Vira Rithy commited on
Commit ·
36b68ca
1
Parent(s): cd03aec
Upload checkpoints and training logs (runs)
Browse files- .gitattributes +1 -0
- checkpoint-1000/adapter_config.json +3 -42
- checkpoint-1000/added_tokens.json +3 -24
- checkpoint-1000/special_tokens_map.json +3 -31
- checkpoint-1000/tokenizer_config.json +3 -208
- checkpoint-1000/trainer_state.json +3 -399
- checkpoint-1000/vocab.json +0 -0
- checkpoint-1788/adapter_config.json +3 -42
- checkpoint-1788/added_tokens.json +3 -24
- checkpoint-1788/special_tokens_map.json +3 -31
- checkpoint-1788/tokenizer_config.json +3 -208
- checkpoint-1788/trainer_state.json +3 -680
- checkpoint-1788/vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -33,6 +33,7 @@ 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
|
|
|
|
| 36 |
checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
checkpoint-1000/*.pt filter=lfs diff=lfs merge=lfs -text
|
| 38 |
checkpoint-1000/*.safetensors 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 |
+
*.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 38 |
checkpoint-1000/*.pt filter=lfs diff=lfs merge=lfs -text
|
| 39 |
checkpoint-1000/*.safetensors filter=lfs diff=lfs merge=lfs -text
|
checkpoint-1000/adapter_config.json
CHANGED
|
@@ -1,42 +1,3 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
"base_model_name_or_path": "Qwen/Qwen2.5-1.5B",
|
| 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": 64,
|
| 17 |
-
"lora_bias": false,
|
| 18 |
-
"lora_dropout": 0.1,
|
| 19 |
-
"megatron_config": null,
|
| 20 |
-
"megatron_core": "megatron.core",
|
| 21 |
-
"modules_to_save": null,
|
| 22 |
-
"peft_type": "LORA",
|
| 23 |
-
"qalora_group_size": 16,
|
| 24 |
-
"r": 32,
|
| 25 |
-
"rank_pattern": {},
|
| 26 |
-
"revision": null,
|
| 27 |
-
"target_modules": [
|
| 28 |
-
"o_proj",
|
| 29 |
-
"k_proj",
|
| 30 |
-
"down_proj",
|
| 31 |
-
"v_proj",
|
| 32 |
-
"gate_proj",
|
| 33 |
-
"up_proj",
|
| 34 |
-
"q_proj"
|
| 35 |
-
],
|
| 36 |
-
"target_parameters": null,
|
| 37 |
-
"task_type": "CAUSAL_LM",
|
| 38 |
-
"trainable_token_indices": null,
|
| 39 |
-
"use_dora": false,
|
| 40 |
-
"use_qalora": false,
|
| 41 |
-
"use_rslora": false
|
| 42 |
-
}
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef1b304e1f3e2f865ca24b9eadff513cad2b85a4dee1a4e0a77a72c73f5f2e77
|
| 3 |
+
size 928
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-1000/added_tokens.json
CHANGED
|
@@ -1,24 +1,3 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
|
| 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 |
-
}
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:58b54bbe36fc752f79a24a271ef66a0a0830054b4dfad94bde757d851968060b
|
| 3 |
+
size 605
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-1000/special_tokens_map.json
CHANGED
|
@@ -1,31 +1,3 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
|
| 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": "<|endoftext|>",
|
| 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 |
-
}
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6676f091c8bc4d1b50146427cfde92073402866b87b6e39223227931b70083e9
|
| 3 |
+
size 616
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-1000/tokenizer_config.json
CHANGED
|
@@ -1,208 +1,3 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
|
| 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 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 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": "<|endoftext|>",
|
| 201 |
-
"errors": "replace",
|
| 202 |
-
"extra_special_tokens": {},
|
| 203 |
-
"model_max_length": 131072,
|
| 204 |
-
"pad_token": "<|endoftext|>",
|
| 205 |
-
"split_special_tokens": false,
|
| 206 |
-
"tokenizer_class": "Qwen2Tokenizer",
|
| 207 |
-
"unk_token": null
|
| 208 |
-
}
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a5dae0102f342a3b6bc2a4d03f430ed83666dcab8879c9ee44c08a3d9095132d
|
| 3 |
+
size 7259
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-1000/trainer_state.json
CHANGED
|
@@ -1,399 +1,3 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
"epoch": 1.6753246753246753,
|
| 5 |
-
"eval_steps": 500,
|
| 6 |
-
"global_step": 1000,
|
| 7 |
-
"is_hyper_param_search": false,
|
| 8 |
-
"is_local_process_zero": true,
|
| 9 |
-
"is_world_process_zero": true,
|
| 10 |
-
"log_history": [
|
| 11 |
-
{
|
| 12 |
-
"epoch": 0.033514872224549644,
|
| 13 |
-
"grad_norm": 6.138762950897217,
|
| 14 |
-
"learning_rate": 2.23463687150838e-06,
|
| 15 |
-
"loss": 6.0548,
|
| 16 |
-
"step": 20
|
| 17 |
-
},
|
| 18 |
-
{
|
| 19 |
-
"epoch": 0.06702974444909929,
|
| 20 |
-
"grad_norm": 4.608607769012451,
|
| 21 |
-
"learning_rate": 4.46927374301676e-06,
|
| 22 |
-
"loss": 5.9799,
|
| 23 |
-
"step": 40
|
| 24 |
-
},
|
| 25 |
-
{
|
| 26 |
-
"epoch": 0.10054461667364893,
|
| 27 |
-
"grad_norm": 3.4575345516204834,
|
| 28 |
-
"learning_rate": 6.70391061452514e-06,
|
| 29 |
-
"loss": 5.61,
|
| 30 |
-
"step": 60
|
| 31 |
-
},
|
| 32 |
-
{
|
| 33 |
-
"epoch": 0.13405948889819858,
|
| 34 |
-
"grad_norm": 3.4996674060821533,
|
| 35 |
-
"learning_rate": 8.93854748603352e-06,
|
| 36 |
-
"loss": 5.0586,
|
| 37 |
-
"step": 80
|
| 38 |
-
},
|
| 39 |
-
{
|
| 40 |
-
"epoch": 0.16757436112274823,
|
| 41 |
-
"grad_norm": 2.155829668045044,
|
| 42 |
-
"learning_rate": 1.11731843575419e-05,
|
| 43 |
-
"loss": 4.7232,
|
| 44 |
-
"step": 100
|
| 45 |
-
},
|
| 46 |
-
{
|
| 47 |
-
"epoch": 0.20108923334729786,
|
| 48 |
-
"grad_norm": 2.0759589672088623,
|
| 49 |
-
"learning_rate": 1.340782122905028e-05,
|
| 50 |
-
"loss": 4.3872,
|
| 51 |
-
"step": 120
|
| 52 |
-
},
|
| 53 |
-
{
|
| 54 |
-
"epoch": 0.23460410557184752,
|
| 55 |
-
"grad_norm": 2.274566173553467,
|
| 56 |
-
"learning_rate": 1.564245810055866e-05,
|
| 57 |
-
"loss": 4.2721,
|
| 58 |
-
"step": 140
|
| 59 |
-
},
|
| 60 |
-
{
|
| 61 |
-
"epoch": 0.26811897779639715,
|
| 62 |
-
"grad_norm": 2.4159297943115234,
|
| 63 |
-
"learning_rate": 1.787709497206704e-05,
|
| 64 |
-
"loss": 4.2317,
|
| 65 |
-
"step": 160
|
| 66 |
-
},
|
| 67 |
-
{
|
| 68 |
-
"epoch": 0.3016338500209468,
|
| 69 |
-
"grad_norm": 2.6904704570770264,
|
| 70 |
-
"learning_rate": 1.9987569919204478e-05,
|
| 71 |
-
"loss": 4.1439,
|
| 72 |
-
"step": 180
|
| 73 |
-
},
|
| 74 |
-
{
|
| 75 |
-
"epoch": 0.33514872224549647,
|
| 76 |
-
"grad_norm": 2.5504817962646484,
|
| 77 |
-
"learning_rate": 1.973896830329397e-05,
|
| 78 |
-
"loss": 4.1092,
|
| 79 |
-
"step": 200
|
| 80 |
-
},
|
| 81 |
-
{
|
| 82 |
-
"epoch": 0.3686635944700461,
|
| 83 |
-
"grad_norm": 2.610886812210083,
|
| 84 |
-
"learning_rate": 1.949036668738347e-05,
|
| 85 |
-
"loss": 4.0378,
|
| 86 |
-
"step": 220
|
| 87 |
-
},
|
| 88 |
-
{
|
| 89 |
-
"epoch": 0.4021784666945957,
|
| 90 |
-
"grad_norm": 3.2515976428985596,
|
| 91 |
-
"learning_rate": 1.9241765071472966e-05,
|
| 92 |
-
"loss": 4.0065,
|
| 93 |
-
"step": 240
|
| 94 |
-
},
|
| 95 |
-
{
|
| 96 |
-
"epoch": 0.43569333891914536,
|
| 97 |
-
"grad_norm": 2.7417995929718018,
|
| 98 |
-
"learning_rate": 1.8993163455562463e-05,
|
| 99 |
-
"loss": 3.9739,
|
| 100 |
-
"step": 260
|
| 101 |
-
},
|
| 102 |
-
{
|
| 103 |
-
"epoch": 0.46920821114369504,
|
| 104 |
-
"grad_norm": 3.18656587600708,
|
| 105 |
-
"learning_rate": 1.874456183965196e-05,
|
| 106 |
-
"loss": 3.9283,
|
| 107 |
-
"step": 280
|
| 108 |
-
},
|
| 109 |
-
{
|
| 110 |
-
"epoch": 0.5027230833682447,
|
| 111 |
-
"grad_norm": 3.2568938732147217,
|
| 112 |
-
"learning_rate": 1.8495960223741457e-05,
|
| 113 |
-
"loss": 3.9329,
|
| 114 |
-
"step": 300
|
| 115 |
-
},
|
| 116 |
-
{
|
| 117 |
-
"epoch": 0.5362379555927943,
|
| 118 |
-
"grad_norm": 3.4298770427703857,
|
| 119 |
-
"learning_rate": 1.824735860783095e-05,
|
| 120 |
-
"loss": 3.8688,
|
| 121 |
-
"step": 320
|
| 122 |
-
},
|
| 123 |
-
{
|
| 124 |
-
"epoch": 0.5697528278173439,
|
| 125 |
-
"grad_norm": 3.3362107276916504,
|
| 126 |
-
"learning_rate": 1.799875699192045e-05,
|
| 127 |
-
"loss": 3.838,
|
| 128 |
-
"step": 340
|
| 129 |
-
},
|
| 130 |
-
{
|
| 131 |
-
"epoch": 0.6032677000418936,
|
| 132 |
-
"grad_norm": 3.6403682231903076,
|
| 133 |
-
"learning_rate": 1.7750155376009945e-05,
|
| 134 |
-
"loss": 3.8048,
|
| 135 |
-
"step": 360
|
| 136 |
-
},
|
| 137 |
-
{
|
| 138 |
-
"epoch": 0.6367825722664432,
|
| 139 |
-
"grad_norm": 3.550356149673462,
|
| 140 |
-
"learning_rate": 1.7501553760099442e-05,
|
| 141 |
-
"loss": 3.7985,
|
| 142 |
-
"step": 380
|
| 143 |
-
},
|
| 144 |
-
{
|
| 145 |
-
"epoch": 0.6702974444909929,
|
| 146 |
-
"grad_norm": 3.2275333404541016,
|
| 147 |
-
"learning_rate": 1.725295214418894e-05,
|
| 148 |
-
"loss": 3.8343,
|
| 149 |
-
"step": 400
|
| 150 |
-
},
|
| 151 |
-
{
|
| 152 |
-
"epoch": 0.7038123167155426,
|
| 153 |
-
"grad_norm": 3.7822248935699463,
|
| 154 |
-
"learning_rate": 1.7004350528278436e-05,
|
| 155 |
-
"loss": 3.788,
|
| 156 |
-
"step": 420
|
| 157 |
-
},
|
| 158 |
-
{
|
| 159 |
-
"epoch": 0.7373271889400922,
|
| 160 |
-
"grad_norm": 3.4543073177337646,
|
| 161 |
-
"learning_rate": 1.675574891236793e-05,
|
| 162 |
-
"loss": 3.8082,
|
| 163 |
-
"step": 440
|
| 164 |
-
},
|
| 165 |
-
{
|
| 166 |
-
"epoch": 0.7708420611646418,
|
| 167 |
-
"grad_norm": 4.029712200164795,
|
| 168 |
-
"learning_rate": 1.6507147296457427e-05,
|
| 169 |
-
"loss": 3.7098,
|
| 170 |
-
"step": 460
|
| 171 |
-
},
|
| 172 |
-
{
|
| 173 |
-
"epoch": 0.8043569333891915,
|
| 174 |
-
"grad_norm": 3.7904953956604004,
|
| 175 |
-
"learning_rate": 1.6258545680546924e-05,
|
| 176 |
-
"loss": 3.7707,
|
| 177 |
-
"step": 480
|
| 178 |
-
},
|
| 179 |
-
{
|
| 180 |
-
"epoch": 0.8378718056137411,
|
| 181 |
-
"grad_norm": 4.178560256958008,
|
| 182 |
-
"learning_rate": 1.600994406463642e-05,
|
| 183 |
-
"loss": 3.6682,
|
| 184 |
-
"step": 500
|
| 185 |
-
},
|
| 186 |
-
{
|
| 187 |
-
"epoch": 0.8378718056137411,
|
| 188 |
-
"eval_loss": 0.9386844635009766,
|
| 189 |
-
"eval_runtime": 18.5481,
|
| 190 |
-
"eval_samples_per_second": 26.094,
|
| 191 |
-
"eval_steps_per_second": 6.524,
|
| 192 |
-
"step": 500
|
| 193 |
-
},
|
| 194 |
-
{
|
| 195 |
-
"epoch": 0.8713866778382907,
|
| 196 |
-
"grad_norm": 4.375622272491455,
|
| 197 |
-
"learning_rate": 1.5761342448725918e-05,
|
| 198 |
-
"loss": 3.7518,
|
| 199 |
-
"step": 520
|
| 200 |
-
},
|
| 201 |
-
{
|
| 202 |
-
"epoch": 0.9049015500628403,
|
| 203 |
-
"grad_norm": 4.24531888961792,
|
| 204 |
-
"learning_rate": 1.5512740832815415e-05,
|
| 205 |
-
"loss": 3.7932,
|
| 206 |
-
"step": 540
|
| 207 |
-
},
|
| 208 |
-
{
|
| 209 |
-
"epoch": 0.9384164222873901,
|
| 210 |
-
"grad_norm": 4.672470569610596,
|
| 211 |
-
"learning_rate": 1.5264139216904912e-05,
|
| 212 |
-
"loss": 3.6302,
|
| 213 |
-
"step": 560
|
| 214 |
-
},
|
| 215 |
-
{
|
| 216 |
-
"epoch": 0.9719312945119397,
|
| 217 |
-
"grad_norm": 4.119604587554932,
|
| 218 |
-
"learning_rate": 1.5015537600994408e-05,
|
| 219 |
-
"loss": 3.6135,
|
| 220 |
-
"step": 580
|
| 221 |
-
},
|
| 222 |
-
{
|
| 223 |
-
"epoch": 1.0050272308336825,
|
| 224 |
-
"grad_norm": 4.428940296173096,
|
| 225 |
-
"learning_rate": 1.4766935985083903e-05,
|
| 226 |
-
"loss": 3.5855,
|
| 227 |
-
"step": 600
|
| 228 |
-
},
|
| 229 |
-
{
|
| 230 |
-
"epoch": 1.038542103058232,
|
| 231 |
-
"grad_norm": 4.126169681549072,
|
| 232 |
-
"learning_rate": 1.4518334369173402e-05,
|
| 233 |
-
"loss": 3.6203,
|
| 234 |
-
"step": 620
|
| 235 |
-
},
|
| 236 |
-
{
|
| 237 |
-
"epoch": 1.0720569752827818,
|
| 238 |
-
"grad_norm": 4.4868597984313965,
|
| 239 |
-
"learning_rate": 1.4269732753262897e-05,
|
| 240 |
-
"loss": 3.6493,
|
| 241 |
-
"step": 640
|
| 242 |
-
},
|
| 243 |
-
{
|
| 244 |
-
"epoch": 1.1055718475073313,
|
| 245 |
-
"grad_norm": 4.799410820007324,
|
| 246 |
-
"learning_rate": 1.4021131137352393e-05,
|
| 247 |
-
"loss": 3.6197,
|
| 248 |
-
"step": 660
|
| 249 |
-
},
|
| 250 |
-
{
|
| 251 |
-
"epoch": 1.139086719731881,
|
| 252 |
-
"grad_norm": 4.666592597961426,
|
| 253 |
-
"learning_rate": 1.377252952144189e-05,
|
| 254 |
-
"loss": 3.5442,
|
| 255 |
-
"step": 680
|
| 256 |
-
},
|
| 257 |
-
{
|
| 258 |
-
"epoch": 1.1726015919564308,
|
| 259 |
-
"grad_norm": 4.51644229888916,
|
| 260 |
-
"learning_rate": 1.3523927905531387e-05,
|
| 261 |
-
"loss": 3.5739,
|
| 262 |
-
"step": 700
|
| 263 |
-
},
|
| 264 |
-
{
|
| 265 |
-
"epoch": 1.2061164641809803,
|
| 266 |
-
"grad_norm": 4.476949214935303,
|
| 267 |
-
"learning_rate": 1.3275326289620884e-05,
|
| 268 |
-
"loss": 3.6179,
|
| 269 |
-
"step": 720
|
| 270 |
-
},
|
| 271 |
-
{
|
| 272 |
-
"epoch": 1.23963133640553,
|
| 273 |
-
"grad_norm": 4.593386173248291,
|
| 274 |
-
"learning_rate": 1.302672467371038e-05,
|
| 275 |
-
"loss": 3.5841,
|
| 276 |
-
"step": 740
|
| 277 |
-
},
|
| 278 |
-
{
|
| 279 |
-
"epoch": 1.2731462086300795,
|
| 280 |
-
"grad_norm": 4.501669883728027,
|
| 281 |
-
"learning_rate": 1.2778123057799877e-05,
|
| 282 |
-
"loss": 3.5903,
|
| 283 |
-
"step": 760
|
| 284 |
-
},
|
| 285 |
-
{
|
| 286 |
-
"epoch": 1.3066610808546293,
|
| 287 |
-
"grad_norm": 4.385534286499023,
|
| 288 |
-
"learning_rate": 1.2529521441889374e-05,
|
| 289 |
-
"loss": 3.5746,
|
| 290 |
-
"step": 780
|
| 291 |
-
},
|
| 292 |
-
{
|
| 293 |
-
"epoch": 1.3401759530791788,
|
| 294 |
-
"grad_norm": 4.455802917480469,
|
| 295 |
-
"learning_rate": 1.228091982597887e-05,
|
| 296 |
-
"loss": 3.6366,
|
| 297 |
-
"step": 800
|
| 298 |
-
},
|
| 299 |
-
{
|
| 300 |
-
"epoch": 1.3736908253037285,
|
| 301 |
-
"grad_norm": 4.496267795562744,
|
| 302 |
-
"learning_rate": 1.2032318210068366e-05,
|
| 303 |
-
"loss": 3.4731,
|
| 304 |
-
"step": 820
|
| 305 |
-
},
|
| 306 |
-
{
|
| 307 |
-
"epoch": 1.407205697528278,
|
| 308 |
-
"grad_norm": 4.637114524841309,
|
| 309 |
-
"learning_rate": 1.1783716594157863e-05,
|
| 310 |
-
"loss": 3.4686,
|
| 311 |
-
"step": 840
|
| 312 |
-
},
|
| 313 |
-
{
|
| 314 |
-
"epoch": 1.4407205697528278,
|
| 315 |
-
"grad_norm": 4.994802474975586,
|
| 316 |
-
"learning_rate": 1.1535114978247359e-05,
|
| 317 |
-
"loss": 3.4906,
|
| 318 |
-
"step": 860
|
| 319 |
-
},
|
| 320 |
-
{
|
| 321 |
-
"epoch": 1.4742354419773775,
|
| 322 |
-
"grad_norm": 5.130626201629639,
|
| 323 |
-
"learning_rate": 1.1286513362336854e-05,
|
| 324 |
-
"loss": 3.5782,
|
| 325 |
-
"step": 880
|
| 326 |
-
},
|
| 327 |
-
{
|
| 328 |
-
"epoch": 1.507750314201927,
|
| 329 |
-
"grad_norm": 5.21913480758667,
|
| 330 |
-
"learning_rate": 1.1037911746426353e-05,
|
| 331 |
-
"loss": 3.5554,
|
| 332 |
-
"step": 900
|
| 333 |
-
},
|
| 334 |
-
{
|
| 335 |
-
"epoch": 1.5412651864264766,
|
| 336 |
-
"grad_norm": 5.335895538330078,
|
| 337 |
-
"learning_rate": 1.0789310130515848e-05,
|
| 338 |
-
"loss": 3.4631,
|
| 339 |
-
"step": 920
|
| 340 |
-
},
|
| 341 |
-
{
|
| 342 |
-
"epoch": 1.5747800586510263,
|
| 343 |
-
"grad_norm": 4.7488627433776855,
|
| 344 |
-
"learning_rate": 1.0540708514605347e-05,
|
| 345 |
-
"loss": 3.5529,
|
| 346 |
-
"step": 940
|
| 347 |
-
},
|
| 348 |
-
{
|
| 349 |
-
"epoch": 1.608294930875576,
|
| 350 |
-
"grad_norm": 5.3310723304748535,
|
| 351 |
-
"learning_rate": 1.0292106898694843e-05,
|
| 352 |
-
"loss": 3.4506,
|
| 353 |
-
"step": 960
|
| 354 |
-
},
|
| 355 |
-
{
|
| 356 |
-
"epoch": 1.6418098031001258,
|
| 357 |
-
"grad_norm": 4.414116382598877,
|
| 358 |
-
"learning_rate": 1.0043505282784338e-05,
|
| 359 |
-
"loss": 3.4512,
|
| 360 |
-
"step": 980
|
| 361 |
-
},
|
| 362 |
-
{
|
| 363 |
-
"epoch": 1.6753246753246753,
|
| 364 |
-
"grad_norm": 5.782153129577637,
|
| 365 |
-
"learning_rate": 9.794903666873835e-06,
|
| 366 |
-
"loss": 3.455,
|
| 367 |
-
"step": 1000
|
| 368 |
-
},
|
| 369 |
-
{
|
| 370 |
-
"epoch": 1.6753246753246753,
|
| 371 |
-
"eval_loss": 0.8815606832504272,
|
| 372 |
-
"eval_runtime": 18.5292,
|
| 373 |
-
"eval_samples_per_second": 26.121,
|
| 374 |
-
"eval_steps_per_second": 6.53,
|
| 375 |
-
"step": 1000
|
| 376 |
-
}
|
| 377 |
-
],
|
| 378 |
-
"logging_steps": 20,
|
| 379 |
-
"max_steps": 1788,
|
| 380 |
-
"num_input_tokens_seen": 0,
|
| 381 |
-
"num_train_epochs": 3,
|
| 382 |
-
"save_steps": 500,
|
| 383 |
-
"stateful_callbacks": {
|
| 384 |
-
"TrainerControl": {
|
| 385 |
-
"args": {
|
| 386 |
-
"should_epoch_stop": false,
|
| 387 |
-
"should_evaluate": false,
|
| 388 |
-
"should_log": false,
|
| 389 |
-
"should_save": true,
|
| 390 |
-
"should_training_stop": false
|
| 391 |
-
},
|
| 392 |
-
"attributes": {}
|
| 393 |
-
}
|
| 394 |
-
},
|
| 395 |
-
"total_flos": 2.648178674494341e+17,
|
| 396 |
-
"train_batch_size": 4,
|
| 397 |
-
"trial_name": null,
|
| 398 |
-
"trial_params": null
|
| 399 |
-
}
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6d88048d3685263a8cf1423048c8228bee9886f9dfa10c91da7de1358abcd391
|
| 3 |
+
size 9875
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-1000/vocab.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1788/adapter_config.json
CHANGED
|
@@ -1,42 +1,3 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
"base_model_name_or_path": "Qwen/Qwen2.5-1.5B",
|
| 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": 64,
|
| 17 |
-
"lora_bias": false,
|
| 18 |
-
"lora_dropout": 0.1,
|
| 19 |
-
"megatron_config": null,
|
| 20 |
-
"megatron_core": "megatron.core",
|
| 21 |
-
"modules_to_save": null,
|
| 22 |
-
"peft_type": "LORA",
|
| 23 |
-
"qalora_group_size": 16,
|
| 24 |
-
"r": 32,
|
| 25 |
-
"rank_pattern": {},
|
| 26 |
-
"revision": null,
|
| 27 |
-
"target_modules": [
|
| 28 |
-
"o_proj",
|
| 29 |
-
"k_proj",
|
| 30 |
-
"down_proj",
|
| 31 |
-
"v_proj",
|
| 32 |
-
"gate_proj",
|
| 33 |
-
"up_proj",
|
| 34 |
-
"q_proj"
|
| 35 |
-
],
|
| 36 |
-
"target_parameters": null,
|
| 37 |
-
"task_type": "CAUSAL_LM",
|
| 38 |
-
"trainable_token_indices": null,
|
| 39 |
-
"use_dora": false,
|
| 40 |
-
"use_qalora": false,
|
| 41 |
-
"use_rslora": false
|
| 42 |
-
}
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef1b304e1f3e2f865ca24b9eadff513cad2b85a4dee1a4e0a77a72c73f5f2e77
|
| 3 |
+
size 928
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-1788/added_tokens.json
CHANGED
|
@@ -1,24 +1,3 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
|
| 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 |
-
}
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:58b54bbe36fc752f79a24a271ef66a0a0830054b4dfad94bde757d851968060b
|
| 3 |
+
size 605
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-1788/special_tokens_map.json
CHANGED
|
@@ -1,31 +1,3 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
|
| 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": "<|endoftext|>",
|
| 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 |
-
}
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6676f091c8bc4d1b50146427cfde92073402866b87b6e39223227931b70083e9
|
| 3 |
+
size 616
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-1788/tokenizer_config.json
CHANGED
|
@@ -1,208 +1,3 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
|
| 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 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 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": "<|endoftext|>",
|
| 201 |
-
"errors": "replace",
|
| 202 |
-
"extra_special_tokens": {},
|
| 203 |
-
"model_max_length": 131072,
|
| 204 |
-
"pad_token": "<|endoftext|>",
|
| 205 |
-
"split_special_tokens": false,
|
| 206 |
-
"tokenizer_class": "Qwen2Tokenizer",
|
| 207 |
-
"unk_token": null
|
| 208 |
-
}
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a5dae0102f342a3b6bc2a4d03f430ed83666dcab8879c9ee44c08a3d9095132d
|
| 3 |
+
size 7259
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-1788/trainer_state.json
CHANGED
|
@@ -1,680 +1,3 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
"epoch": 2.9953917050691246,
|
| 5 |
-
"eval_steps": 500,
|
| 6 |
-
"global_step": 1788,
|
| 7 |
-
"is_hyper_param_search": false,
|
| 8 |
-
"is_local_process_zero": true,
|
| 9 |
-
"is_world_process_zero": true,
|
| 10 |
-
"log_history": [
|
| 11 |
-
{
|
| 12 |
-
"epoch": 0.033514872224549644,
|
| 13 |
-
"grad_norm": 6.138762950897217,
|
| 14 |
-
"learning_rate": 2.23463687150838e-06,
|
| 15 |
-
"loss": 6.0548,
|
| 16 |
-
"step": 20
|
| 17 |
-
},
|
| 18 |
-
{
|
| 19 |
-
"epoch": 0.06702974444909929,
|
| 20 |
-
"grad_norm": 4.608607769012451,
|
| 21 |
-
"learning_rate": 4.46927374301676e-06,
|
| 22 |
-
"loss": 5.9799,
|
| 23 |
-
"step": 40
|
| 24 |
-
},
|
| 25 |
-
{
|
| 26 |
-
"epoch": 0.10054461667364893,
|
| 27 |
-
"grad_norm": 3.4575345516204834,
|
| 28 |
-
"learning_rate": 6.70391061452514e-06,
|
| 29 |
-
"loss": 5.61,
|
| 30 |
-
"step": 60
|
| 31 |
-
},
|
| 32 |
-
{
|
| 33 |
-
"epoch": 0.13405948889819858,
|
| 34 |
-
"grad_norm": 3.4996674060821533,
|
| 35 |
-
"learning_rate": 8.93854748603352e-06,
|
| 36 |
-
"loss": 5.0586,
|
| 37 |
-
"step": 80
|
| 38 |
-
},
|
| 39 |
-
{
|
| 40 |
-
"epoch": 0.16757436112274823,
|
| 41 |
-
"grad_norm": 2.155829668045044,
|
| 42 |
-
"learning_rate": 1.11731843575419e-05,
|
| 43 |
-
"loss": 4.7232,
|
| 44 |
-
"step": 100
|
| 45 |
-
},
|
| 46 |
-
{
|
| 47 |
-
"epoch": 0.20108923334729786,
|
| 48 |
-
"grad_norm": 2.0759589672088623,
|
| 49 |
-
"learning_rate": 1.340782122905028e-05,
|
| 50 |
-
"loss": 4.3872,
|
| 51 |
-
"step": 120
|
| 52 |
-
},
|
| 53 |
-
{
|
| 54 |
-
"epoch": 0.23460410557184752,
|
| 55 |
-
"grad_norm": 2.274566173553467,
|
| 56 |
-
"learning_rate": 1.564245810055866e-05,
|
| 57 |
-
"loss": 4.2721,
|
| 58 |
-
"step": 140
|
| 59 |
-
},
|
| 60 |
-
{
|
| 61 |
-
"epoch": 0.26811897779639715,
|
| 62 |
-
"grad_norm": 2.4159297943115234,
|
| 63 |
-
"learning_rate": 1.787709497206704e-05,
|
| 64 |
-
"loss": 4.2317,
|
| 65 |
-
"step": 160
|
| 66 |
-
},
|
| 67 |
-
{
|
| 68 |
-
"epoch": 0.3016338500209468,
|
| 69 |
-
"grad_norm": 2.6904704570770264,
|
| 70 |
-
"learning_rate": 1.9987569919204478e-05,
|
| 71 |
-
"loss": 4.1439,
|
| 72 |
-
"step": 180
|
| 73 |
-
},
|
| 74 |
-
{
|
| 75 |
-
"epoch": 0.33514872224549647,
|
| 76 |
-
"grad_norm": 2.5504817962646484,
|
| 77 |
-
"learning_rate": 1.973896830329397e-05,
|
| 78 |
-
"loss": 4.1092,
|
| 79 |
-
"step": 200
|
| 80 |
-
},
|
| 81 |
-
{
|
| 82 |
-
"epoch": 0.3686635944700461,
|
| 83 |
-
"grad_norm": 2.610886812210083,
|
| 84 |
-
"learning_rate": 1.949036668738347e-05,
|
| 85 |
-
"loss": 4.0378,
|
| 86 |
-
"step": 220
|
| 87 |
-
},
|
| 88 |
-
{
|
| 89 |
-
"epoch": 0.4021784666945957,
|
| 90 |
-
"grad_norm": 3.2515976428985596,
|
| 91 |
-
"learning_rate": 1.9241765071472966e-05,
|
| 92 |
-
"loss": 4.0065,
|
| 93 |
-
"step": 240
|
| 94 |
-
},
|
| 95 |
-
{
|
| 96 |
-
"epoch": 0.43569333891914536,
|
| 97 |
-
"grad_norm": 2.7417995929718018,
|
| 98 |
-
"learning_rate": 1.8993163455562463e-05,
|
| 99 |
-
"loss": 3.9739,
|
| 100 |
-
"step": 260
|
| 101 |
-
},
|
| 102 |
-
{
|
| 103 |
-
"epoch": 0.46920821114369504,
|
| 104 |
-
"grad_norm": 3.18656587600708,
|
| 105 |
-
"learning_rate": 1.874456183965196e-05,
|
| 106 |
-
"loss": 3.9283,
|
| 107 |
-
"step": 280
|
| 108 |
-
},
|
| 109 |
-
{
|
| 110 |
-
"epoch": 0.5027230833682447,
|
| 111 |
-
"grad_norm": 3.2568938732147217,
|
| 112 |
-
"learning_rate": 1.8495960223741457e-05,
|
| 113 |
-
"loss": 3.9329,
|
| 114 |
-
"step": 300
|
| 115 |
-
},
|
| 116 |
-
{
|
| 117 |
-
"epoch": 0.5362379555927943,
|
| 118 |
-
"grad_norm": 3.4298770427703857,
|
| 119 |
-
"learning_rate": 1.824735860783095e-05,
|
| 120 |
-
"loss": 3.8688,
|
| 121 |
-
"step": 320
|
| 122 |
-
},
|
| 123 |
-
{
|
| 124 |
-
"epoch": 0.5697528278173439,
|
| 125 |
-
"grad_norm": 3.3362107276916504,
|
| 126 |
-
"learning_rate": 1.799875699192045e-05,
|
| 127 |
-
"loss": 3.838,
|
| 128 |
-
"step": 340
|
| 129 |
-
},
|
| 130 |
-
{
|
| 131 |
-
"epoch": 0.6032677000418936,
|
| 132 |
-
"grad_norm": 3.6403682231903076,
|
| 133 |
-
"learning_rate": 1.7750155376009945e-05,
|
| 134 |
-
"loss": 3.8048,
|
| 135 |
-
"step": 360
|
| 136 |
-
},
|
| 137 |
-
{
|
| 138 |
-
"epoch": 0.6367825722664432,
|
| 139 |
-
"grad_norm": 3.550356149673462,
|
| 140 |
-
"learning_rate": 1.7501553760099442e-05,
|
| 141 |
-
"loss": 3.7985,
|
| 142 |
-
"step": 380
|
| 143 |
-
},
|
| 144 |
-
{
|
| 145 |
-
"epoch": 0.6702974444909929,
|
| 146 |
-
"grad_norm": 3.2275333404541016,
|
| 147 |
-
"learning_rate": 1.725295214418894e-05,
|
| 148 |
-
"loss": 3.8343,
|
| 149 |
-
"step": 400
|
| 150 |
-
},
|
| 151 |
-
{
|
| 152 |
-
"epoch": 0.7038123167155426,
|
| 153 |
-
"grad_norm": 3.7822248935699463,
|
| 154 |
-
"learning_rate": 1.7004350528278436e-05,
|
| 155 |
-
"loss": 3.788,
|
| 156 |
-
"step": 420
|
| 157 |
-
},
|
| 158 |
-
{
|
| 159 |
-
"epoch": 0.7373271889400922,
|
| 160 |
-
"grad_norm": 3.4543073177337646,
|
| 161 |
-
"learning_rate": 1.675574891236793e-05,
|
| 162 |
-
"loss": 3.8082,
|
| 163 |
-
"step": 440
|
| 164 |
-
},
|
| 165 |
-
{
|
| 166 |
-
"epoch": 0.7708420611646418,
|
| 167 |
-
"grad_norm": 4.029712200164795,
|
| 168 |
-
"learning_rate": 1.6507147296457427e-05,
|
| 169 |
-
"loss": 3.7098,
|
| 170 |
-
"step": 460
|
| 171 |
-
},
|
| 172 |
-
{
|
| 173 |
-
"epoch": 0.8043569333891915,
|
| 174 |
-
"grad_norm": 3.7904953956604004,
|
| 175 |
-
"learning_rate": 1.6258545680546924e-05,
|
| 176 |
-
"loss": 3.7707,
|
| 177 |
-
"step": 480
|
| 178 |
-
},
|
| 179 |
-
{
|
| 180 |
-
"epoch": 0.8378718056137411,
|
| 181 |
-
"grad_norm": 4.178560256958008,
|
| 182 |
-
"learning_rate": 1.600994406463642e-05,
|
| 183 |
-
"loss": 3.6682,
|
| 184 |
-
"step": 500
|
| 185 |
-
},
|
| 186 |
-
{
|
| 187 |
-
"epoch": 0.8378718056137411,
|
| 188 |
-
"eval_loss": 0.9386844635009766,
|
| 189 |
-
"eval_runtime": 18.5481,
|
| 190 |
-
"eval_samples_per_second": 26.094,
|
| 191 |
-
"eval_steps_per_second": 6.524,
|
| 192 |
-
"step": 500
|
| 193 |
-
},
|
| 194 |
-
{
|
| 195 |
-
"epoch": 0.8713866778382907,
|
| 196 |
-
"grad_norm": 4.375622272491455,
|
| 197 |
-
"learning_rate": 1.5761342448725918e-05,
|
| 198 |
-
"loss": 3.7518,
|
| 199 |
-
"step": 520
|
| 200 |
-
},
|
| 201 |
-
{
|
| 202 |
-
"epoch": 0.9049015500628403,
|
| 203 |
-
"grad_norm": 4.24531888961792,
|
| 204 |
-
"learning_rate": 1.5512740832815415e-05,
|
| 205 |
-
"loss": 3.7932,
|
| 206 |
-
"step": 540
|
| 207 |
-
},
|
| 208 |
-
{
|
| 209 |
-
"epoch": 0.9384164222873901,
|
| 210 |
-
"grad_norm": 4.672470569610596,
|
| 211 |
-
"learning_rate": 1.5264139216904912e-05,
|
| 212 |
-
"loss": 3.6302,
|
| 213 |
-
"step": 560
|
| 214 |
-
},
|
| 215 |
-
{
|
| 216 |
-
"epoch": 0.9719312945119397,
|
| 217 |
-
"grad_norm": 4.119604587554932,
|
| 218 |
-
"learning_rate": 1.5015537600994408e-05,
|
| 219 |
-
"loss": 3.6135,
|
| 220 |
-
"step": 580
|
| 221 |
-
},
|
| 222 |
-
{
|
| 223 |
-
"epoch": 1.0050272308336825,
|
| 224 |
-
"grad_norm": 4.428940296173096,
|
| 225 |
-
"learning_rate": 1.4766935985083903e-05,
|
| 226 |
-
"loss": 3.5855,
|
| 227 |
-
"step": 600
|
| 228 |
-
},
|
| 229 |
-
{
|
| 230 |
-
"epoch": 1.038542103058232,
|
| 231 |
-
"grad_norm": 4.126169681549072,
|
| 232 |
-
"learning_rate": 1.4518334369173402e-05,
|
| 233 |
-
"loss": 3.6203,
|
| 234 |
-
"step": 620
|
| 235 |
-
},
|
| 236 |
-
{
|
| 237 |
-
"epoch": 1.0720569752827818,
|
| 238 |
-
"grad_norm": 4.4868597984313965,
|
| 239 |
-
"learning_rate": 1.4269732753262897e-05,
|
| 240 |
-
"loss": 3.6493,
|
| 241 |
-
"step": 640
|
| 242 |
-
},
|
| 243 |
-
{
|
| 244 |
-
"epoch": 1.1055718475073313,
|
| 245 |
-
"grad_norm": 4.799410820007324,
|
| 246 |
-
"learning_rate": 1.4021131137352393e-05,
|
| 247 |
-
"loss": 3.6197,
|
| 248 |
-
"step": 660
|
| 249 |
-
},
|
| 250 |
-
{
|
| 251 |
-
"epoch": 1.139086719731881,
|
| 252 |
-
"grad_norm": 4.666592597961426,
|
| 253 |
-
"learning_rate": 1.377252952144189e-05,
|
| 254 |
-
"loss": 3.5442,
|
| 255 |
-
"step": 680
|
| 256 |
-
},
|
| 257 |
-
{
|
| 258 |
-
"epoch": 1.1726015919564308,
|
| 259 |
-
"grad_norm": 4.51644229888916,
|
| 260 |
-
"learning_rate": 1.3523927905531387e-05,
|
| 261 |
-
"loss": 3.5739,
|
| 262 |
-
"step": 700
|
| 263 |
-
},
|
| 264 |
-
{
|
| 265 |
-
"epoch": 1.2061164641809803,
|
| 266 |
-
"grad_norm": 4.476949214935303,
|
| 267 |
-
"learning_rate": 1.3275326289620884e-05,
|
| 268 |
-
"loss": 3.6179,
|
| 269 |
-
"step": 720
|
| 270 |
-
},
|
| 271 |
-
{
|
| 272 |
-
"epoch": 1.23963133640553,
|
| 273 |
-
"grad_norm": 4.593386173248291,
|
| 274 |
-
"learning_rate": 1.302672467371038e-05,
|
| 275 |
-
"loss": 3.5841,
|
| 276 |
-
"step": 740
|
| 277 |
-
},
|
| 278 |
-
{
|
| 279 |
-
"epoch": 1.2731462086300795,
|
| 280 |
-
"grad_norm": 4.501669883728027,
|
| 281 |
-
"learning_rate": 1.2778123057799877e-05,
|
| 282 |
-
"loss": 3.5903,
|
| 283 |
-
"step": 760
|
| 284 |
-
},
|
| 285 |
-
{
|
| 286 |
-
"epoch": 1.3066610808546293,
|
| 287 |
-
"grad_norm": 4.385534286499023,
|
| 288 |
-
"learning_rate": 1.2529521441889374e-05,
|
| 289 |
-
"loss": 3.5746,
|
| 290 |
-
"step": 780
|
| 291 |
-
},
|
| 292 |
-
{
|
| 293 |
-
"epoch": 1.3401759530791788,
|
| 294 |
-
"grad_norm": 4.455802917480469,
|
| 295 |
-
"learning_rate": 1.228091982597887e-05,
|
| 296 |
-
"loss": 3.6366,
|
| 297 |
-
"step": 800
|
| 298 |
-
},
|
| 299 |
-
{
|
| 300 |
-
"epoch": 1.3736908253037285,
|
| 301 |
-
"grad_norm": 4.496267795562744,
|
| 302 |
-
"learning_rate": 1.2032318210068366e-05,
|
| 303 |
-
"loss": 3.4731,
|
| 304 |
-
"step": 820
|
| 305 |
-
},
|
| 306 |
-
{
|
| 307 |
-
"epoch": 1.407205697528278,
|
| 308 |
-
"grad_norm": 4.637114524841309,
|
| 309 |
-
"learning_rate": 1.1783716594157863e-05,
|
| 310 |
-
"loss": 3.4686,
|
| 311 |
-
"step": 840
|
| 312 |
-
},
|
| 313 |
-
{
|
| 314 |
-
"epoch": 1.4407205697528278,
|
| 315 |
-
"grad_norm": 4.994802474975586,
|
| 316 |
-
"learning_rate": 1.1535114978247359e-05,
|
| 317 |
-
"loss": 3.4906,
|
| 318 |
-
"step": 860
|
| 319 |
-
},
|
| 320 |
-
{
|
| 321 |
-
"epoch": 1.4742354419773775,
|
| 322 |
-
"grad_norm": 5.130626201629639,
|
| 323 |
-
"learning_rate": 1.1286513362336854e-05,
|
| 324 |
-
"loss": 3.5782,
|
| 325 |
-
"step": 880
|
| 326 |
-
},
|
| 327 |
-
{
|
| 328 |
-
"epoch": 1.507750314201927,
|
| 329 |
-
"grad_norm": 5.21913480758667,
|
| 330 |
-
"learning_rate": 1.1037911746426353e-05,
|
| 331 |
-
"loss": 3.5554,
|
| 332 |
-
"step": 900
|
| 333 |
-
},
|
| 334 |
-
{
|
| 335 |
-
"epoch": 1.5412651864264766,
|
| 336 |
-
"grad_norm": 5.335895538330078,
|
| 337 |
-
"learning_rate": 1.0789310130515848e-05,
|
| 338 |
-
"loss": 3.4631,
|
| 339 |
-
"step": 920
|
| 340 |
-
},
|
| 341 |
-
{
|
| 342 |
-
"epoch": 1.5747800586510263,
|
| 343 |
-
"grad_norm": 4.7488627433776855,
|
| 344 |
-
"learning_rate": 1.0540708514605347e-05,
|
| 345 |
-
"loss": 3.5529,
|
| 346 |
-
"step": 940
|
| 347 |
-
},
|
| 348 |
-
{
|
| 349 |
-
"epoch": 1.608294930875576,
|
| 350 |
-
"grad_norm": 5.3310723304748535,
|
| 351 |
-
"learning_rate": 1.0292106898694843e-05,
|
| 352 |
-
"loss": 3.4506,
|
| 353 |
-
"step": 960
|
| 354 |
-
},
|
| 355 |
-
{
|
| 356 |
-
"epoch": 1.6418098031001258,
|
| 357 |
-
"grad_norm": 4.414116382598877,
|
| 358 |
-
"learning_rate": 1.0043505282784338e-05,
|
| 359 |
-
"loss": 3.4512,
|
| 360 |
-
"step": 980
|
| 361 |
-
},
|
| 362 |
-
{
|
| 363 |
-
"epoch": 1.6753246753246753,
|
| 364 |
-
"grad_norm": 5.782153129577637,
|
| 365 |
-
"learning_rate": 9.794903666873835e-06,
|
| 366 |
-
"loss": 3.455,
|
| 367 |
-
"step": 1000
|
| 368 |
-
},
|
| 369 |
-
{
|
| 370 |
-
"epoch": 1.6753246753246753,
|
| 371 |
-
"eval_loss": 0.8815606832504272,
|
| 372 |
-
"eval_runtime": 18.5292,
|
| 373 |
-
"eval_samples_per_second": 26.121,
|
| 374 |
-
"eval_steps_per_second": 6.53,
|
| 375 |
-
"step": 1000
|
| 376 |
-
},
|
| 377 |
-
{
|
| 378 |
-
"epoch": 1.7088395475492248,
|
| 379 |
-
"grad_norm": 4.971745014190674,
|
| 380 |
-
"learning_rate": 9.546302050963332e-06,
|
| 381 |
-
"loss": 3.4889,
|
| 382 |
-
"step": 1020
|
| 383 |
-
},
|
| 384 |
-
{
|
| 385 |
-
"epoch": 1.7423544197737746,
|
| 386 |
-
"grad_norm": 6.019398212432861,
|
| 387 |
-
"learning_rate": 9.29770043505283e-06,
|
| 388 |
-
"loss": 3.4492,
|
| 389 |
-
"step": 1040
|
| 390 |
-
},
|
| 391 |
-
{
|
| 392 |
-
"epoch": 1.7758692919983243,
|
| 393 |
-
"grad_norm": 5.54038667678833,
|
| 394 |
-
"learning_rate": 9.049098819142326e-06,
|
| 395 |
-
"loss": 3.4148,
|
| 396 |
-
"step": 1060
|
| 397 |
-
},
|
| 398 |
-
{
|
| 399 |
-
"epoch": 1.8093841642228738,
|
| 400 |
-
"grad_norm": 4.966987133026123,
|
| 401 |
-
"learning_rate": 8.800497203231822e-06,
|
| 402 |
-
"loss": 3.4505,
|
| 403 |
-
"step": 1080
|
| 404 |
-
},
|
| 405 |
-
{
|
| 406 |
-
"epoch": 1.8428990364474236,
|
| 407 |
-
"grad_norm": 5.807140827178955,
|
| 408 |
-
"learning_rate": 8.551895587321319e-06,
|
| 409 |
-
"loss": 3.3738,
|
| 410 |
-
"step": 1100
|
| 411 |
-
},
|
| 412 |
-
{
|
| 413 |
-
"epoch": 1.876413908671973,
|
| 414 |
-
"grad_norm": 5.855706691741943,
|
| 415 |
-
"learning_rate": 8.303293971410814e-06,
|
| 416 |
-
"loss": 3.3568,
|
| 417 |
-
"step": 1120
|
| 418 |
-
},
|
| 419 |
-
{
|
| 420 |
-
"epoch": 1.9099287808965228,
|
| 421 |
-
"grad_norm": 5.644012928009033,
|
| 422 |
-
"learning_rate": 8.054692355500311e-06,
|
| 423 |
-
"loss": 3.342,
|
| 424 |
-
"step": 1140
|
| 425 |
-
},
|
| 426 |
-
{
|
| 427 |
-
"epoch": 1.9434436531210726,
|
| 428 |
-
"grad_norm": 5.216829299926758,
|
| 429 |
-
"learning_rate": 7.806090739589809e-06,
|
| 430 |
-
"loss": 3.4563,
|
| 431 |
-
"step": 1160
|
| 432 |
-
},
|
| 433 |
-
{
|
| 434 |
-
"epoch": 1.976958525345622,
|
| 435 |
-
"grad_norm": 5.422548770904541,
|
| 436 |
-
"learning_rate": 7.557489123679305e-06,
|
| 437 |
-
"loss": 3.3337,
|
| 438 |
-
"step": 1180
|
| 439 |
-
},
|
| 440 |
-
{
|
| 441 |
-
"epoch": 2.010054461667365,
|
| 442 |
-
"grad_norm": 5.233990669250488,
|
| 443 |
-
"learning_rate": 7.308887507768801e-06,
|
| 444 |
-
"loss": 3.3357,
|
| 445 |
-
"step": 1200
|
| 446 |
-
},
|
| 447 |
-
{
|
| 448 |
-
"epoch": 2.0435693338919148,
|
| 449 |
-
"grad_norm": 5.096955299377441,
|
| 450 |
-
"learning_rate": 7.060285891858297e-06,
|
| 451 |
-
"loss": 3.3064,
|
| 452 |
-
"step": 1220
|
| 453 |
-
},
|
| 454 |
-
{
|
| 455 |
-
"epoch": 2.077084206116464,
|
| 456 |
-
"grad_norm": 5.115320205688477,
|
| 457 |
-
"learning_rate": 6.8116842759477945e-06,
|
| 458 |
-
"loss": 3.3344,
|
| 459 |
-
"step": 1240
|
| 460 |
-
},
|
| 461 |
-
{
|
| 462 |
-
"epoch": 2.110599078341014,
|
| 463 |
-
"grad_norm": 5.281153202056885,
|
| 464 |
-
"learning_rate": 6.563082660037291e-06,
|
| 465 |
-
"loss": 3.3393,
|
| 466 |
-
"step": 1260
|
| 467 |
-
},
|
| 468 |
-
{
|
| 469 |
-
"epoch": 2.1441139505655635,
|
| 470 |
-
"grad_norm": 5.391426086425781,
|
| 471 |
-
"learning_rate": 6.314481044126788e-06,
|
| 472 |
-
"loss": 3.4095,
|
| 473 |
-
"step": 1280
|
| 474 |
-
},
|
| 475 |
-
{
|
| 476 |
-
"epoch": 2.1776288227901133,
|
| 477 |
-
"grad_norm": 4.950923442840576,
|
| 478 |
-
"learning_rate": 6.065879428216283e-06,
|
| 479 |
-
"loss": 3.3368,
|
| 480 |
-
"step": 1300
|
| 481 |
-
},
|
| 482 |
-
{
|
| 483 |
-
"epoch": 2.2111436950146626,
|
| 484 |
-
"grad_norm": 4.606845378875732,
|
| 485 |
-
"learning_rate": 5.81727781230578e-06,
|
| 486 |
-
"loss": 3.3344,
|
| 487 |
-
"step": 1320
|
| 488 |
-
},
|
| 489 |
-
{
|
| 490 |
-
"epoch": 2.2446585672392123,
|
| 491 |
-
"grad_norm": 5.953337669372559,
|
| 492 |
-
"learning_rate": 5.5686761963952774e-06,
|
| 493 |
-
"loss": 3.2796,
|
| 494 |
-
"step": 1340
|
| 495 |
-
},
|
| 496 |
-
{
|
| 497 |
-
"epoch": 2.278173439463762,
|
| 498 |
-
"grad_norm": 5.810727596282959,
|
| 499 |
-
"learning_rate": 5.320074580484773e-06,
|
| 500 |
-
"loss": 3.3313,
|
| 501 |
-
"step": 1360
|
| 502 |
-
},
|
| 503 |
-
{
|
| 504 |
-
"epoch": 2.311688311688312,
|
| 505 |
-
"grad_norm": 5.921137809753418,
|
| 506 |
-
"learning_rate": 5.07147296457427e-06,
|
| 507 |
-
"loss": 3.3907,
|
| 508 |
-
"step": 1380
|
| 509 |
-
},
|
| 510 |
-
{
|
| 511 |
-
"epoch": 2.3452031839128615,
|
| 512 |
-
"grad_norm": 5.457453727722168,
|
| 513 |
-
"learning_rate": 4.822871348663767e-06,
|
| 514 |
-
"loss": 3.3953,
|
| 515 |
-
"step": 1400
|
| 516 |
-
},
|
| 517 |
-
{
|
| 518 |
-
"epoch": 2.378718056137411,
|
| 519 |
-
"grad_norm": 5.744781970977783,
|
| 520 |
-
"learning_rate": 4.574269732753263e-06,
|
| 521 |
-
"loss": 3.3514,
|
| 522 |
-
"step": 1420
|
| 523 |
-
},
|
| 524 |
-
{
|
| 525 |
-
"epoch": 2.4122329283619606,
|
| 526 |
-
"grad_norm": 6.522769927978516,
|
| 527 |
-
"learning_rate": 4.32566811684276e-06,
|
| 528 |
-
"loss": 3.4018,
|
| 529 |
-
"step": 1440
|
| 530 |
-
},
|
| 531 |
-
{
|
| 532 |
-
"epoch": 2.4457478005865103,
|
| 533 |
-
"grad_norm": 6.107413291931152,
|
| 534 |
-
"learning_rate": 4.077066500932257e-06,
|
| 535 |
-
"loss": 3.3584,
|
| 536 |
-
"step": 1460
|
| 537 |
-
},
|
| 538 |
-
{
|
| 539 |
-
"epoch": 2.47926267281106,
|
| 540 |
-
"grad_norm": 6.571192741394043,
|
| 541 |
-
"learning_rate": 3.828464885021753e-06,
|
| 542 |
-
"loss": 3.3794,
|
| 543 |
-
"step": 1480
|
| 544 |
-
},
|
| 545 |
-
{
|
| 546 |
-
"epoch": 2.5127775450356094,
|
| 547 |
-
"grad_norm": 5.21119499206543,
|
| 548 |
-
"learning_rate": 3.5798632691112496e-06,
|
| 549 |
-
"loss": 3.3415,
|
| 550 |
-
"step": 1500
|
| 551 |
-
},
|
| 552 |
-
{
|
| 553 |
-
"epoch": 2.5127775450356094,
|
| 554 |
-
"eval_loss": 0.8567042350769043,
|
| 555 |
-
"eval_runtime": 18.5416,
|
| 556 |
-
"eval_samples_per_second": 26.104,
|
| 557 |
-
"eval_steps_per_second": 6.526,
|
| 558 |
-
"step": 1500
|
| 559 |
-
},
|
| 560 |
-
{
|
| 561 |
-
"epoch": 2.546292417260159,
|
| 562 |
-
"grad_norm": 6.454400062561035,
|
| 563 |
-
"learning_rate": 3.3312616532007463e-06,
|
| 564 |
-
"loss": 3.2742,
|
| 565 |
-
"step": 1520
|
| 566 |
-
},
|
| 567 |
-
{
|
| 568 |
-
"epoch": 2.579807289484709,
|
| 569 |
-
"grad_norm": 5.700740814208984,
|
| 570 |
-
"learning_rate": 3.0826600372902425e-06,
|
| 571 |
-
"loss": 3.3102,
|
| 572 |
-
"step": 1540
|
| 573 |
-
},
|
| 574 |
-
{
|
| 575 |
-
"epoch": 2.6133221617092586,
|
| 576 |
-
"grad_norm": 5.4897589683532715,
|
| 577 |
-
"learning_rate": 2.834058421379739e-06,
|
| 578 |
-
"loss": 3.3134,
|
| 579 |
-
"step": 1560
|
| 580 |
-
},
|
| 581 |
-
{
|
| 582 |
-
"epoch": 2.6468370339338083,
|
| 583 |
-
"grad_norm": 6.4174346923828125,
|
| 584 |
-
"learning_rate": 2.585456805469236e-06,
|
| 585 |
-
"loss": 3.2656,
|
| 586 |
-
"step": 1580
|
| 587 |
-
},
|
| 588 |
-
{
|
| 589 |
-
"epoch": 2.6803519061583576,
|
| 590 |
-
"grad_norm": 5.981977939605713,
|
| 591 |
-
"learning_rate": 2.3368551895587326e-06,
|
| 592 |
-
"loss": 3.2722,
|
| 593 |
-
"step": 1600
|
| 594 |
-
},
|
| 595 |
-
{
|
| 596 |
-
"epoch": 2.7138667783829074,
|
| 597 |
-
"grad_norm": 6.096819877624512,
|
| 598 |
-
"learning_rate": 2.088253573648229e-06,
|
| 599 |
-
"loss": 3.3567,
|
| 600 |
-
"step": 1620
|
| 601 |
-
},
|
| 602 |
-
{
|
| 603 |
-
"epoch": 2.747381650607457,
|
| 604 |
-
"grad_norm": 5.6323442459106445,
|
| 605 |
-
"learning_rate": 1.8396519577377253e-06,
|
| 606 |
-
"loss": 3.3917,
|
| 607 |
-
"step": 1640
|
| 608 |
-
},
|
| 609 |
-
{
|
| 610 |
-
"epoch": 2.780896522832007,
|
| 611 |
-
"grad_norm": 6.144819736480713,
|
| 612 |
-
"learning_rate": 1.591050341827222e-06,
|
| 613 |
-
"loss": 3.4109,
|
| 614 |
-
"step": 1660
|
| 615 |
-
},
|
| 616 |
-
{
|
| 617 |
-
"epoch": 2.814411395056556,
|
| 618 |
-
"grad_norm": 6.0672287940979,
|
| 619 |
-
"learning_rate": 1.3424487259167184e-06,
|
| 620 |
-
"loss": 3.2653,
|
| 621 |
-
"step": 1680
|
| 622 |
-
},
|
| 623 |
-
{
|
| 624 |
-
"epoch": 2.847926267281106,
|
| 625 |
-
"grad_norm": 5.956326961517334,
|
| 626 |
-
"learning_rate": 1.0938471100062151e-06,
|
| 627 |
-
"loss": 3.3091,
|
| 628 |
-
"step": 1700
|
| 629 |
-
},
|
| 630 |
-
{
|
| 631 |
-
"epoch": 2.8814411395056556,
|
| 632 |
-
"grad_norm": 5.775784492492676,
|
| 633 |
-
"learning_rate": 8.452454940957117e-07,
|
| 634 |
-
"loss": 3.2879,
|
| 635 |
-
"step": 1720
|
| 636 |
-
},
|
| 637 |
-
{
|
| 638 |
-
"epoch": 2.9149560117302054,
|
| 639 |
-
"grad_norm": 5.547178745269775,
|
| 640 |
-
"learning_rate": 5.966438781852083e-07,
|
| 641 |
-
"loss": 3.3084,
|
| 642 |
-
"step": 1740
|
| 643 |
-
},
|
| 644 |
-
{
|
| 645 |
-
"epoch": 2.948470883954755,
|
| 646 |
-
"grad_norm": 5.489889621734619,
|
| 647 |
-
"learning_rate": 3.4804226227470484e-07,
|
| 648 |
-
"loss": 3.2788,
|
| 649 |
-
"step": 1760
|
| 650 |
-
},
|
| 651 |
-
{
|
| 652 |
-
"epoch": 2.981985756179305,
|
| 653 |
-
"grad_norm": 5.366356372833252,
|
| 654 |
-
"learning_rate": 9.944064636420137e-08,
|
| 655 |
-
"loss": 3.2467,
|
| 656 |
-
"step": 1780
|
| 657 |
-
}
|
| 658 |
-
],
|
| 659 |
-
"logging_steps": 20,
|
| 660 |
-
"max_steps": 1788,
|
| 661 |
-
"num_input_tokens_seen": 0,
|
| 662 |
-
"num_train_epochs": 3,
|
| 663 |
-
"save_steps": 500,
|
| 664 |
-
"stateful_callbacks": {
|
| 665 |
-
"TrainerControl": {
|
| 666 |
-
"args": {
|
| 667 |
-
"should_epoch_stop": false,
|
| 668 |
-
"should_evaluate": false,
|
| 669 |
-
"should_log": false,
|
| 670 |
-
"should_save": true,
|
| 671 |
-
"should_training_stop": true
|
| 672 |
-
},
|
| 673 |
-
"attributes": {}
|
| 674 |
-
}
|
| 675 |
-
},
|
| 676 |
-
"total_flos": 4.734803081428992e+17,
|
| 677 |
-
"train_batch_size": 4,
|
| 678 |
-
"trial_name": null,
|
| 679 |
-
"trial_params": null
|
| 680 |
-
}
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:28d569be50390dd686318165c52ce861eb9f1c7d012a2130e1d54b1d1e543a39
|
| 3 |
+
size 16823
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-1788/vocab.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|