mermaid
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 +2374 -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 sha256:19ed9befef51ccb8494992c1a8e112f083a4d3b3afda40c27f1115a758ad1008
|
| 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 +1,2374 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 5.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 10665,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.015002344116268168,
|
| 14 |
+
"grad_norm": 21.375,
|
| 15 |
+
"learning_rate": 2.905342080599813e-07,
|
| 16 |
+
"loss": 0.9809,
|
| 17 |
+
"step": 32
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.030004688232536336,
|
| 21 |
+
"grad_norm": 22.75,
|
| 22 |
+
"learning_rate": 5.904404873477039e-07,
|
| 23 |
+
"loss": 0.9194,
|
| 24 |
+
"step": 64
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.0450070323488045,
|
| 28 |
+
"grad_norm": 21.875,
|
| 29 |
+
"learning_rate": 8.903467666354265e-07,
|
| 30 |
+
"loss": 0.8532,
|
| 31 |
+
"step": 96
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.06000937646507267,
|
| 35 |
+
"grad_norm": 20.125,
|
| 36 |
+
"learning_rate": 1.1902530459231491e-06,
|
| 37 |
+
"loss": 0.875,
|
| 38 |
+
"step": 128
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.07501172058134084,
|
| 42 |
+
"grad_norm": 11.0625,
|
| 43 |
+
"learning_rate": 1.4901593252108717e-06,
|
| 44 |
+
"loss": 0.7929,
|
| 45 |
+
"step": 160
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.090014064697609,
|
| 49 |
+
"grad_norm": 28.125,
|
| 50 |
+
"learning_rate": 1.7900656044985943e-06,
|
| 51 |
+
"loss": 0.7529,
|
| 52 |
+
"step": 192
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.10501640881387717,
|
| 56 |
+
"grad_norm": 11.4375,
|
| 57 |
+
"learning_rate": 2.089971883786317e-06,
|
| 58 |
+
"loss": 0.7193,
|
| 59 |
+
"step": 224
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.12001875293014534,
|
| 63 |
+
"grad_norm": 22.875,
|
| 64 |
+
"learning_rate": 2.3898781630740394e-06,
|
| 65 |
+
"loss": 0.6668,
|
| 66 |
+
"step": 256
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.1350210970464135,
|
| 70 |
+
"grad_norm": 20.25,
|
| 71 |
+
"learning_rate": 2.689784442361762e-06,
|
| 72 |
+
"loss": 0.6509,
|
| 73 |
+
"step": 288
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.15002344116268168,
|
| 77 |
+
"grad_norm": 10.1875,
|
| 78 |
+
"learning_rate": 2.9896907216494846e-06,
|
| 79 |
+
"loss": 0.6039,
|
| 80 |
+
"step": 320
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.16502578527894984,
|
| 84 |
+
"grad_norm": 14.875,
|
| 85 |
+
"learning_rate": 3.2895970009372076e-06,
|
| 86 |
+
"loss": 0.5509,
|
| 87 |
+
"step": 352
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.180028129395218,
|
| 91 |
+
"grad_norm": 11.6875,
|
| 92 |
+
"learning_rate": 3.58950328022493e-06,
|
| 93 |
+
"loss": 0.5364,
|
| 94 |
+
"step": 384
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.19503047351148617,
|
| 98 |
+
"grad_norm": 24.5,
|
| 99 |
+
"learning_rate": 3.889409559512652e-06,
|
| 100 |
+
"loss": 0.5291,
|
| 101 |
+
"step": 416
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.21003281762775433,
|
| 105 |
+
"grad_norm": 20.125,
|
| 106 |
+
"learning_rate": 4.189315838800375e-06,
|
| 107 |
+
"loss": 0.5017,
|
| 108 |
+
"step": 448
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.2250351617440225,
|
| 112 |
+
"grad_norm": 20.75,
|
| 113 |
+
"learning_rate": 4.489222118088098e-06,
|
| 114 |
+
"loss": 0.5199,
|
| 115 |
+
"step": 480
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.24003750586029068,
|
| 119 |
+
"grad_norm": 10.5,
|
| 120 |
+
"learning_rate": 4.789128397375821e-06,
|
| 121 |
+
"loss": 0.5377,
|
| 122 |
+
"step": 512
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.2550398499765588,
|
| 126 |
+
"grad_norm": 20.0,
|
| 127 |
+
"learning_rate": 5.0890346766635435e-06,
|
| 128 |
+
"loss": 0.4862,
|
| 129 |
+
"step": 544
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.270042194092827,
|
| 133 |
+
"grad_norm": 13.625,
|
| 134 |
+
"learning_rate": 5.388940955951266e-06,
|
| 135 |
+
"loss": 0.5037,
|
| 136 |
+
"step": 576
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.28504453820909514,
|
| 140 |
+
"grad_norm": 13.5,
|
| 141 |
+
"learning_rate": 5.688847235238988e-06,
|
| 142 |
+
"loss": 0.4857,
|
| 143 |
+
"step": 608
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.30004688232536336,
|
| 147 |
+
"grad_norm": 12.5625,
|
| 148 |
+
"learning_rate": 5.98875351452671e-06,
|
| 149 |
+
"loss": 0.4565,
|
| 150 |
+
"step": 640
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.3150492264416315,
|
| 154 |
+
"grad_norm": 10.6875,
|
| 155 |
+
"learning_rate": 6.288659793814433e-06,
|
| 156 |
+
"loss": 0.4413,
|
| 157 |
+
"step": 672
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.3300515705578997,
|
| 161 |
+
"grad_norm": 10.25,
|
| 162 |
+
"learning_rate": 6.588566073102156e-06,
|
| 163 |
+
"loss": 0.4185,
|
| 164 |
+
"step": 704
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.34505391467416785,
|
| 168 |
+
"grad_norm": 11.0625,
|
| 169 |
+
"learning_rate": 6.888472352389879e-06,
|
| 170 |
+
"loss": 0.4353,
|
| 171 |
+
"step": 736
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.360056258790436,
|
| 175 |
+
"grad_norm": 12.6875,
|
| 176 |
+
"learning_rate": 7.1883786316776015e-06,
|
| 177 |
+
"loss": 0.3606,
|
| 178 |
+
"step": 768
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.3750586029067042,
|
| 182 |
+
"grad_norm": 16.75,
|
| 183 |
+
"learning_rate": 7.488284910965324e-06,
|
| 184 |
+
"loss": 0.4126,
|
| 185 |
+
"step": 800
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.39006094702297234,
|
| 189 |
+
"grad_norm": 13.5,
|
| 190 |
+
"learning_rate": 7.788191190253046e-06,
|
| 191 |
+
"loss": 0.4052,
|
| 192 |
+
"step": 832
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.4050632911392405,
|
| 196 |
+
"grad_norm": 13.5,
|
| 197 |
+
"learning_rate": 8.08809746954077e-06,
|
| 198 |
+
"loss": 0.383,
|
| 199 |
+
"step": 864
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.42006563525550866,
|
| 203 |
+
"grad_norm": 14.8125,
|
| 204 |
+
"learning_rate": 8.388003748828491e-06,
|
| 205 |
+
"loss": 0.3557,
|
| 206 |
+
"step": 896
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.4350679793717768,
|
| 210 |
+
"grad_norm": 11.9375,
|
| 211 |
+
"learning_rate": 8.687910028116214e-06,
|
| 212 |
+
"loss": 0.3837,
|
| 213 |
+
"step": 928
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.450070323488045,
|
| 217 |
+
"grad_norm": 11.625,
|
| 218 |
+
"learning_rate": 8.987816307403938e-06,
|
| 219 |
+
"loss": 0.3317,
|
| 220 |
+
"step": 960
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.46507266760431315,
|
| 224 |
+
"grad_norm": 12.25,
|
| 225 |
+
"learning_rate": 9.28772258669166e-06,
|
| 226 |
+
"loss": 0.3331,
|
| 227 |
+
"step": 992
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.48007501172058137,
|
| 231 |
+
"grad_norm": 11.3125,
|
| 232 |
+
"learning_rate": 9.587628865979383e-06,
|
| 233 |
+
"loss": 0.3751,
|
| 234 |
+
"step": 1024
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.49507735583684953,
|
| 238 |
+
"grad_norm": 8.8125,
|
| 239 |
+
"learning_rate": 9.887535145267105e-06,
|
| 240 |
+
"loss": 0.3289,
|
| 241 |
+
"step": 1056
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.5100796999531176,
|
| 245 |
+
"grad_norm": 10.875,
|
| 246 |
+
"learning_rate": 9.999892863685326e-06,
|
| 247 |
+
"loss": 0.3429,
|
| 248 |
+
"step": 1088
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.5250820440693859,
|
| 252 |
+
"grad_norm": 11.3125,
|
| 253 |
+
"learning_rate": 9.999275773410506e-06,
|
| 254 |
+
"loss": 0.3186,
|
| 255 |
+
"step": 1120
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.540084388185654,
|
| 259 |
+
"grad_norm": 8.9375,
|
| 260 |
+
"learning_rate": 9.998110227713216e-06,
|
| 261 |
+
"loss": 0.3941,
|
| 262 |
+
"step": 1152
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.5550867323019222,
|
| 266 |
+
"grad_norm": 25.375,
|
| 267 |
+
"learning_rate": 9.996396354461945e-06,
|
| 268 |
+
"loss": 0.3848,
|
| 269 |
+
"step": 1184
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.5700890764181903,
|
| 273 |
+
"grad_norm": 13.125,
|
| 274 |
+
"learning_rate": 9.994134341680546e-06,
|
| 275 |
+
"loss": 0.348,
|
| 276 |
+
"step": 1216
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.5850914205344585,
|
| 280 |
+
"grad_norm": 16.5,
|
| 281 |
+
"learning_rate": 9.991324437527599e-06,
|
| 282 |
+
"loss": 0.3511,
|
| 283 |
+
"step": 1248
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.6000937646507267,
|
| 287 |
+
"grad_norm": 12.0,
|
| 288 |
+
"learning_rate": 9.987966950269184e-06,
|
| 289 |
+
"loss": 0.3655,
|
| 290 |
+
"step": 1280
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.6150961087669948,
|
| 294 |
+
"grad_norm": 15.0,
|
| 295 |
+
"learning_rate": 9.984062248245078e-06,
|
| 296 |
+
"loss": 0.3657,
|
| 297 |
+
"step": 1312
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.630098452883263,
|
| 301 |
+
"grad_norm": 14.375,
|
| 302 |
+
"learning_rate": 9.979610759828324e-06,
|
| 303 |
+
"loss": 0.298,
|
| 304 |
+
"step": 1344
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.6451007969995312,
|
| 308 |
+
"grad_norm": 16.125,
|
| 309 |
+
"learning_rate": 9.974612973378252e-06,
|
| 310 |
+
"loss": 0.3793,
|
| 311 |
+
"step": 1376
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.6601031411157994,
|
| 315 |
+
"grad_norm": 13.0,
|
| 316 |
+
"learning_rate": 9.969069437186899e-06,
|
| 317 |
+
"loss": 0.3425,
|
| 318 |
+
"step": 1408
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.6751054852320675,
|
| 322 |
+
"grad_norm": 12.4375,
|
| 323 |
+
"learning_rate": 9.962980759418844e-06,
|
| 324 |
+
"loss": 0.3424,
|
| 325 |
+
"step": 1440
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.6901078293483357,
|
| 329 |
+
"grad_norm": 15.25,
|
| 330 |
+
"learning_rate": 9.956347608044512e-06,
|
| 331 |
+
"loss": 0.357,
|
| 332 |
+
"step": 1472
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.7051101734646038,
|
| 336 |
+
"grad_norm": 23.75,
|
| 337 |
+
"learning_rate": 9.949170710766875e-06,
|
| 338 |
+
"loss": 0.3335,
|
| 339 |
+
"step": 1504
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.720112517580872,
|
| 343 |
+
"grad_norm": 10.75,
|
| 344 |
+
"learning_rate": 9.94145085494162e-06,
|
| 345 |
+
"loss": 0.3344,
|
| 346 |
+
"step": 1536
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.7351148616971401,
|
| 350 |
+
"grad_norm": 8.5625,
|
| 351 |
+
"learning_rate": 9.933188887490784e-06,
|
| 352 |
+
"loss": 0.3206,
|
| 353 |
+
"step": 1568
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.7501172058134083,
|
| 357 |
+
"grad_norm": 12.9375,
|
| 358 |
+
"learning_rate": 9.924385714809818e-06,
|
| 359 |
+
"loss": 0.3673,
|
| 360 |
+
"step": 1600
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.7651195499296765,
|
| 364 |
+
"grad_norm": 8.75,
|
| 365 |
+
"learning_rate": 9.91504230266817e-06,
|
| 366 |
+
"loss": 0.3392,
|
| 367 |
+
"step": 1632
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.7801218940459447,
|
| 371 |
+
"grad_norm": 18.625,
|
| 372 |
+
"learning_rate": 9.905159676103322e-06,
|
| 373 |
+
"loss": 0.3022,
|
| 374 |
+
"step": 1664
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.7951242381622129,
|
| 378 |
+
"grad_norm": 9.0625,
|
| 379 |
+
"learning_rate": 9.89473891930834e-06,
|
| 380 |
+
"loss": 0.3361,
|
| 381 |
+
"step": 1696
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.810126582278481,
|
| 385 |
+
"grad_norm": 12.5,
|
| 386 |
+
"learning_rate": 9.88378117551293e-06,
|
| 387 |
+
"loss": 0.3299,
|
| 388 |
+
"step": 1728
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.8251289263947492,
|
| 392 |
+
"grad_norm": 14.0,
|
| 393 |
+
"learning_rate": 9.872287646858015e-06,
|
| 394 |
+
"loss": 0.3304,
|
| 395 |
+
"step": 1760
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.8401312705110173,
|
| 399 |
+
"grad_norm": 14.25,
|
| 400 |
+
"learning_rate": 9.860259594263858e-06,
|
| 401 |
+
"loss": 0.3219,
|
| 402 |
+
"step": 1792
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.8551336146272855,
|
| 406 |
+
"grad_norm": 13.375,
|
| 407 |
+
"learning_rate": 9.847698337291725e-06,
|
| 408 |
+
"loss": 0.2956,
|
| 409 |
+
"step": 1824
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.8701359587435537,
|
| 413 |
+
"grad_norm": 10.625,
|
| 414 |
+
"learning_rate": 9.834605253999119e-06,
|
| 415 |
+
"loss": 0.3375,
|
| 416 |
+
"step": 1856
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.8851383028598219,
|
| 420 |
+
"grad_norm": 12.0,
|
| 421 |
+
"learning_rate": 9.820981780788604e-06,
|
| 422 |
+
"loss": 0.3464,
|
| 423 |
+
"step": 1888
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.90014064697609,
|
| 427 |
+
"grad_norm": 9.5625,
|
| 428 |
+
"learning_rate": 9.806829412250215e-06,
|
| 429 |
+
"loss": 0.3522,
|
| 430 |
+
"step": 1920
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.9151429910923582,
|
| 434 |
+
"grad_norm": 8.9375,
|
| 435 |
+
"learning_rate": 9.792149700997492e-06,
|
| 436 |
+
"loss": 0.328,
|
| 437 |
+
"step": 1952
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.9301453352086263,
|
| 441 |
+
"grad_norm": 13.625,
|
| 442 |
+
"learning_rate": 9.776944257497157e-06,
|
| 443 |
+
"loss": 0.3549,
|
| 444 |
+
"step": 1984
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.9451476793248945,
|
| 448 |
+
"grad_norm": 14.1875,
|
| 449 |
+
"learning_rate": 9.761214749892411e-06,
|
| 450 |
+
"loss": 0.3402,
|
| 451 |
+
"step": 2016
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.9601500234411627,
|
| 455 |
+
"grad_norm": 10.1875,
|
| 456 |
+
"learning_rate": 9.74496290381996e-06,
|
| 457 |
+
"loss": 0.3362,
|
| 458 |
+
"step": 2048
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.9751523675574308,
|
| 462 |
+
"grad_norm": 9.875,
|
| 463 |
+
"learning_rate": 9.728190502220673e-06,
|
| 464 |
+
"loss": 0.3825,
|
| 465 |
+
"step": 2080
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.9901547116736991,
|
| 469 |
+
"grad_norm": 12.4375,
|
| 470 |
+
"learning_rate": 9.710899385143993e-06,
|
| 471 |
+
"loss": 0.3536,
|
| 472 |
+
"step": 2112
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.0051570557899672,
|
| 476 |
+
"grad_norm": 5.78125,
|
| 477 |
+
"learning_rate": 9.693091449546068e-06,
|
| 478 |
+
"loss": 0.2984,
|
| 479 |
+
"step": 2144
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.0201593999062353,
|
| 483 |
+
"grad_norm": 14.375,
|
| 484 |
+
"learning_rate": 9.674768649081647e-06,
|
| 485 |
+
"loss": 0.2614,
|
| 486 |
+
"step": 2176
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 1.0351617440225036,
|
| 490 |
+
"grad_norm": 16.5,
|
| 491 |
+
"learning_rate": 9.655932993889742e-06,
|
| 492 |
+
"loss": 0.282,
|
| 493 |
+
"step": 2208
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 1.0501640881387717,
|
| 497 |
+
"grad_norm": 12.25,
|
| 498 |
+
"learning_rate": 9.636586550373105e-06,
|
| 499 |
+
"loss": 0.2256,
|
| 500 |
+
"step": 2240
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.0651664322550398,
|
| 504 |
+
"grad_norm": 12.3125,
|
| 505 |
+
"learning_rate": 9.616731440971536e-06,
|
| 506 |
+
"loss": 0.2698,
|
| 507 |
+
"step": 2272
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.080168776371308,
|
| 511 |
+
"grad_norm": 18.625,
|
| 512 |
+
"learning_rate": 9.596369843929022e-06,
|
| 513 |
+
"loss": 0.2477,
|
| 514 |
+
"step": 2304
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 1.0951711204875763,
|
| 518 |
+
"grad_norm": 12.5625,
|
| 519 |
+
"learning_rate": 9.575503993054787e-06,
|
| 520 |
+
"loss": 0.2369,
|
| 521 |
+
"step": 2336
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.1101734646038444,
|
| 525 |
+
"grad_norm": 9.625,
|
| 526 |
+
"learning_rate": 9.554136177478206e-06,
|
| 527 |
+
"loss": 0.2443,
|
| 528 |
+
"step": 2368
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 1.1251758087201125,
|
| 532 |
+
"grad_norm": 13.625,
|
| 533 |
+
"learning_rate": 9.532268741397692e-06,
|
| 534 |
+
"loss": 0.2789,
|
| 535 |
+
"step": 2400
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 1.1401781528363806,
|
| 539 |
+
"grad_norm": 10.5,
|
| 540 |
+
"learning_rate": 9.50990408382351e-06,
|
| 541 |
+
"loss": 0.2721,
|
| 542 |
+
"step": 2432
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 1.155180496952649,
|
| 546 |
+
"grad_norm": 8.75,
|
| 547 |
+
"learning_rate": 9.487044658314585e-06,
|
| 548 |
+
"loss": 0.2372,
|
| 549 |
+
"step": 2464
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.170182841068917,
|
| 553 |
+
"grad_norm": 10.4375,
|
| 554 |
+
"learning_rate": 9.463692972709349e-06,
|
| 555 |
+
"loss": 0.259,
|
| 556 |
+
"step": 2496
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.1851851851851851,
|
| 560 |
+
"grad_norm": 13.9375,
|
| 561 |
+
"learning_rate": 9.439851588850586e-06,
|
| 562 |
+
"loss": 0.2918,
|
| 563 |
+
"step": 2528
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.2001875293014534,
|
| 567 |
+
"grad_norm": 5.84375,
|
| 568 |
+
"learning_rate": 9.4155231223044e-06,
|
| 569 |
+
"loss": 0.2392,
|
| 570 |
+
"step": 2560
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 1.2151898734177216,
|
| 574 |
+
"grad_norm": 12.0625,
|
| 575 |
+
"learning_rate": 9.390710242073265e-06,
|
| 576 |
+
"loss": 0.2973,
|
| 577 |
+
"step": 2592
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 1.2301922175339897,
|
| 581 |
+
"grad_norm": 6.5,
|
| 582 |
+
"learning_rate": 9.365415670303214e-06,
|
| 583 |
+
"loss": 0.2763,
|
| 584 |
+
"step": 2624
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 1.2451945616502578,
|
| 588 |
+
"grad_norm": 11.375,
|
| 589 |
+
"learning_rate": 9.339642181985196e-06,
|
| 590 |
+
"loss": 0.2845,
|
| 591 |
+
"step": 2656
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.260196905766526,
|
| 595 |
+
"grad_norm": 11.75,
|
| 596 |
+
"learning_rate": 9.313392604650655e-06,
|
| 597 |
+
"loss": 0.2532,
|
| 598 |
+
"step": 2688
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 1.2751992498827942,
|
| 602 |
+
"grad_norm": 9.375,
|
| 603 |
+
"learning_rate": 9.286669818061316e-06,
|
| 604 |
+
"loss": 0.2647,
|
| 605 |
+
"step": 2720
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 1.2902015939990623,
|
| 609 |
+
"grad_norm": 10.6875,
|
| 610 |
+
"learning_rate": 9.259476753893258e-06,
|
| 611 |
+
"loss": 0.256,
|
| 612 |
+
"step": 2752
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 1.3052039381153304,
|
| 616 |
+
"grad_norm": 10.0,
|
| 617 |
+
"learning_rate": 9.231816395415294e-06,
|
| 618 |
+
"loss": 0.2596,
|
| 619 |
+
"step": 2784
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 1.3202062822315987,
|
| 623 |
+
"grad_norm": 12.0625,
|
| 624 |
+
"learning_rate": 9.20369177716168e-06,
|
| 625 |
+
"loss": 0.2589,
|
| 626 |
+
"step": 2816
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.3352086263478669,
|
| 630 |
+
"grad_norm": 7.84375,
|
| 631 |
+
"learning_rate": 9.17510598459921e-06,
|
| 632 |
+
"loss": 0.2753,
|
| 633 |
+
"step": 2848
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.350210970464135,
|
| 637 |
+
"grad_norm": 6.5,
|
| 638 |
+
"learning_rate": 9.146062153788716e-06,
|
| 639 |
+
"loss": 0.2512,
|
| 640 |
+
"step": 2880
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 1.3652133145804033,
|
| 644 |
+
"grad_norm": 9.75,
|
| 645 |
+
"learning_rate": 9.116563471041018e-06,
|
| 646 |
+
"loss": 0.252,
|
| 647 |
+
"step": 2912
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1.3802156586966714,
|
| 651 |
+
"grad_norm": 18.75,
|
| 652 |
+
"learning_rate": 9.086613172567368e-06,
|
| 653 |
+
"loss": 0.2238,
|
| 654 |
+
"step": 2944
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.3952180028129395,
|
| 658 |
+
"grad_norm": 12.9375,
|
| 659 |
+
"learning_rate": 9.056214544124414e-06,
|
| 660 |
+
"loss": 0.2635,
|
| 661 |
+
"step": 2976
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.4102203469292076,
|
| 665 |
+
"grad_norm": 10.125,
|
| 666 |
+
"learning_rate": 9.025370920653723e-06,
|
| 667 |
+
"loss": 0.2525,
|
| 668 |
+
"step": 3008
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.4252226910454757,
|
| 672 |
+
"grad_norm": 11.25,
|
| 673 |
+
"learning_rate": 8.994085685915934e-06,
|
| 674 |
+
"loss": 0.2493,
|
| 675 |
+
"step": 3040
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.440225035161744,
|
| 679 |
+
"grad_norm": 12.875,
|
| 680 |
+
"learning_rate": 8.962362272119504e-06,
|
| 681 |
+
"loss": 0.2551,
|
| 682 |
+
"step": 3072
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.4552273792780122,
|
| 686 |
+
"grad_norm": 10.9375,
|
| 687 |
+
"learning_rate": 8.930204159544208e-06,
|
| 688 |
+
"loss": 0.2573,
|
| 689 |
+
"step": 3104
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.4702297233942803,
|
| 693 |
+
"grad_norm": 15.0625,
|
| 694 |
+
"learning_rate": 8.89761487615929e-06,
|
| 695 |
+
"loss": 0.2544,
|
| 696 |
+
"step": 3136
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 1.4852320675105486,
|
| 700 |
+
"grad_norm": 15.125,
|
| 701 |
+
"learning_rate": 8.864597997236454e-06,
|
| 702 |
+
"loss": 0.2696,
|
| 703 |
+
"step": 3168
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 1.5002344116268167,
|
| 707 |
+
"grad_norm": 18.875,
|
| 708 |
+
"learning_rate": 8.831157144957612e-06,
|
| 709 |
+
"loss": 0.243,
|
| 710 |
+
"step": 3200
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 1.5152367557430848,
|
| 714 |
+
"grad_norm": 7.625,
|
| 715 |
+
"learning_rate": 8.797295988017506e-06,
|
| 716 |
+
"loss": 0.2689,
|
| 717 |
+
"step": 3232
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.5302390998593531,
|
| 721 |
+
"grad_norm": 9.125,
|
| 722 |
+
"learning_rate": 8.763018241221241e-06,
|
| 723 |
+
"loss": 0.2405,
|
| 724 |
+
"step": 3264
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 1.5452414439756212,
|
| 728 |
+
"grad_norm": 9.9375,
|
| 729 |
+
"learning_rate": 8.728327665076726e-06,
|
| 730 |
+
"loss": 0.291,
|
| 731 |
+
"step": 3296
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 1.5602437880918893,
|
| 735 |
+
"grad_norm": 11.8125,
|
| 736 |
+
"learning_rate": 8.693228065382131e-06,
|
| 737 |
+
"loss": 0.2358,
|
| 738 |
+
"step": 3328
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 1.5752461322081577,
|
| 742 |
+
"grad_norm": 15.375,
|
| 743 |
+
"learning_rate": 8.657723292808365e-06,
|
| 744 |
+
"loss": 0.2577,
|
| 745 |
+
"step": 3360
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 1.5902484763244256,
|
| 749 |
+
"grad_norm": 14.25,
|
| 750 |
+
"learning_rate": 8.621817242476626e-06,
|
| 751 |
+
"loss": 0.2358,
|
| 752 |
+
"step": 3392
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 1.605250820440694,
|
| 756 |
+
"grad_norm": 20.75,
|
| 757 |
+
"learning_rate": 8.58551385353108e-06,
|
| 758 |
+
"loss": 0.2879,
|
| 759 |
+
"step": 3424
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.620253164556962,
|
| 763 |
+
"grad_norm": 12.125,
|
| 764 |
+
"learning_rate": 8.548817108706714e-06,
|
| 765 |
+
"loss": 0.2549,
|
| 766 |
+
"step": 3456
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 1.63525550867323,
|
| 770 |
+
"grad_norm": 19.75,
|
| 771 |
+
"learning_rate": 8.511731033892397e-06,
|
| 772 |
+
"loss": 0.2679,
|
| 773 |
+
"step": 3488
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 1.6502578527894984,
|
| 777 |
+
"grad_norm": 7.875,
|
| 778 |
+
"learning_rate": 8.474259697689211e-06,
|
| 779 |
+
"loss": 0.3122,
|
| 780 |
+
"step": 3520
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 1.6652601969057665,
|
| 784 |
+
"grad_norm": 8.3125,
|
| 785 |
+
"learning_rate": 8.436407210964101e-06,
|
| 786 |
+
"loss": 0.284,
|
| 787 |
+
"step": 3552
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 1.6802625410220347,
|
| 791 |
+
"grad_norm": 9.125,
|
| 792 |
+
"learning_rate": 8.398177726398887e-06,
|
| 793 |
+
"loss": 0.2833,
|
| 794 |
+
"step": 3584
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 1.695264885138303,
|
| 798 |
+
"grad_norm": 14.875,
|
| 799 |
+
"learning_rate": 8.359575438034671e-06,
|
| 800 |
+
"loss": 0.2927,
|
| 801 |
+
"step": 3616
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.7102672292545709,
|
| 805 |
+
"grad_norm": 11.3125,
|
| 806 |
+
"learning_rate": 8.320604580811744e-06,
|
| 807 |
+
"loss": 0.2367,
|
| 808 |
+
"step": 3648
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 1.7252695733708392,
|
| 812 |
+
"grad_norm": 11.6875,
|
| 813 |
+
"learning_rate": 8.281269430104965e-06,
|
| 814 |
+
"loss": 0.2772,
|
| 815 |
+
"step": 3680
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 1.7402719174871075,
|
| 819 |
+
"grad_norm": 12.375,
|
| 820 |
+
"learning_rate": 8.241574301254733e-06,
|
| 821 |
+
"loss": 0.2424,
|
| 822 |
+
"step": 3712
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 1.7552742616033754,
|
| 826 |
+
"grad_norm": 15.25,
|
| 827 |
+
"learning_rate": 8.201523549093552e-06,
|
| 828 |
+
"loss": 0.2595,
|
| 829 |
+
"step": 3744
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 1.7702766057196437,
|
| 833 |
+
"grad_norm": 10.3125,
|
| 834 |
+
"learning_rate": 8.161121567468298e-06,
|
| 835 |
+
"loss": 0.2717,
|
| 836 |
+
"step": 3776
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 1.7852789498359118,
|
| 840 |
+
"grad_norm": 10.0,
|
| 841 |
+
"learning_rate": 8.120372788758152e-06,
|
| 842 |
+
"loss": 0.2582,
|
| 843 |
+
"step": 3808
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.80028129395218,
|
| 847 |
+
"grad_norm": 10.1875,
|
| 848 |
+
"learning_rate": 8.079281683388368e-06,
|
| 849 |
+
"loss": 0.2521,
|
| 850 |
+
"step": 3840
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.8152836380684483,
|
| 854 |
+
"grad_norm": 12.9375,
|
| 855 |
+
"learning_rate": 8.037852759339814e-06,
|
| 856 |
+
"loss": 0.252,
|
| 857 |
+
"step": 3872
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 1.8302859821847164,
|
| 861 |
+
"grad_norm": 11.875,
|
| 862 |
+
"learning_rate": 7.99609056165443e-06,
|
| 863 |
+
"loss": 0.2604,
|
| 864 |
+
"step": 3904
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 1.8452883263009845,
|
| 868 |
+
"grad_norm": 15.625,
|
| 869 |
+
"learning_rate": 7.953999671936591e-06,
|
| 870 |
+
"loss": 0.2656,
|
| 871 |
+
"step": 3936
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 1.8602906704172528,
|
| 875 |
+
"grad_norm": 11.875,
|
| 876 |
+
"learning_rate": 7.911584707850487e-06,
|
| 877 |
+
"loss": 0.2208,
|
| 878 |
+
"step": 3968
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 1.8752930145335207,
|
| 882 |
+
"grad_norm": 8.875,
|
| 883 |
+
"learning_rate": 7.868850322613525e-06,
|
| 884 |
+
"loss": 0.2632,
|
| 885 |
+
"step": 4000
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 1.890295358649789,
|
| 889 |
+
"grad_norm": 12.5,
|
| 890 |
+
"learning_rate": 7.825801204485837e-06,
|
| 891 |
+
"loss": 0.2528,
|
| 892 |
+
"step": 4032
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 1.9052977027660571,
|
| 896 |
+
"grad_norm": 9.75,
|
| 897 |
+
"learning_rate": 7.782442076255952e-06,
|
| 898 |
+
"loss": 0.2539,
|
| 899 |
+
"step": 4064
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 1.9203000468823253,
|
| 903 |
+
"grad_norm": 13.625,
|
| 904 |
+
"learning_rate": 7.738777694722666e-06,
|
| 905 |
+
"loss": 0.2846,
|
| 906 |
+
"step": 4096
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 1.9353023909985936,
|
| 910 |
+
"grad_norm": 11.8125,
|
| 911 |
+
"learning_rate": 7.694812850173197e-06,
|
| 912 |
+
"loss": 0.2536,
|
| 913 |
+
"step": 4128
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 1.9503047351148617,
|
| 917 |
+
"grad_norm": 11.8125,
|
| 918 |
+
"learning_rate": 7.650552365857648e-06,
|
| 919 |
+
"loss": 0.2522,
|
| 920 |
+
"step": 4160
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 1.9653070792311298,
|
| 924 |
+
"grad_norm": 17.625,
|
| 925 |
+
"learning_rate": 7.606001097459865e-06,
|
| 926 |
+
"loss": 0.2744,
|
| 927 |
+
"step": 4192
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 1.9803094233473981,
|
| 931 |
+
"grad_norm": 9.25,
|
| 932 |
+
"learning_rate": 7.561163932564739e-06,
|
| 933 |
+
"loss": 0.2725,
|
| 934 |
+
"step": 4224
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 1.9953117674636662,
|
| 938 |
+
"grad_norm": 6.75,
|
| 939 |
+
"learning_rate": 7.516045790122e-06,
|
| 940 |
+
"loss": 0.2576,
|
| 941 |
+
"step": 4256
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 2.0103141115799343,
|
| 945 |
+
"grad_norm": 9.5625,
|
| 946 |
+
"learning_rate": 7.470651619906574e-06,
|
| 947 |
+
"loss": 0.1846,
|
| 948 |
+
"step": 4288
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 2.0253164556962027,
|
| 952 |
+
"grad_norm": 13.5,
|
| 953 |
+
"learning_rate": 7.424986401975561e-06,
|
| 954 |
+
"loss": 0.2504,
|
| 955 |
+
"step": 4320
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 2.0403187998124706,
|
| 959 |
+
"grad_norm": 7.4375,
|
| 960 |
+
"learning_rate": 7.379055146121884e-06,
|
| 961 |
+
"loss": 0.1835,
|
| 962 |
+
"step": 4352
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 2.055321143928739,
|
| 966 |
+
"grad_norm": 13.0,
|
| 967 |
+
"learning_rate": 7.332862891324681e-06,
|
| 968 |
+
"loss": 0.2298,
|
| 969 |
+
"step": 4384
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 2.070323488045007,
|
| 973 |
+
"grad_norm": 11.5625,
|
| 974 |
+
"learning_rate": 7.286414705196499e-06,
|
| 975 |
+
"loss": 0.2158,
|
| 976 |
+
"step": 4416
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 2.085325832161275,
|
| 980 |
+
"grad_norm": 13.625,
|
| 981 |
+
"learning_rate": 7.2397156834273295e-06,
|
| 982 |
+
"loss": 0.2305,
|
| 983 |
+
"step": 4448
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 2.1003281762775434,
|
| 987 |
+
"grad_norm": 15.4375,
|
| 988 |
+
"learning_rate": 7.192770949225591e-06,
|
| 989 |
+
"loss": 0.1828,
|
| 990 |
+
"step": 4480
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 2.1153305203938118,
|
| 994 |
+
"grad_norm": 7.84375,
|
| 995 |
+
"learning_rate": 7.1455856527560666e-06,
|
| 996 |
+
"loss": 0.172,
|
| 997 |
+
"step": 4512
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 2.1303328645100796,
|
| 1001 |
+
"grad_norm": 14.25,
|
| 1002 |
+
"learning_rate": 7.0981649705748955e-06,
|
| 1003 |
+
"loss": 0.164,
|
| 1004 |
+
"step": 4544
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 2.145335208626348,
|
| 1008 |
+
"grad_norm": 13.5,
|
| 1009 |
+
"learning_rate": 7.050514105061679e-06,
|
| 1010 |
+
"loss": 0.1857,
|
| 1011 |
+
"step": 4576
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 2.160337552742616,
|
| 1015 |
+
"grad_norm": 7.375,
|
| 1016 |
+
"learning_rate": 7.002638283848726e-06,
|
| 1017 |
+
"loss": 0.1909,
|
| 1018 |
+
"step": 4608
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 2.175339896858884,
|
| 1022 |
+
"grad_norm": 5.46875,
|
| 1023 |
+
"learning_rate": 6.95454275924756e-06,
|
| 1024 |
+
"loss": 0.1902,
|
| 1025 |
+
"step": 4640
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 2.1903422409751525,
|
| 1029 |
+
"grad_norm": 9.3125,
|
| 1030 |
+
"learning_rate": 6.906232807672699e-06,
|
| 1031 |
+
"loss": 0.1778,
|
| 1032 |
+
"step": 4672
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 2.2053445850914204,
|
| 1036 |
+
"grad_norm": 8.9375,
|
| 1037 |
+
"learning_rate": 6.857713729062794e-06,
|
| 1038 |
+
"loss": 0.1802,
|
| 1039 |
+
"step": 4704
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 2.2203469292076887,
|
| 1043 |
+
"grad_norm": 13.9375,
|
| 1044 |
+
"learning_rate": 6.80899084629919e-06,
|
| 1045 |
+
"loss": 0.2209,
|
| 1046 |
+
"step": 4736
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 2.235349273323957,
|
| 1050 |
+
"grad_norm": 15.625,
|
| 1051 |
+
"learning_rate": 6.760069504621971e-06,
|
| 1052 |
+
"loss": 0.2697,
|
| 1053 |
+
"step": 4768
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 2.250351617440225,
|
| 1057 |
+
"grad_norm": 9.125,
|
| 1058 |
+
"learning_rate": 6.710955071043547e-06,
|
| 1059 |
+
"loss": 0.1916,
|
| 1060 |
+
"step": 4800
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 2.2653539615564933,
|
| 1064 |
+
"grad_norm": 7.71875,
|
| 1065 |
+
"learning_rate": 6.661652933759856e-06,
|
| 1066 |
+
"loss": 0.1851,
|
| 1067 |
+
"step": 4832
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 2.280356305672761,
|
| 1071 |
+
"grad_norm": 18.125,
|
| 1072 |
+
"learning_rate": 6.612168501559242e-06,
|
| 1073 |
+
"loss": 0.2051,
|
| 1074 |
+
"step": 4864
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 2.2953586497890295,
|
| 1078 |
+
"grad_norm": 3.078125,
|
| 1079 |
+
"learning_rate": 6.5625072032290735e-06,
|
| 1080 |
+
"loss": 0.176,
|
| 1081 |
+
"step": 4896
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 2.310360993905298,
|
| 1085 |
+
"grad_norm": 16.25,
|
| 1086 |
+
"learning_rate": 6.512674486960166e-06,
|
| 1087 |
+
"loss": 0.1753,
|
| 1088 |
+
"step": 4928
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 2.3253633380215657,
|
| 1092 |
+
"grad_norm": 11.8125,
|
| 1093 |
+
"learning_rate": 6.462675819749082e-06,
|
| 1094 |
+
"loss": 0.1666,
|
| 1095 |
+
"step": 4960
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 2.340365682137834,
|
| 1099 |
+
"grad_norm": 12.1875,
|
| 1100 |
+
"learning_rate": 6.412516686798354e-06,
|
| 1101 |
+
"loss": 0.1841,
|
| 1102 |
+
"step": 4992
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 2.3553680262541024,
|
| 1106 |
+
"grad_norm": 12.9375,
|
| 1107 |
+
"learning_rate": 6.362202590914728e-06,
|
| 1108 |
+
"loss": 0.2007,
|
| 1109 |
+
"step": 5024
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 2.3703703703703702,
|
| 1113 |
+
"grad_norm": 19.5,
|
| 1114 |
+
"learning_rate": 6.311739051905468e-06,
|
| 1115 |
+
"loss": 0.1642,
|
| 1116 |
+
"step": 5056
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 2.3853727144866386,
|
| 1120 |
+
"grad_norm": 14.1875,
|
| 1121 |
+
"learning_rate": 6.261131605972785e-06,
|
| 1122 |
+
"loss": 0.1976,
|
| 1123 |
+
"step": 5088
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 2.400375058602907,
|
| 1127 |
+
"grad_norm": 10.4375,
|
| 1128 |
+
"learning_rate": 6.2103858051064915e-06,
|
| 1129 |
+
"loss": 0.2102,
|
| 1130 |
+
"step": 5120
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 2.415377402719175,
|
| 1134 |
+
"grad_norm": 9.4375,
|
| 1135 |
+
"learning_rate": 6.159507216474891e-06,
|
| 1136 |
+
"loss": 0.2282,
|
| 1137 |
+
"step": 5152
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 2.430379746835443,
|
| 1141 |
+
"grad_norm": 10.4375,
|
| 1142 |
+
"learning_rate": 6.108501421814039e-06,
|
| 1143 |
+
"loss": 0.2119,
|
| 1144 |
+
"step": 5184
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 2.4453820909517114,
|
| 1148 |
+
"grad_norm": 15.125,
|
| 1149 |
+
"learning_rate": 6.057374016815376e-06,
|
| 1150 |
+
"loss": 0.2176,
|
| 1151 |
+
"step": 5216
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 2.4603844350679793,
|
| 1155 |
+
"grad_norm": 13.125,
|
| 1156 |
+
"learning_rate": 6.0061306105118474e-06,
|
| 1157 |
+
"loss": 0.1872,
|
| 1158 |
+
"step": 5248
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 2.4753867791842477,
|
| 1162 |
+
"grad_norm": 11.25,
|
| 1163 |
+
"learning_rate": 5.954776824662547e-06,
|
| 1164 |
+
"loss": 0.1978,
|
| 1165 |
+
"step": 5280
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 2.4903891233005155,
|
| 1169 |
+
"grad_norm": 6.96875,
|
| 1170 |
+
"learning_rate": 5.90331829313598e-06,
|
| 1171 |
+
"loss": 0.1864,
|
| 1172 |
+
"step": 5312
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 2.505391467416784,
|
| 1176 |
+
"grad_norm": 6.625,
|
| 1177 |
+
"learning_rate": 5.851760661291977e-06,
|
| 1178 |
+
"loss": 0.2036,
|
| 1179 |
+
"step": 5344
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 2.520393811533052,
|
| 1183 |
+
"grad_norm": 10.8125,
|
| 1184 |
+
"learning_rate": 5.80010958536237e-06,
|
| 1185 |
+
"loss": 0.202,
|
| 1186 |
+
"step": 5376
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 2.53539615564932,
|
| 1190 |
+
"grad_norm": 9.5625,
|
| 1191 |
+
"learning_rate": 5.748370731830456e-06,
|
| 1192 |
+
"loss": 0.2186,
|
| 1193 |
+
"step": 5408
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 2.5503984997655884,
|
| 1197 |
+
"grad_norm": 17.75,
|
| 1198 |
+
"learning_rate": 5.696549776809346e-06,
|
| 1199 |
+
"loss": 0.1919,
|
| 1200 |
+
"step": 5440
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 2.5654008438818563,
|
| 1204 |
+
"grad_norm": 10.0625,
|
| 1205 |
+
"learning_rate": 5.6446524054192605e-06,
|
| 1206 |
+
"loss": 0.2007,
|
| 1207 |
+
"step": 5472
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 2.5804031879981246,
|
| 1211 |
+
"grad_norm": 15.9375,
|
| 1212 |
+
"learning_rate": 5.592684311163827e-06,
|
| 1213 |
+
"loss": 0.2096,
|
| 1214 |
+
"step": 5504
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 2.595405532114393,
|
| 1218 |
+
"grad_norm": 11.25,
|
| 1219 |
+
"learning_rate": 5.540651195305464e-06,
|
| 1220 |
+
"loss": 0.2196,
|
| 1221 |
+
"step": 5536
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 2.610407876230661,
|
| 1225 |
+
"grad_norm": 8.4375,
|
| 1226 |
+
"learning_rate": 5.488558766239916e-06,
|
| 1227 |
+
"loss": 0.2207,
|
| 1228 |
+
"step": 5568
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 2.625410220346929,
|
| 1232 |
+
"grad_norm": 19.75,
|
| 1233 |
+
"learning_rate": 5.436412738869995e-06,
|
| 1234 |
+
"loss": 0.1945,
|
| 1235 |
+
"step": 5600
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 2.6404125644631975,
|
| 1239 |
+
"grad_norm": 13.3125,
|
| 1240 |
+
"learning_rate": 5.384218833978626e-06,
|
| 1241 |
+
"loss": 0.1896,
|
| 1242 |
+
"step": 5632
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 2.6554149085794654,
|
| 1246 |
+
"grad_norm": 12.4375,
|
| 1247 |
+
"learning_rate": 5.331982777601228e-06,
|
| 1248 |
+
"loss": 0.2217,
|
| 1249 |
+
"step": 5664
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 2.6704172526957337,
|
| 1253 |
+
"grad_norm": 14.1875,
|
| 1254 |
+
"learning_rate": 5.279710300397537e-06,
|
| 1255 |
+
"loss": 0.1987,
|
| 1256 |
+
"step": 5696
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 2.685419596812002,
|
| 1260 |
+
"grad_norm": 7.59375,
|
| 1261 |
+
"learning_rate": 5.227407137022902e-06,
|
| 1262 |
+
"loss": 0.232,
|
| 1263 |
+
"step": 5728
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 2.70042194092827,
|
| 1267 |
+
"grad_norm": 13.1875,
|
| 1268 |
+
"learning_rate": 5.175079025499163e-06,
|
| 1269 |
+
"loss": 0.1845,
|
| 1270 |
+
"step": 5760
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 2.7154242850445383,
|
| 1274 |
+
"grad_norm": 8.3125,
|
| 1275 |
+
"learning_rate": 5.1227317065851445e-06,
|
| 1276 |
+
"loss": 0.1973,
|
| 1277 |
+
"step": 5792
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 2.7304266291608066,
|
| 1281 |
+
"grad_norm": 10.875,
|
| 1282 |
+
"learning_rate": 5.070370923146855e-06,
|
| 1283 |
+
"loss": 0.1819,
|
| 1284 |
+
"step": 5824
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 2.7454289732770745,
|
| 1288 |
+
"grad_norm": 16.875,
|
| 1289 |
+
"learning_rate": 5.0180024195274555e-06,
|
| 1290 |
+
"loss": 0.1741,
|
| 1291 |
+
"step": 5856
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 2.760431317393343,
|
| 1295 |
+
"grad_norm": 12.1875,
|
| 1296 |
+
"learning_rate": 4.965631940917068e-06,
|
| 1297 |
+
"loss": 0.179,
|
| 1298 |
+
"step": 5888
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 2.775433661509611,
|
| 1302 |
+
"grad_norm": 15.0625,
|
| 1303 |
+
"learning_rate": 4.91326523272248e-06,
|
| 1304 |
+
"loss": 0.1901,
|
| 1305 |
+
"step": 5920
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 2.790436005625879,
|
| 1309 |
+
"grad_norm": 7.9375,
|
| 1310 |
+
"learning_rate": 4.860908039936839e-06,
|
| 1311 |
+
"loss": 0.2238,
|
| 1312 |
+
"step": 5952
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 2.8054383497421473,
|
| 1316 |
+
"grad_norm": 8.375,
|
| 1317 |
+
"learning_rate": 4.80856610650939e-06,
|
| 1318 |
+
"loss": 0.1826,
|
| 1319 |
+
"step": 5984
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 2.8204406938584152,
|
| 1323 |
+
"grad_norm": 12.3125,
|
| 1324 |
+
"learning_rate": 4.756245174715315e-06,
|
| 1325 |
+
"loss": 0.2012,
|
| 1326 |
+
"step": 6016
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 2.8354430379746836,
|
| 1330 |
+
"grad_norm": 12.4375,
|
| 1331 |
+
"learning_rate": 4.703950984525774e-06,
|
| 1332 |
+
"loss": 0.2342,
|
| 1333 |
+
"step": 6048
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 2.8504453820909514,
|
| 1337 |
+
"grad_norm": 10.0,
|
| 1338 |
+
"learning_rate": 4.6516892729781815e-06,
|
| 1339 |
+
"loss": 0.1805,
|
| 1340 |
+
"step": 6080
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 2.8654477262072198,
|
| 1344 |
+
"grad_norm": 17.5,
|
| 1345 |
+
"learning_rate": 4.599465773546822e-06,
|
| 1346 |
+
"loss": 0.1987,
|
| 1347 |
+
"step": 6112
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 2.880450070323488,
|
| 1351 |
+
"grad_norm": 16.625,
|
| 1352 |
+
"learning_rate": 4.547286215513846e-06,
|
| 1353 |
+
"loss": 0.1936,
|
| 1354 |
+
"step": 6144
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 2.895452414439756,
|
| 1358 |
+
"grad_norm": 10.0625,
|
| 1359 |
+
"learning_rate": 4.495156323340724e-06,
|
| 1360 |
+
"loss": 0.2244,
|
| 1361 |
+
"step": 6176
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 2.9104547585560243,
|
| 1365 |
+
"grad_norm": 7.28125,
|
| 1366 |
+
"learning_rate": 4.443081816040233e-06,
|
| 1367 |
+
"loss": 0.2456,
|
| 1368 |
+
"step": 6208
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 2.9254571026722926,
|
| 1372 |
+
"grad_norm": 11.6875,
|
| 1373 |
+
"learning_rate": 4.391068406549049e-06,
|
| 1374 |
+
"loss": 0.2125,
|
| 1375 |
+
"step": 6240
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 2.9404594467885605,
|
| 1379 |
+
"grad_norm": 12.5625,
|
| 1380 |
+
"learning_rate": 4.339121801100982e-06,
|
| 1381 |
+
"loss": 0.2383,
|
| 1382 |
+
"step": 6272
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 2.955461790904829,
|
| 1386 |
+
"grad_norm": 5.34375,
|
| 1387 |
+
"learning_rate": 4.287247698600987e-06,
|
| 1388 |
+
"loss": 0.1784,
|
| 1389 |
+
"step": 6304
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 2.970464135021097,
|
| 1393 |
+
"grad_norm": 10.3125,
|
| 1394 |
+
"learning_rate": 4.235451789999928e-06,
|
| 1395 |
+
"loss": 0.183,
|
| 1396 |
+
"step": 6336
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 2.985466479137365,
|
| 1400 |
+
"grad_norm": 13.0,
|
| 1401 |
+
"learning_rate": 4.1837397576702576e-06,
|
| 1402 |
+
"loss": 0.2395,
|
| 1403 |
+
"step": 6368
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 3.0004688232536334,
|
| 1407 |
+
"grad_norm": 14.375,
|
| 1408 |
+
"learning_rate": 4.132117274782616e-06,
|
| 1409 |
+
"loss": 0.2184,
|
| 1410 |
+
"step": 6400
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 3.0154711673699017,
|
| 1414 |
+
"grad_norm": 13.0,
|
| 1415 |
+
"learning_rate": 4.0805900046834405e-06,
|
| 1416 |
+
"loss": 0.1968,
|
| 1417 |
+
"step": 6432
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 3.0304735114861696,
|
| 1421 |
+
"grad_norm": 6.6875,
|
| 1422 |
+
"learning_rate": 4.0291636002736725e-06,
|
| 1423 |
+
"loss": 0.1868,
|
| 1424 |
+
"step": 6464
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 3.045475855602438,
|
| 1428 |
+
"grad_norm": 14.875,
|
| 1429 |
+
"learning_rate": 3.977843703388572e-06,
|
| 1430 |
+
"loss": 0.1928,
|
| 1431 |
+
"step": 6496
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 3.0604781997187063,
|
| 1435 |
+
"grad_norm": 18.375,
|
| 1436 |
+
"learning_rate": 3.926635944178788e-06,
|
| 1437 |
+
"loss": 0.1874,
|
| 1438 |
+
"step": 6528
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 3.075480543834974,
|
| 1442 |
+
"grad_norm": 12.25,
|
| 1443 |
+
"learning_rate": 3.875545940492681e-06,
|
| 1444 |
+
"loss": 0.1743,
|
| 1445 |
+
"step": 6560
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 3.0904828879512425,
|
| 1449 |
+
"grad_norm": 17.0,
|
| 1450 |
+
"learning_rate": 3.824579297260006e-06,
|
| 1451 |
+
"loss": 0.183,
|
| 1452 |
+
"step": 6592
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 3.1054852320675104,
|
| 1456 |
+
"grad_norm": 15.3125,
|
| 1457 |
+
"learning_rate": 3.773741605877026e-06,
|
| 1458 |
+
"loss": 0.2052,
|
| 1459 |
+
"step": 6624
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 3.1204875761837787,
|
| 1463 |
+
"grad_norm": 11.375,
|
| 1464 |
+
"learning_rate": 3.7230384435930785e-06,
|
| 1465 |
+
"loss": 0.1794,
|
| 1466 |
+
"step": 6656
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 3.135489920300047,
|
| 1470 |
+
"grad_norm": 12.625,
|
| 1471 |
+
"learning_rate": 3.6724753728987206e-06,
|
| 1472 |
+
"loss": 0.1562,
|
| 1473 |
+
"step": 6688
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 3.150492264416315,
|
| 1477 |
+
"grad_norm": 12.25,
|
| 1478 |
+
"learning_rate": 3.6220579409154888e-06,
|
| 1479 |
+
"loss": 0.1605,
|
| 1480 |
+
"step": 6720
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 3.1654946085325832,
|
| 1484 |
+
"grad_norm": 10.125,
|
| 1485 |
+
"learning_rate": 3.571791678787332e-06,
|
| 1486 |
+
"loss": 0.2082,
|
| 1487 |
+
"step": 6752
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 3.1804969526488516,
|
| 1491 |
+
"grad_norm": 9.5625,
|
| 1492 |
+
"learning_rate": 3.521682101073818e-06,
|
| 1493 |
+
"loss": 0.1501,
|
| 1494 |
+
"step": 6784
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 3.1954992967651195,
|
| 1498 |
+
"grad_norm": 18.0,
|
| 1499 |
+
"learning_rate": 3.471734705145138e-06,
|
| 1500 |
+
"loss": 0.1697,
|
| 1501 |
+
"step": 6816
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 3.210501640881388,
|
| 1505 |
+
"grad_norm": 15.5,
|
| 1506 |
+
"learning_rate": 3.421954970579008e-06,
|
| 1507 |
+
"loss": 0.2038,
|
| 1508 |
+
"step": 6848
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 3.2255039849976557,
|
| 1512 |
+
"grad_norm": 21.75,
|
| 1513 |
+
"learning_rate": 3.3723483585595256e-06,
|
| 1514 |
+
"loss": 0.1683,
|
| 1515 |
+
"step": 6880
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 3.240506329113924,
|
| 1519 |
+
"grad_norm": 13.5625,
|
| 1520 |
+
"learning_rate": 3.3229203112780382e-06,
|
| 1521 |
+
"loss": 0.2224,
|
| 1522 |
+
"step": 6912
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 3.2555086732301923,
|
| 1526 |
+
"grad_norm": 11.0625,
|
| 1527 |
+
"learning_rate": 3.2736762513360963e-06,
|
| 1528 |
+
"loss": 0.1734,
|
| 1529 |
+
"step": 6944
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 3.27051101734646,
|
| 1533 |
+
"grad_norm": 17.625,
|
| 1534 |
+
"learning_rate": 3.224621581150553e-06,
|
| 1535 |
+
"loss": 0.1558,
|
| 1536 |
+
"step": 6976
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 3.2855133614627285,
|
| 1540 |
+
"grad_norm": 9.6875,
|
| 1541 |
+
"learning_rate": 3.175761682360885e-06,
|
| 1542 |
+
"loss": 0.1752,
|
| 1543 |
+
"step": 7008
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 3.300515705578997,
|
| 1547 |
+
"grad_norm": 18.375,
|
| 1548 |
+
"learning_rate": 3.1271019152387917e-06,
|
| 1549 |
+
"loss": 0.1734,
|
| 1550 |
+
"step": 7040
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 3.3155180496952648,
|
| 1554 |
+
"grad_norm": 16.875,
|
| 1555 |
+
"learning_rate": 3.0786476181001263e-06,
|
| 1556 |
+
"loss": 0.1868,
|
| 1557 |
+
"step": 7072
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 3.330520393811533,
|
| 1561 |
+
"grad_norm": 10.3125,
|
| 1562 |
+
"learning_rate": 3.030404106719259e-06,
|
| 1563 |
+
"loss": 0.1976,
|
| 1564 |
+
"step": 7104
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 3.3455227379278014,
|
| 1568 |
+
"grad_norm": 16.25,
|
| 1569 |
+
"learning_rate": 2.982376673745887e-06,
|
| 1570 |
+
"loss": 0.2065,
|
| 1571 |
+
"step": 7136
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 3.3605250820440693,
|
| 1575 |
+
"grad_norm": 6.25,
|
| 1576 |
+
"learning_rate": 2.934570588124399e-06,
|
| 1577 |
+
"loss": 0.1526,
|
| 1578 |
+
"step": 7168
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 3.3755274261603376,
|
| 1582 |
+
"grad_norm": 10.9375,
|
| 1583 |
+
"learning_rate": 2.8869910945158407e-06,
|
| 1584 |
+
"loss": 0.1765,
|
| 1585 |
+
"step": 7200
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 3.390529770276606,
|
| 1589 |
+
"grad_norm": 7.375,
|
| 1590 |
+
"learning_rate": 2.839643412722525e-06,
|
| 1591 |
+
"loss": 0.1942,
|
| 1592 |
+
"step": 7232
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 3.405532114392874,
|
| 1596 |
+
"grad_norm": 9.4375,
|
| 1597 |
+
"learning_rate": 2.7925327371153998e-06,
|
| 1598 |
+
"loss": 0.1577,
|
| 1599 |
+
"step": 7264
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 3.420534458509142,
|
| 1603 |
+
"grad_norm": 8.9375,
|
| 1604 |
+
"learning_rate": 2.7456642360641772e-06,
|
| 1605 |
+
"loss": 0.2023,
|
| 1606 |
+
"step": 7296
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 3.43553680262541,
|
| 1610 |
+
"grad_norm": 11.4375,
|
| 1611 |
+
"learning_rate": 2.6990430513703316e-06,
|
| 1612 |
+
"loss": 0.2057,
|
| 1613 |
+
"step": 7328
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 3.4505391467416784,
|
| 1617 |
+
"grad_norm": 9.1875,
|
| 1618 |
+
"learning_rate": 2.6526742977030084e-06,
|
| 1619 |
+
"loss": 0.1727,
|
| 1620 |
+
"step": 7360
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 3.4655414908579467,
|
| 1624 |
+
"grad_norm": 13.8125,
|
| 1625 |
+
"learning_rate": 2.6065630620379062e-06,
|
| 1626 |
+
"loss": 0.1804,
|
| 1627 |
+
"step": 7392
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 3.4805438349742146,
|
| 1631 |
+
"grad_norm": 12.8125,
|
| 1632 |
+
"learning_rate": 2.5607144030992093e-06,
|
| 1633 |
+
"loss": 0.1589,
|
| 1634 |
+
"step": 7424
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 3.495546179090483,
|
| 1638 |
+
"grad_norm": 11.6875,
|
| 1639 |
+
"learning_rate": 2.515133350804598e-06,
|
| 1640 |
+
"loss": 0.173,
|
| 1641 |
+
"step": 7456
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 3.510548523206751,
|
| 1645 |
+
"grad_norm": 9.375,
|
| 1646 |
+
"learning_rate": 2.4698249057134377e-06,
|
| 1647 |
+
"loss": 0.1657,
|
| 1648 |
+
"step": 7488
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 3.525550867323019,
|
| 1652 |
+
"grad_norm": 19.125,
|
| 1653 |
+
"learning_rate": 2.4247940384781834e-06,
|
| 1654 |
+
"loss": 0.1833,
|
| 1655 |
+
"step": 7520
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 3.5405532114392875,
|
| 1659 |
+
"grad_norm": 12.9375,
|
| 1660 |
+
"learning_rate": 2.38004568929906e-06,
|
| 1661 |
+
"loss": 0.1743,
|
| 1662 |
+
"step": 7552
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 3.5555555555555554,
|
| 1666 |
+
"grad_norm": 12.25,
|
| 1667 |
+
"learning_rate": 2.335584767382098e-06,
|
| 1668 |
+
"loss": 0.1886,
|
| 1669 |
+
"step": 7584
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 3.5705578996718237,
|
| 1673 |
+
"grad_norm": 8.625,
|
| 1674 |
+
"learning_rate": 2.291416150400547e-06,
|
| 1675 |
+
"loss": 0.1891,
|
| 1676 |
+
"step": 7616
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 3.585560243788092,
|
| 1680 |
+
"grad_norm": 11.375,
|
| 1681 |
+
"learning_rate": 2.247544683959767e-06,
|
| 1682 |
+
"loss": 0.1598,
|
| 1683 |
+
"step": 7648
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 3.60056258790436,
|
| 1687 |
+
"grad_norm": 9.6875,
|
| 1688 |
+
"learning_rate": 2.203975181065632e-06,
|
| 1689 |
+
"loss": 0.2002,
|
| 1690 |
+
"step": 7680
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 3.6155649320206282,
|
| 1694 |
+
"grad_norm": 10.5625,
|
| 1695 |
+
"learning_rate": 2.160712421596506e-06,
|
| 1696 |
+
"loss": 0.1845,
|
| 1697 |
+
"step": 7712
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 3.6305672761368966,
|
| 1701 |
+
"grad_norm": 15.3125,
|
| 1702 |
+
"learning_rate": 2.1177611517788655e-06,
|
| 1703 |
+
"loss": 0.1477,
|
| 1704 |
+
"step": 7744
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 3.6455696202531644,
|
| 1708 |
+
"grad_norm": 12.0,
|
| 1709 |
+
"learning_rate": 2.0751260836665947e-06,
|
| 1710 |
+
"loss": 0.1685,
|
| 1711 |
+
"step": 7776
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 3.6605719643694328,
|
| 1715 |
+
"grad_norm": 7.75,
|
| 1716 |
+
"learning_rate": 2.0328118946240473e-06,
|
| 1717 |
+
"loss": 0.1954,
|
| 1718 |
+
"step": 7808
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 3.675574308485701,
|
| 1722 |
+
"grad_norm": 9.6875,
|
| 1723 |
+
"learning_rate": 1.9908232268129037e-06,
|
| 1724 |
+
"loss": 0.2078,
|
| 1725 |
+
"step": 7840
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 3.690576652601969,
|
| 1729 |
+
"grad_norm": 7.5625,
|
| 1730 |
+
"learning_rate": 1.9491646866828927e-06,
|
| 1731 |
+
"loss": 0.1719,
|
| 1732 |
+
"step": 7872
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 3.7055789967182373,
|
| 1736 |
+
"grad_norm": 20.75,
|
| 1737 |
+
"learning_rate": 1.9078408444664417e-06,
|
| 1738 |
+
"loss": 0.1844,
|
| 1739 |
+
"step": 7904
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 3.7205813408345056,
|
| 1743 |
+
"grad_norm": 11.0625,
|
| 1744 |
+
"learning_rate": 1.8668562336772734e-06,
|
| 1745 |
+
"loss": 0.2377,
|
| 1746 |
+
"step": 7936
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 3.7355836849507735,
|
| 1750 |
+
"grad_norm": 15.25,
|
| 1751 |
+
"learning_rate": 1.826215350613062e-06,
|
| 1752 |
+
"loss": 0.1571,
|
| 1753 |
+
"step": 7968
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 3.750586029067042,
|
| 1757 |
+
"grad_norm": 9.625,
|
| 1758 |
+
"learning_rate": 1.7859226538621487e-06,
|
| 1759 |
+
"loss": 0.1891,
|
| 1760 |
+
"step": 8000
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 3.7655883731833097,
|
| 1764 |
+
"grad_norm": 13.0625,
|
| 1765 |
+
"learning_rate": 1.745982563814414e-06,
|
| 1766 |
+
"loss": 0.1671,
|
| 1767 |
+
"step": 8032
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 3.780590717299578,
|
| 1771 |
+
"grad_norm": 6.34375,
|
| 1772 |
+
"learning_rate": 1.7063994621763176e-06,
|
| 1773 |
+
"loss": 0.1584,
|
| 1774 |
+
"step": 8064
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 3.795593061415846,
|
| 1778 |
+
"grad_norm": 9.0,
|
| 1779 |
+
"learning_rate": 1.6671776914902027e-06,
|
| 1780 |
+
"loss": 0.1865,
|
| 1781 |
+
"step": 8096
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 3.8105954055321143,
|
| 1785 |
+
"grad_norm": 18.625,
|
| 1786 |
+
"learning_rate": 1.6283215546578862e-06,
|
| 1787 |
+
"loss": 0.2019,
|
| 1788 |
+
"step": 8128
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 3.8255977496483826,
|
| 1792 |
+
"grad_norm": 17.375,
|
| 1793 |
+
"learning_rate": 1.5898353144686036e-06,
|
| 1794 |
+
"loss": 0.1802,
|
| 1795 |
+
"step": 8160
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 3.8406000937646505,
|
| 1799 |
+
"grad_norm": 16.0,
|
| 1800 |
+
"learning_rate": 1.5517231931313454e-06,
|
| 1801 |
+
"loss": 0.1647,
|
| 1802 |
+
"step": 8192
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 3.855602437880919,
|
| 1806 |
+
"grad_norm": 10.9375,
|
| 1807 |
+
"learning_rate": 1.513989371811656e-06,
|
| 1808 |
+
"loss": 0.1205,
|
| 1809 |
+
"step": 8224
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 3.870604781997187,
|
| 1813 |
+
"grad_norm": 9.5,
|
| 1814 |
+
"learning_rate": 1.4766379901729272e-06,
|
| 1815 |
+
"loss": 0.1919,
|
| 1816 |
+
"step": 8256
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 3.885607126113455,
|
| 1820 |
+
"grad_norm": 9.0,
|
| 1821 |
+
"learning_rate": 1.4396731459222546e-06,
|
| 1822 |
+
"loss": 0.1581,
|
| 1823 |
+
"step": 8288
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 3.9006094702297234,
|
| 1827 |
+
"grad_norm": 17.0,
|
| 1828 |
+
"learning_rate": 1.4030988943608826e-06,
|
| 1829 |
+
"loss": 0.2072,
|
| 1830 |
+
"step": 8320
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 3.9156118143459917,
|
| 1834 |
+
"grad_norm": 10.8125,
|
| 1835 |
+
"learning_rate": 1.3669192479393145e-06,
|
| 1836 |
+
"loss": 0.1677,
|
| 1837 |
+
"step": 8352
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 3.9306141584622596,
|
| 1841 |
+
"grad_norm": 11.625,
|
| 1842 |
+
"learning_rate": 1.3311381758171165e-06,
|
| 1843 |
+
"loss": 0.1702,
|
| 1844 |
+
"step": 8384
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 3.945616502578528,
|
| 1848 |
+
"grad_norm": 8.3125,
|
| 1849 |
+
"learning_rate": 1.2957596034274732e-06,
|
| 1850 |
+
"loss": 0.1901,
|
| 1851 |
+
"step": 8416
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 3.9606188466947962,
|
| 1855 |
+
"grad_norm": 11.25,
|
| 1856 |
+
"learning_rate": 1.2607874120465457e-06,
|
| 1857 |
+
"loss": 0.1804,
|
| 1858 |
+
"step": 8448
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 3.975621190811064,
|
| 1862 |
+
"grad_norm": 8.8125,
|
| 1863 |
+
"learning_rate": 1.2262254383676597e-06,
|
| 1864 |
+
"loss": 0.1606,
|
| 1865 |
+
"step": 8480
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 3.9906235349273325,
|
| 1869 |
+
"grad_norm": 15.3125,
|
| 1870 |
+
"learning_rate": 1.192077474080398e-06,
|
| 1871 |
+
"loss": 0.1913,
|
| 1872 |
+
"step": 8512
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 4.005625879043601,
|
| 1876 |
+
"grad_norm": 17.125,
|
| 1877 |
+
"learning_rate": 1.1583472654546257e-06,
|
| 1878 |
+
"loss": 0.1642,
|
| 1879 |
+
"step": 8544
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 4.020628223159869,
|
| 1883 |
+
"grad_norm": 10.9375,
|
| 1884 |
+
"learning_rate": 1.1250385129295005e-06,
|
| 1885 |
+
"loss": 0.1555,
|
| 1886 |
+
"step": 8576
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 4.035630567276137,
|
| 1890 |
+
"grad_norm": 16.125,
|
| 1891 |
+
"learning_rate": 1.0921548707075026e-06,
|
| 1892 |
+
"loss": 0.2104,
|
| 1893 |
+
"step": 8608
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 4.050632911392405,
|
| 1897 |
+
"grad_norm": 9.0,
|
| 1898 |
+
"learning_rate": 1.059699946353549e-06,
|
| 1899 |
+
"loss": 0.1725,
|
| 1900 |
+
"step": 8640
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"epoch": 4.065635255508673,
|
| 1904 |
+
"grad_norm": 12.5625,
|
| 1905 |
+
"learning_rate": 1.0276773003992157e-06,
|
| 1906 |
+
"loss": 0.1715,
|
| 1907 |
+
"step": 8672
|
| 1908 |
+
},
|
| 1909 |
+
{
|
| 1910 |
+
"epoch": 4.080637599624941,
|
| 1911 |
+
"grad_norm": 12.9375,
|
| 1912 |
+
"learning_rate": 9.96090445952121e-07,
|
| 1913 |
+
"loss": 0.1721,
|
| 1914 |
+
"step": 8704
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 4.09563994374121,
|
| 1918 |
+
"grad_norm": 11.0625,
|
| 1919 |
+
"learning_rate": 9.649428483105204e-07,
|
| 1920 |
+
"loss": 0.1912,
|
| 1921 |
+
"step": 8736
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 4.110642287857478,
|
| 1925 |
+
"grad_norm": 5.09375,
|
| 1926 |
+
"learning_rate": 9.34237924583129e-07,
|
| 1927 |
+
"loss": 0.1479,
|
| 1928 |
+
"step": 8768
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 4.125644631973746,
|
| 1932 |
+
"grad_norm": 14.25,
|
| 1933 |
+
"learning_rate": 9.039790433142481e-07,
|
| 1934 |
+
"loss": 0.2151,
|
| 1935 |
+
"step": 8800
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 4.140646976090014,
|
| 1939 |
+
"grad_norm": 13.875,
|
| 1940 |
+
"learning_rate": 8.741695241142095e-07,
|
| 1941 |
+
"loss": 0.1768,
|
| 1942 |
+
"step": 8832
|
| 1943 |
+
},
|
| 1944 |
+
{
|
| 1945 |
+
"epoch": 4.155649320206282,
|
| 1946 |
+
"grad_norm": 11.5,
|
| 1947 |
+
"learning_rate": 8.448126372951904e-07,
|
| 1948 |
+
"loss": 0.1616,
|
| 1949 |
+
"step": 8864
|
| 1950 |
+
},
|
| 1951 |
+
{
|
| 1952 |
+
"epoch": 4.17065166432255,
|
| 1953 |
+
"grad_norm": 9.1875,
|
| 1954 |
+
"learning_rate": 8.159116035124431e-07,
|
| 1955 |
+
"loss": 0.1733,
|
| 1956 |
+
"step": 8896
|
| 1957 |
+
},
|
| 1958 |
+
{
|
| 1959 |
+
"epoch": 4.185654008438819,
|
| 1960 |
+
"grad_norm": 6.46875,
|
| 1961 |
+
"learning_rate": 7.874695934109583e-07,
|
| 1962 |
+
"loss": 0.1801,
|
| 1963 |
+
"step": 8928
|
| 1964 |
+
},
|
| 1965 |
+
{
|
| 1966 |
+
"epoch": 4.200656352555087,
|
| 1967 |
+
"grad_norm": 12.375,
|
| 1968 |
+
"learning_rate": 7.594897272776275e-07,
|
| 1969 |
+
"loss": 0.1977,
|
| 1970 |
+
"step": 8960
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 4.215658696671355,
|
| 1974 |
+
"grad_norm": 16.75,
|
| 1975 |
+
"learning_rate": 7.319750746989262e-07,
|
| 1976 |
+
"loss": 0.1982,
|
| 1977 |
+
"step": 8992
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 4.2306610407876235,
|
| 1981 |
+
"grad_norm": 16.125,
|
| 1982 |
+
"learning_rate": 7.049286542241573e-07,
|
| 1983 |
+
"loss": 0.1527,
|
| 1984 |
+
"step": 9024
|
| 1985 |
+
},
|
| 1986 |
+
{
|
| 1987 |
+
"epoch": 4.245663384903891,
|
| 1988 |
+
"grad_norm": 6.84375,
|
| 1989 |
+
"learning_rate": 6.783534330342984e-07,
|
| 1990 |
+
"loss": 0.1716,
|
| 1991 |
+
"step": 9056
|
| 1992 |
+
},
|
| 1993 |
+
{
|
| 1994 |
+
"epoch": 4.260665729020159,
|
| 1995 |
+
"grad_norm": 10.1875,
|
| 1996 |
+
"learning_rate": 6.522523266164759e-07,
|
| 1997 |
+
"loss": 0.184,
|
| 1998 |
+
"step": 9088
|
| 1999 |
+
},
|
| 2000 |
+
{
|
| 2001 |
+
"epoch": 4.275668073136427,
|
| 2002 |
+
"grad_norm": 7.6875,
|
| 2003 |
+
"learning_rate": 6.266281984441214e-07,
|
| 2004 |
+
"loss": 0.1396,
|
| 2005 |
+
"step": 9120
|
| 2006 |
+
},
|
| 2007 |
+
{
|
| 2008 |
+
"epoch": 4.290670417252696,
|
| 2009 |
+
"grad_norm": 10.5625,
|
| 2010 |
+
"learning_rate": 6.014838596628225e-07,
|
| 2011 |
+
"loss": 0.1483,
|
| 2012 |
+
"step": 9152
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 4.305672761368964,
|
| 2016 |
+
"grad_norm": 10.9375,
|
| 2017 |
+
"learning_rate": 5.768220687819271e-07,
|
| 2018 |
+
"loss": 0.1754,
|
| 2019 |
+
"step": 9184
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 4.320675105485232,
|
| 2023 |
+
"grad_norm": 11.125,
|
| 2024 |
+
"learning_rate": 5.526455313719126e-07,
|
| 2025 |
+
"loss": 0.1736,
|
| 2026 |
+
"step": 9216
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 4.3356774496015005,
|
| 2030 |
+
"grad_norm": 18.125,
|
| 2031 |
+
"learning_rate": 5.289568997675643e-07,
|
| 2032 |
+
"loss": 0.1973,
|
| 2033 |
+
"step": 9248
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 4.350679793717768,
|
| 2037 |
+
"grad_norm": 12.4375,
|
| 2038 |
+
"learning_rate": 5.057587727769981e-07,
|
| 2039 |
+
"loss": 0.1786,
|
| 2040 |
+
"step": 9280
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"epoch": 4.365682137834036,
|
| 2044 |
+
"grad_norm": 6.6875,
|
| 2045 |
+
"learning_rate": 4.830536953965531e-07,
|
| 2046 |
+
"loss": 0.1549,
|
| 2047 |
+
"step": 9312
|
| 2048 |
+
},
|
| 2049 |
+
{
|
| 2050 |
+
"epoch": 4.380684481950305,
|
| 2051 |
+
"grad_norm": 14.1875,
|
| 2052 |
+
"learning_rate": 4.6084415853158537e-07,
|
| 2053 |
+
"loss": 0.1411,
|
| 2054 |
+
"step": 9344
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 4.395686826066573,
|
| 2058 |
+
"grad_norm": 26.125,
|
| 2059 |
+
"learning_rate": 4.391325987232037e-07,
|
| 2060 |
+
"loss": 0.2195,
|
| 2061 |
+
"step": 9376
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"epoch": 4.410689170182841,
|
| 2065 |
+
"grad_norm": 21.75,
|
| 2066 |
+
"learning_rate": 4.17921397880956e-07,
|
| 2067 |
+
"loss": 0.1898,
|
| 2068 |
+
"step": 9408
|
| 2069 |
+
},
|
| 2070 |
+
{
|
| 2071 |
+
"epoch": 4.42569151429911,
|
| 2072 |
+
"grad_norm": 5.0625,
|
| 2073 |
+
"learning_rate": 3.9721288302152493e-07,
|
| 2074 |
+
"loss": 0.1947,
|
| 2075 |
+
"step": 9440
|
| 2076 |
+
},
|
| 2077 |
+
{
|
| 2078 |
+
"epoch": 4.4406938584153774,
|
| 2079 |
+
"grad_norm": 12.5625,
|
| 2080 |
+
"learning_rate": 3.770093260134322e-07,
|
| 2081 |
+
"loss": 0.1821,
|
| 2082 |
+
"step": 9472
|
| 2083 |
+
},
|
| 2084 |
+
{
|
| 2085 |
+
"epoch": 4.455696202531645,
|
| 2086 |
+
"grad_norm": 10.6875,
|
| 2087 |
+
"learning_rate": 3.573129433278011e-07,
|
| 2088 |
+
"loss": 0.2005,
|
| 2089 |
+
"step": 9504
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 4.470698546647914,
|
| 2093 |
+
"grad_norm": 14.4375,
|
| 2094 |
+
"learning_rate": 3.381258957951983e-07,
|
| 2095 |
+
"loss": 0.1658,
|
| 2096 |
+
"step": 9536
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 4.485700890764182,
|
| 2100 |
+
"grad_norm": 20.625,
|
| 2101 |
+
"learning_rate": 3.194502883685663e-07,
|
| 2102 |
+
"loss": 0.2,
|
| 2103 |
+
"step": 9568
|
| 2104 |
+
},
|
| 2105 |
+
{
|
| 2106 |
+
"epoch": 4.50070323488045,
|
| 2107 |
+
"grad_norm": 9.625,
|
| 2108 |
+
"learning_rate": 3.0128816989230315e-07,
|
| 2109 |
+
"loss": 0.1681,
|
| 2110 |
+
"step": 9600
|
| 2111 |
+
},
|
| 2112 |
+
{
|
| 2113 |
+
"epoch": 4.515705578996718,
|
| 2114 |
+
"grad_norm": 5.03125,
|
| 2115 |
+
"learning_rate": 2.836415328774872e-07,
|
| 2116 |
+
"loss": 0.1757,
|
| 2117 |
+
"step": 9632
|
| 2118 |
+
},
|
| 2119 |
+
{
|
| 2120 |
+
"epoch": 4.5307079231129865,
|
| 2121 |
+
"grad_norm": 8.5625,
|
| 2122 |
+
"learning_rate": 2.665123132832842e-07,
|
| 2123 |
+
"loss": 0.1635,
|
| 2124 |
+
"step": 9664
|
| 2125 |
+
},
|
| 2126 |
+
{
|
| 2127 |
+
"epoch": 4.545710267229254,
|
| 2128 |
+
"grad_norm": 13.125,
|
| 2129 |
+
"learning_rate": 2.499023903045622e-07,
|
| 2130 |
+
"loss": 0.2215,
|
| 2131 |
+
"step": 9696
|
| 2132 |
+
},
|
| 2133 |
+
{
|
| 2134 |
+
"epoch": 4.560712611345522,
|
| 2135 |
+
"grad_norm": 10.3125,
|
| 2136 |
+
"learning_rate": 2.3381358616572593e-07,
|
| 2137 |
+
"loss": 0.1952,
|
| 2138 |
+
"step": 9728
|
| 2139 |
+
},
|
| 2140 |
+
{
|
| 2141 |
+
"epoch": 4.575714955461791,
|
| 2142 |
+
"grad_norm": 5.40625,
|
| 2143 |
+
"learning_rate": 2.1824766592080937e-07,
|
| 2144 |
+
"loss": 0.1618,
|
| 2145 |
+
"step": 9760
|
| 2146 |
+
},
|
| 2147 |
+
{
|
| 2148 |
+
"epoch": 4.590717299578059,
|
| 2149 |
+
"grad_norm": 20.625,
|
| 2150 |
+
"learning_rate": 2.0320633725983641e-07,
|
| 2151 |
+
"loss": 0.1983,
|
| 2152 |
+
"step": 9792
|
| 2153 |
+
},
|
| 2154 |
+
{
|
| 2155 |
+
"epoch": 4.605719643694327,
|
| 2156 |
+
"grad_norm": 14.25,
|
| 2157 |
+
"learning_rate": 1.8869125032147384e-07,
|
| 2158 |
+
"loss": 0.1992,
|
| 2159 |
+
"step": 9824
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 4.620721987810596,
|
| 2163 |
+
"grad_norm": 12.1875,
|
| 2164 |
+
"learning_rate": 1.747039975120035e-07,
|
| 2165 |
+
"loss": 0.1966,
|
| 2166 |
+
"step": 9856
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"epoch": 4.6357243319268635,
|
| 2170 |
+
"grad_norm": 15.125,
|
| 2171 |
+
"learning_rate": 1.6124611333062036e-07,
|
| 2172 |
+
"loss": 0.1652,
|
| 2173 |
+
"step": 9888
|
| 2174 |
+
},
|
| 2175 |
+
{
|
| 2176 |
+
"epoch": 4.650726676043131,
|
| 2177 |
+
"grad_norm": 11.5625,
|
| 2178 |
+
"learning_rate": 1.4831907420108705e-07,
|
| 2179 |
+
"loss": 0.1459,
|
| 2180 |
+
"step": 9920
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 4.6657290201594,
|
| 2184 |
+
"grad_norm": 11.125,
|
| 2185 |
+
"learning_rate": 1.3592429830976362e-07,
|
| 2186 |
+
"loss": 0.1759,
|
| 2187 |
+
"step": 9952
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 4.680731364275668,
|
| 2191 |
+
"grad_norm": 11.0625,
|
| 2192 |
+
"learning_rate": 1.2406314545001795e-07,
|
| 2193 |
+
"loss": 0.152,
|
| 2194 |
+
"step": 9984
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 4.695733708391936,
|
| 2198 |
+
"grad_norm": 12.0,
|
| 2199 |
+
"learning_rate": 1.1273691687305299e-07,
|
| 2200 |
+
"loss": 0.1946,
|
| 2201 |
+
"step": 10016
|
| 2202 |
+
},
|
| 2203 |
+
{
|
| 2204 |
+
"epoch": 4.710736052508205,
|
| 2205 |
+
"grad_norm": 13.0,
|
| 2206 |
+
"learning_rate": 1.0194685514514302e-07,
|
| 2207 |
+
"loss": 0.1786,
|
| 2208 |
+
"step": 10048
|
| 2209 |
+
},
|
| 2210 |
+
{
|
| 2211 |
+
"epoch": 4.725738396624473,
|
| 2212 |
+
"grad_norm": 5.3125,
|
| 2213 |
+
"learning_rate": 9.16941440113206e-08,
|
| 2214 |
+
"loss": 0.1709,
|
| 2215 |
+
"step": 10080
|
| 2216 |
+
},
|
| 2217 |
+
{
|
| 2218 |
+
"epoch": 4.7407407407407405,
|
| 2219 |
+
"grad_norm": 8.4375,
|
| 2220 |
+
"learning_rate": 8.197990826551094e-08,
|
| 2221 |
+
"loss": 0.1554,
|
| 2222 |
+
"step": 10112
|
| 2223 |
+
},
|
| 2224 |
+
{
|
| 2225 |
+
"epoch": 4.755743084857009,
|
| 2226 |
+
"grad_norm": 14.125,
|
| 2227 |
+
"learning_rate": 7.280521362713122e-08,
|
| 2228 |
+
"loss": 0.1948,
|
| 2229 |
+
"step": 10144
|
| 2230 |
+
},
|
| 2231 |
+
{
|
| 2232 |
+
"epoch": 4.770745428973277,
|
| 2233 |
+
"grad_norm": 14.375,
|
| 2234 |
+
"learning_rate": 6.417106662417849e-08,
|
| 2235 |
+
"loss": 0.1493,
|
| 2236 |
+
"step": 10176
|
| 2237 |
+
},
|
| 2238 |
+
{
|
| 2239 |
+
"epoch": 4.785747773089545,
|
| 2240 |
+
"grad_norm": 13.0,
|
| 2241 |
+
"learning_rate": 5.607841448280194e-08,
|
| 2242 |
+
"loss": 0.1867,
|
| 2243 |
+
"step": 10208
|
| 2244 |
+
},
|
| 2245 |
+
{
|
| 2246 |
+
"epoch": 4.800750117205814,
|
| 2247 |
+
"grad_norm": 7.875,
|
| 2248 |
+
"learning_rate": 4.852814502338765e-08,
|
| 2249 |
+
"loss": 0.1832,
|
| 2250 |
+
"step": 10240
|
| 2251 |
+
},
|
| 2252 |
+
{
|
| 2253 |
+
"epoch": 4.815752461322082,
|
| 2254 |
+
"grad_norm": 9.6875,
|
| 2255 |
+
"learning_rate": 4.1521086563159344e-08,
|
| 2256 |
+
"loss": 0.1793,
|
| 2257 |
+
"step": 10272
|
| 2258 |
+
},
|
| 2259 |
+
{
|
| 2260 |
+
"epoch": 4.83075480543835,
|
| 2261 |
+
"grad_norm": 8.125,
|
| 2262 |
+
"learning_rate": 3.5058007825303774e-08,
|
| 2263 |
+
"loss": 0.1727,
|
| 2264 |
+
"step": 10304
|
| 2265 |
+
},
|
| 2266 |
+
{
|
| 2267 |
+
"epoch": 4.845757149554618,
|
| 2268 |
+
"grad_norm": 9.75,
|
| 2269 |
+
"learning_rate": 2.9139617854639368e-08,
|
| 2270 |
+
"loss": 0.1745,
|
| 2271 |
+
"step": 10336
|
| 2272 |
+
},
|
| 2273 |
+
{
|
| 2274 |
+
"epoch": 4.860759493670886,
|
| 2275 |
+
"grad_norm": 15.3125,
|
| 2276 |
+
"learning_rate": 2.3766565939826734e-08,
|
| 2277 |
+
"loss": 0.1869,
|
| 2278 |
+
"step": 10368
|
| 2279 |
+
},
|
| 2280 |
+
{
|
| 2281 |
+
"epoch": 4.875761837787154,
|
| 2282 |
+
"grad_norm": 3.84375,
|
| 2283 |
+
"learning_rate": 1.8939441542138448e-08,
|
| 2284 |
+
"loss": 0.1436,
|
| 2285 |
+
"step": 10400
|
| 2286 |
+
},
|
| 2287 |
+
{
|
| 2288 |
+
"epoch": 4.890764181903423,
|
| 2289 |
+
"grad_norm": 10.6875,
|
| 2290 |
+
"learning_rate": 1.4658774230789653e-08,
|
| 2291 |
+
"loss": 0.1762,
|
| 2292 |
+
"step": 10432
|
| 2293 |
+
},
|
| 2294 |
+
{
|
| 2295 |
+
"epoch": 4.905766526019691,
|
| 2296 |
+
"grad_norm": 8.75,
|
| 2297 |
+
"learning_rate": 1.0925033624842874e-08,
|
| 2298 |
+
"loss": 0.1635,
|
| 2299 |
+
"step": 10464
|
| 2300 |
+
},
|
| 2301 |
+
{
|
| 2302 |
+
"epoch": 4.920768870135959,
|
| 2303 |
+
"grad_norm": 17.75,
|
| 2304 |
+
"learning_rate": 7.73862934168479e-09,
|
| 2305 |
+
"loss": 0.171,
|
| 2306 |
+
"step": 10496
|
| 2307 |
+
},
|
| 2308 |
+
{
|
| 2309 |
+
"epoch": 4.9357712142522265,
|
| 2310 |
+
"grad_norm": 18.875,
|
| 2311 |
+
"learning_rate": 5.099910952091059e-09,
|
| 2312 |
+
"loss": 0.1919,
|
| 2313 |
+
"step": 10528
|
| 2314 |
+
},
|
| 2315 |
+
{
|
| 2316 |
+
"epoch": 4.950773558368495,
|
| 2317 |
+
"grad_norm": 11.6875,
|
| 2318 |
+
"learning_rate": 3.0091679418742248e-09,
|
| 2319 |
+
"loss": 0.171,
|
| 2320 |
+
"step": 10560
|
| 2321 |
+
},
|
| 2322 |
+
{
|
| 2323 |
+
"epoch": 4.965775902484763,
|
| 2324 |
+
"grad_norm": 13.0,
|
| 2325 |
+
"learning_rate": 1.4666296801252312e-09,
|
| 2326 |
+
"loss": 0.171,
|
| 2327 |
+
"step": 10592
|
| 2328 |
+
},
|
| 2329 |
+
{
|
| 2330 |
+
"epoch": 4.980778246601031,
|
| 2331 |
+
"grad_norm": 16.625,
|
| 2332 |
+
"learning_rate": 4.724653940513246e-10,
|
| 2333 |
+
"loss": 0.1232,
|
| 2334 |
+
"step": 10624
|
| 2335 |
+
},
|
| 2336 |
+
{
|
| 2337 |
+
"epoch": 4.9957805907173,
|
| 2338 |
+
"grad_norm": 8.75,
|
| 2339 |
+
"learning_rate": 2.6784150408132315e-11,
|
| 2340 |
+
"loss": 0.2079,
|
| 2341 |
+
"step": 10656
|
| 2342 |
+
},
|
| 2343 |
+
{
|
| 2344 |
+
"epoch": 5.0,
|
| 2345 |
+
"step": 10665,
|
| 2346 |
+
"total_flos": 5.821442357117952e+16,
|
| 2347 |
+
"train_loss": 0.25197240614410416,
|
| 2348 |
+
"train_runtime": 2509.3883,
|
| 2349 |
+
"train_samples_per_second": 4.25,
|
| 2350 |
+
"train_steps_per_second": 4.25
|
| 2351 |
+
}
|
| 2352 |
+
],
|
| 2353 |
+
"logging_steps": 32,
|
| 2354 |
+
"max_steps": 10665,
|
| 2355 |
+
"num_input_tokens_seen": 0,
|
| 2356 |
+
"num_train_epochs": 5,
|
| 2357 |
+
"save_steps": 500,
|
| 2358 |
+
"stateful_callbacks": {
|
| 2359 |
+
"TrainerControl": {
|
| 2360 |
+
"args": {
|
| 2361 |
+
"should_epoch_stop": false,
|
| 2362 |
+
"should_evaluate": false,
|
| 2363 |
+
"should_log": false,
|
| 2364 |
+
"should_save": false,
|
| 2365 |
+
"should_training_stop": false
|
| 2366 |
+
},
|
| 2367 |
+
"attributes": {}
|
| 2368 |
+
}
|
| 2369 |
+
},
|
| 2370 |
+
"total_flos": 5.821442357117952e+16,
|
| 2371 |
+
"train_batch_size": 1,
|
| 2372 |
+
"trial_name": null,
|
| 2373 |
+
"trial_params": null
|
| 2374 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f4b5a0596f69c36c817bc8ef2e691198efaac8582886cf9c78a9a31998d46bf9
|
| 3 |
+
size 5777
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|