Upload model
Browse files- .gitattributes +1 -0
- added_tokens.json +24 -0
- chat_template.jinja +54 -0
- config.json +58 -0
- generation_config.json +6 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- special_tokens_map.json +32 -0
- tokenizer.json +3 -0
- tokenizer_config.json +198 -0
- trainer_state.json +2815 -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": "4.55.2",
|
| 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": "4.55.2"
|
| 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:aa2d2a2a9f9d568743895af4554f02c72f5924c88f3ed1e2b2ade9aae88ad961
|
| 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 +1,2815 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 3.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 12699,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.007559650366170565,
|
| 14 |
+
"grad_norm": 30.625,
|
| 15 |
+
"learning_rate": 2.4409448818897637e-07,
|
| 16 |
+
"loss": 0.997,
|
| 17 |
+
"step": 32
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.01511930073234113,
|
| 21 |
+
"grad_norm": 22.75,
|
| 22 |
+
"learning_rate": 4.960629921259843e-07,
|
| 23 |
+
"loss": 1.0127,
|
| 24 |
+
"step": 64
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.022678951098511695,
|
| 28 |
+
"grad_norm": 15.875,
|
| 29 |
+
"learning_rate": 7.480314960629922e-07,
|
| 30 |
+
"loss": 0.9785,
|
| 31 |
+
"step": 96
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.03023860146468226,
|
| 35 |
+
"grad_norm": 19.125,
|
| 36 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 37 |
+
"loss": 0.8948,
|
| 38 |
+
"step": 128
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.03779825183085282,
|
| 42 |
+
"grad_norm": 13.25,
|
| 43 |
+
"learning_rate": 1.251968503937008e-06,
|
| 44 |
+
"loss": 0.9001,
|
| 45 |
+
"step": 160
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.04535790219702339,
|
| 49 |
+
"grad_norm": 10.0,
|
| 50 |
+
"learning_rate": 1.5039370078740158e-06,
|
| 51 |
+
"loss": 0.9018,
|
| 52 |
+
"step": 192
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.05291755256319395,
|
| 56 |
+
"grad_norm": 9.5,
|
| 57 |
+
"learning_rate": 1.7559055118110239e-06,
|
| 58 |
+
"loss": 0.8796,
|
| 59 |
+
"step": 224
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.06047720292936452,
|
| 63 |
+
"grad_norm": 9.8125,
|
| 64 |
+
"learning_rate": 2.007874015748032e-06,
|
| 65 |
+
"loss": 0.7863,
|
| 66 |
+
"step": 256
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.06803685329553508,
|
| 70 |
+
"grad_norm": 13.125,
|
| 71 |
+
"learning_rate": 2.2598425196850397e-06,
|
| 72 |
+
"loss": 0.7503,
|
| 73 |
+
"step": 288
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.07559650366170564,
|
| 77 |
+
"grad_norm": 7.46875,
|
| 78 |
+
"learning_rate": 2.511811023622047e-06,
|
| 79 |
+
"loss": 0.7361,
|
| 80 |
+
"step": 320
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.08315615402787621,
|
| 84 |
+
"grad_norm": 10.125,
|
| 85 |
+
"learning_rate": 2.763779527559055e-06,
|
| 86 |
+
"loss": 0.7236,
|
| 87 |
+
"step": 352
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.09071580439404678,
|
| 91 |
+
"grad_norm": 8.6875,
|
| 92 |
+
"learning_rate": 3.015748031496063e-06,
|
| 93 |
+
"loss": 0.7074,
|
| 94 |
+
"step": 384
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.09827545476021735,
|
| 98 |
+
"grad_norm": 10.0625,
|
| 99 |
+
"learning_rate": 3.267716535433071e-06,
|
| 100 |
+
"loss": 0.7418,
|
| 101 |
+
"step": 416
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.1058351051263879,
|
| 105 |
+
"grad_norm": 17.25,
|
| 106 |
+
"learning_rate": 3.519685039370079e-06,
|
| 107 |
+
"loss": 0.6522,
|
| 108 |
+
"step": 448
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.11339475549255847,
|
| 112 |
+
"grad_norm": 4.8125,
|
| 113 |
+
"learning_rate": 3.7716535433070867e-06,
|
| 114 |
+
"loss": 0.6596,
|
| 115 |
+
"step": 480
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.12095440585872903,
|
| 119 |
+
"grad_norm": 9.375,
|
| 120 |
+
"learning_rate": 4.0236220472440945e-06,
|
| 121 |
+
"loss": 0.6762,
|
| 122 |
+
"step": 512
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.1285140562248996,
|
| 126 |
+
"grad_norm": 7.6875,
|
| 127 |
+
"learning_rate": 4.275590551181103e-06,
|
| 128 |
+
"loss": 0.6657,
|
| 129 |
+
"step": 544
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.13607370659107015,
|
| 133 |
+
"grad_norm": 11.4375,
|
| 134 |
+
"learning_rate": 4.52755905511811e-06,
|
| 135 |
+
"loss": 0.5974,
|
| 136 |
+
"step": 576
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.14363335695724072,
|
| 140 |
+
"grad_norm": 6.3125,
|
| 141 |
+
"learning_rate": 4.779527559055118e-06,
|
| 142 |
+
"loss": 0.6177,
|
| 143 |
+
"step": 608
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.1511930073234113,
|
| 147 |
+
"grad_norm": 16.75,
|
| 148 |
+
"learning_rate": 5.031496062992126e-06,
|
| 149 |
+
"loss": 0.5999,
|
| 150 |
+
"step": 640
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.15875265768958186,
|
| 154 |
+
"grad_norm": 11.625,
|
| 155 |
+
"learning_rate": 5.283464566929134e-06,
|
| 156 |
+
"loss": 0.5413,
|
| 157 |
+
"step": 672
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.16631230805575242,
|
| 161 |
+
"grad_norm": 6.46875,
|
| 162 |
+
"learning_rate": 5.535433070866142e-06,
|
| 163 |
+
"loss": 0.5589,
|
| 164 |
+
"step": 704
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.173871958421923,
|
| 168 |
+
"grad_norm": 8.6875,
|
| 169 |
+
"learning_rate": 5.78740157480315e-06,
|
| 170 |
+
"loss": 0.5491,
|
| 171 |
+
"step": 736
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.18143160878809356,
|
| 175 |
+
"grad_norm": 15.375,
|
| 176 |
+
"learning_rate": 6.039370078740158e-06,
|
| 177 |
+
"loss": 0.523,
|
| 178 |
+
"step": 768
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.18899125915426412,
|
| 182 |
+
"grad_norm": 6.875,
|
| 183 |
+
"learning_rate": 6.291338582677165e-06,
|
| 184 |
+
"loss": 0.5444,
|
| 185 |
+
"step": 800
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.1965509095204347,
|
| 189 |
+
"grad_norm": 24.375,
|
| 190 |
+
"learning_rate": 6.543307086614174e-06,
|
| 191 |
+
"loss": 0.5077,
|
| 192 |
+
"step": 832
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.20411055988660523,
|
| 196 |
+
"grad_norm": 7.21875,
|
| 197 |
+
"learning_rate": 6.795275590551181e-06,
|
| 198 |
+
"loss": 0.4579,
|
| 199 |
+
"step": 864
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.2116702102527758,
|
| 203 |
+
"grad_norm": 11.5625,
|
| 204 |
+
"learning_rate": 7.047244094488189e-06,
|
| 205 |
+
"loss": 0.4787,
|
| 206 |
+
"step": 896
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.21922986061894637,
|
| 210 |
+
"grad_norm": 7.84375,
|
| 211 |
+
"learning_rate": 7.2992125984251975e-06,
|
| 212 |
+
"loss": 0.4627,
|
| 213 |
+
"step": 928
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.22678951098511693,
|
| 217 |
+
"grad_norm": 7.53125,
|
| 218 |
+
"learning_rate": 7.551181102362205e-06,
|
| 219 |
+
"loss": 0.4694,
|
| 220 |
+
"step": 960
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.2343491613512875,
|
| 224 |
+
"grad_norm": 9.6875,
|
| 225 |
+
"learning_rate": 7.803149606299213e-06,
|
| 226 |
+
"loss": 0.4959,
|
| 227 |
+
"step": 992
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.24190881171745807,
|
| 231 |
+
"grad_norm": 9.4375,
|
| 232 |
+
"learning_rate": 8.055118110236221e-06,
|
| 233 |
+
"loss": 0.4708,
|
| 234 |
+
"step": 1024
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.24946846208362863,
|
| 238 |
+
"grad_norm": 8.875,
|
| 239 |
+
"learning_rate": 8.307086614173228e-06,
|
| 240 |
+
"loss": 0.4513,
|
| 241 |
+
"step": 1056
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.2570281124497992,
|
| 245 |
+
"grad_norm": 6.9375,
|
| 246 |
+
"learning_rate": 8.559055118110236e-06,
|
| 247 |
+
"loss": 0.4668,
|
| 248 |
+
"step": 1088
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.26458776281596974,
|
| 252 |
+
"grad_norm": 10.8125,
|
| 253 |
+
"learning_rate": 8.811023622047244e-06,
|
| 254 |
+
"loss": 0.4413,
|
| 255 |
+
"step": 1120
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.2721474131821403,
|
| 259 |
+
"grad_norm": 6.78125,
|
| 260 |
+
"learning_rate": 9.062992125984253e-06,
|
| 261 |
+
"loss": 0.4229,
|
| 262 |
+
"step": 1152
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.2797070635483109,
|
| 266 |
+
"grad_norm": 8.3125,
|
| 267 |
+
"learning_rate": 9.314960629921261e-06,
|
| 268 |
+
"loss": 0.4487,
|
| 269 |
+
"step": 1184
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.28726671391448144,
|
| 273 |
+
"grad_norm": 7.28125,
|
| 274 |
+
"learning_rate": 9.566929133858268e-06,
|
| 275 |
+
"loss": 0.4379,
|
| 276 |
+
"step": 1216
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.294826364280652,
|
| 280 |
+
"grad_norm": 7.375,
|
| 281 |
+
"learning_rate": 9.818897637795276e-06,
|
| 282 |
+
"loss": 0.4577,
|
| 283 |
+
"step": 1248
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.3023860146468226,
|
| 287 |
+
"grad_norm": 7.71875,
|
| 288 |
+
"learning_rate": 9.999984699413235e-06,
|
| 289 |
+
"loss": 0.4738,
|
| 290 |
+
"step": 1280
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.30994566501299314,
|
| 294 |
+
"grad_norm": 4.875,
|
| 295 |
+
"learning_rate": 9.999682468799545e-06,
|
| 296 |
+
"loss": 0.4452,
|
| 297 |
+
"step": 1312
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.3175053153791637,
|
| 301 |
+
"grad_norm": 8.3125,
|
| 302 |
+
"learning_rate": 9.998993405770503e-06,
|
| 303 |
+
"loss": 0.4617,
|
| 304 |
+
"step": 1344
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.3250649657453343,
|
| 308 |
+
"grad_norm": 7.21875,
|
| 309 |
+
"learning_rate": 9.997917563639873e-06,
|
| 310 |
+
"loss": 0.4511,
|
| 311 |
+
"step": 1376
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.33262461611150484,
|
| 315 |
+
"grad_norm": 5.78125,
|
| 316 |
+
"learning_rate": 9.99645502564707e-06,
|
| 317 |
+
"loss": 0.4646,
|
| 318 |
+
"step": 1408
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.3401842664776754,
|
| 322 |
+
"grad_norm": 7.21875,
|
| 323 |
+
"learning_rate": 9.994605904950693e-06,
|
| 324 |
+
"loss": 0.4219,
|
| 325 |
+
"step": 1440
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.347743916843846,
|
| 329 |
+
"grad_norm": 8.75,
|
| 330 |
+
"learning_rate": 9.992370344619799e-06,
|
| 331 |
+
"loss": 0.4755,
|
| 332 |
+
"step": 1472
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.35530356721001655,
|
| 336 |
+
"grad_norm": 5.59375,
|
| 337 |
+
"learning_rate": 9.98974851762281e-06,
|
| 338 |
+
"loss": 0.4415,
|
| 339 |
+
"step": 1504
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.3628632175761871,
|
| 343 |
+
"grad_norm": 10.8125,
|
| 344 |
+
"learning_rate": 9.986740626814144e-06,
|
| 345 |
+
"loss": 0.4628,
|
| 346 |
+
"step": 1536
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.3704228679423577,
|
| 350 |
+
"grad_norm": 5.71875,
|
| 351 |
+
"learning_rate": 9.983346904918514e-06,
|
| 352 |
+
"loss": 0.4241,
|
| 353 |
+
"step": 1568
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.37798251830852825,
|
| 357 |
+
"grad_norm": 7.40625,
|
| 358 |
+
"learning_rate": 9.97956761451292e-06,
|
| 359 |
+
"loss": 0.4183,
|
| 360 |
+
"step": 1600
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.3855421686746988,
|
| 364 |
+
"grad_norm": 4.71875,
|
| 365 |
+
"learning_rate": 9.975403048006342e-06,
|
| 366 |
+
"loss": 0.46,
|
| 367 |
+
"step": 1632
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.3931018190408694,
|
| 371 |
+
"grad_norm": 6.625,
|
| 372 |
+
"learning_rate": 9.970853527617105e-06,
|
| 373 |
+
"loss": 0.4349,
|
| 374 |
+
"step": 1664
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.40066146940703995,
|
| 378 |
+
"grad_norm": 11.3125,
|
| 379 |
+
"learning_rate": 9.965919405347958e-06,
|
| 380 |
+
"loss": 0.4359,
|
| 381 |
+
"step": 1696
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.40822111977321046,
|
| 385 |
+
"grad_norm": 6.5625,
|
| 386 |
+
"learning_rate": 9.960601062958833e-06,
|
| 387 |
+
"loss": 0.4228,
|
| 388 |
+
"step": 1728
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.41578077013938103,
|
| 392 |
+
"grad_norm": 6.75,
|
| 393 |
+
"learning_rate": 9.954898911937302e-06,
|
| 394 |
+
"loss": 0.4545,
|
| 395 |
+
"step": 1760
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.4233404205055516,
|
| 399 |
+
"grad_norm": 7.375,
|
| 400 |
+
"learning_rate": 9.94881339346676e-06,
|
| 401 |
+
"loss": 0.4468,
|
| 402 |
+
"step": 1792
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.43090007087172216,
|
| 406 |
+
"grad_norm": 7.0625,
|
| 407 |
+
"learning_rate": 9.942344978392267e-06,
|
| 408 |
+
"loss": 0.4355,
|
| 409 |
+
"step": 1824
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.43845972123789273,
|
| 413 |
+
"grad_norm": 6.21875,
|
| 414 |
+
"learning_rate": 9.935494167184133e-06,
|
| 415 |
+
"loss": 0.4563,
|
| 416 |
+
"step": 1856
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.4460193716040633,
|
| 420 |
+
"grad_norm": 7.34375,
|
| 421 |
+
"learning_rate": 9.928261489899187e-06,
|
| 422 |
+
"loss": 0.4273,
|
| 423 |
+
"step": 1888
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.45357902197023386,
|
| 427 |
+
"grad_norm": 6.40625,
|
| 428 |
+
"learning_rate": 9.920647506139774e-06,
|
| 429 |
+
"loss": 0.4072,
|
| 430 |
+
"step": 1920
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.46113867233640443,
|
| 434 |
+
"grad_norm": 5.25,
|
| 435 |
+
"learning_rate": 9.912652805010451e-06,
|
| 436 |
+
"loss": 0.4216,
|
| 437 |
+
"step": 1952
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.468698322702575,
|
| 441 |
+
"grad_norm": 5.9375,
|
| 442 |
+
"learning_rate": 9.90427800507241e-06,
|
| 443 |
+
"loss": 0.4853,
|
| 444 |
+
"step": 1984
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.47625797306874557,
|
| 448 |
+
"grad_norm": 6.625,
|
| 449 |
+
"learning_rate": 9.89552375429562e-06,
|
| 450 |
+
"loss": 0.4452,
|
| 451 |
+
"step": 2016
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.48381762343491613,
|
| 455 |
+
"grad_norm": 4.875,
|
| 456 |
+
"learning_rate": 9.886390730008688e-06,
|
| 457 |
+
"loss": 0.4505,
|
| 458 |
+
"step": 2048
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.4913772738010867,
|
| 462 |
+
"grad_norm": 8.9375,
|
| 463 |
+
"learning_rate": 9.87687963884646e-06,
|
| 464 |
+
"loss": 0.4279,
|
| 465 |
+
"step": 2080
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.49893692416725727,
|
| 469 |
+
"grad_norm": 4.46875,
|
| 470 |
+
"learning_rate": 9.86699121669534e-06,
|
| 471 |
+
"loss": 0.4225,
|
| 472 |
+
"step": 2112
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.5064965745334278,
|
| 476 |
+
"grad_norm": 4.75,
|
| 477 |
+
"learning_rate": 9.856726228636364e-06,
|
| 478 |
+
"loss": 0.4333,
|
| 479 |
+
"step": 2144
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.5140562248995983,
|
| 483 |
+
"grad_norm": 7.78125,
|
| 484 |
+
"learning_rate": 9.846085468885994e-06,
|
| 485 |
+
"loss": 0.4262,
|
| 486 |
+
"step": 2176
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.5216158752657689,
|
| 490 |
+
"grad_norm": 6.78125,
|
| 491 |
+
"learning_rate": 9.835069760734673e-06,
|
| 492 |
+
"loss": 0.4474,
|
| 493 |
+
"step": 2208
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.5291755256319395,
|
| 497 |
+
"grad_norm": 7.25,
|
| 498 |
+
"learning_rate": 9.823679956483122e-06,
|
| 499 |
+
"loss": 0.436,
|
| 500 |
+
"step": 2240
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.53673517599811,
|
| 504 |
+
"grad_norm": 5.71875,
|
| 505 |
+
"learning_rate": 9.81191693737641e-06,
|
| 506 |
+
"loss": 0.4293,
|
| 507 |
+
"step": 2272
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.5442948263642806,
|
| 511 |
+
"grad_norm": 7.84375,
|
| 512 |
+
"learning_rate": 9.799781613535747e-06,
|
| 513 |
+
"loss": 0.4253,
|
| 514 |
+
"step": 2304
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.5518544767304512,
|
| 518 |
+
"grad_norm": 5.875,
|
| 519 |
+
"learning_rate": 9.787274923888093e-06,
|
| 520 |
+
"loss": 0.4385,
|
| 521 |
+
"step": 2336
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.5594141270966217,
|
| 525 |
+
"grad_norm": 7.5625,
|
| 526 |
+
"learning_rate": 9.774397836093487e-06,
|
| 527 |
+
"loss": 0.4349,
|
| 528 |
+
"step": 2368
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.5669737774627923,
|
| 532 |
+
"grad_norm": 5.09375,
|
| 533 |
+
"learning_rate": 9.761151346470204e-06,
|
| 534 |
+
"loss": 0.3955,
|
| 535 |
+
"step": 2400
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.5745334278289629,
|
| 539 |
+
"grad_norm": 8.6875,
|
| 540 |
+
"learning_rate": 9.747536479917643e-06,
|
| 541 |
+
"loss": 0.4272,
|
| 542 |
+
"step": 2432
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.5820930781951335,
|
| 546 |
+
"grad_norm": 5.5625,
|
| 547 |
+
"learning_rate": 9.733554289837041e-06,
|
| 548 |
+
"loss": 0.4269,
|
| 549 |
+
"step": 2464
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.589652728561304,
|
| 553 |
+
"grad_norm": 6.40625,
|
| 554 |
+
"learning_rate": 9.719205858049978e-06,
|
| 555 |
+
"loss": 0.4676,
|
| 556 |
+
"step": 2496
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.5972123789274746,
|
| 560 |
+
"grad_norm": 3.578125,
|
| 561 |
+
"learning_rate": 9.704492294714658e-06,
|
| 562 |
+
"loss": 0.4336,
|
| 563 |
+
"step": 2528
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.6047720292936452,
|
| 567 |
+
"grad_norm": 8.4375,
|
| 568 |
+
"learning_rate": 9.689414738240026e-06,
|
| 569 |
+
"loss": 0.4546,
|
| 570 |
+
"step": 2560
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.6123316796598157,
|
| 574 |
+
"grad_norm": 6.65625,
|
| 575 |
+
"learning_rate": 9.673974355197684e-06,
|
| 576 |
+
"loss": 0.3893,
|
| 577 |
+
"step": 2592
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.6198913300259863,
|
| 581 |
+
"grad_norm": 6.78125,
|
| 582 |
+
"learning_rate": 9.658172340231636e-06,
|
| 583 |
+
"loss": 0.4525,
|
| 584 |
+
"step": 2624
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.6274509803921569,
|
| 588 |
+
"grad_norm": 5.78125,
|
| 589 |
+
"learning_rate": 9.642009915965844e-06,
|
| 590 |
+
"loss": 0.4303,
|
| 591 |
+
"step": 2656
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.6350106307583274,
|
| 595 |
+
"grad_norm": 6.125,
|
| 596 |
+
"learning_rate": 9.625488332909649e-06,
|
| 597 |
+
"loss": 0.4332,
|
| 598 |
+
"step": 2688
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.642570281124498,
|
| 602 |
+
"grad_norm": 20.375,
|
| 603 |
+
"learning_rate": 9.608608869361008e-06,
|
| 604 |
+
"loss": 0.4497,
|
| 605 |
+
"step": 2720
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.6501299314906686,
|
| 609 |
+
"grad_norm": 7.09375,
|
| 610 |
+
"learning_rate": 9.59137283130759e-06,
|
| 611 |
+
"loss": 0.4172,
|
| 612 |
+
"step": 2752
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.6576895818568391,
|
| 616 |
+
"grad_norm": 5.09375,
|
| 617 |
+
"learning_rate": 9.573781552325732e-06,
|
| 618 |
+
"loss": 0.4705,
|
| 619 |
+
"step": 2784
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.6652492322230097,
|
| 623 |
+
"grad_norm": 6.625,
|
| 624 |
+
"learning_rate": 9.555836393477254e-06,
|
| 625 |
+
"loss": 0.4326,
|
| 626 |
+
"step": 2816
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.6728088825891803,
|
| 630 |
+
"grad_norm": 5.0,
|
| 631 |
+
"learning_rate": 9.537538743204164e-06,
|
| 632 |
+
"loss": 0.4291,
|
| 633 |
+
"step": 2848
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.6803685329553508,
|
| 637 |
+
"grad_norm": 6.75,
|
| 638 |
+
"learning_rate": 9.518890017221214e-06,
|
| 639 |
+
"loss": 0.4252,
|
| 640 |
+
"step": 2880
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.6879281833215214,
|
| 644 |
+
"grad_norm": 7.125,
|
| 645 |
+
"learning_rate": 9.499891658406381e-06,
|
| 646 |
+
"loss": 0.4019,
|
| 647 |
+
"step": 2912
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.695487833687692,
|
| 651 |
+
"grad_norm": 6.46875,
|
| 652 |
+
"learning_rate": 9.480545136689222e-06,
|
| 653 |
+
"loss": 0.4161,
|
| 654 |
+
"step": 2944
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.7030474840538625,
|
| 658 |
+
"grad_norm": 4.0,
|
| 659 |
+
"learning_rate": 9.46085194893714e-06,
|
| 660 |
+
"loss": 0.4163,
|
| 661 |
+
"step": 2976
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.7106071344200331,
|
| 665 |
+
"grad_norm": 6.65625,
|
| 666 |
+
"learning_rate": 9.440813618839574e-06,
|
| 667 |
+
"loss": 0.4621,
|
| 668 |
+
"step": 3008
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.7181667847862037,
|
| 672 |
+
"grad_norm": 6.90625,
|
| 673 |
+
"learning_rate": 9.420431696790116e-06,
|
| 674 |
+
"loss": 0.4271,
|
| 675 |
+
"step": 3040
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.7257264351523742,
|
| 679 |
+
"grad_norm": 14.1875,
|
| 680 |
+
"learning_rate": 9.399707759766536e-06,
|
| 681 |
+
"loss": 0.4592,
|
| 682 |
+
"step": 3072
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.7332860855185448,
|
| 686 |
+
"grad_norm": 4.75,
|
| 687 |
+
"learning_rate": 9.378643411208785e-06,
|
| 688 |
+
"loss": 0.4204,
|
| 689 |
+
"step": 3104
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.7408457358847154,
|
| 693 |
+
"grad_norm": 6.40625,
|
| 694 |
+
"learning_rate": 9.357240280894935e-06,
|
| 695 |
+
"loss": 0.4407,
|
| 696 |
+
"step": 3136
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.7484053862508859,
|
| 700 |
+
"grad_norm": 7.84375,
|
| 701 |
+
"learning_rate": 9.335500024815066e-06,
|
| 702 |
+
"loss": 0.4412,
|
| 703 |
+
"step": 3168
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.7559650366170565,
|
| 707 |
+
"grad_norm": 6.15625,
|
| 708 |
+
"learning_rate": 9.313424325043156e-06,
|
| 709 |
+
"loss": 0.4509,
|
| 710 |
+
"step": 3200
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.7635246869832271,
|
| 714 |
+
"grad_norm": 6.71875,
|
| 715 |
+
"learning_rate": 9.291014889606927e-06,
|
| 716 |
+
"loss": 0.4084,
|
| 717 |
+
"step": 3232
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.7710843373493976,
|
| 721 |
+
"grad_norm": 7.8125,
|
| 722 |
+
"learning_rate": 9.268273452355698e-06,
|
| 723 |
+
"loss": 0.3744,
|
| 724 |
+
"step": 3264
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.7786439877155682,
|
| 728 |
+
"grad_norm": 5.5,
|
| 729 |
+
"learning_rate": 9.24520177282623e-06,
|
| 730 |
+
"loss": 0.4226,
|
| 731 |
+
"step": 3296
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.7862036380817388,
|
| 735 |
+
"grad_norm": 7.78125,
|
| 736 |
+
"learning_rate": 9.221801636106591e-06,
|
| 737 |
+
"loss": 0.4654,
|
| 738 |
+
"step": 3328
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.7937632884479093,
|
| 742 |
+
"grad_norm": 5.75,
|
| 743 |
+
"learning_rate": 9.198074852698042e-06,
|
| 744 |
+
"loss": 0.4746,
|
| 745 |
+
"step": 3360
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.8013229388140799,
|
| 749 |
+
"grad_norm": 10.0,
|
| 750 |
+
"learning_rate": 9.174023258374951e-06,
|
| 751 |
+
"loss": 0.4012,
|
| 752 |
+
"step": 3392
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.8088825891802505,
|
| 756 |
+
"grad_norm": 8.375,
|
| 757 |
+
"learning_rate": 9.149648714042763e-06,
|
| 758 |
+
"loss": 0.4434,
|
| 759 |
+
"step": 3424
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.8164422395464209,
|
| 763 |
+
"grad_norm": 5.9375,
|
| 764 |
+
"learning_rate": 9.124953105594014e-06,
|
| 765 |
+
"loss": 0.4421,
|
| 766 |
+
"step": 3456
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.8240018899125915,
|
| 770 |
+
"grad_norm": 4.75,
|
| 771 |
+
"learning_rate": 9.099938343762423e-06,
|
| 772 |
+
"loss": 0.4318,
|
| 773 |
+
"step": 3488
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.8315615402787621,
|
| 777 |
+
"grad_norm": 5.90625,
|
| 778 |
+
"learning_rate": 9.074606363975047e-06,
|
| 779 |
+
"loss": 0.4141,
|
| 780 |
+
"step": 3520
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.8391211906449326,
|
| 784 |
+
"grad_norm": 21.375,
|
| 785 |
+
"learning_rate": 9.048959126202543e-06,
|
| 786 |
+
"loss": 0.4459,
|
| 787 |
+
"step": 3552
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.8466808410111032,
|
| 791 |
+
"grad_norm": 13.0625,
|
| 792 |
+
"learning_rate": 9.022998614807519e-06,
|
| 793 |
+
"loss": 0.4449,
|
| 794 |
+
"step": 3584
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.8542404913772738,
|
| 798 |
+
"grad_norm": 6.59375,
|
| 799 |
+
"learning_rate": 8.996726838390995e-06,
|
| 800 |
+
"loss": 0.4375,
|
| 801 |
+
"step": 3616
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.8618001417434443,
|
| 805 |
+
"grad_norm": 5.625,
|
| 806 |
+
"learning_rate": 8.970145829637007e-06,
|
| 807 |
+
"loss": 0.4051,
|
| 808 |
+
"step": 3648
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.8693597921096149,
|
| 812 |
+
"grad_norm": 4.53125,
|
| 813 |
+
"learning_rate": 8.943257645155328e-06,
|
| 814 |
+
"loss": 0.4162,
|
| 815 |
+
"step": 3680
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.8769194424757855,
|
| 819 |
+
"grad_norm": 7.03125,
|
| 820 |
+
"learning_rate": 8.91606436532234e-06,
|
| 821 |
+
"loss": 0.4302,
|
| 822 |
+
"step": 3712
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.884479092841956,
|
| 826 |
+
"grad_norm": 6.0,
|
| 827 |
+
"learning_rate": 8.888568094120088e-06,
|
| 828 |
+
"loss": 0.4083,
|
| 829 |
+
"step": 3744
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.8920387432081266,
|
| 833 |
+
"grad_norm": 4.96875,
|
| 834 |
+
"learning_rate": 8.860770958973472e-06,
|
| 835 |
+
"loss": 0.3913,
|
| 836 |
+
"step": 3776
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.8995983935742972,
|
| 840 |
+
"grad_norm": 15.875,
|
| 841 |
+
"learning_rate": 8.832675110585663e-06,
|
| 842 |
+
"loss": 0.4226,
|
| 843 |
+
"step": 3808
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.9071580439404677,
|
| 847 |
+
"grad_norm": 6.8125,
|
| 848 |
+
"learning_rate": 8.804282722771691e-06,
|
| 849 |
+
"loss": 0.4122,
|
| 850 |
+
"step": 3840
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.9147176943066383,
|
| 854 |
+
"grad_norm": 5.625,
|
| 855 |
+
"learning_rate": 8.775595992290257e-06,
|
| 856 |
+
"loss": 0.4548,
|
| 857 |
+
"step": 3872
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.9222773446728089,
|
| 861 |
+
"grad_norm": 7.875,
|
| 862 |
+
"learning_rate": 8.746617138673761e-06,
|
| 863 |
+
"loss": 0.4418,
|
| 864 |
+
"step": 3904
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.9298369950389794,
|
| 868 |
+
"grad_norm": 12.375,
|
| 869 |
+
"learning_rate": 8.717348404056578e-06,
|
| 870 |
+
"loss": 0.4121,
|
| 871 |
+
"step": 3936
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.93739664540515,
|
| 875 |
+
"grad_norm": 6.3125,
|
| 876 |
+
"learning_rate": 8.687792053001587e-06,
|
| 877 |
+
"loss": 0.4491,
|
| 878 |
+
"step": 3968
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.9449562957713206,
|
| 882 |
+
"grad_norm": 5.625,
|
| 883 |
+
"learning_rate": 8.657950372324947e-06,
|
| 884 |
+
"loss": 0.4384,
|
| 885 |
+
"step": 4000
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.9525159461374911,
|
| 889 |
+
"grad_norm": 6.8125,
|
| 890 |
+
"learning_rate": 8.62782567091917e-06,
|
| 891 |
+
"loss": 0.4195,
|
| 892 |
+
"step": 4032
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.9600755965036617,
|
| 896 |
+
"grad_norm": 8.5625,
|
| 897 |
+
"learning_rate": 8.597420279574478e-06,
|
| 898 |
+
"loss": 0.4195,
|
| 899 |
+
"step": 4064
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.9676352468698323,
|
| 903 |
+
"grad_norm": 5.0625,
|
| 904 |
+
"learning_rate": 8.566736550798462e-06,
|
| 905 |
+
"loss": 0.4166,
|
| 906 |
+
"step": 4096
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.9751948972360028,
|
| 910 |
+
"grad_norm": 5.9375,
|
| 911 |
+
"learning_rate": 8.535776858634076e-06,
|
| 912 |
+
"loss": 0.4142,
|
| 913 |
+
"step": 4128
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.9827545476021734,
|
| 917 |
+
"grad_norm": 7.71875,
|
| 918 |
+
"learning_rate": 8.504543598475939e-06,
|
| 919 |
+
"loss": 0.4273,
|
| 920 |
+
"step": 4160
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.990314197968344,
|
| 924 |
+
"grad_norm": 5.59375,
|
| 925 |
+
"learning_rate": 8.47303918688501e-06,
|
| 926 |
+
"loss": 0.3669,
|
| 927 |
+
"step": 4192
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.9978738483345145,
|
| 931 |
+
"grad_norm": 6.09375,
|
| 932 |
+
"learning_rate": 8.441266061401613e-06,
|
| 933 |
+
"loss": 0.4211,
|
| 934 |
+
"step": 4224
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 1.005433498700685,
|
| 938 |
+
"grad_norm": 6.0,
|
| 939 |
+
"learning_rate": 8.40922668035685e-06,
|
| 940 |
+
"loss": 0.4052,
|
| 941 |
+
"step": 4256
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 1.0129931490668556,
|
| 945 |
+
"grad_norm": 5.5625,
|
| 946 |
+
"learning_rate": 8.376923522682372e-06,
|
| 947 |
+
"loss": 0.3879,
|
| 948 |
+
"step": 4288
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 1.0205527994330261,
|
| 952 |
+
"grad_norm": 7.46875,
|
| 953 |
+
"learning_rate": 8.344359087718607e-06,
|
| 954 |
+
"loss": 0.3971,
|
| 955 |
+
"step": 4320
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 1.0281124497991967,
|
| 959 |
+
"grad_norm": 6.375,
|
| 960 |
+
"learning_rate": 8.311535895021368e-06,
|
| 961 |
+
"loss": 0.3401,
|
| 962 |
+
"step": 4352
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 1.0356721001653673,
|
| 966 |
+
"grad_norm": 6.46875,
|
| 967 |
+
"learning_rate": 8.278456484166916e-06,
|
| 968 |
+
"loss": 0.3999,
|
| 969 |
+
"step": 4384
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.0432317505315378,
|
| 973 |
+
"grad_norm": 6.28125,
|
| 974 |
+
"learning_rate": 8.24512341455547e-06,
|
| 975 |
+
"loss": 0.349,
|
| 976 |
+
"step": 4416
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 1.0507914008977084,
|
| 980 |
+
"grad_norm": 13.375,
|
| 981 |
+
"learning_rate": 8.21153926521318e-06,
|
| 982 |
+
"loss": 0.4037,
|
| 983 |
+
"step": 4448
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 1.058351051263879,
|
| 987 |
+
"grad_norm": 7.125,
|
| 988 |
+
"learning_rate": 8.177706634592584e-06,
|
| 989 |
+
"loss": 0.3845,
|
| 990 |
+
"step": 4480
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 1.0659107016300495,
|
| 994 |
+
"grad_norm": 7.875,
|
| 995 |
+
"learning_rate": 8.143628140371565e-06,
|
| 996 |
+
"loss": 0.3731,
|
| 997 |
+
"step": 4512
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 1.07347035199622,
|
| 1001 |
+
"grad_norm": 8.5625,
|
| 1002 |
+
"learning_rate": 8.109306419250818e-06,
|
| 1003 |
+
"loss": 0.3845,
|
| 1004 |
+
"step": 4544
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 1.0810300023623907,
|
| 1008 |
+
"grad_norm": 9.5,
|
| 1009 |
+
"learning_rate": 8.074744126749839e-06,
|
| 1010 |
+
"loss": 0.4437,
|
| 1011 |
+
"step": 4576
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 1.0885896527285612,
|
| 1015 |
+
"grad_norm": 9.625,
|
| 1016 |
+
"learning_rate": 8.039943937001472e-06,
|
| 1017 |
+
"loss": 0.3819,
|
| 1018 |
+
"step": 4608
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 1.0961493030947318,
|
| 1022 |
+
"grad_norm": 5.46875,
|
| 1023 |
+
"learning_rate": 8.004908542545e-06,
|
| 1024 |
+
"loss": 0.394,
|
| 1025 |
+
"step": 4640
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 1.1037089534609024,
|
| 1029 |
+
"grad_norm": 5.5625,
|
| 1030 |
+
"learning_rate": 7.969640654117822e-06,
|
| 1031 |
+
"loss": 0.4315,
|
| 1032 |
+
"step": 4672
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 1.111268603827073,
|
| 1036 |
+
"grad_norm": 8.5,
|
| 1037 |
+
"learning_rate": 7.934143000445726e-06,
|
| 1038 |
+
"loss": 0.4429,
|
| 1039 |
+
"step": 4704
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 1.1188282541932435,
|
| 1043 |
+
"grad_norm": 6.34375,
|
| 1044 |
+
"learning_rate": 7.898418328031752e-06,
|
| 1045 |
+
"loss": 0.4198,
|
| 1046 |
+
"step": 4736
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 1.126387904559414,
|
| 1050 |
+
"grad_norm": 7.21875,
|
| 1051 |
+
"learning_rate": 7.8624694009437e-06,
|
| 1052 |
+
"loss": 0.3899,
|
| 1053 |
+
"step": 4768
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 1.1339475549255846,
|
| 1057 |
+
"grad_norm": 4.65625,
|
| 1058 |
+
"learning_rate": 7.826299000600262e-06,
|
| 1059 |
+
"loss": 0.3963,
|
| 1060 |
+
"step": 4800
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 1.1415072052917552,
|
| 1064 |
+
"grad_norm": 4.375,
|
| 1065 |
+
"learning_rate": 7.789909925555835e-06,
|
| 1066 |
+
"loss": 0.3925,
|
| 1067 |
+
"step": 4832
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 1.1490668556579258,
|
| 1071 |
+
"grad_norm": 7.96875,
|
| 1072 |
+
"learning_rate": 7.753304991283975e-06,
|
| 1073 |
+
"loss": 0.4087,
|
| 1074 |
+
"step": 4864
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 1.1566265060240963,
|
| 1078 |
+
"grad_norm": 6.625,
|
| 1079 |
+
"learning_rate": 7.71648702995957e-06,
|
| 1080 |
+
"loss": 0.4089,
|
| 1081 |
+
"step": 4896
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 1.164186156390267,
|
| 1085 |
+
"grad_norm": 3.71875,
|
| 1086 |
+
"learning_rate": 7.67945889023971e-06,
|
| 1087 |
+
"loss": 0.4062,
|
| 1088 |
+
"step": 4928
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 1.1717458067564375,
|
| 1092 |
+
"grad_norm": 4.8125,
|
| 1093 |
+
"learning_rate": 7.642223437043279e-06,
|
| 1094 |
+
"loss": 0.41,
|
| 1095 |
+
"step": 4960
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 1.179305457122608,
|
| 1099 |
+
"grad_norm": 8.25,
|
| 1100 |
+
"learning_rate": 7.604783551329298e-06,
|
| 1101 |
+
"loss": 0.3862,
|
| 1102 |
+
"step": 4992
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 1.1868651074887786,
|
| 1106 |
+
"grad_norm": 5.09375,
|
| 1107 |
+
"learning_rate": 7.567142129874012e-06,
|
| 1108 |
+
"loss": 0.383,
|
| 1109 |
+
"step": 5024
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 1.1944247578549492,
|
| 1113 |
+
"grad_norm": 4.84375,
|
| 1114 |
+
"learning_rate": 7.5293020850467705e-06,
|
| 1115 |
+
"loss": 0.4054,
|
| 1116 |
+
"step": 5056
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 1.2019844082211197,
|
| 1120 |
+
"grad_norm": 6.3125,
|
| 1121 |
+
"learning_rate": 7.491266344584691e-06,
|
| 1122 |
+
"loss": 0.4077,
|
| 1123 |
+
"step": 5088
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 1.2095440585872903,
|
| 1127 |
+
"grad_norm": 6.8125,
|
| 1128 |
+
"learning_rate": 7.453037851366136e-06,
|
| 1129 |
+
"loss": 0.4097,
|
| 1130 |
+
"step": 5120
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 1.2171037089534609,
|
| 1134 |
+
"grad_norm": 4.59375,
|
| 1135 |
+
"learning_rate": 7.414619563183017e-06,
|
| 1136 |
+
"loss": 0.3759,
|
| 1137 |
+
"step": 5152
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 1.2246633593196314,
|
| 1141 |
+
"grad_norm": 4.5,
|
| 1142 |
+
"learning_rate": 7.376014452511947e-06,
|
| 1143 |
+
"loss": 0.3878,
|
| 1144 |
+
"step": 5184
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 1.232223009685802,
|
| 1148 |
+
"grad_norm": 6.25,
|
| 1149 |
+
"learning_rate": 7.337225506284255e-06,
|
| 1150 |
+
"loss": 0.3696,
|
| 1151 |
+
"step": 5216
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 1.2397826600519726,
|
| 1155 |
+
"grad_norm": 5.9375,
|
| 1156 |
+
"learning_rate": 7.298255725654884e-06,
|
| 1157 |
+
"loss": 0.4199,
|
| 1158 |
+
"step": 5248
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 1.2473423104181431,
|
| 1162 |
+
"grad_norm": 4.8125,
|
| 1163 |
+
"learning_rate": 7.25910812577019e-06,
|
| 1164 |
+
"loss": 0.4098,
|
| 1165 |
+
"step": 5280
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 1.2549019607843137,
|
| 1169 |
+
"grad_norm": 6.03125,
|
| 1170 |
+
"learning_rate": 7.219785735534653e-06,
|
| 1171 |
+
"loss": 0.3707,
|
| 1172 |
+
"step": 5312
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 1.2624616111504843,
|
| 1176 |
+
"grad_norm": 4.8125,
|
| 1177 |
+
"learning_rate": 7.1802915973765184e-06,
|
| 1178 |
+
"loss": 0.4299,
|
| 1179 |
+
"step": 5344
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 1.2700212615166548,
|
| 1183 |
+
"grad_norm": 4.03125,
|
| 1184 |
+
"learning_rate": 7.14062876701242e-06,
|
| 1185 |
+
"loss": 0.3897,
|
| 1186 |
+
"step": 5376
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 1.2775809118828254,
|
| 1190 |
+
"grad_norm": 5.375,
|
| 1191 |
+
"learning_rate": 7.1008003132109345e-06,
|
| 1192 |
+
"loss": 0.3932,
|
| 1193 |
+
"step": 5408
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 1.285140562248996,
|
| 1197 |
+
"grad_norm": 8.1875,
|
| 1198 |
+
"learning_rate": 7.0608093175551615e-06,
|
| 1199 |
+
"loss": 0.3614,
|
| 1200 |
+
"step": 5440
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 1.2927002126151665,
|
| 1204 |
+
"grad_norm": 5.71875,
|
| 1205 |
+
"learning_rate": 7.020658874204286e-06,
|
| 1206 |
+
"loss": 0.3998,
|
| 1207 |
+
"step": 5472
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 1.3002598629813371,
|
| 1211 |
+
"grad_norm": 4.5,
|
| 1212 |
+
"learning_rate": 6.980352089654184e-06,
|
| 1213 |
+
"loss": 0.3811,
|
| 1214 |
+
"step": 5504
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 1.3078195133475077,
|
| 1218 |
+
"grad_norm": 6.40625,
|
| 1219 |
+
"learning_rate": 6.939892082497073e-06,
|
| 1220 |
+
"loss": 0.379,
|
| 1221 |
+
"step": 5536
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 1.3153791637136782,
|
| 1225 |
+
"grad_norm": 7.21875,
|
| 1226 |
+
"learning_rate": 6.899281983180213e-06,
|
| 1227 |
+
"loss": 0.4307,
|
| 1228 |
+
"step": 5568
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 1.3229388140798488,
|
| 1232 |
+
"grad_norm": 6.21875,
|
| 1233 |
+
"learning_rate": 6.858524933763706e-06,
|
| 1234 |
+
"loss": 0.4209,
|
| 1235 |
+
"step": 5600
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 1.3304984644460194,
|
| 1239 |
+
"grad_norm": 5.5625,
|
| 1240 |
+
"learning_rate": 6.817624087677388e-06,
|
| 1241 |
+
"loss": 0.4009,
|
| 1242 |
+
"step": 5632
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 1.33805811481219,
|
| 1246 |
+
"grad_norm": 6.4375,
|
| 1247 |
+
"learning_rate": 6.776582609476845e-06,
|
| 1248 |
+
"loss": 0.3359,
|
| 1249 |
+
"step": 5664
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 1.3456177651783605,
|
| 1253 |
+
"grad_norm": 5.96875,
|
| 1254 |
+
"learning_rate": 6.735403674598566e-06,
|
| 1255 |
+
"loss": 0.414,
|
| 1256 |
+
"step": 5696
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 1.353177415544531,
|
| 1260 |
+
"grad_norm": 11.5,
|
| 1261 |
+
"learning_rate": 6.694090469114254e-06,
|
| 1262 |
+
"loss": 0.3847,
|
| 1263 |
+
"step": 5728
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 1.3607370659107016,
|
| 1267 |
+
"grad_norm": 3.78125,
|
| 1268 |
+
"learning_rate": 6.652646189484317e-06,
|
| 1269 |
+
"loss": 0.4152,
|
| 1270 |
+
"step": 5760
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 1.3682967162768722,
|
| 1274 |
+
"grad_norm": 5.25,
|
| 1275 |
+
"learning_rate": 6.61107404231055e-06,
|
| 1276 |
+
"loss": 0.3921,
|
| 1277 |
+
"step": 5792
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 1.3758563666430428,
|
| 1281 |
+
"grad_norm": 9.625,
|
| 1282 |
+
"learning_rate": 6.569377244088044e-06,
|
| 1283 |
+
"loss": 0.3857,
|
| 1284 |
+
"step": 5824
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 1.3834160170092134,
|
| 1288 |
+
"grad_norm": 5.375,
|
| 1289 |
+
"learning_rate": 6.527559020956312e-06,
|
| 1290 |
+
"loss": 0.3879,
|
| 1291 |
+
"step": 5856
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 1.390975667375384,
|
| 1295 |
+
"grad_norm": 5.40625,
|
| 1296 |
+
"learning_rate": 6.485622608449684e-06,
|
| 1297 |
+
"loss": 0.3835,
|
| 1298 |
+
"step": 5888
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 1.3985353177415545,
|
| 1302 |
+
"grad_norm": 6.6875,
|
| 1303 |
+
"learning_rate": 6.443571251246964e-06,
|
| 1304 |
+
"loss": 0.3753,
|
| 1305 |
+
"step": 5920
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 1.406094968107725,
|
| 1309 |
+
"grad_norm": 4.625,
|
| 1310 |
+
"learning_rate": 6.401408202920387e-06,
|
| 1311 |
+
"loss": 0.4092,
|
| 1312 |
+
"step": 5952
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 1.4136546184738956,
|
| 1316 |
+
"grad_norm": 6.78125,
|
| 1317 |
+
"learning_rate": 6.3591367256838935e-06,
|
| 1318 |
+
"loss": 0.4141,
|
| 1319 |
+
"step": 5984
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 1.4212142688400662,
|
| 1323 |
+
"grad_norm": 5.5,
|
| 1324 |
+
"learning_rate": 6.316760090140713e-06,
|
| 1325 |
+
"loss": 0.401,
|
| 1326 |
+
"step": 6016
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 1.4287739192062368,
|
| 1330 |
+
"grad_norm": 6.125,
|
| 1331 |
+
"learning_rate": 6.274281575030321e-06,
|
| 1332 |
+
"loss": 0.3655,
|
| 1333 |
+
"step": 6048
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 1.4363335695724073,
|
| 1337 |
+
"grad_norm": 6.9375,
|
| 1338 |
+
"learning_rate": 6.2317044669747595e-06,
|
| 1339 |
+
"loss": 0.4077,
|
| 1340 |
+
"step": 6080
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 1.4438932199385779,
|
| 1344 |
+
"grad_norm": 4.90625,
|
| 1345 |
+
"learning_rate": 6.189032060224344e-06,
|
| 1346 |
+
"loss": 0.3987,
|
| 1347 |
+
"step": 6112
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 1.4514528703047485,
|
| 1351 |
+
"grad_norm": 5.71875,
|
| 1352 |
+
"learning_rate": 6.1462676564027814e-06,
|
| 1353 |
+
"loss": 0.3943,
|
| 1354 |
+
"step": 6144
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 1.459012520670919,
|
| 1358 |
+
"grad_norm": 5.78125,
|
| 1359 |
+
"learning_rate": 6.1034145642517236e-06,
|
| 1360 |
+
"loss": 0.3839,
|
| 1361 |
+
"step": 6176
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 1.4665721710370896,
|
| 1365 |
+
"grad_norm": 19.25,
|
| 1366 |
+
"learning_rate": 6.06047609937476e-06,
|
| 1367 |
+
"loss": 0.412,
|
| 1368 |
+
"step": 6208
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 1.4741318214032602,
|
| 1372 |
+
"grad_norm": 7.375,
|
| 1373 |
+
"learning_rate": 6.017455583980887e-06,
|
| 1374 |
+
"loss": 0.3862,
|
| 1375 |
+
"step": 6240
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 1.4816914717694307,
|
| 1379 |
+
"grad_norm": 12.0625,
|
| 1380 |
+
"learning_rate": 5.974356346627463e-06,
|
| 1381 |
+
"loss": 0.4054,
|
| 1382 |
+
"step": 6272
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 1.4892511221356013,
|
| 1386 |
+
"grad_norm": 7.5,
|
| 1387 |
+
"learning_rate": 5.931181721962682e-06,
|
| 1388 |
+
"loss": 0.3772,
|
| 1389 |
+
"step": 6304
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 1.4968107725017719,
|
| 1393 |
+
"grad_norm": 7.46875,
|
| 1394 |
+
"learning_rate": 5.887935050467547e-06,
|
| 1395 |
+
"loss": 0.4123,
|
| 1396 |
+
"step": 6336
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 1.5043704228679422,
|
| 1400 |
+
"grad_norm": 8.4375,
|
| 1401 |
+
"learning_rate": 5.844619678197434e-06,
|
| 1402 |
+
"loss": 0.3815,
|
| 1403 |
+
"step": 6368
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 1.511930073234113,
|
| 1407 |
+
"grad_norm": 5.875,
|
| 1408 |
+
"learning_rate": 5.801238956523192e-06,
|
| 1409 |
+
"loss": 0.4348,
|
| 1410 |
+
"step": 6400
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 1.5194897236002833,
|
| 1414 |
+
"grad_norm": 6.375,
|
| 1415 |
+
"learning_rate": 5.757796241871844e-06,
|
| 1416 |
+
"loss": 0.3863,
|
| 1417 |
+
"step": 6432
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 1.5270493739664541,
|
| 1421 |
+
"grad_norm": 7.15625,
|
| 1422 |
+
"learning_rate": 5.714294895466897e-06,
|
| 1423 |
+
"loss": 0.4001,
|
| 1424 |
+
"step": 6464
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 1.5346090243326245,
|
| 1428 |
+
"grad_norm": 5.0,
|
| 1429 |
+
"learning_rate": 5.670738283068273e-06,
|
| 1430 |
+
"loss": 0.3793,
|
| 1431 |
+
"step": 6496
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 1.5421686746987953,
|
| 1435 |
+
"grad_norm": 6.65625,
|
| 1436 |
+
"learning_rate": 5.627129774711912e-06,
|
| 1437 |
+
"loss": 0.3899,
|
| 1438 |
+
"step": 6528
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 1.5497283250649656,
|
| 1442 |
+
"grad_norm": 5.75,
|
| 1443 |
+
"learning_rate": 5.58347274444901e-06,
|
| 1444 |
+
"loss": 0.3811,
|
| 1445 |
+
"step": 6560
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 1.5572879754311364,
|
| 1449 |
+
"grad_norm": 5.09375,
|
| 1450 |
+
"learning_rate": 5.539770570084968e-06,
|
| 1451 |
+
"loss": 0.3998,
|
| 1452 |
+
"step": 6592
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 1.5648476257973067,
|
| 1456 |
+
"grad_norm": 6.40625,
|
| 1457 |
+
"learning_rate": 5.496026632918055e-06,
|
| 1458 |
+
"loss": 0.3703,
|
| 1459 |
+
"step": 6624
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 1.5724072761634775,
|
| 1463 |
+
"grad_norm": 7.25,
|
| 1464 |
+
"learning_rate": 5.452244317477785e-06,
|
| 1465 |
+
"loss": 0.3892,
|
| 1466 |
+
"step": 6656
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 1.5799669265296479,
|
| 1470 |
+
"grad_norm": 7.46875,
|
| 1471 |
+
"learning_rate": 5.40842701126305e-06,
|
| 1472 |
+
"loss": 0.4057,
|
| 1473 |
+
"step": 6688
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 1.5875265768958187,
|
| 1477 |
+
"grad_norm": 5.625,
|
| 1478 |
+
"learning_rate": 5.364578104480029e-06,
|
| 1479 |
+
"loss": 0.4182,
|
| 1480 |
+
"step": 6720
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 1.595086227261989,
|
| 1484 |
+
"grad_norm": 5.25,
|
| 1485 |
+
"learning_rate": 5.3207009897798825e-06,
|
| 1486 |
+
"loss": 0.3668,
|
| 1487 |
+
"step": 6752
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 1.6026458776281598,
|
| 1491 |
+
"grad_norm": 7.28125,
|
| 1492 |
+
"learning_rate": 5.276799061996252e-06,
|
| 1493 |
+
"loss": 0.3976,
|
| 1494 |
+
"step": 6784
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 1.6102055279943301,
|
| 1498 |
+
"grad_norm": 5.625,
|
| 1499 |
+
"learning_rate": 5.232875717882606e-06,
|
| 1500 |
+
"loss": 0.4012,
|
| 1501 |
+
"step": 6816
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 1.617765178360501,
|
| 1505 |
+
"grad_norm": 8.5,
|
| 1506 |
+
"learning_rate": 5.1889343558494264e-06,
|
| 1507 |
+
"loss": 0.413,
|
| 1508 |
+
"step": 6848
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 1.6253248287266713,
|
| 1512 |
+
"grad_norm": 7.9375,
|
| 1513 |
+
"learning_rate": 5.144978375701261e-06,
|
| 1514 |
+
"loss": 0.435,
|
| 1515 |
+
"step": 6880
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 1.632884479092842,
|
| 1519 |
+
"grad_norm": 6.34375,
|
| 1520 |
+
"learning_rate": 5.101011178373687e-06,
|
| 1521 |
+
"loss": 0.3851,
|
| 1522 |
+
"step": 6912
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 1.6404441294590124,
|
| 1526 |
+
"grad_norm": 5.53125,
|
| 1527 |
+
"learning_rate": 5.057036165670165e-06,
|
| 1528 |
+
"loss": 0.3728,
|
| 1529 |
+
"step": 6944
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 1.6480037798251832,
|
| 1533 |
+
"grad_norm": 6.0625,
|
| 1534 |
+
"learning_rate": 5.013056739998845e-06,
|
| 1535 |
+
"loss": 0.4223,
|
| 1536 |
+
"step": 6976
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 1.6555634301913535,
|
| 1540 |
+
"grad_norm": 5.34375,
|
| 1541 |
+
"learning_rate": 4.969076304109316e-06,
|
| 1542 |
+
"loss": 0.4188,
|
| 1543 |
+
"step": 7008
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 1.6631230805575243,
|
| 1547 |
+
"grad_norm": 7.28125,
|
| 1548 |
+
"learning_rate": 4.92509826082933e-06,
|
| 1549 |
+
"loss": 0.3932,
|
| 1550 |
+
"step": 7040
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 1.6706827309236947,
|
| 1554 |
+
"grad_norm": 4.625,
|
| 1555 |
+
"learning_rate": 4.881126012801512e-06,
|
| 1556 |
+
"loss": 0.3873,
|
| 1557 |
+
"step": 7072
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 1.6782423812898655,
|
| 1561 |
+
"grad_norm": 5.8125,
|
| 1562 |
+
"learning_rate": 4.8371629622201084e-06,
|
| 1563 |
+
"loss": 0.3801,
|
| 1564 |
+
"step": 7104
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 1.6858020316560358,
|
| 1568 |
+
"grad_norm": 7.5,
|
| 1569 |
+
"learning_rate": 4.793212510567741e-06,
|
| 1570 |
+
"loss": 0.381,
|
| 1571 |
+
"step": 7136
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 1.6933616820222066,
|
| 1575 |
+
"grad_norm": 5.40625,
|
| 1576 |
+
"learning_rate": 4.749278058352238e-06,
|
| 1577 |
+
"loss": 0.4149,
|
| 1578 |
+
"step": 7168
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 1.700921332388377,
|
| 1582 |
+
"grad_norm": 4.0,
|
| 1583 |
+
"learning_rate": 4.7053630048435295e-06,
|
| 1584 |
+
"loss": 0.3805,
|
| 1585 |
+
"step": 7200
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 1.7084809827545477,
|
| 1589 |
+
"grad_norm": 5.6875,
|
| 1590 |
+
"learning_rate": 4.661470747810635e-06,
|
| 1591 |
+
"loss": 0.3912,
|
| 1592 |
+
"step": 7232
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 1.716040633120718,
|
| 1596 |
+
"grad_norm": 6.03125,
|
| 1597 |
+
"learning_rate": 4.617604683258787e-06,
|
| 1598 |
+
"loss": 0.4288,
|
| 1599 |
+
"step": 7264
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 1.7236002834868889,
|
| 1603 |
+
"grad_norm": 6.9375,
|
| 1604 |
+
"learning_rate": 4.573768205166663e-06,
|
| 1605 |
+
"loss": 0.3611,
|
| 1606 |
+
"step": 7296
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 1.7311599338530592,
|
| 1610 |
+
"grad_norm": 7.125,
|
| 1611 |
+
"learning_rate": 4.529964705223796e-06,
|
| 1612 |
+
"loss": 0.3765,
|
| 1613 |
+
"step": 7328
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 1.73871958421923,
|
| 1617 |
+
"grad_norm": 7.0625,
|
| 1618 |
+
"learning_rate": 4.486197572568154e-06,
|
| 1619 |
+
"loss": 0.4224,
|
| 1620 |
+
"step": 7360
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 1.7462792345854004,
|
| 1624 |
+
"grad_norm": 4.78125,
|
| 1625 |
+
"learning_rate": 4.442470193523919e-06,
|
| 1626 |
+
"loss": 0.4066,
|
| 1627 |
+
"step": 7392
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 1.7538388849515711,
|
| 1631 |
+
"grad_norm": 7.28125,
|
| 1632 |
+
"learning_rate": 4.398785951339476e-06,
|
| 1633 |
+
"loss": 0.4138,
|
| 1634 |
+
"step": 7424
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 1.7613985353177415,
|
| 1638 |
+
"grad_norm": 7.0,
|
| 1639 |
+
"learning_rate": 4.355148225925658e-06,
|
| 1640 |
+
"loss": 0.4131,
|
| 1641 |
+
"step": 7456
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 1.7689581856839123,
|
| 1645 |
+
"grad_norm": 6.125,
|
| 1646 |
+
"learning_rate": 4.3115603935942226e-06,
|
| 1647 |
+
"loss": 0.3907,
|
| 1648 |
+
"step": 7488
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 1.7765178360500826,
|
| 1652 |
+
"grad_norm": 6.1875,
|
| 1653 |
+
"learning_rate": 4.268025826796636e-06,
|
| 1654 |
+
"loss": 0.4282,
|
| 1655 |
+
"step": 7520
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 1.7840774864162534,
|
| 1659 |
+
"grad_norm": 6.15625,
|
| 1660 |
+
"learning_rate": 4.224547893863133e-06,
|
| 1661 |
+
"loss": 0.3837,
|
| 1662 |
+
"step": 7552
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 1.7916371367824238,
|
| 1666 |
+
"grad_norm": 7.46875,
|
| 1667 |
+
"learning_rate": 4.181129958742107e-06,
|
| 1668 |
+
"loss": 0.3634,
|
| 1669 |
+
"step": 7584
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 1.7991967871485943,
|
| 1673 |
+
"grad_norm": 6.0625,
|
| 1674 |
+
"learning_rate": 4.137775380739839e-06,
|
| 1675 |
+
"loss": 0.3652,
|
| 1676 |
+
"step": 7616
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 1.806756437514765,
|
| 1680 |
+
"grad_norm": 8.6875,
|
| 1681 |
+
"learning_rate": 4.094487514260575e-06,
|
| 1682 |
+
"loss": 0.4116,
|
| 1683 |
+
"step": 7648
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 1.8143160878809355,
|
| 1687 |
+
"grad_norm": 7.75,
|
| 1688 |
+
"learning_rate": 4.051269708547008e-06,
|
| 1689 |
+
"loss": 0.4062,
|
| 1690 |
+
"step": 7680
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 1.821875738247106,
|
| 1694 |
+
"grad_norm": 15.0,
|
| 1695 |
+
"learning_rate": 4.0081253074211204e-06,
|
| 1696 |
+
"loss": 0.3903,
|
| 1697 |
+
"step": 7712
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 1.8294353886132766,
|
| 1701 |
+
"grad_norm": 6.21875,
|
| 1702 |
+
"learning_rate": 3.965057649025489e-06,
|
| 1703 |
+
"loss": 0.3491,
|
| 1704 |
+
"step": 7744
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 1.8369950389794472,
|
| 1708 |
+
"grad_norm": 6.375,
|
| 1709 |
+
"learning_rate": 3.9220700655649916e-06,
|
| 1710 |
+
"loss": 0.3592,
|
| 1711 |
+
"step": 7776
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 1.8445546893456177,
|
| 1715 |
+
"grad_norm": 6.28125,
|
| 1716 |
+
"learning_rate": 3.879165883048997e-06,
|
| 1717 |
+
"loss": 0.3775,
|
| 1718 |
+
"step": 7808
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 1.8521143397117883,
|
| 1722 |
+
"grad_norm": 5.875,
|
| 1723 |
+
"learning_rate": 3.8363484210340315e-06,
|
| 1724 |
+
"loss": 0.4107,
|
| 1725 |
+
"step": 7840
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 1.8596739900779589,
|
| 1729 |
+
"grad_norm": 5.21875,
|
| 1730 |
+
"learning_rate": 3.7936209923669286e-06,
|
| 1731 |
+
"loss": 0.3756,
|
| 1732 |
+
"step": 7872
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 1.8672336404441294,
|
| 1736 |
+
"grad_norm": 6.25,
|
| 1737 |
+
"learning_rate": 3.7509869029285216e-06,
|
| 1738 |
+
"loss": 0.3981,
|
| 1739 |
+
"step": 7904
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 1.8747932908103,
|
| 1743 |
+
"grad_norm": 6.625,
|
| 1744 |
+
"learning_rate": 3.708449451377851e-06,
|
| 1745 |
+
"loss": 0.3983,
|
| 1746 |
+
"step": 7936
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 1.8823529411764706,
|
| 1750 |
+
"grad_norm": 5.9375,
|
| 1751 |
+
"learning_rate": 3.6660119288969577e-06,
|
| 1752 |
+
"loss": 0.4131,
|
| 1753 |
+
"step": 7968
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 1.8899125915426411,
|
| 1757 |
+
"grad_norm": 7.375,
|
| 1758 |
+
"learning_rate": 3.623677618936221e-06,
|
| 1759 |
+
"loss": 0.3686,
|
| 1760 |
+
"step": 8000
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 1.8974722419088117,
|
| 1764 |
+
"grad_norm": 6.3125,
|
| 1765 |
+
"learning_rate": 3.5814497969603324e-06,
|
| 1766 |
+
"loss": 0.3864,
|
| 1767 |
+
"step": 8032
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 1.9050318922749823,
|
| 1771 |
+
"grad_norm": 4.84375,
|
| 1772 |
+
"learning_rate": 3.5393317301948517e-06,
|
| 1773 |
+
"loss": 0.4053,
|
| 1774 |
+
"step": 8064
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 1.9125915426411528,
|
| 1778 |
+
"grad_norm": 5.125,
|
| 1779 |
+
"learning_rate": 3.497326677373431e-06,
|
| 1780 |
+
"loss": 0.3841,
|
| 1781 |
+
"step": 8096
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 1.9201511930073234,
|
| 1785 |
+
"grad_norm": 5.34375,
|
| 1786 |
+
"learning_rate": 3.4554378884856694e-06,
|
| 1787 |
+
"loss": 0.3439,
|
| 1788 |
+
"step": 8128
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 1.927710843373494,
|
| 1792 |
+
"grad_norm": 5.53125,
|
| 1793 |
+
"learning_rate": 3.41366860452567e-06,
|
| 1794 |
+
"loss": 0.4156,
|
| 1795 |
+
"step": 8160
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 1.9352704937396645,
|
| 1799 |
+
"grad_norm": 4.5,
|
| 1800 |
+
"learning_rate": 3.372022057241269e-06,
|
| 1801 |
+
"loss": 0.4258,
|
| 1802 |
+
"step": 8192
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 1.942830144105835,
|
| 1806 |
+
"grad_norm": 6.3125,
|
| 1807 |
+
"learning_rate": 3.330501468883992e-06,
|
| 1808 |
+
"loss": 0.419,
|
| 1809 |
+
"step": 8224
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 1.9503897944720057,
|
| 1813 |
+
"grad_norm": 9.4375,
|
| 1814 |
+
"learning_rate": 3.289110051959754e-06,
|
| 1815 |
+
"loss": 0.4285,
|
| 1816 |
+
"step": 8256
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 1.9579494448381762,
|
| 1820 |
+
"grad_norm": 6.1875,
|
| 1821 |
+
"learning_rate": 3.247851008980286e-06,
|
| 1822 |
+
"loss": 0.4105,
|
| 1823 |
+
"step": 8288
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 1.9655090952043468,
|
| 1827 |
+
"grad_norm": 8.375,
|
| 1828 |
+
"learning_rate": 3.206727532215372e-06,
|
| 1829 |
+
"loss": 0.4125,
|
| 1830 |
+
"step": 8320
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 1.9730687455705174,
|
| 1834 |
+
"grad_norm": 8.1875,
|
| 1835 |
+
"learning_rate": 3.165742803445841e-06,
|
| 1836 |
+
"loss": 0.3931,
|
| 1837 |
+
"step": 8352
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 1.980628395936688,
|
| 1841 |
+
"grad_norm": 6.03125,
|
| 1842 |
+
"learning_rate": 3.1248999937174007e-06,
|
| 1843 |
+
"loss": 0.3599,
|
| 1844 |
+
"step": 8384
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 1.9881880463028585,
|
| 1848 |
+
"grad_norm": 7.09375,
|
| 1849 |
+
"learning_rate": 3.0842022630952784e-06,
|
| 1850 |
+
"loss": 0.3852,
|
| 1851 |
+
"step": 8416
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 1.995747696669029,
|
| 1855 |
+
"grad_norm": 3.78125,
|
| 1856 |
+
"learning_rate": 3.0436527604197374e-06,
|
| 1857 |
+
"loss": 0.3744,
|
| 1858 |
+
"step": 8448
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 2.0033073470351996,
|
| 1862 |
+
"grad_norm": 6.34375,
|
| 1863 |
+
"learning_rate": 3.00325462306243e-06,
|
| 1864 |
+
"loss": 0.3665,
|
| 1865 |
+
"step": 8480
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 2.01086699740137,
|
| 1869 |
+
"grad_norm": 4.125,
|
| 1870 |
+
"learning_rate": 2.9630109766836634e-06,
|
| 1871 |
+
"loss": 0.3574,
|
| 1872 |
+
"step": 8512
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 2.0184266477675408,
|
| 1876 |
+
"grad_norm": 4.78125,
|
| 1877 |
+
"learning_rate": 2.9229249349905686e-06,
|
| 1878 |
+
"loss": 0.3651,
|
| 1879 |
+
"step": 8544
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 2.025986298133711,
|
| 1883 |
+
"grad_norm": 6.4375,
|
| 1884 |
+
"learning_rate": 2.8829995994961725e-06,
|
| 1885 |
+
"loss": 0.3792,
|
| 1886 |
+
"step": 8576
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 2.033545948499882,
|
| 1890 |
+
"grad_norm": 4.75,
|
| 1891 |
+
"learning_rate": 2.8432380592794466e-06,
|
| 1892 |
+
"loss": 0.4099,
|
| 1893 |
+
"step": 8608
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 2.0411055988660523,
|
| 1897 |
+
"grad_norm": 5.375,
|
| 1898 |
+
"learning_rate": 2.8036433907462866e-06,
|
| 1899 |
+
"loss": 0.3701,
|
| 1900 |
+
"step": 8640
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"epoch": 2.048665249232223,
|
| 1904 |
+
"grad_norm": 6.46875,
|
| 1905 |
+
"learning_rate": 2.7642186573915e-06,
|
| 1906 |
+
"loss": 0.3454,
|
| 1907 |
+
"step": 8672
|
| 1908 |
+
},
|
| 1909 |
+
{
|
| 1910 |
+
"epoch": 2.0562248995983934,
|
| 1911 |
+
"grad_norm": 8.1875,
|
| 1912 |
+
"learning_rate": 2.724966909561765e-06,
|
| 1913 |
+
"loss": 0.3676,
|
| 1914 |
+
"step": 8704
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 2.063784549964564,
|
| 1918 |
+
"grad_norm": 4.03125,
|
| 1919 |
+
"learning_rate": 2.685891184219635e-06,
|
| 1920 |
+
"loss": 0.3714,
|
| 1921 |
+
"step": 8736
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 2.0713442003307345,
|
| 1925 |
+
"grad_norm": 9.375,
|
| 1926 |
+
"learning_rate": 2.646994504708551e-06,
|
| 1927 |
+
"loss": 0.4112,
|
| 1928 |
+
"step": 8768
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 2.0789038506969053,
|
| 1932 |
+
"grad_norm": 5.0,
|
| 1933 |
+
"learning_rate": 2.6082798805189347e-06,
|
| 1934 |
+
"loss": 0.3587,
|
| 1935 |
+
"step": 8800
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 2.0864635010630757,
|
| 1939 |
+
"grad_norm": 11.25,
|
| 1940 |
+
"learning_rate": 2.569750307055329e-06,
|
| 1941 |
+
"loss": 0.3693,
|
| 1942 |
+
"step": 8832
|
| 1943 |
+
},
|
| 1944 |
+
{
|
| 1945 |
+
"epoch": 2.0940231514292464,
|
| 1946 |
+
"grad_norm": 7.4375,
|
| 1947 |
+
"learning_rate": 2.5314087654046403e-06,
|
| 1948 |
+
"loss": 0.3768,
|
| 1949 |
+
"step": 8864
|
| 1950 |
+
},
|
| 1951 |
+
{
|
| 1952 |
+
"epoch": 2.101582801795417,
|
| 1953 |
+
"grad_norm": 5.65625,
|
| 1954 |
+
"learning_rate": 2.4932582221055024e-06,
|
| 1955 |
+
"loss": 0.3525,
|
| 1956 |
+
"step": 8896
|
| 1957 |
+
},
|
| 1958 |
+
{
|
| 1959 |
+
"epoch": 2.1091424521615876,
|
| 1960 |
+
"grad_norm": 7.59375,
|
| 1961 |
+
"learning_rate": 2.455301628918727e-06,
|
| 1962 |
+
"loss": 0.3835,
|
| 1963 |
+
"step": 8928
|
| 1964 |
+
},
|
| 1965 |
+
{
|
| 1966 |
+
"epoch": 2.116702102527758,
|
| 1967 |
+
"grad_norm": 4.96875,
|
| 1968 |
+
"learning_rate": 2.417541922598945e-06,
|
| 1969 |
+
"loss": 0.3802,
|
| 1970 |
+
"step": 8960
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 2.1242617528939287,
|
| 1974 |
+
"grad_norm": 5.90625,
|
| 1975 |
+
"learning_rate": 2.379982024667367e-06,
|
| 1976 |
+
"loss": 0.4005,
|
| 1977 |
+
"step": 8992
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 2.131821403260099,
|
| 1981 |
+
"grad_norm": 10.1875,
|
| 1982 |
+
"learning_rate": 2.3426248411857573e-06,
|
| 1983 |
+
"loss": 0.3815,
|
| 1984 |
+
"step": 9024
|
| 1985 |
+
},
|
| 1986 |
+
{
|
| 1987 |
+
"epoch": 2.13938105362627,
|
| 1988 |
+
"grad_norm": 6.09375,
|
| 1989 |
+
"learning_rate": 2.3054732625315725e-06,
|
| 1990 |
+
"loss": 0.3349,
|
| 1991 |
+
"step": 9056
|
| 1992 |
+
},
|
| 1993 |
+
{
|
| 1994 |
+
"epoch": 2.14694070399244,
|
| 1995 |
+
"grad_norm": 7.28125,
|
| 1996 |
+
"learning_rate": 2.2685301631743437e-06,
|
| 1997 |
+
"loss": 0.3962,
|
| 1998 |
+
"step": 9088
|
| 1999 |
+
},
|
| 2000 |
+
{
|
| 2001 |
+
"epoch": 2.154500354358611,
|
| 2002 |
+
"grad_norm": 4.0625,
|
| 2003 |
+
"learning_rate": 2.2317984014532634e-06,
|
| 2004 |
+
"loss": 0.3707,
|
| 2005 |
+
"step": 9120
|
| 2006 |
+
},
|
| 2007 |
+
{
|
| 2008 |
+
"epoch": 2.1620600047247813,
|
| 2009 |
+
"grad_norm": 5.0625,
|
| 2010 |
+
"learning_rate": 2.1952808193560367e-06,
|
| 2011 |
+
"loss": 0.4251,
|
| 2012 |
+
"step": 9152
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 2.169619655090952,
|
| 2016 |
+
"grad_norm": 6.75,
|
| 2017 |
+
"learning_rate": 2.158980242298989e-06,
|
| 2018 |
+
"loss": 0.3916,
|
| 2019 |
+
"step": 9184
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 2.1771793054571225,
|
| 2023 |
+
"grad_norm": 9.9375,
|
| 2024 |
+
"learning_rate": 2.12289947890847e-06,
|
| 2025 |
+
"loss": 0.3959,
|
| 2026 |
+
"step": 9216
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 2.1847389558232932,
|
| 2030 |
+
"grad_norm": 5.5,
|
| 2031 |
+
"learning_rate": 2.087041320803535e-06,
|
| 2032 |
+
"loss": 0.3586,
|
| 2033 |
+
"step": 9248
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 2.1922986061894636,
|
| 2037 |
+
"grad_norm": 5.78125,
|
| 2038 |
+
"learning_rate": 2.051408542379955e-06,
|
| 2039 |
+
"loss": 0.3692,
|
| 2040 |
+
"step": 9280
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"epoch": 2.1998582565556344,
|
| 2044 |
+
"grad_norm": 6.40625,
|
| 2045 |
+
"learning_rate": 2.016003900595566e-06,
|
| 2046 |
+
"loss": 0.3709,
|
| 2047 |
+
"step": 9312
|
| 2048 |
+
},
|
| 2049 |
+
{
|
| 2050 |
+
"epoch": 2.2074179069218047,
|
| 2051 |
+
"grad_norm": 4.28125,
|
| 2052 |
+
"learning_rate": 1.980830134756946e-06,
|
| 2053 |
+
"loss": 0.3729,
|
| 2054 |
+
"step": 9344
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 2.2149775572879755,
|
| 2058 |
+
"grad_norm": 6.03125,
|
| 2059 |
+
"learning_rate": 1.945889966307487e-06,
|
| 2060 |
+
"loss": 0.3655,
|
| 2061 |
+
"step": 9376
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"epoch": 2.222537207654146,
|
| 2065 |
+
"grad_norm": 6.28125,
|
| 2066 |
+
"learning_rate": 1.911186098616819e-06,
|
| 2067 |
+
"loss": 0.3661,
|
| 2068 |
+
"step": 9408
|
| 2069 |
+
},
|
| 2070 |
+
{
|
| 2071 |
+
"epoch": 2.2300968580203167,
|
| 2072 |
+
"grad_norm": 8.875,
|
| 2073 |
+
"learning_rate": 1.8767212167716536e-06,
|
| 2074 |
+
"loss": 0.3685,
|
| 2075 |
+
"step": 9440
|
| 2076 |
+
},
|
| 2077 |
+
{
|
| 2078 |
+
"epoch": 2.237656508386487,
|
| 2079 |
+
"grad_norm": 5.8125,
|
| 2080 |
+
"learning_rate": 1.8424979873680332e-06,
|
| 2081 |
+
"loss": 0.3623,
|
| 2082 |
+
"step": 9472
|
| 2083 |
+
},
|
| 2084 |
+
{
|
| 2085 |
+
"epoch": 2.245216158752658,
|
| 2086 |
+
"grad_norm": 3.78125,
|
| 2087 |
+
"learning_rate": 1.8085190583050166e-06,
|
| 2088 |
+
"loss": 0.378,
|
| 2089 |
+
"step": 9504
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 2.252775809118828,
|
| 2093 |
+
"grad_norm": 6.375,
|
| 2094 |
+
"learning_rate": 1.774787058579799e-06,
|
| 2095 |
+
"loss": 0.3688,
|
| 2096 |
+
"step": 9536
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 2.260335459484999,
|
| 2100 |
+
"grad_norm": 7.625,
|
| 2101 |
+
"learning_rate": 1.7413045980843119e-06,
|
| 2102 |
+
"loss": 0.3841,
|
| 2103 |
+
"step": 9568
|
| 2104 |
+
},
|
| 2105 |
+
{
|
| 2106 |
+
"epoch": 2.2678951098511693,
|
| 2107 |
+
"grad_norm": 5.34375,
|
| 2108 |
+
"learning_rate": 1.7080742674032886e-06,
|
| 2109 |
+
"loss": 0.3937,
|
| 2110 |
+
"step": 9600
|
| 2111 |
+
},
|
| 2112 |
+
{
|
| 2113 |
+
"epoch": 2.27545476021734,
|
| 2114 |
+
"grad_norm": 6.75,
|
| 2115 |
+
"learning_rate": 1.6750986376138207e-06,
|
| 2116 |
+
"loss": 0.3752,
|
| 2117 |
+
"step": 9632
|
| 2118 |
+
},
|
| 2119 |
+
{
|
| 2120 |
+
"epoch": 2.2830144105835104,
|
| 2121 |
+
"grad_norm": 6.40625,
|
| 2122 |
+
"learning_rate": 1.6423802600864436e-06,
|
| 2123 |
+
"loss": 0.394,
|
| 2124 |
+
"step": 9664
|
| 2125 |
+
},
|
| 2126 |
+
{
|
| 2127 |
+
"epoch": 2.290574060949681,
|
| 2128 |
+
"grad_norm": 7.0625,
|
| 2129 |
+
"learning_rate": 1.6099216662877204e-06,
|
| 2130 |
+
"loss": 0.3868,
|
| 2131 |
+
"step": 9696
|
| 2132 |
+
},
|
| 2133 |
+
{
|
| 2134 |
+
"epoch": 2.2981337113158515,
|
| 2135 |
+
"grad_norm": 6.5,
|
| 2136 |
+
"learning_rate": 1.5777253675843873e-06,
|
| 2137 |
+
"loss": 0.4061,
|
| 2138 |
+
"step": 9728
|
| 2139 |
+
},
|
| 2140 |
+
{
|
| 2141 |
+
"epoch": 2.3056933616820223,
|
| 2142 |
+
"grad_norm": 12.25,
|
| 2143 |
+
"learning_rate": 1.5457938550490387e-06,
|
| 2144 |
+
"loss": 0.364,
|
| 2145 |
+
"step": 9760
|
| 2146 |
+
},
|
| 2147 |
+
{
|
| 2148 |
+
"epoch": 2.3132530120481927,
|
| 2149 |
+
"grad_norm": 4.59375,
|
| 2150 |
+
"learning_rate": 1.5141295992674e-06,
|
| 2151 |
+
"loss": 0.3626,
|
| 2152 |
+
"step": 9792
|
| 2153 |
+
},
|
| 2154 |
+
{
|
| 2155 |
+
"epoch": 2.3208126624143635,
|
| 2156 |
+
"grad_norm": 6.125,
|
| 2157 |
+
"learning_rate": 1.482735050147161e-06,
|
| 2158 |
+
"loss": 0.4113,
|
| 2159 |
+
"step": 9824
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 2.328372312780534,
|
| 2163 |
+
"grad_norm": 6.15625,
|
| 2164 |
+
"learning_rate": 1.4516126367284355e-06,
|
| 2165 |
+
"loss": 0.4139,
|
| 2166 |
+
"step": 9856
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"epoch": 2.3359319631467046,
|
| 2170 |
+
"grad_norm": 4.875,
|
| 2171 |
+
"learning_rate": 1.4207647669958186e-06,
|
| 2172 |
+
"loss": 0.3712,
|
| 2173 |
+
"step": 9888
|
| 2174 |
+
},
|
| 2175 |
+
{
|
| 2176 |
+
"epoch": 2.343491613512875,
|
| 2177 |
+
"grad_norm": 6.15625,
|
| 2178 |
+
"learning_rate": 1.3901938276920712e-06,
|
| 2179 |
+
"loss": 0.3864,
|
| 2180 |
+
"step": 9920
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 2.3510512638790457,
|
| 2184 |
+
"grad_norm": 4.6875,
|
| 2185 |
+
"learning_rate": 1.359902184133467e-06,
|
| 2186 |
+
"loss": 0.3999,
|
| 2187 |
+
"step": 9952
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 2.358610914245216,
|
| 2191 |
+
"grad_norm": 6.25,
|
| 2192 |
+
"learning_rate": 1.3298921800267728e-06,
|
| 2193 |
+
"loss": 0.3774,
|
| 2194 |
+
"step": 9984
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 2.366170564611387,
|
| 2198 |
+
"grad_norm": 6.4375,
|
| 2199 |
+
"learning_rate": 1.3001661372879194e-06,
|
| 2200 |
+
"loss": 0.4082,
|
| 2201 |
+
"step": 10016
|
| 2202 |
+
},
|
| 2203 |
+
{
|
| 2204 |
+
"epoch": 2.373730214977557,
|
| 2205 |
+
"grad_norm": 9.1875,
|
| 2206 |
+
"learning_rate": 1.2707263558623483e-06,
|
| 2207 |
+
"loss": 0.3886,
|
| 2208 |
+
"step": 10048
|
| 2209 |
+
},
|
| 2210 |
+
{
|
| 2211 |
+
"epoch": 2.381289865343728,
|
| 2212 |
+
"grad_norm": 5.875,
|
| 2213 |
+
"learning_rate": 1.2415751135470693e-06,
|
| 2214 |
+
"loss": 0.418,
|
| 2215 |
+
"step": 10080
|
| 2216 |
+
},
|
| 2217 |
+
{
|
| 2218 |
+
"epoch": 2.3888495157098983,
|
| 2219 |
+
"grad_norm": 6.5625,
|
| 2220 |
+
"learning_rate": 1.2127146658144095e-06,
|
| 2221 |
+
"loss": 0.3886,
|
| 2222 |
+
"step": 10112
|
| 2223 |
+
},
|
| 2224 |
+
{
|
| 2225 |
+
"epoch": 2.396409166076069,
|
| 2226 |
+
"grad_norm": 6.15625,
|
| 2227 |
+
"learning_rate": 1.1841472456375219e-06,
|
| 2228 |
+
"loss": 0.3816,
|
| 2229 |
+
"step": 10144
|
| 2230 |
+
},
|
| 2231 |
+
{
|
| 2232 |
+
"epoch": 2.4039688164422395,
|
| 2233 |
+
"grad_norm": 4.46875,
|
| 2234 |
+
"learning_rate": 1.1558750633175998e-06,
|
| 2235 |
+
"loss": 0.3795,
|
| 2236 |
+
"step": 10176
|
| 2237 |
+
},
|
| 2238 |
+
{
|
| 2239 |
+
"epoch": 2.4115284668084103,
|
| 2240 |
+
"grad_norm": 4.78125,
|
| 2241 |
+
"learning_rate": 1.1279003063128773e-06,
|
| 2242 |
+
"loss": 0.3967,
|
| 2243 |
+
"step": 10208
|
| 2244 |
+
},
|
| 2245 |
+
{
|
| 2246 |
+
"epoch": 2.4190881171745806,
|
| 2247 |
+
"grad_norm": 4.25,
|
| 2248 |
+
"learning_rate": 1.1002251390693763e-06,
|
| 2249 |
+
"loss": 0.3719,
|
| 2250 |
+
"step": 10240
|
| 2251 |
+
},
|
| 2252 |
+
{
|
| 2253 |
+
"epoch": 2.4266477675407514,
|
| 2254 |
+
"grad_norm": 4.09375,
|
| 2255 |
+
"learning_rate": 1.0728517028534364e-06,
|
| 2256 |
+
"loss": 0.3794,
|
| 2257 |
+
"step": 10272
|
| 2258 |
+
},
|
| 2259 |
+
{
|
| 2260 |
+
"epoch": 2.4342074179069217,
|
| 2261 |
+
"grad_norm": 7.84375,
|
| 2262 |
+
"learning_rate": 1.0457821155860488e-06,
|
| 2263 |
+
"loss": 0.3876,
|
| 2264 |
+
"step": 10304
|
| 2265 |
+
},
|
| 2266 |
+
{
|
| 2267 |
+
"epoch": 2.4417670682730925,
|
| 2268 |
+
"grad_norm": 4.40625,
|
| 2269 |
+
"learning_rate": 1.0190184716789853e-06,
|
| 2270 |
+
"loss": 0.4292,
|
| 2271 |
+
"step": 10336
|
| 2272 |
+
},
|
| 2273 |
+
{
|
| 2274 |
+
"epoch": 2.449326718639263,
|
| 2275 |
+
"grad_norm": 6.78125,
|
| 2276 |
+
"learning_rate": 9.925628418727563e-07,
|
| 2277 |
+
"loss": 0.3976,
|
| 2278 |
+
"step": 10368
|
| 2279 |
+
},
|
| 2280 |
+
{
|
| 2281 |
+
"epoch": 2.4568863690054337,
|
| 2282 |
+
"grad_norm": 4.5,
|
| 2283 |
+
"learning_rate": 9.664172730763872e-07,
|
| 2284 |
+
"loss": 0.4061,
|
| 2285 |
+
"step": 10400
|
| 2286 |
+
},
|
| 2287 |
+
{
|
| 2288 |
+
"epoch": 2.464446019371604,
|
| 2289 |
+
"grad_norm": 5.90625,
|
| 2290 |
+
"learning_rate": 9.405837882090534e-07,
|
| 2291 |
+
"loss": 0.3729,
|
| 2292 |
+
"step": 10432
|
| 2293 |
+
},
|
| 2294 |
+
{
|
| 2295 |
+
"epoch": 2.472005669737775,
|
| 2296 |
+
"grad_norm": 5.65625,
|
| 2297 |
+
"learning_rate": 9.150643860435571e-07,
|
| 2298 |
+
"loss": 0.3747,
|
| 2299 |
+
"step": 10464
|
| 2300 |
+
},
|
| 2301 |
+
{
|
| 2302 |
+
"epoch": 2.479565320103945,
|
| 2303 |
+
"grad_norm": 7.34375,
|
| 2304 |
+
"learning_rate": 8.898610410516873e-07,
|
| 2305 |
+
"loss": 0.3779,
|
| 2306 |
+
"step": 10496
|
| 2307 |
+
},
|
| 2308 |
+
{
|
| 2309 |
+
"epoch": 2.487124970470116,
|
| 2310 |
+
"grad_norm": 5.875,
|
| 2311 |
+
"learning_rate": 8.649757032514439e-07,
|
| 2312 |
+
"loss": 0.3851,
|
| 2313 |
+
"step": 10528
|
| 2314 |
+
},
|
| 2315 |
+
{
|
| 2316 |
+
"epoch": 2.4946846208362863,
|
| 2317 |
+
"grad_norm": 11.0,
|
| 2318 |
+
"learning_rate": 8.404102980561702e-07,
|
| 2319 |
+
"loss": 0.3837,
|
| 2320 |
+
"step": 10560
|
| 2321 |
+
},
|
| 2322 |
+
{
|
| 2323 |
+
"epoch": 2.502244271202457,
|
| 2324 |
+
"grad_norm": 5.3125,
|
| 2325 |
+
"learning_rate": 8.161667261255746e-07,
|
| 2326 |
+
"loss": 0.3362,
|
| 2327 |
+
"step": 10592
|
| 2328 |
+
},
|
| 2329 |
+
{
|
| 2330 |
+
"epoch": 2.5098039215686274,
|
| 2331 |
+
"grad_norm": 7.34375,
|
| 2332 |
+
"learning_rate": 7.922468632186748e-07,
|
| 2333 |
+
"loss": 0.3638,
|
| 2334 |
+
"step": 10624
|
| 2335 |
+
},
|
| 2336 |
+
{
|
| 2337 |
+
"epoch": 2.5173635719347978,
|
| 2338 |
+
"grad_norm": 4.34375,
|
| 2339 |
+
"learning_rate": 7.686525600486743e-07,
|
| 2340 |
+
"loss": 0.3874,
|
| 2341 |
+
"step": 10656
|
| 2342 |
+
},
|
| 2343 |
+
{
|
| 2344 |
+
"epoch": 2.5249232223009686,
|
| 2345 |
+
"grad_norm": 7.53125,
|
| 2346 |
+
"learning_rate": 7.453856421397598e-07,
|
| 2347 |
+
"loss": 0.372,
|
| 2348 |
+
"step": 10688
|
| 2349 |
+
},
|
| 2350 |
+
{
|
| 2351 |
+
"epoch": 2.5324828726671393,
|
| 2352 |
+
"grad_norm": 6.0625,
|
| 2353 |
+
"learning_rate": 7.224479096858672e-07,
|
| 2354 |
+
"loss": 0.4139,
|
| 2355 |
+
"step": 10720
|
| 2356 |
+
},
|
| 2357 |
+
{
|
| 2358 |
+
"epoch": 2.5400425230333097,
|
| 2359 |
+
"grad_norm": 5.125,
|
| 2360 |
+
"learning_rate": 6.9984113741139e-07,
|
| 2361 |
+
"loss": 0.3876,
|
| 2362 |
+
"step": 10752
|
| 2363 |
+
},
|
| 2364 |
+
{
|
| 2365 |
+
"epoch": 2.54760217339948,
|
| 2366 |
+
"grad_norm": 5.40625,
|
| 2367 |
+
"learning_rate": 6.775670744338747e-07,
|
| 2368 |
+
"loss": 0.3811,
|
| 2369 |
+
"step": 10784
|
| 2370 |
+
},
|
| 2371 |
+
{
|
| 2372 |
+
"epoch": 2.555161823765651,
|
| 2373 |
+
"grad_norm": 5.9375,
|
| 2374 |
+
"learning_rate": 6.556274441286809e-07,
|
| 2375 |
+
"loss": 0.3698,
|
| 2376 |
+
"step": 10816
|
| 2377 |
+
},
|
| 2378 |
+
{
|
| 2379 |
+
"epoch": 2.5627214741318216,
|
| 2380 |
+
"grad_norm": 4.09375,
|
| 2381 |
+
"learning_rate": 6.340239439956486e-07,
|
| 2382 |
+
"loss": 0.3724,
|
| 2383 |
+
"step": 10848
|
| 2384 |
+
},
|
| 2385 |
+
{
|
| 2386 |
+
"epoch": 2.570281124497992,
|
| 2387 |
+
"grad_norm": 7.3125,
|
| 2388 |
+
"learning_rate": 6.127582455277547e-07,
|
| 2389 |
+
"loss": 0.4228,
|
| 2390 |
+
"step": 10880
|
| 2391 |
+
},
|
| 2392 |
+
{
|
| 2393 |
+
"epoch": 2.5778407748641623,
|
| 2394 |
+
"grad_norm": 5.8125,
|
| 2395 |
+
"learning_rate": 5.918319940817884e-07,
|
| 2396 |
+
"loss": 0.3607,
|
| 2397 |
+
"step": 10912
|
| 2398 |
+
},
|
| 2399 |
+
{
|
| 2400 |
+
"epoch": 2.585400425230333,
|
| 2401 |
+
"grad_norm": 10.625,
|
| 2402 |
+
"learning_rate": 5.712468087510536e-07,
|
| 2403 |
+
"loss": 0.3846,
|
| 2404 |
+
"step": 10944
|
| 2405 |
+
},
|
| 2406 |
+
{
|
| 2407 |
+
"epoch": 2.592960075596504,
|
| 2408 |
+
"grad_norm": 8.375,
|
| 2409 |
+
"learning_rate": 5.510042822400868e-07,
|
| 2410 |
+
"loss": 0.4124,
|
| 2411 |
+
"step": 10976
|
| 2412 |
+
},
|
| 2413 |
+
{
|
| 2414 |
+
"epoch": 2.6005197259626742,
|
| 2415 |
+
"grad_norm": 6.0,
|
| 2416 |
+
"learning_rate": 5.311059807414376e-07,
|
| 2417 |
+
"loss": 0.3939,
|
| 2418 |
+
"step": 11008
|
| 2419 |
+
},
|
| 2420 |
+
{
|
| 2421 |
+
"epoch": 2.6080793763288446,
|
| 2422 |
+
"grad_norm": 7.96875,
|
| 2423 |
+
"learning_rate": 5.11553443814482e-07,
|
| 2424 |
+
"loss": 0.4022,
|
| 2425 |
+
"step": 11040
|
| 2426 |
+
},
|
| 2427 |
+
{
|
| 2428 |
+
"epoch": 2.6156390266950154,
|
| 2429 |
+
"grad_norm": 9.1875,
|
| 2430 |
+
"learning_rate": 4.923481842663114e-07,
|
| 2431 |
+
"loss": 0.3872,
|
| 2432 |
+
"step": 11072
|
| 2433 |
+
},
|
| 2434 |
+
{
|
| 2435 |
+
"epoch": 2.623198677061186,
|
| 2436 |
+
"grad_norm": 5.65625,
|
| 2437 |
+
"learning_rate": 4.734916880346774e-07,
|
| 2438 |
+
"loss": 0.4234,
|
| 2439 |
+
"step": 11104
|
| 2440 |
+
},
|
| 2441 |
+
{
|
| 2442 |
+
"epoch": 2.6307583274273565,
|
| 2443 |
+
"grad_norm": 12.0,
|
| 2444 |
+
"learning_rate": 4.549854140730325e-07,
|
| 2445 |
+
"loss": 0.3591,
|
| 2446 |
+
"step": 11136
|
| 2447 |
+
},
|
| 2448 |
+
{
|
| 2449 |
+
"epoch": 2.638317977793527,
|
| 2450 |
+
"grad_norm": 4.78125,
|
| 2451 |
+
"learning_rate": 4.368307942376371e-07,
|
| 2452 |
+
"loss": 0.4013,
|
| 2453 |
+
"step": 11168
|
| 2454 |
+
},
|
| 2455 |
+
{
|
| 2456 |
+
"epoch": 2.6458776281596976,
|
| 2457 |
+
"grad_norm": 8.8125,
|
| 2458 |
+
"learning_rate": 4.190292331767848e-07,
|
| 2459 |
+
"loss": 0.3419,
|
| 2460 |
+
"step": 11200
|
| 2461 |
+
},
|
| 2462 |
+
{
|
| 2463 |
+
"epoch": 2.6534372785258684,
|
| 2464 |
+
"grad_norm": 5.4375,
|
| 2465 |
+
"learning_rate": 4.0158210822211496e-07,
|
| 2466 |
+
"loss": 0.384,
|
| 2467 |
+
"step": 11232
|
| 2468 |
+
},
|
| 2469 |
+
{
|
| 2470 |
+
"epoch": 2.6609969288920388,
|
| 2471 |
+
"grad_norm": 7.28125,
|
| 2472 |
+
"learning_rate": 3.844907692820543e-07,
|
| 2473 |
+
"loss": 0.3919,
|
| 2474 |
+
"step": 11264
|
| 2475 |
+
},
|
| 2476 |
+
{
|
| 2477 |
+
"epoch": 2.668556579258209,
|
| 2478 |
+
"grad_norm": 4.625,
|
| 2479 |
+
"learning_rate": 3.6775653873736774e-07,
|
| 2480 |
+
"loss": 0.3707,
|
| 2481 |
+
"step": 11296
|
| 2482 |
+
},
|
| 2483 |
+
{
|
| 2484 |
+
"epoch": 2.67611622962438,
|
| 2485 |
+
"grad_norm": 5.96875,
|
| 2486 |
+
"learning_rate": 3.5138071133884235e-07,
|
| 2487 |
+
"loss": 0.372,
|
| 2488 |
+
"step": 11328
|
| 2489 |
+
},
|
| 2490 |
+
{
|
| 2491 |
+
"epoch": 2.6836758799905507,
|
| 2492 |
+
"grad_norm": 5.96875,
|
| 2493 |
+
"learning_rate": 3.3536455410711654e-07,
|
| 2494 |
+
"loss": 0.3835,
|
| 2495 |
+
"step": 11360
|
| 2496 |
+
},
|
| 2497 |
+
{
|
| 2498 |
+
"epoch": 2.691235530356721,
|
| 2499 |
+
"grad_norm": 7.28125,
|
| 2500 |
+
"learning_rate": 3.1970930623464403e-07,
|
| 2501 |
+
"loss": 0.3677,
|
| 2502 |
+
"step": 11392
|
| 2503 |
+
},
|
| 2504 |
+
{
|
| 2505 |
+
"epoch": 2.6987951807228914,
|
| 2506 |
+
"grad_norm": 5.3125,
|
| 2507 |
+
"learning_rate": 3.044161789898159e-07,
|
| 2508 |
+
"loss": 0.3694,
|
| 2509 |
+
"step": 11424
|
| 2510 |
+
},
|
| 2511 |
+
{
|
| 2512 |
+
"epoch": 2.706354831089062,
|
| 2513 |
+
"grad_norm": 7.46875,
|
| 2514 |
+
"learning_rate": 2.8948635562324747e-07,
|
| 2515 |
+
"loss": 0.3782,
|
| 2516 |
+
"step": 11456
|
| 2517 |
+
},
|
| 2518 |
+
{
|
| 2519 |
+
"epoch": 2.713914481455233,
|
| 2520 |
+
"grad_norm": 6.0625,
|
| 2521 |
+
"learning_rate": 2.749209912762241e-07,
|
| 2522 |
+
"loss": 0.3956,
|
| 2523 |
+
"step": 11488
|
| 2524 |
+
},
|
| 2525 |
+
{
|
| 2526 |
+
"epoch": 2.7214741318214033,
|
| 2527 |
+
"grad_norm": 6.09375,
|
| 2528 |
+
"learning_rate": 2.607212128913267e-07,
|
| 2529 |
+
"loss": 0.406,
|
| 2530 |
+
"step": 11520
|
| 2531 |
+
},
|
| 2532 |
+
{
|
| 2533 |
+
"epoch": 2.7290337821875736,
|
| 2534 |
+
"grad_norm": 8.75,
|
| 2535 |
+
"learning_rate": 2.4688811912524204e-07,
|
| 2536 |
+
"loss": 0.3621,
|
| 2537 |
+
"step": 11552
|
| 2538 |
+
},
|
| 2539 |
+
{
|
| 2540 |
+
"epoch": 2.7365934325537444,
|
| 2541 |
+
"grad_norm": 4.65625,
|
| 2542 |
+
"learning_rate": 2.3342278026375397e-07,
|
| 2543 |
+
"loss": 0.3859,
|
| 2544 |
+
"step": 11584
|
| 2545 |
+
},
|
| 2546 |
+
{
|
| 2547 |
+
"epoch": 2.744153082919915,
|
| 2548 |
+
"grad_norm": 5.9375,
|
| 2549 |
+
"learning_rate": 2.203262381389365e-07,
|
| 2550 |
+
"loss": 0.3772,
|
| 2551 |
+
"step": 11616
|
| 2552 |
+
},
|
| 2553 |
+
{
|
| 2554 |
+
"epoch": 2.7517127332860856,
|
| 2555 |
+
"grad_norm": 5.21875,
|
| 2556 |
+
"learning_rate": 2.0759950604854583e-07,
|
| 2557 |
+
"loss": 0.3757,
|
| 2558 |
+
"step": 11648
|
| 2559 |
+
},
|
| 2560 |
+
{
|
| 2561 |
+
"epoch": 2.759272383652256,
|
| 2562 |
+
"grad_norm": 6.09375,
|
| 2563 |
+
"learning_rate": 1.9524356867761772e-07,
|
| 2564 |
+
"loss": 0.4159,
|
| 2565 |
+
"step": 11680
|
| 2566 |
+
},
|
| 2567 |
+
{
|
| 2568 |
+
"epoch": 2.7668320340184267,
|
| 2569 |
+
"grad_norm": 7.15625,
|
| 2570 |
+
"learning_rate": 1.8325938202228276e-07,
|
| 2571 |
+
"loss": 0.374,
|
| 2572 |
+
"step": 11712
|
| 2573 |
+
},
|
| 2574 |
+
{
|
| 2575 |
+
"epoch": 2.7743916843845975,
|
| 2576 |
+
"grad_norm": 5.5,
|
| 2577 |
+
"learning_rate": 1.7164787331580058e-07,
|
| 2578 |
+
"loss": 0.3731,
|
| 2579 |
+
"step": 11744
|
| 2580 |
+
},
|
| 2581 |
+
{
|
| 2582 |
+
"epoch": 2.781951334750768,
|
| 2583 |
+
"grad_norm": 6.375,
|
| 2584 |
+
"learning_rate": 1.6040994095681716e-07,
|
| 2585 |
+
"loss": 0.3725,
|
| 2586 |
+
"step": 11776
|
| 2587 |
+
},
|
| 2588 |
+
{
|
| 2589 |
+
"epoch": 2.789510985116938,
|
| 2590 |
+
"grad_norm": 5.125,
|
| 2591 |
+
"learning_rate": 1.4954645443985337e-07,
|
| 2592 |
+
"loss": 0.4074,
|
| 2593 |
+
"step": 11808
|
| 2594 |
+
},
|
| 2595 |
+
{
|
| 2596 |
+
"epoch": 2.797070635483109,
|
| 2597 |
+
"grad_norm": 5.3125,
|
| 2598 |
+
"learning_rate": 1.3905825428803477e-07,
|
| 2599 |
+
"loss": 0.3863,
|
| 2600 |
+
"step": 11840
|
| 2601 |
+
},
|
| 2602 |
+
{
|
| 2603 |
+
"epoch": 2.8046302858492793,
|
| 2604 |
+
"grad_norm": 3.828125,
|
| 2605 |
+
"learning_rate": 1.2894615198805415e-07,
|
| 2606 |
+
"loss": 0.3922,
|
| 2607 |
+
"step": 11872
|
| 2608 |
+
},
|
| 2609 |
+
{
|
| 2610 |
+
"epoch": 2.81218993621545,
|
| 2611 |
+
"grad_norm": 6.4375,
|
| 2612 |
+
"learning_rate": 1.1921092992739025e-07,
|
| 2613 |
+
"loss": 0.3889,
|
| 2614 |
+
"step": 11904
|
| 2615 |
+
},
|
| 2616 |
+
{
|
| 2617 |
+
"epoch": 2.8197495865816204,
|
| 2618 |
+
"grad_norm": 7.75,
|
| 2619 |
+
"learning_rate": 1.0985334133376991e-07,
|
| 2620 |
+
"loss": 0.3989,
|
| 2621 |
+
"step": 11936
|
| 2622 |
+
},
|
| 2623 |
+
{
|
| 2624 |
+
"epoch": 2.8273092369477912,
|
| 2625 |
+
"grad_norm": 8.0,
|
| 2626 |
+
"learning_rate": 1.0087411021689252e-07,
|
| 2627 |
+
"loss": 0.3941,
|
| 2628 |
+
"step": 11968
|
| 2629 |
+
},
|
| 2630 |
+
{
|
| 2631 |
+
"epoch": 2.8348688873139616,
|
| 2632 |
+
"grad_norm": 5.5,
|
| 2633 |
+
"learning_rate": 9.227393131240992e-08,
|
| 2634 |
+
"loss": 0.3675,
|
| 2635 |
+
"step": 12000
|
| 2636 |
+
},
|
| 2637 |
+
{
|
| 2638 |
+
"epoch": 2.8424285376801324,
|
| 2639 |
+
"grad_norm": 5.09375,
|
| 2640 |
+
"learning_rate": 8.405347002817421e-08,
|
| 2641 |
+
"loss": 0.3858,
|
| 2642 |
+
"step": 12032
|
| 2643 |
+
},
|
| 2644 |
+
{
|
| 2645 |
+
"epoch": 2.8499881880463027,
|
| 2646 |
+
"grad_norm": 6.09375,
|
| 2647 |
+
"learning_rate": 7.6213362392758e-08,
|
| 2648 |
+
"loss": 0.4184,
|
| 2649 |
+
"step": 12064
|
| 2650 |
+
},
|
| 2651 |
+
{
|
| 2652 |
+
"epoch": 2.8575478384124735,
|
| 2653 |
+
"grad_norm": 8.9375,
|
| 2654 |
+
"learning_rate": 6.875421500623703e-08,
|
| 2655 |
+
"loss": 0.3729,
|
| 2656 |
+
"step": 12096
|
| 2657 |
+
},
|
| 2658 |
+
{
|
| 2659 |
+
"epoch": 2.865107488778644,
|
| 2660 |
+
"grad_norm": 7.1875,
|
| 2661 |
+
"learning_rate": 6.167660499326322e-08,
|
| 2662 |
+
"loss": 0.3836,
|
| 2663 |
+
"step": 12128
|
| 2664 |
+
},
|
| 2665 |
+
{
|
| 2666 |
+
"epoch": 2.8726671391448146,
|
| 2667 |
+
"grad_norm": 4.59375,
|
| 2668 |
+
"learning_rate": 5.498107995840774e-08,
|
| 2669 |
+
"loss": 0.3789,
|
| 2670 |
+
"step": 12160
|
| 2671 |
+
},
|
| 2672 |
+
{
|
| 2673 |
+
"epoch": 2.880226789510985,
|
| 2674 |
+
"grad_norm": 10.125,
|
| 2675 |
+
"learning_rate": 4.86681579437942e-08,
|
| 2676 |
+
"loss": 0.4012,
|
| 2677 |
+
"step": 12192
|
| 2678 |
+
},
|
| 2679 |
+
{
|
| 2680 |
+
"epoch": 2.8877864398771558,
|
| 2681 |
+
"grad_norm": 4.21875,
|
| 2682 |
+
"learning_rate": 4.273832738901529e-08,
|
| 2683 |
+
"loss": 0.365,
|
| 2684 |
+
"step": 12224
|
| 2685 |
+
},
|
| 2686 |
+
{
|
| 2687 |
+
"epoch": 2.895346090243326,
|
| 2688 |
+
"grad_norm": 6.0625,
|
| 2689 |
+
"learning_rate": 3.719204709334345e-08,
|
| 2690 |
+
"loss": 0.3903,
|
| 2691 |
+
"step": 12256
|
| 2692 |
+
},
|
| 2693 |
+
{
|
| 2694 |
+
"epoch": 2.902905740609497,
|
| 2695 |
+
"grad_norm": 5.5625,
|
| 2696 |
+
"learning_rate": 3.2029746180231023e-08,
|
| 2697 |
+
"loss": 0.4063,
|
| 2698 |
+
"step": 12288
|
| 2699 |
+
},
|
| 2700 |
+
{
|
| 2701 |
+
"epoch": 2.9104653909756673,
|
| 2702 |
+
"grad_norm": 6.8125,
|
| 2703 |
+
"learning_rate": 2.725182406410842e-08,
|
| 2704 |
+
"loss": 0.3909,
|
| 2705 |
+
"step": 12320
|
| 2706 |
+
},
|
| 2707 |
+
{
|
| 2708 |
+
"epoch": 2.918025041341838,
|
| 2709 |
+
"grad_norm": 4.0625,
|
| 2710 |
+
"learning_rate": 2.2858650419484985e-08,
|
| 2711 |
+
"loss": 0.3711,
|
| 2712 |
+
"step": 12352
|
| 2713 |
+
},
|
| 2714 |
+
{
|
| 2715 |
+
"epoch": 2.9255846917080084,
|
| 2716 |
+
"grad_norm": 5.71875,
|
| 2717 |
+
"learning_rate": 1.8850565152339072e-08,
|
| 2718 |
+
"loss": 0.3463,
|
| 2719 |
+
"step": 12384
|
| 2720 |
+
},
|
| 2721 |
+
{
|
| 2722 |
+
"epoch": 2.933144342074179,
|
| 2723 |
+
"grad_norm": 5.0,
|
| 2724 |
+
"learning_rate": 1.5227878373827443e-08,
|
| 2725 |
+
"loss": 0.443,
|
| 2726 |
+
"step": 12416
|
| 2727 |
+
},
|
| 2728 |
+
{
|
| 2729 |
+
"epoch": 2.9407039924403495,
|
| 2730 |
+
"grad_norm": 4.78125,
|
| 2731 |
+
"learning_rate": 1.1990870376284435e-08,
|
| 2732 |
+
"loss": 0.405,
|
| 2733 |
+
"step": 12448
|
| 2734 |
+
},
|
| 2735 |
+
{
|
| 2736 |
+
"epoch": 2.9482636428065203,
|
| 2737 |
+
"grad_norm": 6.25,
|
| 2738 |
+
"learning_rate": 9.139791611540438e-09,
|
| 2739 |
+
"loss": 0.3871,
|
| 2740 |
+
"step": 12480
|
| 2741 |
+
},
|
| 2742 |
+
{
|
| 2743 |
+
"epoch": 2.9558232931726907,
|
| 2744 |
+
"grad_norm": 5.28125,
|
| 2745 |
+
"learning_rate": 6.6748626715407165e-09,
|
| 2746 |
+
"loss": 0.4238,
|
| 2747 |
+
"step": 12512
|
| 2748 |
+
},
|
| 2749 |
+
{
|
| 2750 |
+
"epoch": 2.9633829435388614,
|
| 2751 |
+
"grad_norm": 6.46875,
|
| 2752 |
+
"learning_rate": 4.596274271280732e-09,
|
| 2753 |
+
"loss": 0.3852,
|
| 2754 |
+
"step": 12544
|
| 2755 |
+
},
|
| 2756 |
+
{
|
| 2757 |
+
"epoch": 2.970942593905032,
|
| 2758 |
+
"grad_norm": 5.8125,
|
| 2759 |
+
"learning_rate": 2.9041872340479505e-09,
|
| 2760 |
+
"loss": 0.3845,
|
| 2761 |
+
"step": 12576
|
| 2762 |
+
},
|
| 2763 |
+
{
|
| 2764 |
+
"epoch": 2.9785022442712026,
|
| 2765 |
+
"grad_norm": 4.21875,
|
| 2766 |
+
"learning_rate": 1.59873247897957e-09,
|
| 2767 |
+
"loss": 0.4169,
|
| 2768 |
+
"step": 12608
|
| 2769 |
+
},
|
| 2770 |
+
{
|
| 2771 |
+
"epoch": 2.986061894637373,
|
| 2772 |
+
"grad_norm": 5.96875,
|
| 2773 |
+
"learning_rate": 6.800110109328462e-10,
|
| 2774 |
+
"loss": 0.3872,
|
| 2775 |
+
"step": 12640
|
| 2776 |
+
},
|
| 2777 |
+
{
|
| 2778 |
+
"epoch": 2.9936215450035437,
|
| 2779 |
+
"grad_norm": 11.125,
|
| 2780 |
+
"learning_rate": 1.480939126713432e-10,
|
| 2781 |
+
"loss": 0.3957,
|
| 2782 |
+
"step": 12672
|
| 2783 |
+
},
|
| 2784 |
+
{
|
| 2785 |
+
"epoch": 3.0,
|
| 2786 |
+
"step": 12699,
|
| 2787 |
+
"total_flos": 2.247355191985367e+17,
|
| 2788 |
+
"train_loss": 0.4236195460108568,
|
| 2789 |
+
"train_runtime": 3683.6752,
|
| 2790 |
+
"train_samples_per_second": 13.789,
|
| 2791 |
+
"train_steps_per_second": 3.447
|
| 2792 |
+
}
|
| 2793 |
+
],
|
| 2794 |
+
"logging_steps": 32,
|
| 2795 |
+
"max_steps": 12699,
|
| 2796 |
+
"num_input_tokens_seen": 0,
|
| 2797 |
+
"num_train_epochs": 3,
|
| 2798 |
+
"save_steps": 500,
|
| 2799 |
+
"stateful_callbacks": {
|
| 2800 |
+
"TrainerControl": {
|
| 2801 |
+
"args": {
|
| 2802 |
+
"should_epoch_stop": false,
|
| 2803 |
+
"should_evaluate": false,
|
| 2804 |
+
"should_log": false,
|
| 2805 |
+
"should_save": false,
|
| 2806 |
+
"should_training_stop": false
|
| 2807 |
+
},
|
| 2808 |
+
"attributes": {}
|
| 2809 |
+
}
|
| 2810 |
+
},
|
| 2811 |
+
"total_flos": 2.247355191985367e+17,
|
| 2812 |
+
"train_batch_size": 4,
|
| 2813 |
+
"trial_name": null,
|
| 2814 |
+
"trial_params": null
|
| 2815 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:800acf4bdffc93294d275d853cf5c6da0335aefda2fadf62dcdaf7d18dff5711
|
| 3 |
+
size 5777
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|