Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- added_tokens.json +24 -0
- chat_template.jinja +54 -0
- config.json +58 -0
- generation_config.json +6 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- special_tokens_map.json +32 -0
- tokenizer.json +3 -0
- tokenizer_config.json +198 -0
- trainer_state.json +967 -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
|
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 |
+
}
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 4 |
+
{{- messages[0]['content'] }}
|
| 5 |
+
{%- else %}
|
| 6 |
+
{{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
|
| 7 |
+
{%- endif %}
|
| 8 |
+
{{- "\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>" }}
|
| 9 |
+
{%- for tool in tools %}
|
| 10 |
+
{{- "\n" }}
|
| 11 |
+
{{- tool | tojson }}
|
| 12 |
+
{%- endfor %}
|
| 13 |
+
{{- "\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" }}
|
| 14 |
+
{%- else %}
|
| 15 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 16 |
+
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
|
| 17 |
+
{%- else %}
|
| 18 |
+
{{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
|
| 19 |
+
{%- endif %}
|
| 20 |
+
{%- endif %}
|
| 21 |
+
{%- for message in messages %}
|
| 22 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
|
| 23 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
| 24 |
+
{%- elif message.role == "assistant" %}
|
| 25 |
+
{{- '<|im_start|>' + message.role }}
|
| 26 |
+
{%- if message.content %}
|
| 27 |
+
{{- '\n' + message.content }}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{%- for tool_call in message.tool_calls %}
|
| 30 |
+
{%- if tool_call.function is defined %}
|
| 31 |
+
{%- set tool_call = tool_call.function %}
|
| 32 |
+
{%- endif %}
|
| 33 |
+
{{- '\n<tool_call>\n{"name": "' }}
|
| 34 |
+
{{- tool_call.name }}
|
| 35 |
+
{{- '", "arguments": ' }}
|
| 36 |
+
{{- tool_call.arguments | tojson }}
|
| 37 |
+
{{- '}\n</tool_call>' }}
|
| 38 |
+
{%- endfor %}
|
| 39 |
+
{{- '<|im_end|>\n' }}
|
| 40 |
+
{%- elif message.role == "tool" %}
|
| 41 |
+
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
|
| 42 |
+
{{- '<|im_start|>user' }}
|
| 43 |
+
{%- endif %}
|
| 44 |
+
{{- '\n<tool_response>\n' }}
|
| 45 |
+
{{- message.content }}
|
| 46 |
+
{{- '\n</tool_response>' }}
|
| 47 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 48 |
+
{{- '<|im_end|>\n' }}
|
| 49 |
+
{%- endif %}
|
| 50 |
+
{%- endif %}
|
| 51 |
+
{%- endfor %}
|
| 52 |
+
{%- if add_generation_prompt %}
|
| 53 |
+
{{- '<|im_start|>assistant\n' }}
|
| 54 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"bos_token_id": 151643,
|
| 7 |
+
"eos_token_id": 151643,
|
| 8 |
+
"hidden_act": "silu",
|
| 9 |
+
"hidden_size": 1536,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 8960,
|
| 12 |
+
"layer_types": [
|
| 13 |
+
"full_attention",
|
| 14 |
+
"full_attention",
|
| 15 |
+
"full_attention",
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention"
|
| 41 |
+
],
|
| 42 |
+
"max_position_embeddings": 32768,
|
| 43 |
+
"max_window_layers": 28,
|
| 44 |
+
"model_type": "qwen2",
|
| 45 |
+
"num_attention_heads": 12,
|
| 46 |
+
"num_hidden_layers": 28,
|
| 47 |
+
"num_key_value_heads": 2,
|
| 48 |
+
"rms_norm_eps": 1e-06,
|
| 49 |
+
"rope_scaling": null,
|
| 50 |
+
"rope_theta": 1000000.0,
|
| 51 |
+
"sliding_window": null,
|
| 52 |
+
"tie_word_embeddings": true,
|
| 53 |
+
"torch_dtype": "bfloat16",
|
| 54 |
+
"transformers_version": "4.54.1",
|
| 55 |
+
"use_cache": false,
|
| 56 |
+
"use_sliding_window": false,
|
| 57 |
+
"vocab_size": 151936
|
| 58 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"eos_token_id": 151643,
|
| 4 |
+
"max_new_tokens": 2048,
|
| 5 |
+
"transformers_version": "4.54.1"
|
| 6 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1277aa33274a4952b5236d2248d7af56b868c942f790fdd1853ec12a4deac47b
|
| 3 |
+
size 3087467144
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
{
|
| 4 |
+
"content": "<|im_end|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
},
|
| 10 |
+
{
|
| 11 |
+
"content": "<|im_start|>",
|
| 12 |
+
"lstrip": false,
|
| 13 |
+
"normalized": false,
|
| 14 |
+
"rstrip": false,
|
| 15 |
+
"single_word": false
|
| 16 |
+
}
|
| 17 |
+
],
|
| 18 |
+
"eos_token": {
|
| 19 |
+
"content": "<|im_end|>",
|
| 20 |
+
"lstrip": false,
|
| 21 |
+
"normalized": false,
|
| 22 |
+
"rstrip": false,
|
| 23 |
+
"single_word": false
|
| 24 |
+
},
|
| 25 |
+
"pad_token": {
|
| 26 |
+
"content": "<|endoftext|>",
|
| 27 |
+
"lstrip": false,
|
| 28 |
+
"normalized": false,
|
| 29 |
+
"rstrip": false,
|
| 30 |
+
"single_word": false
|
| 31 |
+
}
|
| 32 |
+
}
|
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 +1,198 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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_end|>",
|
| 184 |
+
"<|im_start|>"
|
| 185 |
+
],
|
| 186 |
+
"bos_token": null,
|
| 187 |
+
"clean_up_tokenization_spaces": false,
|
| 188 |
+
"eos_token": "<|im_end|>",
|
| 189 |
+
"errors": "replace",
|
| 190 |
+
"extra_special_tokens": {},
|
| 191 |
+
"model_max_length": 1024,
|
| 192 |
+
"pad_token": "<|endoftext|>",
|
| 193 |
+
"padding_side": "right",
|
| 194 |
+
"split_special_tokens": false,
|
| 195 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 196 |
+
"truncation": true,
|
| 197 |
+
"unk_token": null
|
| 198 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,967 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 4233,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.007559650366170565,
|
| 14 |
+
"grad_norm": 32.25,
|
| 15 |
+
"learning_rate": 7.311320754716981e-07,
|
| 16 |
+
"loss": 0.6915,
|
| 17 |
+
"step": 32
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.01511930073234113,
|
| 21 |
+
"grad_norm": 14.5625,
|
| 22 |
+
"learning_rate": 1.4858490566037737e-06,
|
| 23 |
+
"loss": 0.6792,
|
| 24 |
+
"step": 64
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.022678951098511695,
|
| 28 |
+
"grad_norm": 16.875,
|
| 29 |
+
"learning_rate": 2.2405660377358494e-06,
|
| 30 |
+
"loss": 0.5993,
|
| 31 |
+
"step": 96
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.03023860146468226,
|
| 35 |
+
"grad_norm": 11.5625,
|
| 36 |
+
"learning_rate": 2.995283018867925e-06,
|
| 37 |
+
"loss": 0.5179,
|
| 38 |
+
"step": 128
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.03779825183085282,
|
| 42 |
+
"grad_norm": 14.5625,
|
| 43 |
+
"learning_rate": 3.7500000000000005e-06,
|
| 44 |
+
"loss": 0.5111,
|
| 45 |
+
"step": 160
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.04535790219702339,
|
| 49 |
+
"grad_norm": 9.8125,
|
| 50 |
+
"learning_rate": 4.504716981132076e-06,
|
| 51 |
+
"loss": 0.5109,
|
| 52 |
+
"step": 192
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.05291755256319395,
|
| 56 |
+
"grad_norm": 7.34375,
|
| 57 |
+
"learning_rate": 5.259433962264151e-06,
|
| 58 |
+
"loss": 0.5106,
|
| 59 |
+
"step": 224
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.06047720292936452,
|
| 63 |
+
"grad_norm": 6.1875,
|
| 64 |
+
"learning_rate": 6.014150943396226e-06,
|
| 65 |
+
"loss": 0.4514,
|
| 66 |
+
"step": 256
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.06803685329553508,
|
| 70 |
+
"grad_norm": 7.875,
|
| 71 |
+
"learning_rate": 6.768867924528303e-06,
|
| 72 |
+
"loss": 0.4862,
|
| 73 |
+
"step": 288
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.07559650366170564,
|
| 77 |
+
"grad_norm": 6.03125,
|
| 78 |
+
"learning_rate": 7.523584905660378e-06,
|
| 79 |
+
"loss": 0.4711,
|
| 80 |
+
"step": 320
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.08315615402787621,
|
| 84 |
+
"grad_norm": 6.1875,
|
| 85 |
+
"learning_rate": 8.278301886792453e-06,
|
| 86 |
+
"loss": 0.4783,
|
| 87 |
+
"step": 352
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.09071580439404678,
|
| 91 |
+
"grad_norm": 7.78125,
|
| 92 |
+
"learning_rate": 9.03301886792453e-06,
|
| 93 |
+
"loss": 0.4457,
|
| 94 |
+
"step": 384
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.09827545476021735,
|
| 98 |
+
"grad_norm": 6.59375,
|
| 99 |
+
"learning_rate": 9.787735849056604e-06,
|
| 100 |
+
"loss": 0.5125,
|
| 101 |
+
"step": 416
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.1058351051263879,
|
| 105 |
+
"grad_norm": 13.5625,
|
| 106 |
+
"learning_rate": 9.99910037719311e-06,
|
| 107 |
+
"loss": 0.4171,
|
| 108 |
+
"step": 448
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.11339475549255847,
|
| 112 |
+
"grad_norm": 3.921875,
|
| 113 |
+
"learning_rate": 9.994856381944038e-06,
|
| 114 |
+
"loss": 0.4538,
|
| 115 |
+
"step": 480
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.12095440585872903,
|
| 119 |
+
"grad_norm": 6.15625,
|
| 120 |
+
"learning_rate": 9.987133217483066e-06,
|
| 121 |
+
"loss": 0.4629,
|
| 122 |
+
"step": 512
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.1285140562248996,
|
| 126 |
+
"grad_norm": 6.28125,
|
| 127 |
+
"learning_rate": 9.975936263383488e-06,
|
| 128 |
+
"loss": 0.4744,
|
| 129 |
+
"step": 544
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.13607370659107015,
|
| 133 |
+
"grad_norm": 7.125,
|
| 134 |
+
"learning_rate": 9.96127331888816e-06,
|
| 135 |
+
"loss": 0.4292,
|
| 136 |
+
"step": 576
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.14363335695724072,
|
| 140 |
+
"grad_norm": 5.15625,
|
| 141 |
+
"learning_rate": 9.943154597476943e-06,
|
| 142 |
+
"loss": 0.4558,
|
| 143 |
+
"step": 608
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.1511930073234113,
|
| 147 |
+
"grad_norm": 10.6875,
|
| 148 |
+
"learning_rate": 9.921592719752486e-06,
|
| 149 |
+
"loss": 0.448,
|
| 150 |
+
"step": 640
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.15875265768958186,
|
| 154 |
+
"grad_norm": 8.125,
|
| 155 |
+
"learning_rate": 9.896602704649348e-06,
|
| 156 |
+
"loss": 0.4117,
|
| 157 |
+
"step": 672
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.16631230805575242,
|
| 161 |
+
"grad_norm": 4.84375,
|
| 162 |
+
"learning_rate": 9.868201958972548e-06,
|
| 163 |
+
"loss": 0.4303,
|
| 164 |
+
"step": 704
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.173871958421923,
|
| 168 |
+
"grad_norm": 5.0625,
|
| 169 |
+
"learning_rate": 9.836410265272857e-06,
|
| 170 |
+
"loss": 0.4402,
|
| 171 |
+
"step": 736
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.18143160878809356,
|
| 175 |
+
"grad_norm": 8.875,
|
| 176 |
+
"learning_rate": 9.801249768067246e-06,
|
| 177 |
+
"loss": 0.4242,
|
| 178 |
+
"step": 768
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.18899125915426412,
|
| 182 |
+
"grad_norm": 5.625,
|
| 183 |
+
"learning_rate": 9.762744958414113e-06,
|
| 184 |
+
"loss": 0.4771,
|
| 185 |
+
"step": 800
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.1965509095204347,
|
| 189 |
+
"grad_norm": 14.875,
|
| 190 |
+
"learning_rate": 9.720922656854032e-06,
|
| 191 |
+
"loss": 0.4497,
|
| 192 |
+
"step": 832
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.20411055988660523,
|
| 196 |
+
"grad_norm": 6.3125,
|
| 197 |
+
"learning_rate": 9.675811994727897e-06,
|
| 198 |
+
"loss": 0.4141,
|
| 199 |
+
"step": 864
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.2116702102527758,
|
| 203 |
+
"grad_norm": 6.15625,
|
| 204 |
+
"learning_rate": 9.627444393885463e-06,
|
| 205 |
+
"loss": 0.432,
|
| 206 |
+
"step": 896
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.21922986061894637,
|
| 210 |
+
"grad_norm": 6.28125,
|
| 211 |
+
"learning_rate": 9.575853544798453e-06,
|
| 212 |
+
"loss": 0.4253,
|
| 213 |
+
"step": 928
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.22678951098511693,
|
| 217 |
+
"grad_norm": 7.4375,
|
| 218 |
+
"learning_rate": 9.521075383093452e-06,
|
| 219 |
+
"loss": 0.4334,
|
| 220 |
+
"step": 960
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.2343491613512875,
|
| 224 |
+
"grad_norm": 9.0625,
|
| 225 |
+
"learning_rate": 9.463148064520913e-06,
|
| 226 |
+
"loss": 0.4595,
|
| 227 |
+
"step": 992
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.24190881171745807,
|
| 231 |
+
"grad_norm": 6.71875,
|
| 232 |
+
"learning_rate": 9.402111938377776e-06,
|
| 233 |
+
"loss": 0.4401,
|
| 234 |
+
"step": 1024
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.24946846208362863,
|
| 238 |
+
"grad_norm": 9.0625,
|
| 239 |
+
"learning_rate": 9.338009519402132e-06,
|
| 240 |
+
"loss": 0.4216,
|
| 241 |
+
"step": 1056
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.2570281124497992,
|
| 245 |
+
"grad_norm": 7.59375,
|
| 246 |
+
"learning_rate": 9.270885458159576e-06,
|
| 247 |
+
"loss": 0.4391,
|
| 248 |
+
"step": 1088
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.26458776281596974,
|
| 252 |
+
"grad_norm": 7.875,
|
| 253 |
+
"learning_rate": 9.200786509941827e-06,
|
| 254 |
+
"loss": 0.4116,
|
| 255 |
+
"step": 1120
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.2721474131821403,
|
| 259 |
+
"grad_norm": 11.5625,
|
| 260 |
+
"learning_rate": 9.127761502199325e-06,
|
| 261 |
+
"loss": 0.4004,
|
| 262 |
+
"step": 1152
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.2797070635483109,
|
| 266 |
+
"grad_norm": 7.8125,
|
| 267 |
+
"learning_rate": 9.051861300530438e-06,
|
| 268 |
+
"loss": 0.4261,
|
| 269 |
+
"step": 1184
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.28726671391448144,
|
| 273 |
+
"grad_norm": 6.53125,
|
| 274 |
+
"learning_rate": 8.973138773251015e-06,
|
| 275 |
+
"loss": 0.4075,
|
| 276 |
+
"step": 1216
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.294826364280652,
|
| 280 |
+
"grad_norm": 6.78125,
|
| 281 |
+
"learning_rate": 8.891648754568943e-06,
|
| 282 |
+
"loss": 0.4398,
|
| 283 |
+
"step": 1248
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.3023860146468226,
|
| 287 |
+
"grad_norm": 7.40625,
|
| 288 |
+
"learning_rate": 8.807448006389343e-06,
|
| 289 |
+
"loss": 0.4517,
|
| 290 |
+
"step": 1280
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.30994566501299314,
|
| 294 |
+
"grad_norm": 4.3125,
|
| 295 |
+
"learning_rate": 8.720595178777063e-06,
|
| 296 |
+
"loss": 0.4254,
|
| 297 |
+
"step": 1312
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.3175053153791637,
|
| 301 |
+
"grad_norm": 7.25,
|
| 302 |
+
"learning_rate": 8.631150769103934e-06,
|
| 303 |
+
"loss": 0.441,
|
| 304 |
+
"step": 1344
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.3250649657453343,
|
| 308 |
+
"grad_norm": 6.65625,
|
| 309 |
+
"learning_rate": 8.539177079909315e-06,
|
| 310 |
+
"loss": 0.4337,
|
| 311 |
+
"step": 1376
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.33262461611150484,
|
| 315 |
+
"grad_norm": 5.8125,
|
| 316 |
+
"learning_rate": 8.444738175503222e-06,
|
| 317 |
+
"loss": 0.4537,
|
| 318 |
+
"step": 1408
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.3401842664776754,
|
| 322 |
+
"grad_norm": 5.5625,
|
| 323 |
+
"learning_rate": 8.347899837342315e-06,
|
| 324 |
+
"loss": 0.4071,
|
| 325 |
+
"step": 1440
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.347743916843846,
|
| 329 |
+
"grad_norm": 7.875,
|
| 330 |
+
"learning_rate": 8.2487295182098e-06,
|
| 331 |
+
"loss": 0.4612,
|
| 332 |
+
"step": 1472
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.35530356721001655,
|
| 336 |
+
"grad_norm": 5.1875,
|
| 337 |
+
"learning_rate": 8.147296295231158e-06,
|
| 338 |
+
"loss": 0.4296,
|
| 339 |
+
"step": 1504
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.3628632175761871,
|
| 343 |
+
"grad_norm": 8.625,
|
| 344 |
+
"learning_rate": 8.04367082175845e-06,
|
| 345 |
+
"loss": 0.4491,
|
| 346 |
+
"step": 1536
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.3704228679423577,
|
| 350 |
+
"grad_norm": 5.25,
|
| 351 |
+
"learning_rate": 7.937925278156698e-06,
|
| 352 |
+
"loss": 0.4132,
|
| 353 |
+
"step": 1568
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.37798251830852825,
|
| 357 |
+
"grad_norm": 6.8125,
|
| 358 |
+
"learning_rate": 7.830133321526615e-06,
|
| 359 |
+
"loss": 0.4068,
|
| 360 |
+
"step": 1600
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.3855421686746988,
|
| 364 |
+
"grad_norm": 4.375,
|
| 365 |
+
"learning_rate": 7.720370034398741e-06,
|
| 366 |
+
"loss": 0.4499,
|
| 367 |
+
"step": 1632
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.3931018190408694,
|
| 371 |
+
"grad_norm": 6.96875,
|
| 372 |
+
"learning_rate": 7.608711872434648e-06,
|
| 373 |
+
"loss": 0.4256,
|
| 374 |
+
"step": 1664
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.40066146940703995,
|
| 378 |
+
"grad_norm": 9.875,
|
| 379 |
+
"learning_rate": 7.495236611171741e-06,
|
| 380 |
+
"loss": 0.428,
|
| 381 |
+
"step": 1696
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.40822111977321046,
|
| 385 |
+
"grad_norm": 5.90625,
|
| 386 |
+
"learning_rate": 7.3800232918486715e-06,
|
| 387 |
+
"loss": 0.4146,
|
| 388 |
+
"step": 1728
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.41578077013938103,
|
| 392 |
+
"grad_norm": 6.4375,
|
| 393 |
+
"learning_rate": 7.263152166349122e-06,
|
| 394 |
+
"loss": 0.4476,
|
| 395 |
+
"step": 1760
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.4233404205055516,
|
| 399 |
+
"grad_norm": 7.3125,
|
| 400 |
+
"learning_rate": 7.144704641302337e-06,
|
| 401 |
+
"loss": 0.4387,
|
| 402 |
+
"step": 1792
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.43090007087172216,
|
| 406 |
+
"grad_norm": 6.84375,
|
| 407 |
+
"learning_rate": 7.024763221379289e-06,
|
| 408 |
+
"loss": 0.4276,
|
| 409 |
+
"step": 1824
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.43845972123789273,
|
| 413 |
+
"grad_norm": 7.25,
|
| 414 |
+
"learning_rate": 6.903411451824033e-06,
|
| 415 |
+
"loss": 0.4482,
|
| 416 |
+
"step": 1856
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.4460193716040633,
|
| 420 |
+
"grad_norm": 6.9375,
|
| 421 |
+
"learning_rate": 6.780733860260216e-06,
|
| 422 |
+
"loss": 0.4187,
|
| 423 |
+
"step": 1888
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.45357902197023386,
|
| 427 |
+
"grad_norm": 6.09375,
|
| 428 |
+
"learning_rate": 6.6568158978133455e-06,
|
| 429 |
+
"loss": 0.402,
|
| 430 |
+
"step": 1920
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.46113867233640443,
|
| 434 |
+
"grad_norm": 5.34375,
|
| 435 |
+
"learning_rate": 6.531743879589754e-06,
|
| 436 |
+
"loss": 0.4157,
|
| 437 |
+
"step": 1952
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.468698322702575,
|
| 441 |
+
"grad_norm": 5.8125,
|
| 442 |
+
"learning_rate": 6.405604924553797e-06,
|
| 443 |
+
"loss": 0.4771,
|
| 444 |
+
"step": 1984
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.47625797306874557,
|
| 448 |
+
"grad_norm": 6.53125,
|
| 449 |
+
"learning_rate": 6.278486894845084e-06,
|
| 450 |
+
"loss": 0.4408,
|
| 451 |
+
"step": 2016
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.48381762343491613,
|
| 455 |
+
"grad_norm": 5.96875,
|
| 456 |
+
"learning_rate": 6.150478334578085e-06,
|
| 457 |
+
"loss": 0.4434,
|
| 458 |
+
"step": 2048
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.4913772738010867,
|
| 462 |
+
"grad_norm": 8.3125,
|
| 463 |
+
"learning_rate": 6.021668408166688e-06,
|
| 464 |
+
"loss": 0.4214,
|
| 465 |
+
"step": 2080
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.49893692416725727,
|
| 469 |
+
"grad_norm": 4.28125,
|
| 470 |
+
"learning_rate": 5.892146838216687e-06,
|
| 471 |
+
"loss": 0.4164,
|
| 472 |
+
"step": 2112
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.5064965745334278,
|
| 476 |
+
"grad_norm": 4.25,
|
| 477 |
+
"learning_rate": 5.762003843029466e-06,
|
| 478 |
+
"loss": 0.426,
|
| 479 |
+
"step": 2144
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.5140562248995983,
|
| 483 |
+
"grad_norm": 6.96875,
|
| 484 |
+
"learning_rate": 5.631330073760413e-06,
|
| 485 |
+
"loss": 0.4205,
|
| 486 |
+
"step": 2176
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.5216158752657689,
|
| 490 |
+
"grad_norm": 6.6875,
|
| 491 |
+
"learning_rate": 5.500216551275807e-06,
|
| 492 |
+
"loss": 0.4429,
|
| 493 |
+
"step": 2208
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.5291755256319395,
|
| 497 |
+
"grad_norm": 7.15625,
|
| 498 |
+
"learning_rate": 5.368754602752213e-06,
|
| 499 |
+
"loss": 0.431,
|
| 500 |
+
"step": 2240
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.53673517599811,
|
| 504 |
+
"grad_norm": 5.28125,
|
| 505 |
+
"learning_rate": 5.237035798062489e-06,
|
| 506 |
+
"loss": 0.4224,
|
| 507 |
+
"step": 2272
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.5442948263642806,
|
| 511 |
+
"grad_norm": 8.125,
|
| 512 |
+
"learning_rate": 5.105151885992754e-06,
|
| 513 |
+
"loss": 0.4194,
|
| 514 |
+
"step": 2304
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.5518544767304512,
|
| 518 |
+
"grad_norm": 5.5,
|
| 519 |
+
"learning_rate": 4.9731947303347485e-06,
|
| 520 |
+
"loss": 0.434,
|
| 521 |
+
"step": 2336
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.5594141270966217,
|
| 525 |
+
"grad_norm": 6.09375,
|
| 526 |
+
"learning_rate": 4.841256245898055e-06,
|
| 527 |
+
"loss": 0.4308,
|
| 528 |
+
"step": 2368
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.5669737774627923,
|
| 532 |
+
"grad_norm": 4.3125,
|
| 533 |
+
"learning_rate": 4.709428334486816e-06,
|
| 534 |
+
"loss": 0.3907,
|
| 535 |
+
"step": 2400
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.5745334278289629,
|
| 539 |
+
"grad_norm": 6.96875,
|
| 540 |
+
"learning_rate": 4.577802820885482e-06,
|
| 541 |
+
"loss": 0.4226,
|
| 542 |
+
"step": 2432
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.5820930781951335,
|
| 546 |
+
"grad_norm": 5.75,
|
| 547 |
+
"learning_rate": 4.446471388898236e-06,
|
| 548 |
+
"loss": 0.4216,
|
| 549 |
+
"step": 2464
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.589652728561304,
|
| 553 |
+
"grad_norm": 6.46875,
|
| 554 |
+
"learning_rate": 4.315525517486586e-06,
|
| 555 |
+
"loss": 0.4632,
|
| 556 |
+
"step": 2496
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.5972123789274746,
|
| 560 |
+
"grad_norm": 3.46875,
|
| 561 |
+
"learning_rate": 4.185056417049674e-06,
|
| 562 |
+
"loss": 0.4304,
|
| 563 |
+
"step": 2528
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.6047720292936452,
|
| 567 |
+
"grad_norm": 8.25,
|
| 568 |
+
"learning_rate": 4.055154965891625e-06,
|
| 569 |
+
"loss": 0.451,
|
| 570 |
+
"step": 2560
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.6123316796598157,
|
| 574 |
+
"grad_norm": 6.78125,
|
| 575 |
+
"learning_rate": 3.925911646920235e-06,
|
| 576 |
+
"loss": 0.3851,
|
| 577 |
+
"step": 2592
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.6198913300259863,
|
| 581 |
+
"grad_norm": 6.84375,
|
| 582 |
+
"learning_rate": 3.797416484621057e-06,
|
| 583 |
+
"loss": 0.4486,
|
| 584 |
+
"step": 2624
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.6274509803921569,
|
| 588 |
+
"grad_norm": 5.28125,
|
| 589 |
+
"learning_rate": 3.669758982350821e-06,
|
| 590 |
+
"loss": 0.4258,
|
| 591 |
+
"step": 2656
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.6350106307583274,
|
| 595 |
+
"grad_norm": 6.53125,
|
| 596 |
+
"learning_rate": 3.5430280599938204e-06,
|
| 597 |
+
"loss": 0.4303,
|
| 598 |
+
"step": 2688
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.642570281124498,
|
| 602 |
+
"grad_norm": 12.1875,
|
| 603 |
+
"learning_rate": 3.4173119920247454e-06,
|
| 604 |
+
"loss": 0.4466,
|
| 605 |
+
"step": 2720
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.6501299314906686,
|
| 609 |
+
"grad_norm": 5.1875,
|
| 610 |
+
"learning_rate": 3.2926983460210564e-06,
|
| 611 |
+
"loss": 0.4131,
|
| 612 |
+
"step": 2752
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.6576895818568391,
|
| 616 |
+
"grad_norm": 4.6875,
|
| 617 |
+
"learning_rate": 3.1692739216677483e-06,
|
| 618 |
+
"loss": 0.4672,
|
| 619 |
+
"step": 2784
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.6652492322230097,
|
| 623 |
+
"grad_norm": 5.5625,
|
| 624 |
+
"learning_rate": 3.0471246902970032e-06,
|
| 625 |
+
"loss": 0.4291,
|
| 626 |
+
"step": 2816
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.6728088825891803,
|
| 630 |
+
"grad_norm": 4.71875,
|
| 631 |
+
"learning_rate": 2.926335735004817e-06,
|
| 632 |
+
"loss": 0.4264,
|
| 633 |
+
"step": 2848
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.6803685329553508,
|
| 637 |
+
"grad_norm": 6.0625,
|
| 638 |
+
"learning_rate": 2.8069911913863414e-06,
|
| 639 |
+
"loss": 0.422,
|
| 640 |
+
"step": 2880
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.6879281833215214,
|
| 644 |
+
"grad_norm": 6.9375,
|
| 645 |
+
"learning_rate": 2.689174188931202e-06,
|
| 646 |
+
"loss": 0.4005,
|
| 647 |
+
"step": 2912
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.695487833687692,
|
| 651 |
+
"grad_norm": 6.125,
|
| 652 |
+
"learning_rate": 2.5729667931196103e-06,
|
| 653 |
+
"loss": 0.4137,
|
| 654 |
+
"step": 2944
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.7030474840538625,
|
| 658 |
+
"grad_norm": 4.0625,
|
| 659 |
+
"learning_rate": 2.4584499482596274e-06,
|
| 660 |
+
"loss": 0.4145,
|
| 661 |
+
"step": 2976
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.7106071344200331,
|
| 665 |
+
"grad_norm": 6.1875,
|
| 666 |
+
"learning_rate": 2.3457034211053703e-06,
|
| 667 |
+
"loss": 0.4601,
|
| 668 |
+
"step": 3008
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.7181667847862037,
|
| 672 |
+
"grad_norm": 9.0,
|
| 673 |
+
"learning_rate": 2.234805745295457e-06,
|
| 674 |
+
"loss": 0.4238,
|
| 675 |
+
"step": 3040
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.7257264351523742,
|
| 679 |
+
"grad_norm": 15.625,
|
| 680 |
+
"learning_rate": 2.125834166650354e-06,
|
| 681 |
+
"loss": 0.4579,
|
| 682 |
+
"step": 3072
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.7332860855185448,
|
| 686 |
+
"grad_norm": 4.8125,
|
| 687 |
+
"learning_rate": 2.018864589366778e-06,
|
| 688 |
+
"loss": 0.4183,
|
| 689 |
+
"step": 3104
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.7408457358847154,
|
| 693 |
+
"grad_norm": 6.1875,
|
| 694 |
+
"learning_rate": 1.9139715231466014e-06,
|
| 695 |
+
"loss": 0.4387,
|
| 696 |
+
"step": 3136
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.7484053862508859,
|
| 700 |
+
"grad_norm": 7.03125,
|
| 701 |
+
"learning_rate": 1.811228031297077e-06,
|
| 702 |
+
"loss": 0.4367,
|
| 703 |
+
"step": 3168
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.7559650366170565,
|
| 707 |
+
"grad_norm": 5.65625,
|
| 708 |
+
"learning_rate": 1.7107056798385763e-06,
|
| 709 |
+
"loss": 0.451,
|
| 710 |
+
"step": 3200
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.7635246869832271,
|
| 714 |
+
"grad_norm": 6.65625,
|
| 715 |
+
"learning_rate": 1.6124744876552373e-06,
|
| 716 |
+
"loss": 0.4101,
|
| 717 |
+
"step": 3232
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.7710843373493976,
|
| 721 |
+
"grad_norm": 6.8125,
|
| 722 |
+
"learning_rate": 1.5166028777232884e-06,
|
| 723 |
+
"loss": 0.3734,
|
| 724 |
+
"step": 3264
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.7786439877155682,
|
| 728 |
+
"grad_norm": 5.34375,
|
| 729 |
+
"learning_rate": 1.4231576294510013e-06,
|
| 730 |
+
"loss": 0.4194,
|
| 731 |
+
"step": 3296
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.7862036380817388,
|
| 735 |
+
"grad_norm": 7.8125,
|
| 736 |
+
"learning_rate": 1.3322038321634567e-06,
|
| 737 |
+
"loss": 0.465,
|
| 738 |
+
"step": 3328
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.7937632884479093,
|
| 742 |
+
"grad_norm": 5.75,
|
| 743 |
+
"learning_rate": 1.2438048397645558e-06,
|
| 744 |
+
"loss": 0.4751,
|
| 745 |
+
"step": 3360
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.8013229388140799,
|
| 749 |
+
"grad_norm": 8.75,
|
| 750 |
+
"learning_rate": 1.1580222266078367e-06,
|
| 751 |
+
"loss": 0.401,
|
| 752 |
+
"step": 3392
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.8088825891802505,
|
| 756 |
+
"grad_norm": 8.375,
|
| 757 |
+
"learning_rate": 1.0749157446068242e-06,
|
| 758 |
+
"loss": 0.4418,
|
| 759 |
+
"step": 3424
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.8164422395464209,
|
| 763 |
+
"grad_norm": 7.375,
|
| 764 |
+
"learning_rate": 9.945432816148175e-07,
|
| 765 |
+
"loss": 0.4405,
|
| 766 |
+
"step": 3456
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.8240018899125915,
|
| 770 |
+
"grad_norm": 4.84375,
|
| 771 |
+
"learning_rate": 9.169608211030783e-07,
|
| 772 |
+
"loss": 0.4298,
|
| 773 |
+
"step": 3488
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.8315615402787621,
|
| 777 |
+
"grad_norm": 5.78125,
|
| 778 |
+
"learning_rate": 8.422224031655313e-07,
|
| 779 |
+
"loss": 0.4156,
|
| 780 |
+
"step": 3520
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.8391211906449326,
|
| 784 |
+
"grad_norm": 21.25,
|
| 785 |
+
"learning_rate": 7.703800868771e-07,
|
| 786 |
+
"loss": 0.4467,
|
| 787 |
+
"step": 3552
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.8466808410111032,
|
| 791 |
+
"grad_norm": 14.3125,
|
| 792 |
+
"learning_rate": 7.014839140319485e-07,
|
| 793 |
+
"loss": 0.4443,
|
| 794 |
+
"step": 3584
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.8542404913772738,
|
| 798 |
+
"grad_norm": 6.59375,
|
| 799 |
+
"learning_rate": 6.355818742868447e-07,
|
| 800 |
+
"loss": 0.4381,
|
| 801 |
+
"step": 3616
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.8618001417434443,
|
| 805 |
+
"grad_norm": 5.46875,
|
| 806 |
+
"learning_rate": 5.727198717339511e-07,
|
| 807 |
+
"loss": 0.405,
|
| 808 |
+
"step": 3648
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.8693597921096149,
|
| 812 |
+
"grad_norm": 4.3125,
|
| 813 |
+
"learning_rate": 5.129416929263031e-07,
|
| 814 |
+
"loss": 0.4161,
|
| 815 |
+
"step": 3680
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.8769194424757855,
|
| 819 |
+
"grad_norm": 6.84375,
|
| 820 |
+
"learning_rate": 4.5628897637827354e-07,
|
| 821 |
+
"loss": 0.4294,
|
| 822 |
+
"step": 3712
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.884479092841956,
|
| 826 |
+
"grad_norm": 6.0,
|
| 827 |
+
"learning_rate": 4.028011835622492e-07,
|
| 828 |
+
"loss": 0.4084,
|
| 829 |
+
"step": 3744
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.8920387432081266,
|
| 833 |
+
"grad_norm": 5.1875,
|
| 834 |
+
"learning_rate": 3.525155714217227e-07,
|
| 835 |
+
"loss": 0.3902,
|
| 836 |
+
"step": 3776
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.8995983935742972,
|
| 840 |
+
"grad_norm": 5.8125,
|
| 841 |
+
"learning_rate": 3.054671664199543e-07,
|
| 842 |
+
"loss": 0.423,
|
| 843 |
+
"step": 3808
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.9071580439404677,
|
| 847 |
+
"grad_norm": 6.75,
|
| 848 |
+
"learning_rate": 2.616887401422796e-07,
|
| 849 |
+
"loss": 0.4108,
|
| 850 |
+
"step": 3840
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.9147176943066383,
|
| 854 |
+
"grad_norm": 5.9375,
|
| 855 |
+
"learning_rate": 2.212107864690438e-07,
|
| 856 |
+
"loss": 0.4546,
|
| 857 |
+
"step": 3872
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.9222773446728089,
|
| 861 |
+
"grad_norm": 8.0625,
|
| 862 |
+
"learning_rate": 1.8406150033507764e-07,
|
| 863 |
+
"loss": 0.4434,
|
| 864 |
+
"step": 3904
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.9298369950389794,
|
| 868 |
+
"grad_norm": 10.4375,
|
| 869 |
+
"learning_rate": 1.502667580905054e-07,
|
| 870 |
+
"loss": 0.4149,
|
| 871 |
+
"step": 3936
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.93739664540515,
|
| 875 |
+
"grad_norm": 6.0625,
|
| 876 |
+
"learning_rate": 1.1985009947656278e-07,
|
| 877 |
+
"loss": 0.4504,
|
| 878 |
+
"step": 3968
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.9449562957713206,
|
| 882 |
+
"grad_norm": 5.625,
|
| 883 |
+
"learning_rate": 9.283271122898174e-08,
|
| 884 |
+
"loss": 0.437,
|
| 885 |
+
"step": 4000
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.9525159461374911,
|
| 889 |
+
"grad_norm": 6.90625,
|
| 890 |
+
"learning_rate": 6.923341232035863e-08,
|
| 891 |
+
"loss": 0.4205,
|
| 892 |
+
"step": 4032
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.9600755965036617,
|
| 896 |
+
"grad_norm": 9.625,
|
| 897 |
+
"learning_rate": 4.9068640851792636e-08,
|
| 898 |
+
"loss": 0.4221,
|
| 899 |
+
"step": 4064
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.9676352468698323,
|
| 903 |
+
"grad_norm": 5.09375,
|
| 904 |
+
"learning_rate": 3.235244260292147e-08,
|
| 905 |
+
"loss": 0.4172,
|
| 906 |
+
"step": 4096
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.9751948972360028,
|
| 910 |
+
"grad_norm": 6.0,
|
| 911 |
+
"learning_rate": 1.909646124832576e-08,
|
| 912 |
+
"loss": 0.415,
|
| 913 |
+
"step": 4128
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.9827545476021734,
|
| 917 |
+
"grad_norm": 7.34375,
|
| 918 |
+
"learning_rate": 9.30993024712279e-09,
|
| 919 |
+
"loss": 0.4298,
|
| 920 |
+
"step": 4160
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.990314197968344,
|
| 924 |
+
"grad_norm": 5.25,
|
| 925 |
+
"learning_rate": 2.999666411398483e-09,
|
| 926 |
+
"loss": 0.3673,
|
| 927 |
+
"step": 4192
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.9978738483345145,
|
| 931 |
+
"grad_norm": 5.28125,
|
| 932 |
+
"learning_rate": 1.7006515795336963e-10,
|
| 933 |
+
"loss": 0.422,
|
| 934 |
+
"step": 4224
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 1.0,
|
| 938 |
+
"step": 4233,
|
| 939 |
+
"total_flos": 7.498056185637274e+16,
|
| 940 |
+
"train_loss": 0.4399125433520113,
|
| 941 |
+
"train_runtime": 1541.2359,
|
| 942 |
+
"train_samples_per_second": 10.985,
|
| 943 |
+
"train_steps_per_second": 2.746
|
| 944 |
+
}
|
| 945 |
+
],
|
| 946 |
+
"logging_steps": 32,
|
| 947 |
+
"max_steps": 4233,
|
| 948 |
+
"num_input_tokens_seen": 0,
|
| 949 |
+
"num_train_epochs": 1,
|
| 950 |
+
"save_steps": 500,
|
| 951 |
+
"stateful_callbacks": {
|
| 952 |
+
"TrainerControl": {
|
| 953 |
+
"args": {
|
| 954 |
+
"should_epoch_stop": false,
|
| 955 |
+
"should_evaluate": false,
|
| 956 |
+
"should_log": false,
|
| 957 |
+
"should_save": false,
|
| 958 |
+
"should_training_stop": false
|
| 959 |
+
},
|
| 960 |
+
"attributes": {}
|
| 961 |
+
}
|
| 962 |
+
},
|
| 963 |
+
"total_flos": 7.498056185637274e+16,
|
| 964 |
+
"train_batch_size": 4,
|
| 965 |
+
"trial_name": null,
|
| 966 |
+
"trial_params": null
|
| 967 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5fcca8e6c6ad75e58af68af977f742fda2f5739dd94a2204c0d5bb50980a7925
|
| 3 |
+
size 5777
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|