.2195, "lr": 9.173527223254044e-05, "epoch": 0.80370942812983, "percentage": 26.8, "elapsed_time": "3:46:09", "remaining_time": "10:17:36"}
|
| 43 |
+
{"current_steps": 400, "total_steps": 1455, "loss": 0.2021, "lr": 9.106248208841569e-05, "epoch": 0.824317362184441, "percentage": 27.49, "elapsed_time": "3:51:37", "remaining_time": "10:10:54"}
|
| 44 |
+
{"current_steps": 400, "total_steps": 1455, "eval_loss": 0.19942662119865417, "epoch": 0.824317362184441, "percentage": 27.49, "elapsed_time": "3:54:10", "remaining_time": "10:17:38"}
|
| 45 |
+
{"current_steps": 410, "total_steps": 1455, "loss": 0.2139, "lr": 9.036604120048799e-05, "epoch": 0.844925296239052, "percentage": 28.18, "elapsed_time": "3:59:31", "remaining_time": "10:10:30"}
|
| 46 |
+
{"current_steps": 420, "total_steps": 1455, "loss": 0.1967, "lr": 8.964635069757802e-05, "epoch": 0.865533230293663, "percentage": 28.87, "elapsed_time": "4:04:49", "remaining_time": "10:03:18"}
|
| 47 |
+
{"current_steps": 410, "total_steps": 1455, "loss": 0.2139, "lr": 9.036604120048799e-05, "epoch": 0.844925296239052, "percentage": 28.18, "elapsed_time": "0:04:58", "remaining_time": "0:12:41"}
|
| 48 |
+
{"current_steps": 420, "total_steps": 1455, "loss": 0.1967, "lr": 8.964635069757802e-05, "epoch": 0.865533230293663, "percentage": 28.87, "elapsed_time": "0:10:03", "remaining_time": "0:24:47"}
|
| 49 |
+
{"current_steps": 430, "total_steps": 1455, "loss": 0.2141, "lr": 8.890382509957928e-05, "epoch": 0.8861411643482741, "percentage": 29.55, "elapsed_time": "0:15:11", "remaining_time": "0:36:13"}
|
| 50 |
+
{"current_steps": 440, "total_steps": 1455, "loss": 0.1967, "lr": 8.813889207870718e-05, "epoch": 0.9067490984028851, "percentage": 30.24, "elapsed_time": "0:20:30", "remaining_time": "0:47:17"}
|
| 51 |
+
{"current_steps": 450, "total_steps": 1455, "loss": 0.2231, "lr": 8.735199221317285e-05, "epoch": 0.9273570324574961, "percentage": 30.93, "elapsed_time": "0:26:18", "remaining_time": "0:58:44"}
|
| 52 |
+
{"current_steps": 460, "total_steps": 1455, "loss": 0.1916, "lr": 8.654357873342345e-05, "epoch": 0.9479649665121072, "percentage": 31.62, "elapsed_time": "0:31:32", "remaining_time": "1:08:13"}
|
| 53 |
+
{"current_steps": 470, "total_steps": 1455, "loss": 0.2261, "lr": 8.571411726109519e-05, "epoch": 0.9685729005667182, "percentage": 32.3, "elapsed_time": "0:36:51", "remaining_time": "1:17:14"}
|
| 54 |
+
{"current_steps": 480, "total_steps": 1455, "loss": 0.1987, "lr": 8.486408554082935e-05, "epoch": 0.9891808346213292, "percentage": 32.99, "elapsed_time": "0:41:35", "remaining_time": "1:24:29"}
|
| 55 |
+
{"current_steps": 490, "total_steps": 1455, "loss": 0.2067, "lr": 8.399397316510596e-05, "epoch": 1.0103039670273055, "percentage": 33.68, "elapsed_time": "0:46:49", "remaining_time": "1:32:13"}
|
| 56 |
+
{"current_steps": 500, "total_steps": 1455, "loss": 0.1384, "lr": 8.310428129225325e-05, "epoch": 1.0309119010819165, "percentage": 34.36, "elapsed_time": "0:51:57", "remaining_time": "1:39:14"}
|
| 57 |
+
{"current_steps": 500, "total_steps": 1455, "eval_loss": 0.19919553399085999, "epoch": 1.0309119010819165, "percentage": 34.36, "elapsed_time": "0:54:24", "remaining_time": "1:43:55"}
|
| 58 |
+
{"current_steps": 510, "total_steps": 1455, "loss": 0.1319, "lr": 8.219552235779578e-05, "epoch": 1.0515198351365276, "percentage": 35.05, "elapsed_time": "0:59:09", "remaining_time": "1:49:36"}
|
| 59 |
+
{"current_steps": 520, "total_steps": 1455, "loss": 0.126, "lr": 8.126821977930711e-05, "epoch": 1.0721277691911386, "percentage": 35.74, "elapsed_time": "1:04:04", "remaining_time": "1:55:12"}
|
| 60 |
+
{"current_steps": 530, "total_steps": 1455, "loss": 0.1473, "lr": 8.032290765493704e-05, "epoch": 1.0927357032457496, "percentage": 36.43, "elapsed_time": "1:09:07", "remaining_time": "2:00:39"}
|
| 61 |
+
{"current_steps": 540, "total_steps": 1455, "loss": 0.146, "lr": 7.936013045578745e-05, "epoch": 1.1133436373003607, "percentage": 37.11, "elapsed_time": "1:14:45", "remaining_time": "2:06:40"}
|
| 62 |
+
{"current_steps": 550, "total_steps": 1455, "loss": 0.1349, "lr": 7.838044271231333e-05, "epoch": 1.1339515713549717, "percentage": 37.8, "elapsed_time": "1:20:26", "remaining_time": "2:12:22"}
|
| 63 |
+
{"current_steps": 560, "total_steps": 1455, "loss": 0.14, "lr": 7.738440869493018e-05, "epoch": 1.1545595054095827, "percentage": 38.49, "elapsed_time": "1:25:20", "remaining_time": "2:16:23"}
|
| 64 |
+
{"current_steps": 570, "total_steps": 1455, "loss": 0.1395, "lr": 7.63726020890112e-05, "epoch": 1.1751674394641938, "percentage": 39.18, "elapsed_time": "1:30:54", "remaining_time": "2:21:09"}
|
| 65 |
+
{"current_steps": 580, "total_steps": 1455, "loss": 0.1381, "lr": 7.534560566446216e-05, "epoch": 1.1957753735188048, "percentage": 39.86, "elapsed_time": "1:36:05", "remaining_time": "2:24:57"}
|
| 66 |
+
{"current_steps": 590, "total_steps": 1455, "loss": 0.1267, "lr": 7.430401094006339e-05, "epoch": 1.2163833075734158, "percentage": 40.55, "elapsed_time": "1:41:27", "remaining_time": "2:28:44"}
|
| 67 |
+
{"current_steps": 600, "total_steps": 1455, "loss": 0.1487, "lr": 7.324841784277302e-05, "epoch": 1.2369912416280269, "percentage": 41.24, "elapsed_time": "1:46:35", "remaining_time": "2:31:53"}
|
| 68 |
+
{"current_steps": 600, "total_steps": 1455, "eval_loss": 0.19719114899635315, "epoch": 1.2369912416280269, "percentage": 41.24, "elapsed_time": "1:49:02", "remaining_time": "2:35:23"}
|
| 69 |
+
{"current_steps": 610, "total_steps": 1455, "loss": 0.1515, "lr": 7.217943436218728e-05, "epoch": 1.2575991756826377, "percentage": 41.92, "elapsed_time": "1:54:30", "remaining_time": "2:38:36"}
|
| 70 |
+
{"current_steps": 620, "total_steps": 1455, "loss": 0.1345, "lr": 7.109767620035689e-05, "epoch": 1.2782071097372487, "percentage": 42.61, "elapsed_time": "1:59:47", "remaining_time": "2:41:19"}
|
| 71 |
+
{"current_steps": 630, "total_steps": 1455, "loss": 0.1387, "lr": 7.000376641716133e-05, "epoch": 1.2988150437918597, "percentage": 43.3, "elapsed_time": "2:04:52", "remaining_time": "2:43:30"}
|
| 72 |
+
{"current_steps": 640, "total_steps": 1455, "loss": 0.1185, "lr": 6.889833507144532e-05, "epoch": 1.3194229778464708, "percentage": 43.99, "elapsed_time": "2:09:55", "remaining_time": "2:45:27"}
|
| 73 |
+
{"current_steps": 650, "total_steps": 1455, "loss": 0.1569, "lr": 6.778201885812404e-05, "epoch": 1.3400309119010818, "percentage": 44.67, "elapsed_time": "2:15:22", "remaining_time": "2:47:39"}
|
| 74 |
+
{"current_steps": 660, "total_steps": 1455, "loss": 0.1469, "lr": 6.66554607414661e-05, "epoch": 1.3606388459556928, "percentage": 45.36, "elapsed_time": "2:20:43", "remaining_time": "2:49:30"}
|
| 75 |
+
{"current_steps": 670, "total_steps": 1455, "loss": 0.1249, "lr": 6.551930958476571e-05, "epoch": 1.3812467800103039, "percentage": 46.05, "elapsed_time": "2:25:43", "remaining_time": "2:50:43"}
|
| 76 |
+
{"current_steps": 680, "total_steps": 1455, "loss": 0.1348, "lr": 6.437421977661709e-05, "epoch": 1.401854714064915, "percentage": 46.74, "elapsed_time": "2:31:19", "remaining_time": "2:52:27"}
|
| 77 |
+
{"current_steps": 690, "total_steps": 1455, "loss": 0.1274, "lr": 6.322085085400644e-05, "epoch": 1.422462648119526, "percentage": 47.42, "elapsed_time": "2:36:57", "remaining_time": "2:54:01"}
|
| 78 |
+
{"current_steps": 700, "total_steps": 1455, "loss": 0.1437, "lr": 6.205986712243875e-05, "epoch": 1.443070582174137, "percentage": 48.11, "elapsed_time": "2:42:04", "remaining_time": "2:54:48"}
|
| 79 |
+
{"current_steps": 700, "total_steps": 1455, "eval_loss": 0.1935451626777649, "epoch": 1.443070582174137, "percentage": 48.11, "elapsed_time": "2:44:31", "remaining_time": "2:57:27"}
|
| 80 |
+
{"current_steps": 710, "total_steps": 1455, "loss": 0.1407, "lr": 6.0891937273317935e-05, "epoch": 1.463678516228748, "percentage": 48.8, "elapsed_time": "2:49:37", "remaining_time": "2:57:58"}
|
| 81 |
+
{"current_steps": 720, "total_steps": 1455, "loss": 0.1474, "lr": 5.9717733998800803e-05, "epoch": 1.484286450283359, "percentage": 49.48, "elapsed_time": "2:54:49", "remaining_time": "2:58:28"}
|
| 82 |
+
{"current_steps": 730, "total_steps": 1455, "loss": 0.1393, "lr": 5.853793360434687e-05, "epoch": 1.50489438433797, "percentage": 50.17, "elapsed_time": "3:00:10", "remaining_time": "2:58:56"}
|
| 83 |
+
{"current_steps": 740, "total_steps": 1455, "loss": 0.1396, "lr": 5.735321561918697e-05, "epoch": 1.525502318392581, "percentage": 50.86, "elapsed_time": "3:05:55", "remaining_time": "2:59:38"}
|
| 84 |
+
{"current_steps": 750, "total_steps": 1455, "loss": 0.1296, "lr": 5.61642624049349e-05, "epoch": 1.5461102524471921, "percentage": 51.55, "elapsed_time": "3:11:35", "remaining_time": "3:00:05"}
|
| 85 |
+
{"current_steps": 760, "total_steps": 1455, "loss": 0.1261, "lr": 5.497175876256796e-05, "epoch": 1.5667181865018032, "percentage": 52.23, "elapsed_time": "3:17:17", "remaining_time": "3:00:24"}
|
| 86 |
+
{"current_steps": 770, "total_steps": 1455, "loss": 0.1513, "lr": 5.377639153800229e-05, "epoch": 1.5873261205564142, "percentage": 52.92, "elapsed_time": "3:22:26", "remaining_time": "3:00:05"}
|
| 87 |
+
{"current_steps": 780, "total_steps": 1455, "loss": 0.1465, "lr": 5.2578849226490525e-05, "epoch": 1.6079340546110252, "percentage": 53.61, "elapsed_time": "3:27:51", "remaining_time": "2:59:52"}
|
| 88 |
+
{"current_steps": 790, "total_steps": 1455, "loss": 0.1214, "lr": 5.137982157606937e-05, "epoch": 1.6285419886656363, "percentage": 54.3, "elapsed_time": "3:33:30", "remaining_time": "2:59:43"}
|
| 89 |
+
{"current_steps": 800, "total_steps": 1455, "loss": 0.1371, "lr": 5.017999919028566e-05, "epoch": 1.6491499227202473, "percentage": 54.98, "elapsed_time": "3:39:20", "remaining_time": "2:59:34"}
|
| 90 |
+
{"current_steps": 800, "total_steps": 1455, "eval_loss": 0.19273868203163147, "epoch": 1.6491499227202473, "percentage": 54.98, "elapsed_time": "3:41:47", "remaining_time": "3:01:35"}
|
| 91 |
+
{"current_steps": 810, "total_steps": 1455, "loss": 0.1359, "lr": 4.898007313042975e-05, "epoch": 1.6697578567748583, "percentage": 55.67, "elapsed_time": "3:47:22", "remaining_time": "3:01:03"}
|
| 92 |
+
{"current_steps": 820, "total_steps": 1455, "loss": 0.1306, "lr": 4.7780734517504985e-05, "epoch": 1.6903657908294694, "percentage": 56.36, "elapsed_time": "3:52:28", "remaining_time": "3:00:01"}
|
| 93 |
+
{"current_steps": 830, "total_steps": 1455, "loss": 0.1414, "lr": 4.658267413416326e-05, "epoch": 1.7109737248840804, "percentage": 57.04, "elapsed_time": "3:58:37", "remaining_time": "2:59:41"}
|
| 94 |
+
{"current_steps": 840, "total_steps": 1455, "loss": 0.1407, "lr": 4.5386582026834906e-05, "epoch": 1.7315816589386914, "percentage": 57.73, "elapsed_time": "4:03:51", "remaining_time": "2:58:32"}
|
| 95 |
+
{"current_steps": 810, "total_steps": 1455, "loss": 0.1359, "lr": 4.898007313042975e-05, "epoch": 1.6697578567748583, "percentage": 55.67, "elapsed_time": "0:05:33", "remaining_time": "0:04:25"}
|
| 96 |
+
{"current_steps": 820, "total_steps": 1455, "loss": 0.1306, "lr": 4.7780734517504985e-05, "epoch": 1.6903657908294694, "percentage": 56.36, "elapsed_time": "0:10:43", "remaining_time": "0:08:18"}
|
| 97 |
+
{"current_steps": 830, "total_steps": 1455, "loss": 0.1414, "lr": 4.658267413416326e-05, "epoch": 1.7109737248840804, "percentage": 57.04, "elapsed_time": "0:16:58", "remaining_time": "0:12:46"}
|
| 98 |
+
{"current_steps": 840, "total_steps": 1455, "loss": 0.1407, "lr": 4.5386582026834906e-05, "epoch": 1.7315816589386914, "percentage": 57.73, "elapsed_time": "0:22:16", "remaining_time": "0:16:18"}
|
| 99 |
+
{"current_steps": 850, "total_steps": 1455, "loss": 0.1291, "lr": 4.4193147108283016e-05, "epoch": 1.7521895929933025, "percentage": 58.42, "elapsed_time": "0:27:44", "remaining_time": "0:19:44"}
|
| 100 |
+
{"current_steps": 860, "total_steps": 1455, "loss": 0.1434, "lr": 4.300305676081057e-05, "epoch": 1.7727975270479135, "percentage": 59.11, "elapsed_time": "0:32:53", "remaining_time": "0:22:45"}
|
| 101 |
+
{"current_steps": 870, "total_steps": 1455, "loss": 0.1295, "lr": 4.1816996440349104e-05, "epoch": 1.7934054611025245, "percentage": 59.79, "elapsed_time": "0:38:04", "remaining_time": "0:25:36"}
|
| 102 |
+
{"current_steps": 880, "total_steps": 1455, "loss": 0.1325, "lr": 4.063564928165682e-05, "epoch": 1.8140133951571356, "percentage": 60.48, "elapsed_time": "0:43:14", "remaining_time": "0:28:15"}
|
| 103 |
+
{"current_steps": 890, "total_steps": 1455, "loss": 0.164, "lr": 3.9459695704853836e-05, "epoch": 1.8346213292117466, "percentage": 61.17, "elapsed_time": "0:49:06", "remaining_time": "0:31:10"}
|
| 104 |
+
{"current_steps": 900, "total_steps": 1455, "loss": 0.147, "lr": 3.828981302352065e-05, "epoch": 1.8552292632663576, "percentage": 61.86, "elapsed_time": "0:54:55", "remaining_time": "0:33:52"}
|
| 105 |
+
{"current_steps": 900, "total_steps": 1455, "eval_loss": 0.1883440464735031, "epoch": 1.8552292632663576, "percentage": 61.86, "elapsed_time": "0:57:24", "remaining_time": "0:35:24"}
|
| 106 |
+
{"current_steps": 910, "total_steps": 1455, "loss": 0.1228, "lr": 3.712667505458622e-05, "epoch": 1.8758371973209687, "percentage": 62.54, "elapsed_time": "1:02:23", "remaining_time": "0:37:21"}
|
| 107 |
+
{"current_steps": 920, "total_steps": 1455, "loss": 0.135, "lr": 3.5970951730229785e-05, "epoch": 1.8964451313755797, "percentage": 63.23, "elapsed_time": "1:07:28", "remaining_time": "0:39:14"}
|
| 108 |
+
{"current_steps": 930, "total_steps": 1455, "loss": 0.1197, "lr": 3.482330871202029e-05, "epoch": 1.9170530654301907, "percentage": 63.92, "elapsed_time": "1:12:55", "remaining_time": "0:41:09"}
|
| 109 |
+
{"current_steps": 940, "total_steps": 1455, "loss": 0.1395, "lr": 3.3684407007515484e-05, "epoch": 1.9376609994848017, "percentage": 64.6, "elapsed_time": "1:18:46", "remaining_time": "0:43:09"}
|
| 110 |
+
{"current_steps": 950, "total_steps": 1455, "loss": 0.1347, "lr": 3.255490258954167e-05, "epoch": 1.9582689335394128, "percentage": 65.29, "elapsed_time": "1:24:10", "remaining_time": "0:44:44"}
|
| 111 |
+
{"current_steps": 960, "total_steps": 1455, "loss": 0.12, "lr": 3.14354460183732e-05, "epoch": 1.9788768675940238, "percentage": 65.98, "elapsed_time": "1:29:31", "remaining_time": "0:46:09"}
|
| 112 |
+
{"current_steps": 970, "total_steps": 1455, "loss": 0.1289, "lr": 3.032668206702959e-05, "epoch": 1.9994848016486348, "percentage": 66.67, "elapsed_time": "1:35:03", "remaining_time": "0:47:31"}
|
| 113 |
+
{"current_steps": 980, "total_steps": 1455, "loss": 0.0908, "lr": 2.9229249349905684e-05, "epoch": 2.020607934054611, "percentage": 67.35, "elapsed_time": "1:40:36", "remaining_time": "0:48:45"}
|
| 114 |
+
{"current_steps": 990, "total_steps": 1455, "loss": 0.0718, "lr": 2.8143779954949267e-05, "epoch": 2.041215868109222, "percentage": 68.04, "elapsed_time": "1:46:12", "remaining_time": "0:49:53"}
|
| 115 |
+
{"current_steps": 1000, "total_steps": 1455, "loss": 0.0668, "lr": 2.70708990795975e-05, "epoch": 2.061823802163833, "percentage": 68.73, "elapsed_time": "1:51:32", "remaining_time": "0:50:45"}
|
| 116 |
+
{"current_steps": 1000, "total_steps": 1455, "eval_loss": 0.1961071491241455, "epoch": 2.061823802163833, "percentage": 68.73, "elapsed_time": "1:54:02", "remaining_time": "0:51:53"}
|
| 117 |
+
{"current_steps": 1010, "total_steps": 1455, "loss": 0.0782, "lr": 2.6011224670682244e-05, "epoch": 2.082431736218444, "percentage": 69.42, "elapsed_time": "1:59:43", "remaining_time": "0:52:44"}
|
| 118 |
+
{"current_steps": 1020, "total_steps": 1455, "loss": 0.0598, "lr": 2.4965367068511365e-05, "epoch": 2.103039670273055, "percentage": 70.1, "elapsed_time": "2:05:12", "remaining_time": "0:53:23"}
|
| 119 |
+
{"current_steps": 1030, "total_steps": 1455, "loss": 0.0744, "lr": 2.393392865533129e-05, "epoch": 2.123647604327666, "percentage": 70.79, "elapsed_time": "2:10:52", "remaining_time": "0:54:00"}
|
| 120 |
+
{"current_steps": 1040, "total_steps": 1455, "loss": 0.0604, "lr": 2.291750350837301e-05, "epoch": 2.1442555383822772, "percentage": 71.48, "elapsed_time": "2:15:39", "remaining_time": "0:54:07"}
|
| 121 |
+
{"current_steps": 1050, "total_steps": 1455, "loss": 0.0635, "lr": 2.1916677057681785e-05, "epoch": 2.1648634724368883, "percentage": 72.16, "elapsed_time": "2:20:40", "remaining_time": "0:54:15"}
|
| 122 |
+
{"current_steps": 1060, "total_steps": 1455, "loss": 0.0795, "lr": 2.0932025748927013e-05, "epoch": 2.1854714064914993, "percentage": 72.85, "elapsed_time": "2:25:56", "remaining_time": "0:54:23"}
|
| 123 |
+
{"current_steps": 1070, "total_steps": 1455, "loss": 0.0662, "lr": 1.996411671138718e-05, "epoch": 2.2060793405461103, "percentage": 73.54, "elapsed_time": "2:31:17", "remaining_time": "0:54:26"}
|
| 124 |
+
{"current_steps": 1080, "total_steps": 1455, "loss": 0.0669, "lr": 1.901350743130051e-05, "epoch": 2.2266872746007214, "percentage": 74.23, "elapsed_time": "2:36:57", "remaining_time": "0:54:29"}
|
| 125 |
+
{"current_steps": 1090, "total_steps": 1455, "loss": 0.0717, "lr": 1.8080745430769814e-05, "epoch": 2.2472952086553324, "percentage": 74.91, "elapsed_time": "2:42:21", "remaining_time": "0:54:22"}
|
| 126 |
+
{"current_steps": 1100, "total_steps": 1455, "loss": 0.077, "lr": 1.716636795240641e-05, "epoch": 2.2679031427099434, "percentage": 75.6, "elapsed_time": "2:47:42", "remaining_time": "0:54:07"}
|
| 127 |
+
{"current_steps": 1100, "total_steps": 1455, "eval_loss": 0.20724114775657654, "epoch": 2.2679031427099434, "percentage": 75.6, "elapsed_time": "2:50:11", "remaining_time": "0:54:55"}
|
| 128 |
+
{"current_steps": 1110, "total_steps": 1455, "loss": 0.074, "lr": 1.6270901649894604e-05, "epoch": 2.2885110767645545, "percentage": 76.29, "elapsed_time": "2:55:41", "remaining_time": "0:54:36"}
|
| 129 |
+
{"current_steps": 1120, "total_steps": 1455, "loss": 0.0753, "lr": 1.5394862284655264e-05, "epoch": 2.3091190108191655, "percentage": 76.98, "elapsed_time": "3:01:07", "remaining_time": "0:54:10"}
|
| 130 |
+
{"current_steps": 1130, "total_steps": 1455, "loss": 0.0679, "lr": 1.4538754428782753e-05, "epoch": 2.3297269448737765, "percentage": 77.66, "elapsed_time": "3:06:24", "remaining_time": "0:53:36"}
|
| 131 |
+
{"current_steps": 1140, "total_steps": 1455, "loss": 0.0678, "lr": 1.370307117442684e-05, "epoch": 2.3503348789283875, "percentage": 78.35, "elapsed_time": "3:11:33", "remaining_time": "0:52:55"}
|
| 132 |
+
{"current_steps": 1150, "total_steps": 1455, "loss": 0.0658, "lr": 1.2888293849786503e-05, "epoch": 2.3709428129829986, "percentage": 79.04, "elapsed_time": "3:17:05", "remaining_time": "0:52:16"}
|
| 133 |
+
{"current_steps": 1160, "total_steps": 1455, "loss": 0.0671, "lr": 1.2094891741879521e-05, "epoch": 2.3915507470376096, "percentage": 79.73, "elapsed_time": "3:22:45", "remaining_time": "0:51:33"}
|
| 134 |
+
{"current_steps": 1170, "total_steps": 1455, "loss": 0.0686, "lr": 1.1323321826247346e-05, "epoch": 2.4121586810922206, "percentage": 80.41, "elapsed_time": "3:27:35", "remaining_time": "0:50:34"}
|
| 135 |
+
{"current_steps": 1180, "total_steps": 1455, "loss": 0.0594, "lr": 1.0574028503751138e-05, "epoch": 2.4327666151468317, "percentage": 81.1, "elapsed_time": "3:32:44", "remaining_time": "0:49:34"}
|
| 136 |
+
{"current_steps": 1190, "total_steps": 1455, "loss": 0.0668, "lr": 9.847443344610297e-06, "epoch": 2.4533745492014427, "percentage": 81.79, "elapsed_time": "3:38:12", "remaining_time": "0:48:35"}
|
| 137 |
+
{"current_steps": 1200, "total_steps": 1455, "loss": 0.0707, "lr": 9.143984839831082e-06, "epoch": 2.4739824832560537, "percentage": 82.47, "elapsed_time": "3:43:14", "remaining_time": "0:47:26"}
|
| 138 |
+
{"current_steps": 1010, "total_steps": 1455, "loss": 0.0782, "lr": 2.6011224670682244e-05, "epoch": 2.082431736218444, "percentage": 69.42, "elapsed_time": "0:05:24", "remaining_time": "0:02:23"}
|
| 139 |
+
{"current_steps": 1020, "total_steps": 1455, "loss": 0.0598, "lr": 2.4965367068511365e-05, "epoch": 2.103039670273055, "percentage": 70.1, "elapsed_time": "0:11:04", "remaining_time": "0:04:43"}
|
| 140 |
+
{"current_steps": 1030, "total_steps": 1455, "loss": 0.0744, "lr": 2.393392865533129e-05, "epoch": 2.123647604327666, "percentage": 70.79, "elapsed_time": "0:16:58", "remaining_time": "0:07:00"}
|
| 141 |
+
{"current_steps": 1040, "total_steps": 1455, "loss": 0.0604, "lr": 2.291750350837301e-05, "epoch": 2.1442555383822772, "percentage": 71.48, "elapsed_time": "0:21:54", "remaining_time": "0:08:44"}
|
| 142 |
+
{"current_steps": 1050, "total_steps": 1455, "loss": 0.0635, "lr": 2.1916677057681785e-05, "epoch": 2.1648634724368883, "percentage": 72.16, "elapsed_time": "0:27:04", "remaining_time": "0:10:26"}
|
| 143 |
+
{"current_steps": 1060, "total_steps": 1455, "loss": 0.0795, "lr": 2.0932025748927013e-05, "epoch": 2.1854714064914993, "percentage": 72.85, "elapsed_time": "0:32:31", "remaining_time": "0:12:07"}
|
| 144 |
+
{"current_steps": 1070, "total_steps": 1455, "loss": 0.0662, "lr": 1.996411671138718e-05, "epoch": 2.2060793405461103, "percentage": 73.54, "elapsed_time": "0:38:02", "remaining_time": "0:13:41"}
|
| 145 |
+
{"current_steps": 1080, "total_steps": 1455, "loss": 0.0669, "lr": 1.901350743130051e-05, "epoch": 2.2266872746007214, "percentage": 74.23, "elapsed_time": "0:43:52", "remaining_time": "0:15:14"}
|
| 146 |
+
{"current_steps": 1090, "total_steps": 1455, "loss": 0.0717, "lr": 1.8080745430769814e-05, "epoch": 2.2472952086553324, "percentage": 74.91, "elapsed_time": "0:49:26", "remaining_time": "0:16:33"}
|
| 147 |
+
{"current_steps": 1100, "total_steps": 1455, "loss": 0.077, "lr": 1.716636795240641e-05, "epoch": 2.2679031427099434, "percentage": 75.6, "elapsed_time": "0:54:57", "remaining_time": "0:17:44"}
|
| 148 |
+
{"current_steps": 1100, "total_steps": 1455, "eval_loss": 0.20724114775657654, "epoch": 2.2679031427099434, "percentage": 75.6, "elapsed_time": "0:57:31", "remaining_time": "0:18:33"}
|
| 149 |
+
{"current_steps": 1110, "total_steps": 1455, "loss": 0.074, "lr": 1.6270901649894604e-05, "epoch": 2.2885110767645545, "percentage": 76.29, "elapsed_time": "1:03:12", "remaining_time": "0:19:38"}
|
| 150 |
+
{"current_steps": 1120, "total_steps": 1455, "loss": 0.0753, "lr": 1.5394862284655264e-05, "epoch": 2.3091190108191655, "percentage": 76.98, "elapsed_time": "1:08:48", "remaining_time": "0:20:34"}
|
| 151 |
+
{"current_steps": 1130, "total_steps": 1455, "loss": 0.0679, "lr": 1.4538754428782753e-05, "epoch": 2.3297269448737765, "percentage": 77.66, "elapsed_time": "1:14:15", "remaining_time": "0:21:21"}
|
| 152 |
+
{"current_steps": 1140, "total_steps": 1455, "loss": 0.0678, "lr": 1.370307117442684e-05, "epoch": 2.3503348789283875, "percentage": 78.35, "elapsed_time": "1:19:34", "remaining_time": "0:21:59"}
|
| 153 |
+
{"current_steps": 1150, "total_steps": 1455, "loss": 0.0658, "lr": 1.2888293849786503e-05, "epoch": 2.3709428129829986, "percentage": 79.04, "elapsed_time": "1:25:18", "remaining_time": "0:22:37"}
|
| 154 |
+
{"current_steps": 1160, "total_steps": 1455, "loss": 0.0671, "lr": 1.2094891741879521e-05, "epoch": 2.3915507470376096, "percentage": 79.73, "elapsed_time": "1:31:08", "remaining_time": "0:23:10"}
|
| 155 |
+
{"current_steps": 1170, "total_steps": 1455, "loss": 0.0686, "lr": 1.1323321826247346e-05, "epoch": 2.4121586810922206, "percentage": 80.41, "elapsed_time": "1:36:08", "remaining_time": "0:23:25"}
|
| 156 |
+
{"current_steps": 1180, "total_steps": 1455, "loss": 0.0594, "lr": 1.0574028503751138e-05, "epoch": 2.4327666151468317, "percentage": 81.1, "elapsed_time": "1:41:27", "remaining_time": "0:23:38"}
|
| 157 |
+
{"current_steps": 1190, "total_steps": 1455, "loss": 0.0668, "lr": 9.847443344610297e-06, "epoch": 2.4533745492014427, "percentage": 81.79, "elapsed_time": "1:47:07", "remaining_time": "0:23:51"}
|
| 158 |
+
{"current_steps": 1200, "total_steps": 1455, "loss": 0.0707, "lr": 9.143984839831082e-06, "epoch": 2.4739824832560537, "percentage": 82.47, "elapsed_time": "1:52:18", "remaining_time": "0:23:52"}
|
| 159 |
+
{"current_steps": 1200, "total_steps": 1455, "eval_loss": 0.2032017707824707, "epoch": 2.4739824832560537, "percentage": 82.47, "elapsed_time": "1:54:52", "remaining_time": "0:24:24"}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b4fdf6b353a5b60166b0a095e0400b0da11001271684dfd8a6b84b3ca19b3172
|
| 3 |
+
size 5816
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|