my_model
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 +1891 -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 sha256:266f54f732bf1128b9acedff75a831fbd022fdb78e61b7614e09e4c167751770
|
| 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 +1,1891 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 2.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 8466,
|
| 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": 10.1875,
|
| 15 |
+
"learning_rate": 3.6599763872491147e-07,
|
| 16 |
+
"loss": 0.4442,
|
| 17 |
+
"step": 32
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.01511930073234113,
|
| 21 |
+
"grad_norm": 4.71875,
|
| 22 |
+
"learning_rate": 7.438016528925621e-07,
|
| 23 |
+
"loss": 0.4186,
|
| 24 |
+
"step": 64
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.022678951098511695,
|
| 28 |
+
"grad_norm": 7.0,
|
| 29 |
+
"learning_rate": 1.1216056670602125e-06,
|
| 30 |
+
"loss": 0.3941,
|
| 31 |
+
"step": 96
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.03023860146468226,
|
| 35 |
+
"grad_norm": 5.4375,
|
| 36 |
+
"learning_rate": 1.4994096812278634e-06,
|
| 37 |
+
"loss": 0.3913,
|
| 38 |
+
"step": 128
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.03779825183085282,
|
| 42 |
+
"grad_norm": 8.625,
|
| 43 |
+
"learning_rate": 1.8772136953955136e-06,
|
| 44 |
+
"loss": 0.4175,
|
| 45 |
+
"step": 160
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.04535790219702339,
|
| 49 |
+
"grad_norm": 6.4375,
|
| 50 |
+
"learning_rate": 2.2550177095631644e-06,
|
| 51 |
+
"loss": 0.4357,
|
| 52 |
+
"step": 192
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.05291755256319395,
|
| 56 |
+
"grad_norm": 5.75,
|
| 57 |
+
"learning_rate": 2.632821723730815e-06,
|
| 58 |
+
"loss": 0.4368,
|
| 59 |
+
"step": 224
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.06047720292936452,
|
| 63 |
+
"grad_norm": 5.15625,
|
| 64 |
+
"learning_rate": 3.0106257378984653e-06,
|
| 65 |
+
"loss": 0.3838,
|
| 66 |
+
"step": 256
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.06803685329553508,
|
| 70 |
+
"grad_norm": 5.84375,
|
| 71 |
+
"learning_rate": 3.388429752066116e-06,
|
| 72 |
+
"loss": 0.4227,
|
| 73 |
+
"step": 288
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.07559650366170564,
|
| 77 |
+
"grad_norm": 8.1875,
|
| 78 |
+
"learning_rate": 3.7662337662337666e-06,
|
| 79 |
+
"loss": 0.3997,
|
| 80 |
+
"step": 320
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.08315615402787621,
|
| 84 |
+
"grad_norm": 5.28125,
|
| 85 |
+
"learning_rate": 4.144037780401417e-06,
|
| 86 |
+
"loss": 0.4102,
|
| 87 |
+
"step": 352
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.09071580439404678,
|
| 91 |
+
"grad_norm": 5.15625,
|
| 92 |
+
"learning_rate": 4.521841794569068e-06,
|
| 93 |
+
"loss": 0.3753,
|
| 94 |
+
"step": 384
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.09827545476021735,
|
| 98 |
+
"grad_norm": 5.78125,
|
| 99 |
+
"learning_rate": 4.8996458087367186e-06,
|
| 100 |
+
"loss": 0.4282,
|
| 101 |
+
"step": 416
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.1058351051263879,
|
| 105 |
+
"grad_norm": 9.875,
|
| 106 |
+
"learning_rate": 5.277449822904369e-06,
|
| 107 |
+
"loss": 0.3424,
|
| 108 |
+
"step": 448
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.11339475549255847,
|
| 112 |
+
"grad_norm": 3.390625,
|
| 113 |
+
"learning_rate": 5.655253837072019e-06,
|
| 114 |
+
"loss": 0.3747,
|
| 115 |
+
"step": 480
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.12095440585872903,
|
| 119 |
+
"grad_norm": 5.15625,
|
| 120 |
+
"learning_rate": 6.03305785123967e-06,
|
| 121 |
+
"loss": 0.3818,
|
| 122 |
+
"step": 512
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.1285140562248996,
|
| 126 |
+
"grad_norm": 5.96875,
|
| 127 |
+
"learning_rate": 6.41086186540732e-06,
|
| 128 |
+
"loss": 0.3944,
|
| 129 |
+
"step": 544
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.13607370659107015,
|
| 133 |
+
"grad_norm": 5.0625,
|
| 134 |
+
"learning_rate": 6.788665879574971e-06,
|
| 135 |
+
"loss": 0.3564,
|
| 136 |
+
"step": 576
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.14363335695724072,
|
| 140 |
+
"grad_norm": 5.03125,
|
| 141 |
+
"learning_rate": 7.166469893742622e-06,
|
| 142 |
+
"loss": 0.3824,
|
| 143 |
+
"step": 608
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.1511930073234113,
|
| 147 |
+
"grad_norm": 8.375,
|
| 148 |
+
"learning_rate": 7.544273907910273e-06,
|
| 149 |
+
"loss": 0.3792,
|
| 150 |
+
"step": 640
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.15875265768958186,
|
| 154 |
+
"grad_norm": 6.78125,
|
| 155 |
+
"learning_rate": 7.922077922077924e-06,
|
| 156 |
+
"loss": 0.3423,
|
| 157 |
+
"step": 672
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.16631230805575242,
|
| 161 |
+
"grad_norm": 4.375,
|
| 162 |
+
"learning_rate": 8.299881936245572e-06,
|
| 163 |
+
"loss": 0.3628,
|
| 164 |
+
"step": 704
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.173871958421923,
|
| 168 |
+
"grad_norm": 5.46875,
|
| 169 |
+
"learning_rate": 8.677685950413224e-06,
|
| 170 |
+
"loss": 0.3727,
|
| 171 |
+
"step": 736
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.18143160878809356,
|
| 175 |
+
"grad_norm": 10.0625,
|
| 176 |
+
"learning_rate": 9.055489964580874e-06,
|
| 177 |
+
"loss": 0.3586,
|
| 178 |
+
"step": 768
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.18899125915426412,
|
| 182 |
+
"grad_norm": 5.0625,
|
| 183 |
+
"learning_rate": 9.433293978748525e-06,
|
| 184 |
+
"loss": 0.4148,
|
| 185 |
+
"step": 800
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.1965509095204347,
|
| 189 |
+
"grad_norm": 9.75,
|
| 190 |
+
"learning_rate": 9.811097992916175e-06,
|
| 191 |
+
"loss": 0.3842,
|
| 192 |
+
"step": 832
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.20411055988660523,
|
| 196 |
+
"grad_norm": 5.40625,
|
| 197 |
+
"learning_rate": 9.999891186645991e-06,
|
| 198 |
+
"loss": 0.3526,
|
| 199 |
+
"step": 864
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.2116702102527758,
|
| 203 |
+
"grad_norm": 5.625,
|
| 204 |
+
"learning_rate": 9.999020708230543e-06,
|
| 205 |
+
"loss": 0.3771,
|
| 206 |
+
"step": 896
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.21922986061894637,
|
| 210 |
+
"grad_norm": 7.75,
|
| 211 |
+
"learning_rate": 9.997279902949477e-06,
|
| 212 |
+
"loss": 0.3687,
|
| 213 |
+
"step": 928
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.22678951098511693,
|
| 217 |
+
"grad_norm": 7.25,
|
| 218 |
+
"learning_rate": 9.994669073876077e-06,
|
| 219 |
+
"loss": 0.3761,
|
| 220 |
+
"step": 960
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.2343491613512875,
|
| 224 |
+
"grad_norm": 7.5625,
|
| 225 |
+
"learning_rate": 9.991188675554302e-06,
|
| 226 |
+
"loss": 0.3955,
|
| 227 |
+
"step": 992
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.24190881171745807,
|
| 231 |
+
"grad_norm": 6.34375,
|
| 232 |
+
"learning_rate": 9.986839313919666e-06,
|
| 233 |
+
"loss": 0.3875,
|
| 234 |
+
"step": 1024
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.24946846208362863,
|
| 238 |
+
"grad_norm": 6.21875,
|
| 239 |
+
"learning_rate": 9.981621746193731e-06,
|
| 240 |
+
"loss": 0.3682,
|
| 241 |
+
"step": 1056
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.2570281124497992,
|
| 245 |
+
"grad_norm": 6.8125,
|
| 246 |
+
"learning_rate": 9.975536880752282e-06,
|
| 247 |
+
"loss": 0.394,
|
| 248 |
+
"step": 1088
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.26458776281596974,
|
| 252 |
+
"grad_norm": 7.6875,
|
| 253 |
+
"learning_rate": 9.968585776967178e-06,
|
| 254 |
+
"loss": 0.3638,
|
| 255 |
+
"step": 1120
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.2721474131821403,
|
| 259 |
+
"grad_norm": 5.71875,
|
| 260 |
+
"learning_rate": 9.960769645021923e-06,
|
| 261 |
+
"loss": 0.3534,
|
| 262 |
+
"step": 1152
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.2797070635483109,
|
| 266 |
+
"grad_norm": 7.25,
|
| 267 |
+
"learning_rate": 9.952089845700958e-06,
|
| 268 |
+
"loss": 0.3772,
|
| 269 |
+
"step": 1184
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.28726671391448144,
|
| 273 |
+
"grad_norm": 8.6875,
|
| 274 |
+
"learning_rate": 9.94254789015276e-06,
|
| 275 |
+
"loss": 0.3568,
|
| 276 |
+
"step": 1216
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.294826364280652,
|
| 280 |
+
"grad_norm": 6.8125,
|
| 281 |
+
"learning_rate": 9.932145439626755e-06,
|
| 282 |
+
"loss": 0.3967,
|
| 283 |
+
"step": 1248
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.3023860146468226,
|
| 287 |
+
"grad_norm": 6.09375,
|
| 288 |
+
"learning_rate": 9.920884305184083e-06,
|
| 289 |
+
"loss": 0.4089,
|
| 290 |
+
"step": 1280
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.30994566501299314,
|
| 294 |
+
"grad_norm": 4.21875,
|
| 295 |
+
"learning_rate": 9.908766447382307e-06,
|
| 296 |
+
"loss": 0.3839,
|
| 297 |
+
"step": 1312
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.3175053153791637,
|
| 301 |
+
"grad_norm": 6.5625,
|
| 302 |
+
"learning_rate": 9.89579397593407e-06,
|
| 303 |
+
"loss": 0.3999,
|
| 304 |
+
"step": 1344
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.3250649657453343,
|
| 308 |
+
"grad_norm": 6.6875,
|
| 309 |
+
"learning_rate": 9.881969149339804e-06,
|
| 310 |
+
"loss": 0.3946,
|
| 311 |
+
"step": 1376
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.33262461611150484,
|
| 315 |
+
"grad_norm": 5.8125,
|
| 316 |
+
"learning_rate": 9.867294374494514e-06,
|
| 317 |
+
"loss": 0.4175,
|
| 318 |
+
"step": 1408
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.3401842664776754,
|
| 322 |
+
"grad_norm": 5.375,
|
| 323 |
+
"learning_rate": 9.851772206268755e-06,
|
| 324 |
+
"loss": 0.3738,
|
| 325 |
+
"step": 1440
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.347743916843846,
|
| 329 |
+
"grad_norm": 7.78125,
|
| 330 |
+
"learning_rate": 9.83540534706382e-06,
|
| 331 |
+
"loss": 0.4253,
|
| 332 |
+
"step": 1472
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.35530356721001655,
|
| 336 |
+
"grad_norm": 4.90625,
|
| 337 |
+
"learning_rate": 9.81819664634125e-06,
|
| 338 |
+
"loss": 0.3961,
|
| 339 |
+
"step": 1504
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.3628632175761871,
|
| 343 |
+
"grad_norm": 8.5,
|
| 344 |
+
"learning_rate": 9.800149100126755e-06,
|
| 345 |
+
"loss": 0.4147,
|
| 346 |
+
"step": 1536
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.3704228679423577,
|
| 350 |
+
"grad_norm": 4.875,
|
| 351 |
+
"learning_rate": 9.781265850488604e-06,
|
| 352 |
+
"loss": 0.3814,
|
| 353 |
+
"step": 1568
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.37798251830852825,
|
| 357 |
+
"grad_norm": 6.5625,
|
| 358 |
+
"learning_rate": 9.761550184990588e-06,
|
| 359 |
+
"loss": 0.3778,
|
| 360 |
+
"step": 1600
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.3855421686746988,
|
| 364 |
+
"grad_norm": 4.15625,
|
| 365 |
+
"learning_rate": 9.741005536119654e-06,
|
| 366 |
+
"loss": 0.4191,
|
| 367 |
+
"step": 1632
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.3931018190408694,
|
| 371 |
+
"grad_norm": 6.34375,
|
| 372 |
+
"learning_rate": 9.719635480688328e-06,
|
| 373 |
+
"loss": 0.3992,
|
| 374 |
+
"step": 1664
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.40066146940703995,
|
| 378 |
+
"grad_norm": 8.5625,
|
| 379 |
+
"learning_rate": 9.697443739211974e-06,
|
| 380 |
+
"loss": 0.4003,
|
| 381 |
+
"step": 1696
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.40822111977321046,
|
| 385 |
+
"grad_norm": 6.09375,
|
| 386 |
+
"learning_rate": 9.674434175261064e-06,
|
| 387 |
+
"loss": 0.3886,
|
| 388 |
+
"step": 1728
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.41578077013938103,
|
| 392 |
+
"grad_norm": 6.46875,
|
| 393 |
+
"learning_rate": 9.650610794788534e-06,
|
| 394 |
+
"loss": 0.4198,
|
| 395 |
+
"step": 1760
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.4233404205055516,
|
| 399 |
+
"grad_norm": 7.84375,
|
| 400 |
+
"learning_rate": 9.625977745432342e-06,
|
| 401 |
+
"loss": 0.4141,
|
| 402 |
+
"step": 1792
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.43090007087172216,
|
| 406 |
+
"grad_norm": 6.78125,
|
| 407 |
+
"learning_rate": 9.600539315793375e-06,
|
| 408 |
+
"loss": 0.4043,
|
| 409 |
+
"step": 1824
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.43845972123789273,
|
| 413 |
+
"grad_norm": 6.125,
|
| 414 |
+
"learning_rate": 9.574299934688802e-06,
|
| 415 |
+
"loss": 0.4255,
|
| 416 |
+
"step": 1856
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.4460193716040633,
|
| 420 |
+
"grad_norm": 6.21875,
|
| 421 |
+
"learning_rate": 9.547264170381017e-06,
|
| 422 |
+
"loss": 0.3972,
|
| 423 |
+
"step": 1888
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.45357902197023386,
|
| 427 |
+
"grad_norm": 5.90625,
|
| 428 |
+
"learning_rate": 9.519436729782307e-06,
|
| 429 |
+
"loss": 0.3803,
|
| 430 |
+
"step": 1920
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.46113867233640443,
|
| 434 |
+
"grad_norm": 5.0,
|
| 435 |
+
"learning_rate": 9.490822457635392e-06,
|
| 436 |
+
"loss": 0.3979,
|
| 437 |
+
"step": 1952
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.468698322702575,
|
| 441 |
+
"grad_norm": 5.65625,
|
| 442 |
+
"learning_rate": 9.461426335669936e-06,
|
| 443 |
+
"loss": 0.4565,
|
| 444 |
+
"step": 1984
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.47625797306874557,
|
| 448 |
+
"grad_norm": 6.53125,
|
| 449 |
+
"learning_rate": 9.43125348173526e-06,
|
| 450 |
+
"loss": 0.4239,
|
| 451 |
+
"step": 2016
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.48381762343491613,
|
| 455 |
+
"grad_norm": 5.0625,
|
| 456 |
+
"learning_rate": 9.400309148909292e-06,
|
| 457 |
+
"loss": 0.4245,
|
| 458 |
+
"step": 2048
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.4913772738010867,
|
| 462 |
+
"grad_norm": 8.8125,
|
| 463 |
+
"learning_rate": 9.368598724584041e-06,
|
| 464 |
+
"loss": 0.4047,
|
| 465 |
+
"step": 2080
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.49893692416725727,
|
| 469 |
+
"grad_norm": 4.125,
|
| 470 |
+
"learning_rate": 9.33612772952764e-06,
|
| 471 |
+
"loss": 0.4006,
|
| 472 |
+
"step": 2112
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.5064965745334278,
|
| 476 |
+
"grad_norm": 4.28125,
|
| 477 |
+
"learning_rate": 9.30290181692318e-06,
|
| 478 |
+
"loss": 0.4124,
|
| 479 |
+
"step": 2144
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.5140562248995983,
|
| 483 |
+
"grad_norm": 7.0,
|
| 484 |
+
"learning_rate": 9.268926771384502e-06,
|
| 485 |
+
"loss": 0.4066,
|
| 486 |
+
"step": 2176
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.5216158752657689,
|
| 490 |
+
"grad_norm": 7.21875,
|
| 491 |
+
"learning_rate": 9.234208507949091e-06,
|
| 492 |
+
"loss": 0.4305,
|
| 493 |
+
"step": 2208
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.5291755256319395,
|
| 497 |
+
"grad_norm": 7.21875,
|
| 498 |
+
"learning_rate": 9.198753071048284e-06,
|
| 499 |
+
"loss": 0.4171,
|
| 500 |
+
"step": 2240
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.53673517599811,
|
| 504 |
+
"grad_norm": 5.6875,
|
| 505 |
+
"learning_rate": 9.162566633454919e-06,
|
| 506 |
+
"loss": 0.4098,
|
| 507 |
+
"step": 2272
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.5442948263642806,
|
| 511 |
+
"grad_norm": 6.75,
|
| 512 |
+
"learning_rate": 9.125655495208675e-06,
|
| 513 |
+
"loss": 0.4072,
|
| 514 |
+
"step": 2304
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.5518544767304512,
|
| 518 |
+
"grad_norm": 5.6875,
|
| 519 |
+
"learning_rate": 9.088026082519227e-06,
|
| 520 |
+
"loss": 0.4236,
|
| 521 |
+
"step": 2336
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.5594141270966217,
|
| 525 |
+
"grad_norm": 5.8125,
|
| 526 |
+
"learning_rate": 9.04968494664746e-06,
|
| 527 |
+
"loss": 0.4206,
|
| 528 |
+
"step": 2368
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.5669737774627923,
|
| 532 |
+
"grad_norm": 4.84375,
|
| 533 |
+
"learning_rate": 9.010638762764875e-06,
|
| 534 |
+
"loss": 0.3786,
|
| 535 |
+
"step": 2400
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.5745334278289629,
|
| 539 |
+
"grad_norm": 6.90625,
|
| 540 |
+
"learning_rate": 8.970894328791479e-06,
|
| 541 |
+
"loss": 0.4122,
|
| 542 |
+
"step": 2432
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.5820930781951335,
|
| 546 |
+
"grad_norm": 5.375,
|
| 547 |
+
"learning_rate": 8.930458564212233e-06,
|
| 548 |
+
"loss": 0.4128,
|
| 549 |
+
"step": 2464
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.589652728561304,
|
| 553 |
+
"grad_norm": 6.21875,
|
| 554 |
+
"learning_rate": 8.889338508872397e-06,
|
| 555 |
+
"loss": 0.4537,
|
| 556 |
+
"step": 2496
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.5972123789274746,
|
| 560 |
+
"grad_norm": 3.375,
|
| 561 |
+
"learning_rate": 8.8475413217519e-06,
|
| 562 |
+
"loss": 0.42,
|
| 563 |
+
"step": 2528
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.6047720292936452,
|
| 567 |
+
"grad_norm": 8.3125,
|
| 568 |
+
"learning_rate": 8.805074279718941e-06,
|
| 569 |
+
"loss": 0.443,
|
| 570 |
+
"step": 2560
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.6123316796598157,
|
| 574 |
+
"grad_norm": 6.84375,
|
| 575 |
+
"learning_rate": 8.761944776263121e-06,
|
| 576 |
+
"loss": 0.3792,
|
| 577 |
+
"step": 2592
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.6198913300259863,
|
| 581 |
+
"grad_norm": 7.09375,
|
| 582 |
+
"learning_rate": 8.718160320208212e-06,
|
| 583 |
+
"loss": 0.4396,
|
| 584 |
+
"step": 2624
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.6274509803921569,
|
| 588 |
+
"grad_norm": 5.75,
|
| 589 |
+
"learning_rate": 8.673728534404892e-06,
|
| 590 |
+
"loss": 0.4181,
|
| 591 |
+
"step": 2656
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.6350106307583274,
|
| 595 |
+
"grad_norm": 6.21875,
|
| 596 |
+
"learning_rate": 8.628657154403613e-06,
|
| 597 |
+
"loss": 0.4243,
|
| 598 |
+
"step": 2688
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.642570281124498,
|
| 602 |
+
"grad_norm": 11.0625,
|
| 603 |
+
"learning_rate": 8.582954027107832e-06,
|
| 604 |
+
"loss": 0.4382,
|
| 605 |
+
"step": 2720
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.6501299314906686,
|
| 609 |
+
"grad_norm": 4.53125,
|
| 610 |
+
"learning_rate": 8.536627109407877e-06,
|
| 611 |
+
"loss": 0.4081,
|
| 612 |
+
"step": 2752
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.6576895818568391,
|
| 616 |
+
"grad_norm": 4.9375,
|
| 617 |
+
"learning_rate": 8.489684466795657e-06,
|
| 618 |
+
"loss": 0.46,
|
| 619 |
+
"step": 2784
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.6652492322230097,
|
| 623 |
+
"grad_norm": 5.625,
|
| 624 |
+
"learning_rate": 8.442134271960463e-06,
|
| 625 |
+
"loss": 0.4227,
|
| 626 |
+
"step": 2816
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.6728088825891803,
|
| 630 |
+
"grad_norm": 4.84375,
|
| 631 |
+
"learning_rate": 8.393984803366108e-06,
|
| 632 |
+
"loss": 0.4226,
|
| 633 |
+
"step": 2848
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.6803685329553508,
|
| 637 |
+
"grad_norm": 5.875,
|
| 638 |
+
"learning_rate": 8.34524444380965e-06,
|
| 639 |
+
"loss": 0.4168,
|
| 640 |
+
"step": 2880
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.6879281833215214,
|
| 644 |
+
"grad_norm": 6.96875,
|
| 645 |
+
"learning_rate": 8.29592167896195e-06,
|
| 646 |
+
"loss": 0.3943,
|
| 647 |
+
"step": 2912
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.695487833687692,
|
| 651 |
+
"grad_norm": 6.15625,
|
| 652 |
+
"learning_rate": 8.246025095890322e-06,
|
| 653 |
+
"loss": 0.4094,
|
| 654 |
+
"step": 2944
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.7030474840538625,
|
| 658 |
+
"grad_norm": 4.09375,
|
| 659 |
+
"learning_rate": 8.195563381563535e-06,
|
| 660 |
+
"loss": 0.4096,
|
| 661 |
+
"step": 2976
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.7106071344200331,
|
| 665 |
+
"grad_norm": 6.03125,
|
| 666 |
+
"learning_rate": 8.144545321339405e-06,
|
| 667 |
+
"loss": 0.4545,
|
| 668 |
+
"step": 3008
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.7181667847862037,
|
| 672 |
+
"grad_norm": 6.875,
|
| 673 |
+
"learning_rate": 8.092979797435278e-06,
|
| 674 |
+
"loss": 0.4199,
|
| 675 |
+
"step": 3040
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.7257264351523742,
|
| 679 |
+
"grad_norm": 14.6875,
|
| 680 |
+
"learning_rate": 8.040875787381637e-06,
|
| 681 |
+
"loss": 0.4526,
|
| 682 |
+
"step": 3072
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.7332860855185448,
|
| 686 |
+
"grad_norm": 4.71875,
|
| 687 |
+
"learning_rate": 7.988242362459119e-06,
|
| 688 |
+
"loss": 0.4139,
|
| 689 |
+
"step": 3104
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.7408457358847154,
|
| 693 |
+
"grad_norm": 6.21875,
|
| 694 |
+
"learning_rate": 7.93508868611921e-06,
|
| 695 |
+
"loss": 0.4341,
|
| 696 |
+
"step": 3136
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.7484053862508859,
|
| 700 |
+
"grad_norm": 7.0625,
|
| 701 |
+
"learning_rate": 7.881424012388895e-06,
|
| 702 |
+
"loss": 0.4321,
|
| 703 |
+
"step": 3168
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.7559650366170565,
|
| 707 |
+
"grad_norm": 5.78125,
|
| 708 |
+
"learning_rate": 7.827257684259533e-06,
|
| 709 |
+
"loss": 0.4468,
|
| 710 |
+
"step": 3200
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.7635246869832271,
|
| 714 |
+
"grad_norm": 6.15625,
|
| 715 |
+
"learning_rate": 7.772599132060246e-06,
|
| 716 |
+
"loss": 0.4038,
|
| 717 |
+
"step": 3232
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.7710843373493976,
|
| 721 |
+
"grad_norm": 7.15625,
|
| 722 |
+
"learning_rate": 7.717457871816114e-06,
|
| 723 |
+
"loss": 0.3692,
|
| 724 |
+
"step": 3264
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.7786439877155682,
|
| 728 |
+
"grad_norm": 5.25,
|
| 729 |
+
"learning_rate": 7.661843503591429e-06,
|
| 730 |
+
"loss": 0.4177,
|
| 731 |
+
"step": 3296
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.7862036380817388,
|
| 735 |
+
"grad_norm": 7.8125,
|
| 736 |
+
"learning_rate": 7.605765709818329e-06,
|
| 737 |
+
"loss": 0.4604,
|
| 738 |
+
"step": 3328
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.7937632884479093,
|
| 742 |
+
"grad_norm": 5.53125,
|
| 743 |
+
"learning_rate": 7.5492342536111e-06,
|
| 744 |
+
"loss": 0.47,
|
| 745 |
+
"step": 3360
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.8013229388140799,
|
| 749 |
+
"grad_norm": 8.375,
|
| 750 |
+
"learning_rate": 7.4922589770664175e-06,
|
| 751 |
+
"loss": 0.3945,
|
| 752 |
+
"step": 3392
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.8088825891802505,
|
| 756 |
+
"grad_norm": 7.96875,
|
| 757 |
+
"learning_rate": 7.434849799549842e-06,
|
| 758 |
+
"loss": 0.4388,
|
| 759 |
+
"step": 3424
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.8164422395464209,
|
| 763 |
+
"grad_norm": 6.46875,
|
| 764 |
+
"learning_rate": 7.3770167159688655e-06,
|
| 765 |
+
"loss": 0.4361,
|
| 766 |
+
"step": 3456
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.8240018899125915,
|
| 770 |
+
"grad_norm": 4.625,
|
| 771 |
+
"learning_rate": 7.318769795032799e-06,
|
| 772 |
+
"loss": 0.4252,
|
| 773 |
+
"step": 3488
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.8315615402787621,
|
| 777 |
+
"grad_norm": 6.84375,
|
| 778 |
+
"learning_rate": 7.260119177499824e-06,
|
| 779 |
+
"loss": 0.4105,
|
| 780 |
+
"step": 3520
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.8391211906449326,
|
| 784 |
+
"grad_norm": 19.0,
|
| 785 |
+
"learning_rate": 7.201075074411479e-06,
|
| 786 |
+
"loss": 0.4404,
|
| 787 |
+
"step": 3552
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.8466808410111032,
|
| 791 |
+
"grad_norm": 12.3125,
|
| 792 |
+
"learning_rate": 7.141647765314939e-06,
|
| 793 |
+
"loss": 0.4392,
|
| 794 |
+
"step": 3584
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.8542404913772738,
|
| 798 |
+
"grad_norm": 6.75,
|
| 799 |
+
"learning_rate": 7.081847596473332e-06,
|
| 800 |
+
"loss": 0.4338,
|
| 801 |
+
"step": 3616
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.8618001417434443,
|
| 805 |
+
"grad_norm": 5.53125,
|
| 806 |
+
"learning_rate": 7.021684979064483e-06,
|
| 807 |
+
"loss": 0.4007,
|
| 808 |
+
"step": 3648
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.8693597921096149,
|
| 812 |
+
"grad_norm": 4.4375,
|
| 813 |
+
"learning_rate": 6.9611703873683075e-06,
|
| 814 |
+
"loss": 0.4123,
|
| 815 |
+
"step": 3680
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.8769194424757855,
|
| 819 |
+
"grad_norm": 6.90625,
|
| 820 |
+
"learning_rate": 6.900314356943272e-06,
|
| 821 |
+
"loss": 0.4258,
|
| 822 |
+
"step": 3712
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.884479092841956,
|
| 826 |
+
"grad_norm": 5.90625,
|
| 827 |
+
"learning_rate": 6.839127482792134e-06,
|
| 828 |
+
"loss": 0.4045,
|
| 829 |
+
"step": 3744
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.8920387432081266,
|
| 833 |
+
"grad_norm": 4.96875,
|
| 834 |
+
"learning_rate": 6.777620417517376e-06,
|
| 835 |
+
"loss": 0.3874,
|
| 836 |
+
"step": 3776
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.8995983935742972,
|
| 840 |
+
"grad_norm": 11.125,
|
| 841 |
+
"learning_rate": 6.715803869466585e-06,
|
| 842 |
+
"loss": 0.4199,
|
| 843 |
+
"step": 3808
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.9071580439404677,
|
| 847 |
+
"grad_norm": 6.65625,
|
| 848 |
+
"learning_rate": 6.653688600868135e-06,
|
| 849 |
+
"loss": 0.4087,
|
| 850 |
+
"step": 3840
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.9147176943066383,
|
| 854 |
+
"grad_norm": 5.90625,
|
| 855 |
+
"learning_rate": 6.591285425957488e-06,
|
| 856 |
+
"loss": 0.4506,
|
| 857 |
+
"step": 3872
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.9222773446728089,
|
| 861 |
+
"grad_norm": 7.875,
|
| 862 |
+
"learning_rate": 6.528605209094445e-06,
|
| 863 |
+
"loss": 0.4385,
|
| 864 |
+
"step": 3904
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.9298369950389794,
|
| 868 |
+
"grad_norm": 7.46875,
|
| 869 |
+
"learning_rate": 6.465658862871665e-06,
|
| 870 |
+
"loss": 0.4093,
|
| 871 |
+
"step": 3936
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.93739664540515,
|
| 875 |
+
"grad_norm": 6.59375,
|
| 876 |
+
"learning_rate": 6.402457346214787e-06,
|
| 877 |
+
"loss": 0.4455,
|
| 878 |
+
"step": 3968
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.9449562957713206,
|
| 882 |
+
"grad_norm": 5.46875,
|
| 883 |
+
"learning_rate": 6.339011662474488e-06,
|
| 884 |
+
"loss": 0.4327,
|
| 885 |
+
"step": 4000
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.9525159461374911,
|
| 889 |
+
"grad_norm": 6.625,
|
| 890 |
+
"learning_rate": 6.275332857510803e-06,
|
| 891 |
+
"loss": 0.4151,
|
| 892 |
+
"step": 4032
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.9600755965036617,
|
| 896 |
+
"grad_norm": 9.8125,
|
| 897 |
+
"learning_rate": 6.2114320177700545e-06,
|
| 898 |
+
"loss": 0.4168,
|
| 899 |
+
"step": 4064
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.9676352468698323,
|
| 903 |
+
"grad_norm": 4.96875,
|
| 904 |
+
"learning_rate": 6.147320268354698e-06,
|
| 905 |
+
"loss": 0.4115,
|
| 906 |
+
"step": 4096
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.9751948972360028,
|
| 910 |
+
"grad_norm": 5.96875,
|
| 911 |
+
"learning_rate": 6.083008771086453e-06,
|
| 912 |
+
"loss": 0.4109,
|
| 913 |
+
"step": 4128
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.9827545476021734,
|
| 917 |
+
"grad_norm": 7.3125,
|
| 918 |
+
"learning_rate": 6.018508722563033e-06,
|
| 919 |
+
"loss": 0.4238,
|
| 920 |
+
"step": 4160
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.990314197968344,
|
| 924 |
+
"grad_norm": 5.0625,
|
| 925 |
+
"learning_rate": 5.953831352208831e-06,
|
| 926 |
+
"loss": 0.3625,
|
| 927 |
+
"step": 4192
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.9978738483345145,
|
| 931 |
+
"grad_norm": 5.125,
|
| 932 |
+
"learning_rate": 5.888987920319869e-06,
|
| 933 |
+
"loss": 0.4183,
|
| 934 |
+
"step": 4224
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 1.005433498700685,
|
| 938 |
+
"grad_norm": 5.25,
|
| 939 |
+
"learning_rate": 5.823989716103402e-06,
|
| 940 |
+
"loss": 0.3975,
|
| 941 |
+
"step": 4256
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 1.0129931490668556,
|
| 945 |
+
"grad_norm": 6.25,
|
| 946 |
+
"learning_rate": 5.7588480557124625e-06,
|
| 947 |
+
"loss": 0.3779,
|
| 948 |
+
"step": 4288
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 1.0205527994330261,
|
| 952 |
+
"grad_norm": 7.09375,
|
| 953 |
+
"learning_rate": 5.693574280275727e-06,
|
| 954 |
+
"loss": 0.3862,
|
| 955 |
+
"step": 4320
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 1.0281124497991967,
|
| 959 |
+
"grad_norm": 6.28125,
|
| 960 |
+
"learning_rate": 5.628179753923029e-06,
|
| 961 |
+
"loss": 0.3278,
|
| 962 |
+
"step": 4352
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 1.0356721001653673,
|
| 966 |
+
"grad_norm": 6.4375,
|
| 967 |
+
"learning_rate": 5.562675861806877e-06,
|
| 968 |
+
"loss": 0.3923,
|
| 969 |
+
"step": 4384
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.0432317505315378,
|
| 973 |
+
"grad_norm": 5.71875,
|
| 974 |
+
"learning_rate": 5.497074008120302e-06,
|
| 975 |
+
"loss": 0.3352,
|
| 976 |
+
"step": 4416
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 1.0507914008977084,
|
| 980 |
+
"grad_norm": 9.25,
|
| 981 |
+
"learning_rate": 5.431385614111387e-06,
|
| 982 |
+
"loss": 0.3921,
|
| 983 |
+
"step": 4448
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 1.058351051263879,
|
| 987 |
+
"grad_norm": 6.875,
|
| 988 |
+
"learning_rate": 5.365622116094847e-06,
|
| 989 |
+
"loss": 0.3742,
|
| 990 |
+
"step": 4480
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 1.0659107016300495,
|
| 994 |
+
"grad_norm": 8.125,
|
| 995 |
+
"learning_rate": 5.299794963460955e-06,
|
| 996 |
+
"loss": 0.3601,
|
| 997 |
+
"step": 4512
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 1.07347035199622,
|
| 1001 |
+
"grad_norm": 7.65625,
|
| 1002 |
+
"learning_rate": 5.23391561668223e-06,
|
| 1003 |
+
"loss": 0.3677,
|
| 1004 |
+
"step": 4544
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 1.0810300023623907,
|
| 1008 |
+
"grad_norm": 9.125,
|
| 1009 |
+
"learning_rate": 5.167995545318157e-06,
|
| 1010 |
+
"loss": 0.4346,
|
| 1011 |
+
"step": 4576
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 1.0885896527285612,
|
| 1015 |
+
"grad_norm": 6.5,
|
| 1016 |
+
"learning_rate": 5.102046226018354e-06,
|
| 1017 |
+
"loss": 0.3668,
|
| 1018 |
+
"step": 4608
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 1.0961493030947318,
|
| 1022 |
+
"grad_norm": 5.53125,
|
| 1023 |
+
"learning_rate": 5.036079140524485e-06,
|
| 1024 |
+
"loss": 0.3819,
|
| 1025 |
+
"step": 4640
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 1.1037089534609024,
|
| 1029 |
+
"grad_norm": 5.375,
|
| 1030 |
+
"learning_rate": 4.9701057736713004e-06,
|
| 1031 |
+
"loss": 0.4159,
|
| 1032 |
+
"step": 4672
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 1.111268603827073,
|
| 1036 |
+
"grad_norm": 7.09375,
|
| 1037 |
+
"learning_rate": 4.904137611387137e-06,
|
| 1038 |
+
"loss": 0.4258,
|
| 1039 |
+
"step": 4704
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 1.1188282541932435,
|
| 1043 |
+
"grad_norm": 5.84375,
|
| 1044 |
+
"learning_rate": 4.8381861386942104e-06,
|
| 1045 |
+
"loss": 0.407,
|
| 1046 |
+
"step": 4736
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 1.126387904559414,
|
| 1050 |
+
"grad_norm": 7.0625,
|
| 1051 |
+
"learning_rate": 4.772262837709093e-06,
|
| 1052 |
+
"loss": 0.3729,
|
| 1053 |
+
"step": 4768
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 1.1339475549255846,
|
| 1057 |
+
"grad_norm": 4.34375,
|
| 1058 |
+
"learning_rate": 4.706379185643675e-06,
|
| 1059 |
+
"loss": 0.3861,
|
| 1060 |
+
"step": 4800
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 1.1415072052917552,
|
| 1064 |
+
"grad_norm": 4.5,
|
| 1065 |
+
"learning_rate": 4.6405466528069955e-06,
|
| 1066 |
+
"loss": 0.3807,
|
| 1067 |
+
"step": 4832
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 1.1490668556579258,
|
| 1071 |
+
"grad_norm": 7.84375,
|
| 1072 |
+
"learning_rate": 4.574776700608253e-06,
|
| 1073 |
+
"loss": 0.3897,
|
| 1074 |
+
"step": 4864
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 1.1566265060240963,
|
| 1078 |
+
"grad_norm": 6.59375,
|
| 1079 |
+
"learning_rate": 4.509080779561401e-06,
|
| 1080 |
+
"loss": 0.3994,
|
| 1081 |
+
"step": 4896
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 1.164186156390267,
|
| 1085 |
+
"grad_norm": 3.515625,
|
| 1086 |
+
"learning_rate": 4.443470327291603e-06,
|
| 1087 |
+
"loss": 0.3903,
|
| 1088 |
+
"step": 4928
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 1.1717458067564375,
|
| 1092 |
+
"grad_norm": 5.1875,
|
| 1093 |
+
"learning_rate": 4.37795676654395e-06,
|
| 1094 |
+
"loss": 0.392,
|
| 1095 |
+
"step": 4960
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 1.179305457122608,
|
| 1099 |
+
"grad_norm": 8.0,
|
| 1100 |
+
"learning_rate": 4.31255150319478e-06,
|
| 1101 |
+
"loss": 0.3721,
|
| 1102 |
+
"step": 4992
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 1.1868651074887786,
|
| 1106 |
+
"grad_norm": 4.84375,
|
| 1107 |
+
"learning_rate": 4.247265924265903e-06,
|
| 1108 |
+
"loss": 0.3727,
|
| 1109 |
+
"step": 5024
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 1.1944247578549492,
|
| 1113 |
+
"grad_norm": 4.71875,
|
| 1114 |
+
"learning_rate": 4.182111395942135e-06,
|
| 1115 |
+
"loss": 0.3912,
|
| 1116 |
+
"step": 5056
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 1.2019844082211197,
|
| 1120 |
+
"grad_norm": 6.34375,
|
| 1121 |
+
"learning_rate": 4.117099261592459e-06,
|
| 1122 |
+
"loss": 0.3921,
|
| 1123 |
+
"step": 5088
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 1.2095440585872903,
|
| 1127 |
+
"grad_norm": 6.40625,
|
| 1128 |
+
"learning_rate": 4.052240839795127e-06,
|
| 1129 |
+
"loss": 0.3911,
|
| 1130 |
+
"step": 5120
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 1.2171037089534609,
|
| 1134 |
+
"grad_norm": 4.5,
|
| 1135 |
+
"learning_rate": 3.987547422367134e-06,
|
| 1136 |
+
"loss": 0.3621,
|
| 1137 |
+
"step": 5152
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 1.2246633593196314,
|
| 1141 |
+
"grad_norm": 4.53125,
|
| 1142 |
+
"learning_rate": 3.923030272398292e-06,
|
| 1143 |
+
"loss": 0.3714,
|
| 1144 |
+
"step": 5184
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 1.232223009685802,
|
| 1148 |
+
"grad_norm": 5.78125,
|
| 1149 |
+
"learning_rate": 3.858700622290338e-06,
|
| 1150 |
+
"loss": 0.3583,
|
| 1151 |
+
"step": 5216
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 1.2397826600519726,
|
| 1155 |
+
"grad_norm": 6.21875,
|
| 1156 |
+
"learning_rate": 3.7945696718013942e-06,
|
| 1157 |
+
"loss": 0.4043,
|
| 1158 |
+
"step": 5248
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 1.2473423104181431,
|
| 1162 |
+
"grad_norm": 4.84375,
|
| 1163 |
+
"learning_rate": 3.730648586096072e-06,
|
| 1164 |
+
"loss": 0.3933,
|
| 1165 |
+
"step": 5280
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 1.2549019607843137,
|
| 1169 |
+
"grad_norm": 6.0,
|
| 1170 |
+
"learning_rate": 3.6669484938016396e-06,
|
| 1171 |
+
"loss": 0.3552,
|
| 1172 |
+
"step": 5312
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 1.2624616111504843,
|
| 1176 |
+
"grad_norm": 4.5625,
|
| 1177 |
+
"learning_rate": 3.603480485070533e-06,
|
| 1178 |
+
"loss": 0.4135,
|
| 1179 |
+
"step": 5344
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 1.2700212615166548,
|
| 1183 |
+
"grad_norm": 4.375,
|
| 1184 |
+
"learning_rate": 3.5402556096495566e-06,
|
| 1185 |
+
"loss": 0.3806,
|
| 1186 |
+
"step": 5376
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 1.2775809118828254,
|
| 1190 |
+
"grad_norm": 5.0625,
|
| 1191 |
+
"learning_rate": 3.477284874956134e-06,
|
| 1192 |
+
"loss": 0.3799,
|
| 1193 |
+
"step": 5408
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 1.285140562248996,
|
| 1197 |
+
"grad_norm": 7.46875,
|
| 1198 |
+
"learning_rate": 3.414579244161927e-06,
|
| 1199 |
+
"loss": 0.3496,
|
| 1200 |
+
"step": 5440
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 1.2927002126151665,
|
| 1204 |
+
"grad_norm": 5.90625,
|
| 1205 |
+
"learning_rate": 3.3521496342841443e-06,
|
| 1206 |
+
"loss": 0.3798,
|
| 1207 |
+
"step": 5472
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 1.3002598629813371,
|
| 1211 |
+
"grad_norm": 4.34375,
|
| 1212 |
+
"learning_rate": 3.2900069142848997e-06,
|
| 1213 |
+
"loss": 0.3662,
|
| 1214 |
+
"step": 5504
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 1.3078195133475077,
|
| 1218 |
+
"grad_norm": 6.15625,
|
| 1219 |
+
"learning_rate": 3.2281619031789334e-06,
|
| 1220 |
+
"loss": 0.3645,
|
| 1221 |
+
"step": 5536
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 1.3153791637136782,
|
| 1225 |
+
"grad_norm": 7.1875,
|
| 1226 |
+
"learning_rate": 3.16662536815002e-06,
|
| 1227 |
+
"loss": 0.416,
|
| 1228 |
+
"step": 5568
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 1.3229388140798488,
|
| 1232 |
+
"grad_norm": 6.15625,
|
| 1233 |
+
"learning_rate": 3.105408022676416e-06,
|
| 1234 |
+
"loss": 0.4065,
|
| 1235 |
+
"step": 5600
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 1.3304984644460194,
|
| 1239 |
+
"grad_norm": 5.625,
|
| 1240 |
+
"learning_rate": 3.0445205246656427e-06,
|
| 1241 |
+
"loss": 0.3884,
|
| 1242 |
+
"step": 5632
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 1.33805811481219,
|
| 1246 |
+
"grad_norm": 6.875,
|
| 1247 |
+
"learning_rate": 2.983973474598949e-06,
|
| 1248 |
+
"loss": 0.3227,
|
| 1249 |
+
"step": 5664
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 1.3456177651783605,
|
| 1253 |
+
"grad_norm": 5.9375,
|
| 1254 |
+
"learning_rate": 2.923777413685788e-06,
|
| 1255 |
+
"loss": 0.3935,
|
| 1256 |
+
"step": 5696
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 1.353177415544531,
|
| 1260 |
+
"grad_norm": 4.1875,
|
| 1261 |
+
"learning_rate": 2.8639428220285716e-06,
|
| 1262 |
+
"loss": 0.3729,
|
| 1263 |
+
"step": 5728
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 1.3607370659107016,
|
| 1267 |
+
"grad_norm": 3.40625,
|
| 1268 |
+
"learning_rate": 2.804480116798115e-06,
|
| 1269 |
+
"loss": 0.3924,
|
| 1270 |
+
"step": 5760
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 1.3682967162768722,
|
| 1274 |
+
"grad_norm": 5.28125,
|
| 1275 |
+
"learning_rate": 2.7453996504200002e-06,
|
| 1276 |
+
"loss": 0.3846,
|
| 1277 |
+
"step": 5792
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 1.3758563666430428,
|
| 1281 |
+
"grad_norm": 8.6875,
|
| 1282 |
+
"learning_rate": 2.686711708772226e-06,
|
| 1283 |
+
"loss": 0.3729,
|
| 1284 |
+
"step": 5824
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 1.3834160170092134,
|
| 1288 |
+
"grad_norm": 5.0625,
|
| 1289 |
+
"learning_rate": 2.628426509394443e-06,
|
| 1290 |
+
"loss": 0.3725,
|
| 1291 |
+
"step": 5856
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 1.390975667375384,
|
| 1295 |
+
"grad_norm": 5.5625,
|
| 1296 |
+
"learning_rate": 2.57055419970909e-06,
|
| 1297 |
+
"loss": 0.3684,
|
| 1298 |
+
"step": 5888
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 1.3985353177415545,
|
| 1302 |
+
"grad_norm": 6.21875,
|
| 1303 |
+
"learning_rate": 2.51310485525472e-06,
|
| 1304 |
+
"loss": 0.3596,
|
| 1305 |
+
"step": 5920
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 1.406094968107725,
|
| 1309 |
+
"grad_norm": 3.953125,
|
| 1310 |
+
"learning_rate": 2.4560884779318655e-06,
|
| 1311 |
+
"loss": 0.3933,
|
| 1312 |
+
"step": 5952
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 1.4136546184738956,
|
| 1316 |
+
"grad_norm": 6.625,
|
| 1317 |
+
"learning_rate": 2.3995149942617184e-06,
|
| 1318 |
+
"loss": 0.4046,
|
| 1319 |
+
"step": 5984
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 1.4212142688400662,
|
| 1323 |
+
"grad_norm": 5.40625,
|
| 1324 |
+
"learning_rate": 2.343394253657904e-06,
|
| 1325 |
+
"loss": 0.389,
|
| 1326 |
+
"step": 6016
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 1.4287739192062368,
|
| 1330 |
+
"grad_norm": 5.71875,
|
| 1331 |
+
"learning_rate": 2.2877360267117344e-06,
|
| 1332 |
+
"loss": 0.35,
|
| 1333 |
+
"step": 6048
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 1.4363335695724073,
|
| 1337 |
+
"grad_norm": 7.34375,
|
| 1338 |
+
"learning_rate": 2.2325500034911275e-06,
|
| 1339 |
+
"loss": 0.3948,
|
| 1340 |
+
"step": 6080
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 1.4438932199385779,
|
| 1344 |
+
"grad_norm": 4.8125,
|
| 1345 |
+
"learning_rate": 2.1778457918535868e-06,
|
| 1346 |
+
"loss": 0.3793,
|
| 1347 |
+
"step": 6112
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 1.4514528703047485,
|
| 1351 |
+
"grad_norm": 5.71875,
|
| 1352 |
+
"learning_rate": 2.123632915773472e-06,
|
| 1353 |
+
"loss": 0.3803,
|
| 1354 |
+
"step": 6144
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 1.459012520670919,
|
| 1358 |
+
"grad_norm": 5.96875,
|
| 1359 |
+
"learning_rate": 2.0699208136838816e-06,
|
| 1360 |
+
"loss": 0.3781,
|
| 1361 |
+
"step": 6176
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 1.4665721710370896,
|
| 1365 |
+
"grad_norm": 11.3125,
|
| 1366 |
+
"learning_rate": 2.0167188368334277e-06,
|
| 1367 |
+
"loss": 0.3961,
|
| 1368 |
+
"step": 6208
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 1.4741318214032602,
|
| 1372 |
+
"grad_norm": 6.75,
|
| 1373 |
+
"learning_rate": 1.9640362476581874e-06,
|
| 1374 |
+
"loss": 0.3729,
|
| 1375 |
+
"step": 6240
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 1.4816914717694307,
|
| 1379 |
+
"grad_norm": 8.125,
|
| 1380 |
+
"learning_rate": 1.9118822181691173e-06,
|
| 1381 |
+
"loss": 0.3913,
|
| 1382 |
+
"step": 6272
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 1.4892511221356013,
|
| 1386 |
+
"grad_norm": 6.75,
|
| 1387 |
+
"learning_rate": 1.860265828355211e-06,
|
| 1388 |
+
"loss": 0.3672,
|
| 1389 |
+
"step": 6304
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 1.4968107725017719,
|
| 1393 |
+
"grad_norm": 7.8125,
|
| 1394 |
+
"learning_rate": 1.8091960646026812e-06,
|
| 1395 |
+
"loss": 0.401,
|
| 1396 |
+
"step": 6336
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 1.5043704228679422,
|
| 1400 |
+
"grad_norm": 7.875,
|
| 1401 |
+
"learning_rate": 1.7586818181304294e-06,
|
| 1402 |
+
"loss": 0.3668,
|
| 1403 |
+
"step": 6368
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 1.511930073234113,
|
| 1407 |
+
"grad_norm": 5.125,
|
| 1408 |
+
"learning_rate": 1.7087318834420912e-06,
|
| 1409 |
+
"loss": 0.4126,
|
| 1410 |
+
"step": 6400
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 1.5194897236002833,
|
| 1414 |
+
"grad_norm": 6.40625,
|
| 1415 |
+
"learning_rate": 1.6593549567949258e-06,
|
| 1416 |
+
"loss": 0.3745,
|
| 1417 |
+
"step": 6432
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 1.5270493739664541,
|
| 1421 |
+
"grad_norm": 6.15625,
|
| 1422 |
+
"learning_rate": 1.6105596346857822e-06,
|
| 1423 |
+
"loss": 0.3844,
|
| 1424 |
+
"step": 6464
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 1.5346090243326245,
|
| 1428 |
+
"grad_norm": 4.96875,
|
| 1429 |
+
"learning_rate": 1.562354412354478e-06,
|
| 1430 |
+
"loss": 0.3708,
|
| 1431 |
+
"step": 6496
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 1.5421686746987953,
|
| 1435 |
+
"grad_norm": 6.4375,
|
| 1436 |
+
"learning_rate": 1.514747682304767e-06,
|
| 1437 |
+
"loss": 0.3761,
|
| 1438 |
+
"step": 6528
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 1.5497283250649656,
|
| 1442 |
+
"grad_norm": 6.84375,
|
| 1443 |
+
"learning_rate": 1.467747732843211e-06,
|
| 1444 |
+
"loss": 0.3663,
|
| 1445 |
+
"step": 6560
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 1.5572879754311364,
|
| 1449 |
+
"grad_norm": 4.75,
|
| 1450 |
+
"learning_rate": 1.4213627466361933e-06,
|
| 1451 |
+
"loss": 0.3836,
|
| 1452 |
+
"step": 6592
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 1.5648476257973067,
|
| 1456 |
+
"grad_norm": 6.15625,
|
| 1457 |
+
"learning_rate": 1.375600799285321e-06,
|
| 1458 |
+
"loss": 0.3563,
|
| 1459 |
+
"step": 6624
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 1.5724072761634775,
|
| 1463 |
+
"grad_norm": 6.5,
|
| 1464 |
+
"learning_rate": 1.330469857921462e-06,
|
| 1465 |
+
"loss": 0.3755,
|
| 1466 |
+
"step": 6656
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 1.5799669265296479,
|
| 1470 |
+
"grad_norm": 7.15625,
|
| 1471 |
+
"learning_rate": 1.285977779817677e-06,
|
| 1472 |
+
"loss": 0.39,
|
| 1473 |
+
"step": 6688
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 1.5875265768958187,
|
| 1477 |
+
"grad_norm": 5.5,
|
| 1478 |
+
"learning_rate": 1.2421323110212713e-06,
|
| 1479 |
+
"loss": 0.4053,
|
| 1480 |
+
"step": 6720
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 1.595086227261989,
|
| 1484 |
+
"grad_norm": 5.0,
|
| 1485 |
+
"learning_rate": 1.1989410850052092e-06,
|
| 1486 |
+
"loss": 0.3539,
|
| 1487 |
+
"step": 6752
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 1.6026458776281598,
|
| 1491 |
+
"grad_norm": 7.1875,
|
| 1492 |
+
"learning_rate": 1.1564116213391335e-06,
|
| 1493 |
+
"loss": 0.387,
|
| 1494 |
+
"step": 6784
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 1.6102055279943301,
|
| 1498 |
+
"grad_norm": 6.0,
|
| 1499 |
+
"learning_rate": 1.114551324380212e-06,
|
| 1500 |
+
"loss": 0.3817,
|
| 1501 |
+
"step": 6816
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 1.617765178360501,
|
| 1505 |
+
"grad_norm": 7.1875,
|
| 1506 |
+
"learning_rate": 1.0733674819840385e-06,
|
| 1507 |
+
"loss": 0.3969,
|
| 1508 |
+
"step": 6848
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 1.6253248287266713,
|
| 1512 |
+
"grad_norm": 6.375,
|
| 1513 |
+
"learning_rate": 1.0328672642358328e-06,
|
| 1514 |
+
"loss": 0.4199,
|
| 1515 |
+
"step": 6880
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 1.632884479092842,
|
| 1519 |
+
"grad_norm": 6.1875,
|
| 1520 |
+
"learning_rate": 9.93057722202113e-07,
|
| 1521 |
+
"loss": 0.3709,
|
| 1522 |
+
"step": 6912
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 1.6404441294590124,
|
| 1526 |
+
"grad_norm": 5.09375,
|
| 1527 |
+
"learning_rate": 9.539457867031305e-07,
|
| 1528 |
+
"loss": 0.3578,
|
| 1529 |
+
"step": 6944
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 1.6480037798251832,
|
| 1533 |
+
"grad_norm": 6.5,
|
| 1534 |
+
"learning_rate": 9.155382671062024e-07,
|
| 1535 |
+
"loss": 0.4118,
|
| 1536 |
+
"step": 6976
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 1.6555634301913535,
|
| 1540 |
+
"grad_norm": 4.25,
|
| 1541 |
+
"learning_rate": 8.778418501402064e-07,
|
| 1542 |
+
"loss": 0.4025,
|
| 1543 |
+
"step": 7008
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 1.6631230805575243,
|
| 1547 |
+
"grad_norm": 6.625,
|
| 1548 |
+
"learning_rate": 8.408630987314348e-07,
|
| 1549 |
+
"loss": 0.3777,
|
| 1550 |
+
"step": 7040
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 1.6706827309236947,
|
| 1554 |
+
"grad_norm": 3.4375,
|
| 1555 |
+
"learning_rate": 8.046084508609802e-07,
|
| 1556 |
+
"loss": 0.371,
|
| 1557 |
+
"step": 7072
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 1.6782423812898655,
|
| 1561 |
+
"grad_norm": 6.09375,
|
| 1562 |
+
"learning_rate": 7.690842184438929e-07,
|
| 1563 |
+
"loss": 0.3648,
|
| 1564 |
+
"step": 7104
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 1.6858020316560358,
|
| 1568 |
+
"grad_norm": 7.65625,
|
| 1569 |
+
"learning_rate": 7.342965862302786e-07,
|
| 1570 |
+
"loss": 0.371,
|
| 1571 |
+
"step": 7136
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 1.6933616820222066,
|
| 1575 |
+
"grad_norm": 5.40625,
|
| 1576 |
+
"learning_rate": 7.002516107285362e-07,
|
| 1577 |
+
"loss": 0.3965,
|
| 1578 |
+
"step": 7168
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 1.700921332388377,
|
| 1582 |
+
"grad_norm": 4.125,
|
| 1583 |
+
"learning_rate": 6.669552191509238e-07,
|
| 1584 |
+
"loss": 0.3656,
|
| 1585 |
+
"step": 7200
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 1.7084809827545477,
|
| 1589 |
+
"grad_norm": 5.4375,
|
| 1590 |
+
"learning_rate": 6.344132083816329e-07,
|
| 1591 |
+
"loss": 0.3754,
|
| 1592 |
+
"step": 7232
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 1.716040633120718,
|
| 1596 |
+
"grad_norm": 5.4375,
|
| 1597 |
+
"learning_rate": 6.026312439675553e-07,
|
| 1598 |
+
"loss": 0.4162,
|
| 1599 |
+
"step": 7264
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 1.7236002834868889,
|
| 1603 |
+
"grad_norm": 5.8125,
|
| 1604 |
+
"learning_rate": 5.716148591319126e-07,
|
| 1605 |
+
"loss": 0.3487,
|
| 1606 |
+
"step": 7296
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 1.7311599338530592,
|
| 1610 |
+
"grad_norm": 6.5,
|
| 1611 |
+
"learning_rate": 5.413694538109271e-07,
|
| 1612 |
+
"loss": 0.3607,
|
| 1613 |
+
"step": 7328
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 1.73871958421923,
|
| 1617 |
+
"grad_norm": 7.1875,
|
| 1618 |
+
"learning_rate": 5.119002937136946e-07,
|
| 1619 |
+
"loss": 0.4093,
|
| 1620 |
+
"step": 7360
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 1.7462792345854004,
|
| 1624 |
+
"grad_norm": 4.34375,
|
| 1625 |
+
"learning_rate": 4.832125094054263e-07,
|
| 1626 |
+
"loss": 0.3881,
|
| 1627 |
+
"step": 7392
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 1.7538388849515711,
|
| 1631 |
+
"grad_norm": 6.8125,
|
| 1632 |
+
"learning_rate": 4.553110954142242e-07,
|
| 1633 |
+
"loss": 0.4017,
|
| 1634 |
+
"step": 7424
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 1.7613985353177415,
|
| 1638 |
+
"grad_norm": 6.9375,
|
| 1639 |
+
"learning_rate": 4.28200909361528e-07,
|
| 1640 |
+
"loss": 0.4021,
|
| 1641 |
+
"step": 7456
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 1.7689581856839123,
|
| 1645 |
+
"grad_norm": 5.875,
|
| 1646 |
+
"learning_rate": 4.01886671116416e-07,
|
| 1647 |
+
"loss": 0.3795,
|
| 1648 |
+
"step": 7488
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 1.7765178360500826,
|
| 1652 |
+
"grad_norm": 5.375,
|
| 1653 |
+
"learning_rate": 3.763729619738726e-07,
|
| 1654 |
+
"loss": 0.4083,
|
| 1655 |
+
"step": 7520
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 1.7840774864162534,
|
| 1659 |
+
"grad_norm": 5.75,
|
| 1660 |
+
"learning_rate": 3.5166422385718435e-07,
|
| 1661 |
+
"loss": 0.367,
|
| 1662 |
+
"step": 7552
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 1.7916371367824238,
|
| 1666 |
+
"grad_norm": 6.40625,
|
| 1667 |
+
"learning_rate": 3.277647585446131e-07,
|
| 1668 |
+
"loss": 0.3465,
|
| 1669 |
+
"step": 7584
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 1.7991967871485943,
|
| 1673 |
+
"grad_norm": 5.5625,
|
| 1674 |
+
"learning_rate": 3.046787269204482e-07,
|
| 1675 |
+
"loss": 0.3534,
|
| 1676 |
+
"step": 7616
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 1.806756437514765,
|
| 1680 |
+
"grad_norm": 7.90625,
|
| 1681 |
+
"learning_rate": 2.824101482506053e-07,
|
| 1682 |
+
"loss": 0.3944,
|
| 1683 |
+
"step": 7648
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 1.8143160878809355,
|
| 1687 |
+
"grad_norm": 8.9375,
|
| 1688 |
+
"learning_rate": 2.609628994828722e-07,
|
| 1689 |
+
"loss": 0.3943,
|
| 1690 |
+
"step": 7680
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 1.821875738247106,
|
| 1694 |
+
"grad_norm": 14.0,
|
| 1695 |
+
"learning_rate": 2.403407145719344e-07,
|
| 1696 |
+
"loss": 0.376,
|
| 1697 |
+
"step": 7712
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 1.8294353886132766,
|
| 1701 |
+
"grad_norm": 6.03125,
|
| 1702 |
+
"learning_rate": 2.2054718382929552e-07,
|
| 1703 |
+
"loss": 0.3359,
|
| 1704 |
+
"step": 7744
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 1.8369950389794472,
|
| 1708 |
+
"grad_norm": 6.21875,
|
| 1709 |
+
"learning_rate": 2.0158575329820628e-07,
|
| 1710 |
+
"loss": 0.3468,
|
| 1711 |
+
"step": 7776
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 1.8445546893456177,
|
| 1715 |
+
"grad_norm": 6.28125,
|
| 1716 |
+
"learning_rate": 1.834597241537095e-07,
|
| 1717 |
+
"loss": 0.3631,
|
| 1718 |
+
"step": 7808
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 1.8521143397117883,
|
| 1722 |
+
"grad_norm": 5.21875,
|
| 1723 |
+
"learning_rate": 1.6617225212790799e-07,
|
| 1724 |
+
"loss": 0.3991,
|
| 1725 |
+
"step": 7840
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 1.8596739900779589,
|
| 1729 |
+
"grad_norm": 5.46875,
|
| 1730 |
+
"learning_rate": 1.497263469605531e-07,
|
| 1731 |
+
"loss": 0.3659,
|
| 1732 |
+
"step": 7872
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 1.8672336404441294,
|
| 1736 |
+
"grad_norm": 5.96875,
|
| 1737 |
+
"learning_rate": 1.341248718750493e-07,
|
| 1738 |
+
"loss": 0.3921,
|
| 1739 |
+
"step": 7904
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 1.8747932908103,
|
| 1743 |
+
"grad_norm": 6.53125,
|
| 1744 |
+
"learning_rate": 1.1937054307997243e-07,
|
| 1745 |
+
"loss": 0.3845,
|
| 1746 |
+
"step": 7936
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 1.8823529411764706,
|
| 1750 |
+
"grad_norm": 5.34375,
|
| 1751 |
+
"learning_rate": 1.054659292961746e-07,
|
| 1752 |
+
"loss": 0.3989,
|
| 1753 |
+
"step": 7968
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 1.8899125915426411,
|
| 1757 |
+
"grad_norm": 6.1875,
|
| 1758 |
+
"learning_rate": 9.241345130957146e-08,
|
| 1759 |
+
"loss": 0.3561,
|
| 1760 |
+
"step": 8000
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 1.8974722419088117,
|
| 1764 |
+
"grad_norm": 6.09375,
|
| 1765 |
+
"learning_rate": 8.021538154969033e-08,
|
| 1766 |
+
"loss": 0.3713,
|
| 1767 |
+
"step": 8032
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 1.9050318922749823,
|
| 1771 |
+
"grad_norm": 4.65625,
|
| 1772 |
+
"learning_rate": 6.887384369403505e-08,
|
| 1773 |
+
"loss": 0.3967,
|
| 1774 |
+
"step": 8064
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 1.9125915426411528,
|
| 1778 |
+
"grad_norm": 4.5625,
|
| 1779 |
+
"learning_rate": 5.8390812298356195e-08,
|
| 1780 |
+
"loss": 0.3708,
|
| 1781 |
+
"step": 8096
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 1.9201511930073234,
|
| 1785 |
+
"grad_norm": 5.0625,
|
| 1786 |
+
"learning_rate": 4.876811245288549e-08,
|
| 1787 |
+
"loss": 0.3362,
|
| 1788 |
+
"step": 8128
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 1.927710843373494,
|
| 1792 |
+
"grad_norm": 5.46875,
|
| 1793 |
+
"learning_rate": 4.0007419464584416e-08,
|
| 1794 |
+
"loss": 0.3945,
|
| 1795 |
+
"step": 8160
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 1.9352704937396645,
|
| 1799 |
+
"grad_norm": 4.40625,
|
| 1800 |
+
"learning_rate": 3.2110258565476447e-08,
|
| 1801 |
+
"loss": 0.4087,
|
| 1802 |
+
"step": 8192
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 1.942830144105835,
|
| 1806 |
+
"grad_norm": 6.0,
|
| 1807 |
+
"learning_rate": 2.5078004647104415e-08,
|
| 1808 |
+
"loss": 0.3988,
|
| 1809 |
+
"step": 8224
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 1.9503897944720057,
|
| 1813 |
+
"grad_norm": 8.625,
|
| 1814 |
+
"learning_rate": 1.8911882021160898e-08,
|
| 1815 |
+
"loss": 0.419,
|
| 1816 |
+
"step": 8256
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 1.9579494448381762,
|
| 1820 |
+
"grad_norm": 6.21875,
|
| 1821 |
+
"learning_rate": 1.3612964206340395e-08,
|
| 1822 |
+
"loss": 0.3907,
|
| 1823 |
+
"step": 8288
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 1.9655090952043468,
|
| 1827 |
+
"grad_norm": 8.5625,
|
| 1828 |
+
"learning_rate": 9.18217374143604e-09,
|
| 1829 |
+
"loss": 0.3963,
|
| 1830 |
+
"step": 8320
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 1.9730687455705174,
|
| 1834 |
+
"grad_norm": 7.875,
|
| 1835 |
+
"learning_rate": 5.62028202472753e-09,
|
| 1836 |
+
"loss": 0.3773,
|
| 1837 |
+
"step": 8352
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 1.980628395936688,
|
| 1841 |
+
"grad_norm": 5.53125,
|
| 1842 |
+
"learning_rate": 2.9279091796829972e-09,
|
| 1843 |
+
"loss": 0.3533,
|
| 1844 |
+
"step": 8384
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 1.9881880463028585,
|
| 1848 |
+
"grad_norm": 6.8125,
|
| 1849 |
+
"learning_rate": 1.1055239469925927e-09,
|
| 1850 |
+
"loss": 0.3715,
|
| 1851 |
+
"step": 8416
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 1.995747696669029,
|
| 1855 |
+
"grad_norm": 3.796875,
|
| 1856 |
+
"learning_rate": 1.5344360296265516e-10,
|
| 1857 |
+
"loss": 0.3632,
|
| 1858 |
+
"step": 8448
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 2.0,
|
| 1862 |
+
"step": 8466,
|
| 1863 |
+
"total_flos": 1.4971758118666138e+17,
|
| 1864 |
+
"train_loss": 0.3941649041107127,
|
| 1865 |
+
"train_runtime": 3102.2811,
|
| 1866 |
+
"train_samples_per_second": 10.915,
|
| 1867 |
+
"train_steps_per_second": 2.729
|
| 1868 |
+
}
|
| 1869 |
+
],
|
| 1870 |
+
"logging_steps": 32,
|
| 1871 |
+
"max_steps": 8466,
|
| 1872 |
+
"num_input_tokens_seen": 0,
|
| 1873 |
+
"num_train_epochs": 2,
|
| 1874 |
+
"save_steps": 500,
|
| 1875 |
+
"stateful_callbacks": {
|
| 1876 |
+
"TrainerControl": {
|
| 1877 |
+
"args": {
|
| 1878 |
+
"should_epoch_stop": false,
|
| 1879 |
+
"should_evaluate": false,
|
| 1880 |
+
"should_log": false,
|
| 1881 |
+
"should_save": false,
|
| 1882 |
+
"should_training_stop": false
|
| 1883 |
+
},
|
| 1884 |
+
"attributes": {}
|
| 1885 |
+
}
|
| 1886 |
+
},
|
| 1887 |
+
"total_flos": 1.4971758118666138e+17,
|
| 1888 |
+
"train_batch_size": 4,
|
| 1889 |
+
"trial_name": null,
|
| 1890 |
+
"trial_params": null
|
| 1891 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d526b6a8c1754682d3bf31a1b29bb00c930623a42a943c432bac5e7accc81723
|
| 3 |
+
size 5777
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|