Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- added_tokens.json +28 -0
- chat_template.jinja +89 -0
- config.json +60 -0
- generation_config.json +12 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +25 -0
- tokenizer.json +3 -0
- tokenizer_config.json +239 -0
- trainer_state.json +1890 -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 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</think>": 151668,
|
| 3 |
+
"</tool_call>": 151658,
|
| 4 |
+
"</tool_response>": 151666,
|
| 5 |
+
"<think>": 151667,
|
| 6 |
+
"<tool_call>": 151657,
|
| 7 |
+
"<tool_response>": 151665,
|
| 8 |
+
"<|box_end|>": 151649,
|
| 9 |
+
"<|box_start|>": 151648,
|
| 10 |
+
"<|endoftext|>": 151643,
|
| 11 |
+
"<|file_sep|>": 151664,
|
| 12 |
+
"<|fim_middle|>": 151660,
|
| 13 |
+
"<|fim_pad|>": 151662,
|
| 14 |
+
"<|fim_prefix|>": 151659,
|
| 15 |
+
"<|fim_suffix|>": 151661,
|
| 16 |
+
"<|im_end|>": 151645,
|
| 17 |
+
"<|im_start|>": 151644,
|
| 18 |
+
"<|image_pad|>": 151655,
|
| 19 |
+
"<|object_ref_end|>": 151647,
|
| 20 |
+
"<|object_ref_start|>": 151646,
|
| 21 |
+
"<|quad_end|>": 151651,
|
| 22 |
+
"<|quad_start|>": 151650,
|
| 23 |
+
"<|repo_name|>": 151663,
|
| 24 |
+
"<|video_pad|>": 151656,
|
| 25 |
+
"<|vision_end|>": 151653,
|
| 26 |
+
"<|vision_pad|>": 151654,
|
| 27 |
+
"<|vision_start|>": 151652
|
| 28 |
+
}
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,89 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0].role == 'system' %}
|
| 4 |
+
{{- messages[0].content + '\n\n' }}
|
| 5 |
+
{%- endif %}
|
| 6 |
+
{{- "# 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>" }}
|
| 7 |
+
{%- for tool in tools %}
|
| 8 |
+
{{- "\n" }}
|
| 9 |
+
{{- tool | tojson }}
|
| 10 |
+
{%- endfor %}
|
| 11 |
+
{{- "\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" }}
|
| 12 |
+
{%- else %}
|
| 13 |
+
{%- if messages[0].role == 'system' %}
|
| 14 |
+
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
| 15 |
+
{%- endif %}
|
| 16 |
+
{%- endif %}
|
| 17 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 18 |
+
{%- for message in messages[::-1] %}
|
| 19 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 20 |
+
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
| 21 |
+
{%- set ns.multi_step_tool = false %}
|
| 22 |
+
{%- set ns.last_query_index = index %}
|
| 23 |
+
{%- endif %}
|
| 24 |
+
{%- endfor %}
|
| 25 |
+
{%- for message in messages %}
|
| 26 |
+
{%- if message.content is string %}
|
| 27 |
+
{%- set content = message.content %}
|
| 28 |
+
{%- else %}
|
| 29 |
+
{%- set content = '' %}
|
| 30 |
+
{%- endif %}
|
| 31 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
| 32 |
+
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 33 |
+
{%- elif message.role == "assistant" %}
|
| 34 |
+
{%- set reasoning_content = '' %}
|
| 35 |
+
{%- if message.reasoning_content is string %}
|
| 36 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 37 |
+
{%- else %}
|
| 38 |
+
{%- if '</think>' in content %}
|
| 39 |
+
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 40 |
+
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
| 41 |
+
{%- endif %}
|
| 42 |
+
{%- endif %}
|
| 43 |
+
{%- if loop.index0 > ns.last_query_index %}
|
| 44 |
+
{%- if loop.last or (not loop.last and reasoning_content) %}
|
| 45 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
| 46 |
+
{%- else %}
|
| 47 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 48 |
+
{%- endif %}
|
| 49 |
+
{%- else %}
|
| 50 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 51 |
+
{%- endif %}
|
| 52 |
+
{%- if message.tool_calls %}
|
| 53 |
+
{%- for tool_call in message.tool_calls %}
|
| 54 |
+
{%- if (loop.first and content) or (not loop.first) %}
|
| 55 |
+
{{- '\n' }}
|
| 56 |
+
{%- endif %}
|
| 57 |
+
{%- if tool_call.function %}
|
| 58 |
+
{%- set tool_call = tool_call.function %}
|
| 59 |
+
{%- endif %}
|
| 60 |
+
{{- '<tool_call>\n{"name": "' }}
|
| 61 |
+
{{- tool_call.name }}
|
| 62 |
+
{{- '", "arguments": ' }}
|
| 63 |
+
{%- if tool_call.arguments is string %}
|
| 64 |
+
{{- tool_call.arguments }}
|
| 65 |
+
{%- else %}
|
| 66 |
+
{{- tool_call.arguments | tojson }}
|
| 67 |
+
{%- endif %}
|
| 68 |
+
{{- '}\n</tool_call>' }}
|
| 69 |
+
{%- endfor %}
|
| 70 |
+
{%- endif %}
|
| 71 |
+
{{- '<|im_end|>\n' }}
|
| 72 |
+
{%- elif message.role == "tool" %}
|
| 73 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 74 |
+
{{- '<|im_start|>user' }}
|
| 75 |
+
{%- endif %}
|
| 76 |
+
{{- '\n<tool_response>\n' }}
|
| 77 |
+
{{- content }}
|
| 78 |
+
{{- '\n</tool_response>' }}
|
| 79 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 80 |
+
{{- '<|im_end|>\n' }}
|
| 81 |
+
{%- endif %}
|
| 82 |
+
{%- endif %}
|
| 83 |
+
{%- endfor %}
|
| 84 |
+
{%- if add_generation_prompt %}
|
| 85 |
+
{{- '<|im_start|>assistant\n' }}
|
| 86 |
+
{%- if enable_thinking is defined and enable_thinking is false %}
|
| 87 |
+
{{- '<think>\n\n</think>\n\n' }}
|
| 88 |
+
{%- endif %}
|
| 89 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"dtype": "bfloat16",
|
| 8 |
+
"eos_token_id": 151645,
|
| 9 |
+
"head_dim": 128,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 1024,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 3072,
|
| 14 |
+
"layer_types": [
|
| 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 |
+
"full_attention",
|
| 42 |
+
"full_attention"
|
| 43 |
+
],
|
| 44 |
+
"max_position_embeddings": 40960,
|
| 45 |
+
"max_window_layers": 28,
|
| 46 |
+
"model_type": "qwen3",
|
| 47 |
+
"num_attention_heads": 16,
|
| 48 |
+
"num_hidden_layers": 28,
|
| 49 |
+
"num_key_value_heads": 8,
|
| 50 |
+
"pad_token_id": 151645,
|
| 51 |
+
"rms_norm_eps": 1e-06,
|
| 52 |
+
"rope_scaling": null,
|
| 53 |
+
"rope_theta": 1000000,
|
| 54 |
+
"sliding_window": null,
|
| 55 |
+
"tie_word_embeddings": true,
|
| 56 |
+
"transformers_version": "4.57.3",
|
| 57 |
+
"use_cache": true,
|
| 58 |
+
"use_sliding_window": false,
|
| 59 |
+
"vocab_size": 151669
|
| 60 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_sample": true,
|
| 3 |
+
"eos_token_id": [
|
| 4 |
+
151645,
|
| 5 |
+
151643
|
| 6 |
+
],
|
| 7 |
+
"pad_token_id": 151645,
|
| 8 |
+
"temperature": 0.6,
|
| 9 |
+
"top_k": 20,
|
| 10 |
+
"top_p": 0.95,
|
| 11 |
+
"transformers_version": "4.57.3"
|
| 12 |
+
}
|
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:da0a12eb3ad86c86c0b09b30112c5072c1c5ceeb9631e6ba89e4599eef8dc346
|
| 3 |
+
size 1191588280
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f8472912f4fa3feeff5ee907deae55c921053351e7a7f6b36d8882b8237703e1
|
| 3 |
+
size 3628043
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef9acad5dfe6355012be16c2854f2d692974d86e83413f9cfdf1067fc122d44c
|
| 3 |
+
size 14645
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6a531435eae04e8235804d04df93951cd9b6b4b80afa9c7e68f2ff2d1734526
|
| 3 |
+
size 1465
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": "<|im_end|>"
|
| 25 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
| 3 |
+
size 11422654
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,239 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"151665": {
|
| 182 |
+
"content": "<tool_response>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"151666": {
|
| 190 |
+
"content": "</tool_response>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"151667": {
|
| 198 |
+
"content": "<think>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"151668": {
|
| 206 |
+
"content": "</think>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
}
|
| 213 |
+
},
|
| 214 |
+
"additional_special_tokens": [
|
| 215 |
+
"<|im_start|>",
|
| 216 |
+
"<|im_end|>",
|
| 217 |
+
"<|object_ref_start|>",
|
| 218 |
+
"<|object_ref_end|>",
|
| 219 |
+
"<|box_start|>",
|
| 220 |
+
"<|box_end|>",
|
| 221 |
+
"<|quad_start|>",
|
| 222 |
+
"<|quad_end|>",
|
| 223 |
+
"<|vision_start|>",
|
| 224 |
+
"<|vision_end|>",
|
| 225 |
+
"<|vision_pad|>",
|
| 226 |
+
"<|image_pad|>",
|
| 227 |
+
"<|video_pad|>"
|
| 228 |
+
],
|
| 229 |
+
"bos_token": null,
|
| 230 |
+
"clean_up_tokenization_spaces": false,
|
| 231 |
+
"eos_token": "<|im_end|>",
|
| 232 |
+
"errors": "replace",
|
| 233 |
+
"extra_special_tokens": {},
|
| 234 |
+
"model_max_length": 131072,
|
| 235 |
+
"pad_token": "<|im_end|>",
|
| 236 |
+
"split_special_tokens": false,
|
| 237 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 238 |
+
"unk_token": null
|
| 239 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1890 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 1995,
|
| 3 |
+
"best_metric": 0.13476963341236115,
|
| 4 |
+
"best_model_checkpoint": "models/qwen3-0.6b-distilled/checkpoint-1995",
|
| 5 |
+
"epoch": 1.8805090737685601,
|
| 6 |
+
"eval_steps": 35,
|
| 7 |
+
"global_step": 1995,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.0009427292010370022,
|
| 14 |
+
"grad_norm": 38.25,
|
| 15 |
+
"learning_rate": 0.0,
|
| 16 |
+
"loss": 1.0185,
|
| 17 |
+
"step": 1
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.009427292010370021,
|
| 21 |
+
"grad_norm": 27.125,
|
| 22 |
+
"learning_rate": 1.8000000000000001e-06,
|
| 23 |
+
"loss": 0.8484,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.018854584020740042,
|
| 28 |
+
"grad_norm": 12.1875,
|
| 29 |
+
"learning_rate": 3.8000000000000005e-06,
|
| 30 |
+
"loss": 0.6648,
|
| 31 |
+
"step": 20
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.028281876031110063,
|
| 35 |
+
"grad_norm": 15.5,
|
| 36 |
+
"learning_rate": 5.8e-06,
|
| 37 |
+
"loss": 0.4851,
|
| 38 |
+
"step": 30
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.03299552203629508,
|
| 42 |
+
"eval_loss": 0.31027188897132874,
|
| 43 |
+
"eval_runtime": 3.3754,
|
| 44 |
+
"eval_samples_per_second": 12.739,
|
| 45 |
+
"eval_steps_per_second": 12.739,
|
| 46 |
+
"step": 35
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.037709168041480084,
|
| 50 |
+
"grad_norm": 10.75,
|
| 51 |
+
"learning_rate": 7.800000000000002e-06,
|
| 52 |
+
"loss": 0.4117,
|
| 53 |
+
"step": 40
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.047136460051850106,
|
| 57 |
+
"grad_norm": 9.4375,
|
| 58 |
+
"learning_rate": 9.800000000000001e-06,
|
| 59 |
+
"loss": 0.2625,
|
| 60 |
+
"step": 50
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.05656375206222013,
|
| 64 |
+
"grad_norm": 9.5625,
|
| 65 |
+
"learning_rate": 1.18e-05,
|
| 66 |
+
"loss": 0.2868,
|
| 67 |
+
"step": 60
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 0.06599104407259015,
|
| 71 |
+
"grad_norm": 10.625,
|
| 72 |
+
"learning_rate": 1.38e-05,
|
| 73 |
+
"loss": 0.2278,
|
| 74 |
+
"step": 70
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.06599104407259015,
|
| 78 |
+
"eval_loss": 0.22450809180736542,
|
| 79 |
+
"eval_runtime": 3.3497,
|
| 80 |
+
"eval_samples_per_second": 12.837,
|
| 81 |
+
"eval_steps_per_second": 12.837,
|
| 82 |
+
"step": 70
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.07541833608296017,
|
| 86 |
+
"grad_norm": 7.75,
|
| 87 |
+
"learning_rate": 1.58e-05,
|
| 88 |
+
"loss": 0.2753,
|
| 89 |
+
"step": 80
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.0848456280933302,
|
| 93 |
+
"grad_norm": 7.5625,
|
| 94 |
+
"learning_rate": 1.7800000000000002e-05,
|
| 95 |
+
"loss": 0.2747,
|
| 96 |
+
"step": 90
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 0.09427292010370021,
|
| 100 |
+
"grad_norm": 6.6875,
|
| 101 |
+
"learning_rate": 1.98e-05,
|
| 102 |
+
"loss": 0.2809,
|
| 103 |
+
"step": 100
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 0.09898656610888522,
|
| 107 |
+
"eval_loss": 0.21436083316802979,
|
| 108 |
+
"eval_runtime": 3.3464,
|
| 109 |
+
"eval_samples_per_second": 12.85,
|
| 110 |
+
"eval_steps_per_second": 12.85,
|
| 111 |
+
"step": 105
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.10370021211407024,
|
| 115 |
+
"grad_norm": 7.125,
|
| 116 |
+
"learning_rate": 1.991097922848665e-05,
|
| 117 |
+
"loss": 0.2175,
|
| 118 |
+
"step": 110
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 0.11312750412444025,
|
| 122 |
+
"grad_norm": 7.28125,
|
| 123 |
+
"learning_rate": 1.9812067260138478e-05,
|
| 124 |
+
"loss": 0.2321,
|
| 125 |
+
"step": 120
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 0.12255479613481028,
|
| 129 |
+
"grad_norm": 5.28125,
|
| 130 |
+
"learning_rate": 1.971315529179031e-05,
|
| 131 |
+
"loss": 0.1813,
|
| 132 |
+
"step": 130
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 0.1319820881451803,
|
| 136 |
+
"grad_norm": 5.59375,
|
| 137 |
+
"learning_rate": 1.9614243323442137e-05,
|
| 138 |
+
"loss": 0.1908,
|
| 139 |
+
"step": 140
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 0.1319820881451803,
|
| 143 |
+
"eval_loss": 0.19741062819957733,
|
| 144 |
+
"eval_runtime": 2.8143,
|
| 145 |
+
"eval_samples_per_second": 15.279,
|
| 146 |
+
"eval_steps_per_second": 15.279,
|
| 147 |
+
"step": 140
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.14140938015555032,
|
| 151 |
+
"grad_norm": 5.65625,
|
| 152 |
+
"learning_rate": 1.9515331355093966e-05,
|
| 153 |
+
"loss": 0.2125,
|
| 154 |
+
"step": 150
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.15083667216592034,
|
| 158 |
+
"grad_norm": 6.1875,
|
| 159 |
+
"learning_rate": 1.94164193867458e-05,
|
| 160 |
+
"loss": 0.2225,
|
| 161 |
+
"step": 160
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 0.16026396417629035,
|
| 165 |
+
"grad_norm": 6.375,
|
| 166 |
+
"learning_rate": 1.931750741839763e-05,
|
| 167 |
+
"loss": 0.2087,
|
| 168 |
+
"step": 170
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 0.16497761018147536,
|
| 172 |
+
"eval_loss": 0.2068619579076767,
|
| 173 |
+
"eval_runtime": 2.8432,
|
| 174 |
+
"eval_samples_per_second": 15.124,
|
| 175 |
+
"eval_steps_per_second": 15.124,
|
| 176 |
+
"step": 175
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.1696912561866604,
|
| 180 |
+
"grad_norm": 7.1875,
|
| 181 |
+
"learning_rate": 1.9218595450049458e-05,
|
| 182 |
+
"loss": 0.185,
|
| 183 |
+
"step": 180
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.1791185481970304,
|
| 187 |
+
"grad_norm": 6.78125,
|
| 188 |
+
"learning_rate": 1.9119683481701287e-05,
|
| 189 |
+
"loss": 0.1982,
|
| 190 |
+
"step": 190
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 0.18854584020740042,
|
| 194 |
+
"grad_norm": 5.96875,
|
| 195 |
+
"learning_rate": 1.9020771513353117e-05,
|
| 196 |
+
"loss": 0.2325,
|
| 197 |
+
"step": 200
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 0.19797313221777044,
|
| 201 |
+
"grad_norm": 9.0,
|
| 202 |
+
"learning_rate": 1.892185954500495e-05,
|
| 203 |
+
"loss": 0.1901,
|
| 204 |
+
"step": 210
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.19797313221777044,
|
| 208 |
+
"eval_loss": 0.18724432587623596,
|
| 209 |
+
"eval_runtime": 2.7949,
|
| 210 |
+
"eval_samples_per_second": 15.385,
|
| 211 |
+
"eval_steps_per_second": 15.385,
|
| 212 |
+
"step": 210
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.20740042422814048,
|
| 216 |
+
"grad_norm": 8.9375,
|
| 217 |
+
"learning_rate": 1.8822947576656775e-05,
|
| 218 |
+
"loss": 0.2276,
|
| 219 |
+
"step": 220
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.2168277162385105,
|
| 223 |
+
"grad_norm": 6.25,
|
| 224 |
+
"learning_rate": 1.8724035608308605e-05,
|
| 225 |
+
"loss": 0.1917,
|
| 226 |
+
"step": 230
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.2262550082488805,
|
| 230 |
+
"grad_norm": 6.34375,
|
| 231 |
+
"learning_rate": 1.8625123639960438e-05,
|
| 232 |
+
"loss": 0.1856,
|
| 233 |
+
"step": 240
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.23096865425406551,
|
| 237 |
+
"eval_loss": 0.17589253187179565,
|
| 238 |
+
"eval_runtime": 2.8142,
|
| 239 |
+
"eval_samples_per_second": 15.28,
|
| 240 |
+
"eval_steps_per_second": 15.28,
|
| 241 |
+
"step": 245
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.23568230025925052,
|
| 245 |
+
"grad_norm": 7.0625,
|
| 246 |
+
"learning_rate": 1.8526211671612267e-05,
|
| 247 |
+
"loss": 0.1666,
|
| 248 |
+
"step": 250
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.24510959226962056,
|
| 252 |
+
"grad_norm": 7.40625,
|
| 253 |
+
"learning_rate": 1.8427299703264096e-05,
|
| 254 |
+
"loss": 0.2121,
|
| 255 |
+
"step": 260
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.25453688427999055,
|
| 259 |
+
"grad_norm": 4.6875,
|
| 260 |
+
"learning_rate": 1.8328387734915926e-05,
|
| 261 |
+
"loss": 0.2028,
|
| 262 |
+
"step": 270
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.2639641762903606,
|
| 266 |
+
"grad_norm": 5.90625,
|
| 267 |
+
"learning_rate": 1.8229475766567755e-05,
|
| 268 |
+
"loss": 0.1484,
|
| 269 |
+
"step": 280
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.2639641762903606,
|
| 273 |
+
"eval_loss": 0.19002647697925568,
|
| 274 |
+
"eval_runtime": 2.8169,
|
| 275 |
+
"eval_samples_per_second": 15.265,
|
| 276 |
+
"eval_steps_per_second": 15.265,
|
| 277 |
+
"step": 280
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 0.27339146830073063,
|
| 281 |
+
"grad_norm": 4.71875,
|
| 282 |
+
"learning_rate": 1.8130563798219588e-05,
|
| 283 |
+
"loss": 0.1817,
|
| 284 |
+
"step": 290
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 0.28281876031110065,
|
| 288 |
+
"grad_norm": 6.78125,
|
| 289 |
+
"learning_rate": 1.8031651829871414e-05,
|
| 290 |
+
"loss": 0.2572,
|
| 291 |
+
"step": 300
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.29224605232147066,
|
| 295 |
+
"grad_norm": 6.1875,
|
| 296 |
+
"learning_rate": 1.7932739861523244e-05,
|
| 297 |
+
"loss": 0.1882,
|
| 298 |
+
"step": 310
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 0.29695969832665564,
|
| 302 |
+
"eval_loss": 0.16693313419818878,
|
| 303 |
+
"eval_runtime": 2.8909,
|
| 304 |
+
"eval_samples_per_second": 14.874,
|
| 305 |
+
"eval_steps_per_second": 14.874,
|
| 306 |
+
"step": 315
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 0.3016733443318407,
|
| 310 |
+
"grad_norm": 8.875,
|
| 311 |
+
"learning_rate": 1.7833827893175076e-05,
|
| 312 |
+
"loss": 0.2174,
|
| 313 |
+
"step": 320
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 0.3111006363422107,
|
| 317 |
+
"grad_norm": 5.96875,
|
| 318 |
+
"learning_rate": 1.7734915924826906e-05,
|
| 319 |
+
"loss": 0.1945,
|
| 320 |
+
"step": 330
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.3205279283525807,
|
| 324 |
+
"grad_norm": 8.8125,
|
| 325 |
+
"learning_rate": 1.7636003956478735e-05,
|
| 326 |
+
"loss": 0.197,
|
| 327 |
+
"step": 340
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.3299552203629507,
|
| 331 |
+
"grad_norm": 8.8125,
|
| 332 |
+
"learning_rate": 1.7537091988130565e-05,
|
| 333 |
+
"loss": 0.169,
|
| 334 |
+
"step": 350
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 0.3299552203629507,
|
| 338 |
+
"eval_loss": 0.16657419502735138,
|
| 339 |
+
"eval_runtime": 2.8397,
|
| 340 |
+
"eval_samples_per_second": 15.143,
|
| 341 |
+
"eval_steps_per_second": 15.143,
|
| 342 |
+
"step": 350
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 0.3393825123733208,
|
| 346 |
+
"grad_norm": 5.4375,
|
| 347 |
+
"learning_rate": 1.7438180019782397e-05,
|
| 348 |
+
"loss": 0.1996,
|
| 349 |
+
"step": 360
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 0.3488098043836908,
|
| 353 |
+
"grad_norm": 5.03125,
|
| 354 |
+
"learning_rate": 1.7339268051434227e-05,
|
| 355 |
+
"loss": 0.1717,
|
| 356 |
+
"step": 370
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 0.3582370963940608,
|
| 360 |
+
"grad_norm": 4.5,
|
| 361 |
+
"learning_rate": 1.7240356083086053e-05,
|
| 362 |
+
"loss": 0.1714,
|
| 363 |
+
"step": 380
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.3629507423992458,
|
| 367 |
+
"eval_loss": 0.16206760704517365,
|
| 368 |
+
"eval_runtime": 2.8698,
|
| 369 |
+
"eval_samples_per_second": 14.984,
|
| 370 |
+
"eval_steps_per_second": 14.984,
|
| 371 |
+
"step": 385
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 0.36766438840443083,
|
| 375 |
+
"grad_norm": 7.0,
|
| 376 |
+
"learning_rate": 1.7141444114737886e-05,
|
| 377 |
+
"loss": 0.1849,
|
| 378 |
+
"step": 390
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 0.37709168041480084,
|
| 382 |
+
"grad_norm": 10.75,
|
| 383 |
+
"learning_rate": 1.7042532146389715e-05,
|
| 384 |
+
"loss": 0.2017,
|
| 385 |
+
"step": 400
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 0.38651897242517086,
|
| 389 |
+
"grad_norm": 7.125,
|
| 390 |
+
"learning_rate": 1.6943620178041544e-05,
|
| 391 |
+
"loss": 0.1925,
|
| 392 |
+
"step": 410
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 0.3959462644355409,
|
| 396 |
+
"grad_norm": 5.46875,
|
| 397 |
+
"learning_rate": 1.6844708209693374e-05,
|
| 398 |
+
"loss": 0.1611,
|
| 399 |
+
"step": 420
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.3959462644355409,
|
| 403 |
+
"eval_loss": 0.1687425971031189,
|
| 404 |
+
"eval_runtime": 2.8778,
|
| 405 |
+
"eval_samples_per_second": 14.942,
|
| 406 |
+
"eval_steps_per_second": 14.942,
|
| 407 |
+
"step": 420
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 0.4053735564459109,
|
| 411 |
+
"grad_norm": 3.453125,
|
| 412 |
+
"learning_rate": 1.6745796241345203e-05,
|
| 413 |
+
"loss": 0.1983,
|
| 414 |
+
"step": 430
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 0.41480084845628096,
|
| 418 |
+
"grad_norm": 5.15625,
|
| 419 |
+
"learning_rate": 1.6646884272997036e-05,
|
| 420 |
+
"loss": 0.1961,
|
| 421 |
+
"step": 440
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 0.42422814046665097,
|
| 425 |
+
"grad_norm": 5.90625,
|
| 426 |
+
"learning_rate": 1.6547972304648865e-05,
|
| 427 |
+
"loss": 0.1952,
|
| 428 |
+
"step": 450
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 0.42894178647183595,
|
| 432 |
+
"eval_loss": 0.15973812341690063,
|
| 433 |
+
"eval_runtime": 2.8233,
|
| 434 |
+
"eval_samples_per_second": 15.23,
|
| 435 |
+
"eval_steps_per_second": 15.23,
|
| 436 |
+
"step": 455
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.433655432477021,
|
| 440 |
+
"grad_norm": 5.21875,
|
| 441 |
+
"learning_rate": 1.644906033630069e-05,
|
| 442 |
+
"loss": 0.1782,
|
| 443 |
+
"step": 460
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.443082724487391,
|
| 447 |
+
"grad_norm": 5.375,
|
| 448 |
+
"learning_rate": 1.6350148367952524e-05,
|
| 449 |
+
"loss": 0.1463,
|
| 450 |
+
"step": 470
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.452510016497761,
|
| 454 |
+
"grad_norm": 5.09375,
|
| 455 |
+
"learning_rate": 1.6251236399604354e-05,
|
| 456 |
+
"loss": 0.1774,
|
| 457 |
+
"step": 480
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.46193730850813103,
|
| 461 |
+
"grad_norm": 3.734375,
|
| 462 |
+
"learning_rate": 1.6152324431256183e-05,
|
| 463 |
+
"loss": 0.1956,
|
| 464 |
+
"step": 490
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.46193730850813103,
|
| 468 |
+
"eval_loss": 0.1619725376367569,
|
| 469 |
+
"eval_runtime": 2.8042,
|
| 470 |
+
"eval_samples_per_second": 15.334,
|
| 471 |
+
"eval_steps_per_second": 15.334,
|
| 472 |
+
"step": 490
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.47136460051850104,
|
| 476 |
+
"grad_norm": 6.75,
|
| 477 |
+
"learning_rate": 1.6053412462908013e-05,
|
| 478 |
+
"loss": 0.1327,
|
| 479 |
+
"step": 500
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.48079189252887106,
|
| 483 |
+
"grad_norm": 5.4375,
|
| 484 |
+
"learning_rate": 1.5954500494559842e-05,
|
| 485 |
+
"loss": 0.1798,
|
| 486 |
+
"step": 510
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.4902191845392411,
|
| 490 |
+
"grad_norm": 6.875,
|
| 491 |
+
"learning_rate": 1.5855588526211675e-05,
|
| 492 |
+
"loss": 0.18,
|
| 493 |
+
"step": 520
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.4949328305444261,
|
| 497 |
+
"eval_loss": 0.15706923604011536,
|
| 498 |
+
"eval_runtime": 2.8106,
|
| 499 |
+
"eval_samples_per_second": 15.299,
|
| 500 |
+
"eval_steps_per_second": 15.299,
|
| 501 |
+
"step": 525
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.49964647654961114,
|
| 505 |
+
"grad_norm": 5.25,
|
| 506 |
+
"learning_rate": 1.57566765578635e-05,
|
| 507 |
+
"loss": 0.1886,
|
| 508 |
+
"step": 530
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.5090737685599811,
|
| 512 |
+
"grad_norm": 4.46875,
|
| 513 |
+
"learning_rate": 1.565776458951533e-05,
|
| 514 |
+
"loss": 0.2052,
|
| 515 |
+
"step": 540
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.5185010605703512,
|
| 519 |
+
"grad_norm": 2.640625,
|
| 520 |
+
"learning_rate": 1.5558852621167163e-05,
|
| 521 |
+
"loss": 0.1506,
|
| 522 |
+
"step": 550
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.5279283525807212,
|
| 526 |
+
"grad_norm": 5.5625,
|
| 527 |
+
"learning_rate": 1.5459940652818992e-05,
|
| 528 |
+
"loss": 0.2149,
|
| 529 |
+
"step": 560
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.5279283525807212,
|
| 533 |
+
"eval_loss": 0.15407335758209229,
|
| 534 |
+
"eval_runtime": 2.9014,
|
| 535 |
+
"eval_samples_per_second": 14.821,
|
| 536 |
+
"eval_steps_per_second": 14.821,
|
| 537 |
+
"step": 560
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.5373556445910912,
|
| 541 |
+
"grad_norm": 4.28125,
|
| 542 |
+
"learning_rate": 1.5361028684470822e-05,
|
| 543 |
+
"loss": 0.1745,
|
| 544 |
+
"step": 570
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 0.5467829366014613,
|
| 548 |
+
"grad_norm": 4.625,
|
| 549 |
+
"learning_rate": 1.526211671612265e-05,
|
| 550 |
+
"loss": 0.1382,
|
| 551 |
+
"step": 580
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 0.5562102286118312,
|
| 555 |
+
"grad_norm": 7.5625,
|
| 556 |
+
"learning_rate": 1.5163204747774482e-05,
|
| 557 |
+
"loss": 0.1739,
|
| 558 |
+
"step": 590
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 0.5609238746170163,
|
| 562 |
+
"eval_loss": 0.15476632118225098,
|
| 563 |
+
"eval_runtime": 3.4281,
|
| 564 |
+
"eval_samples_per_second": 12.543,
|
| 565 |
+
"eval_steps_per_second": 12.543,
|
| 566 |
+
"step": 595
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 0.5656375206222013,
|
| 570 |
+
"grad_norm": 3.21875,
|
| 571 |
+
"learning_rate": 1.5064292779426313e-05,
|
| 572 |
+
"loss": 0.1492,
|
| 573 |
+
"step": 600
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.5750648126325713,
|
| 577 |
+
"grad_norm": 6.8125,
|
| 578 |
+
"learning_rate": 1.4965380811078141e-05,
|
| 579 |
+
"loss": 0.1487,
|
| 580 |
+
"step": 610
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 0.5844921046429413,
|
| 584 |
+
"grad_norm": 7.375,
|
| 585 |
+
"learning_rate": 1.486646884272997e-05,
|
| 586 |
+
"loss": 0.2154,
|
| 587 |
+
"step": 620
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 0.5939193966533113,
|
| 591 |
+
"grad_norm": 4.84375,
|
| 592 |
+
"learning_rate": 1.4767556874381802e-05,
|
| 593 |
+
"loss": 0.1679,
|
| 594 |
+
"step": 630
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 0.5939193966533113,
|
| 598 |
+
"eval_loss": 0.15013353526592255,
|
| 599 |
+
"eval_runtime": 2.7977,
|
| 600 |
+
"eval_samples_per_second": 15.37,
|
| 601 |
+
"eval_steps_per_second": 15.37,
|
| 602 |
+
"step": 630
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 0.6033466886636814,
|
| 606 |
+
"grad_norm": 6.96875,
|
| 607 |
+
"learning_rate": 1.4668644906033631e-05,
|
| 608 |
+
"loss": 0.182,
|
| 609 |
+
"step": 640
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.6127739806740514,
|
| 613 |
+
"grad_norm": 4.46875,
|
| 614 |
+
"learning_rate": 1.456973293768546e-05,
|
| 615 |
+
"loss": 0.1666,
|
| 616 |
+
"step": 650
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 0.6222012726844214,
|
| 620 |
+
"grad_norm": 4.65625,
|
| 621 |
+
"learning_rate": 1.4470820969337292e-05,
|
| 622 |
+
"loss": 0.1241,
|
| 623 |
+
"step": 660
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 0.6269149186896064,
|
| 627 |
+
"eval_loss": 0.1542421579360962,
|
| 628 |
+
"eval_runtime": 2.8955,
|
| 629 |
+
"eval_samples_per_second": 14.85,
|
| 630 |
+
"eval_steps_per_second": 14.85,
|
| 631 |
+
"step": 665
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 0.6316285646947915,
|
| 635 |
+
"grad_norm": 4.6875,
|
| 636 |
+
"learning_rate": 1.4371909000989121e-05,
|
| 637 |
+
"loss": 0.1584,
|
| 638 |
+
"step": 670
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 0.6410558567051614,
|
| 642 |
+
"grad_norm": 5.375,
|
| 643 |
+
"learning_rate": 1.4272997032640952e-05,
|
| 644 |
+
"loss": 0.1627,
|
| 645 |
+
"step": 680
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 0.6504831487155315,
|
| 649 |
+
"grad_norm": 4.78125,
|
| 650 |
+
"learning_rate": 1.417408506429278e-05,
|
| 651 |
+
"loss": 0.1207,
|
| 652 |
+
"step": 690
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 0.6599104407259014,
|
| 656 |
+
"grad_norm": 5.65625,
|
| 657 |
+
"learning_rate": 1.407517309594461e-05,
|
| 658 |
+
"loss": 0.2057,
|
| 659 |
+
"step": 700
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 0.6599104407259014,
|
| 663 |
+
"eval_loss": 0.15335653722286224,
|
| 664 |
+
"eval_runtime": 2.8317,
|
| 665 |
+
"eval_samples_per_second": 15.185,
|
| 666 |
+
"eval_steps_per_second": 15.185,
|
| 667 |
+
"step": 700
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.6693377327362715,
|
| 671 |
+
"grad_norm": 3.578125,
|
| 672 |
+
"learning_rate": 1.397626112759644e-05,
|
| 673 |
+
"loss": 0.1882,
|
| 674 |
+
"step": 710
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.6787650247466416,
|
| 678 |
+
"grad_norm": 9.5,
|
| 679 |
+
"learning_rate": 1.387734915924827e-05,
|
| 680 |
+
"loss": 0.1758,
|
| 681 |
+
"step": 720
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.6881923167570115,
|
| 685 |
+
"grad_norm": 5.9375,
|
| 686 |
+
"learning_rate": 1.3778437190900101e-05,
|
| 687 |
+
"loss": 0.1939,
|
| 688 |
+
"step": 730
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.6929059627621965,
|
| 692 |
+
"eval_loss": 0.15230855345726013,
|
| 693 |
+
"eval_runtime": 3.345,
|
| 694 |
+
"eval_samples_per_second": 12.855,
|
| 695 |
+
"eval_steps_per_second": 12.855,
|
| 696 |
+
"step": 735
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.6976196087673816,
|
| 700 |
+
"grad_norm": 4.71875,
|
| 701 |
+
"learning_rate": 1.367952522255193e-05,
|
| 702 |
+
"loss": 0.1548,
|
| 703 |
+
"step": 740
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.7070469007777516,
|
| 707 |
+
"grad_norm": 3.90625,
|
| 708 |
+
"learning_rate": 1.358061325420376e-05,
|
| 709 |
+
"loss": 0.1724,
|
| 710 |
+
"step": 750
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.7164741927881216,
|
| 714 |
+
"grad_norm": 5.125,
|
| 715 |
+
"learning_rate": 1.3481701285855591e-05,
|
| 716 |
+
"loss": 0.2,
|
| 717 |
+
"step": 760
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.7259014847984916,
|
| 721 |
+
"grad_norm": 3.296875,
|
| 722 |
+
"learning_rate": 1.3382789317507419e-05,
|
| 723 |
+
"loss": 0.1707,
|
| 724 |
+
"step": 770
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.7259014847984916,
|
| 728 |
+
"eval_loss": 0.14677099883556366,
|
| 729 |
+
"eval_runtime": 2.9348,
|
| 730 |
+
"eval_samples_per_second": 14.652,
|
| 731 |
+
"eval_steps_per_second": 14.652,
|
| 732 |
+
"step": 770
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 0.7353287768088617,
|
| 736 |
+
"grad_norm": 4.78125,
|
| 737 |
+
"learning_rate": 1.3283877349159248e-05,
|
| 738 |
+
"loss": 0.1631,
|
| 739 |
+
"step": 780
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 0.7447560688192316,
|
| 743 |
+
"grad_norm": 7.6875,
|
| 744 |
+
"learning_rate": 1.3184965380811079e-05,
|
| 745 |
+
"loss": 0.1723,
|
| 746 |
+
"step": 790
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 0.7541833608296017,
|
| 750 |
+
"grad_norm": 8.25,
|
| 751 |
+
"learning_rate": 1.3086053412462909e-05,
|
| 752 |
+
"loss": 0.1526,
|
| 753 |
+
"step": 800
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 0.7588970068347867,
|
| 757 |
+
"eval_loss": 0.14969274401664734,
|
| 758 |
+
"eval_runtime": 2.8149,
|
| 759 |
+
"eval_samples_per_second": 15.276,
|
| 760 |
+
"eval_steps_per_second": 15.276,
|
| 761 |
+
"step": 805
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.7636106528399718,
|
| 765 |
+
"grad_norm": 5.71875,
|
| 766 |
+
"learning_rate": 1.298714144411474e-05,
|
| 767 |
+
"loss": 0.1505,
|
| 768 |
+
"step": 810
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.7730379448503417,
|
| 772 |
+
"grad_norm": 3.984375,
|
| 773 |
+
"learning_rate": 1.2888229475766569e-05,
|
| 774 |
+
"loss": 0.1657,
|
| 775 |
+
"step": 820
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 0.7824652368607118,
|
| 779 |
+
"grad_norm": 5.5625,
|
| 780 |
+
"learning_rate": 1.27893175074184e-05,
|
| 781 |
+
"loss": 0.1558,
|
| 782 |
+
"step": 830
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 0.7918925288710817,
|
| 786 |
+
"grad_norm": 5.875,
|
| 787 |
+
"learning_rate": 1.2690405539070228e-05,
|
| 788 |
+
"loss": 0.1449,
|
| 789 |
+
"step": 840
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.7918925288710817,
|
| 793 |
+
"eval_loss": 0.147576704621315,
|
| 794 |
+
"eval_runtime": 2.8182,
|
| 795 |
+
"eval_samples_per_second": 15.258,
|
| 796 |
+
"eval_steps_per_second": 15.258,
|
| 797 |
+
"step": 840
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 0.8013198208814518,
|
| 801 |
+
"grad_norm": 7.84375,
|
| 802 |
+
"learning_rate": 1.2591493570722057e-05,
|
| 803 |
+
"loss": 0.178,
|
| 804 |
+
"step": 850
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 0.8107471128918218,
|
| 808 |
+
"grad_norm": 6.28125,
|
| 809 |
+
"learning_rate": 1.2492581602373888e-05,
|
| 810 |
+
"loss": 0.172,
|
| 811 |
+
"step": 860
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 0.8201744049021918,
|
| 815 |
+
"grad_norm": 4.625,
|
| 816 |
+
"learning_rate": 1.2393669634025718e-05,
|
| 817 |
+
"loss": 0.1812,
|
| 818 |
+
"step": 870
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 0.8248880509073768,
|
| 822 |
+
"eval_loss": 0.14615514874458313,
|
| 823 |
+
"eval_runtime": 2.8438,
|
| 824 |
+
"eval_samples_per_second": 15.12,
|
| 825 |
+
"eval_steps_per_second": 15.12,
|
| 826 |
+
"step": 875
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 0.8296016969125619,
|
| 830 |
+
"grad_norm": 4.53125,
|
| 831 |
+
"learning_rate": 1.2294757665677547e-05,
|
| 832 |
+
"loss": 0.1366,
|
| 833 |
+
"step": 880
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 0.8390289889229319,
|
| 837 |
+
"grad_norm": 2.265625,
|
| 838 |
+
"learning_rate": 1.2195845697329378e-05,
|
| 839 |
+
"loss": 0.1517,
|
| 840 |
+
"step": 890
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 0.8484562809333019,
|
| 844 |
+
"grad_norm": 5.15625,
|
| 845 |
+
"learning_rate": 1.2096933728981208e-05,
|
| 846 |
+
"loss": 0.1838,
|
| 847 |
+
"step": 900
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 0.8578835729436719,
|
| 851 |
+
"grad_norm": 4.375,
|
| 852 |
+
"learning_rate": 1.1998021760633039e-05,
|
| 853 |
+
"loss": 0.1513,
|
| 854 |
+
"step": 910
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 0.8578835729436719,
|
| 858 |
+
"eval_loss": 0.1435091495513916,
|
| 859 |
+
"eval_runtime": 2.8827,
|
| 860 |
+
"eval_samples_per_second": 14.917,
|
| 861 |
+
"eval_steps_per_second": 14.917,
|
| 862 |
+
"step": 910
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"epoch": 0.867310864954042,
|
| 866 |
+
"grad_norm": 9.5,
|
| 867 |
+
"learning_rate": 1.1899109792284867e-05,
|
| 868 |
+
"loss": 0.1824,
|
| 869 |
+
"step": 920
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 0.8767381569644119,
|
| 873 |
+
"grad_norm": 4.125,
|
| 874 |
+
"learning_rate": 1.1800197823936696e-05,
|
| 875 |
+
"loss": 0.1749,
|
| 876 |
+
"step": 930
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 0.886165448974782,
|
| 880 |
+
"grad_norm": 1.546875,
|
| 881 |
+
"learning_rate": 1.1701285855588527e-05,
|
| 882 |
+
"loss": 0.1428,
|
| 883 |
+
"step": 940
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 0.890879094979967,
|
| 887 |
+
"eval_loss": 0.14254696667194366,
|
| 888 |
+
"eval_runtime": 3.4673,
|
| 889 |
+
"eval_samples_per_second": 12.401,
|
| 890 |
+
"eval_steps_per_second": 12.401,
|
| 891 |
+
"step": 945
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.8955927409851521,
|
| 895 |
+
"grad_norm": 4.65625,
|
| 896 |
+
"learning_rate": 1.1602373887240357e-05,
|
| 897 |
+
"loss": 0.1886,
|
| 898 |
+
"step": 950
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.905020032995522,
|
| 902 |
+
"grad_norm": 5.4375,
|
| 903 |
+
"learning_rate": 1.1503461918892188e-05,
|
| 904 |
+
"loss": 0.1705,
|
| 905 |
+
"step": 960
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.9144473250058921,
|
| 909 |
+
"grad_norm": 3.625,
|
| 910 |
+
"learning_rate": 1.1404549950544017e-05,
|
| 911 |
+
"loss": 0.1538,
|
| 912 |
+
"step": 970
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.9238746170162621,
|
| 916 |
+
"grad_norm": 5.71875,
|
| 917 |
+
"learning_rate": 1.1305637982195846e-05,
|
| 918 |
+
"loss": 0.1268,
|
| 919 |
+
"step": 980
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.9238746170162621,
|
| 923 |
+
"eval_loss": 0.1375056654214859,
|
| 924 |
+
"eval_runtime": 3.3962,
|
| 925 |
+
"eval_samples_per_second": 12.661,
|
| 926 |
+
"eval_steps_per_second": 12.661,
|
| 927 |
+
"step": 980
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.9333019090266321,
|
| 931 |
+
"grad_norm": 5.96875,
|
| 932 |
+
"learning_rate": 1.1206726013847678e-05,
|
| 933 |
+
"loss": 0.1882,
|
| 934 |
+
"step": 990
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.9427292010370021,
|
| 938 |
+
"grad_norm": 4.84375,
|
| 939 |
+
"learning_rate": 1.1107814045499505e-05,
|
| 940 |
+
"loss": 0.1376,
|
| 941 |
+
"step": 1000
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.9521564930473722,
|
| 945 |
+
"grad_norm": 6.0625,
|
| 946 |
+
"learning_rate": 1.1008902077151335e-05,
|
| 947 |
+
"loss": 0.1451,
|
| 948 |
+
"step": 1010
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.9568701390525571,
|
| 952 |
+
"eval_loss": 0.13927814364433289,
|
| 953 |
+
"eval_runtime": 2.8779,
|
| 954 |
+
"eval_samples_per_second": 14.941,
|
| 955 |
+
"eval_steps_per_second": 14.941,
|
| 956 |
+
"step": 1015
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 0.9615837850577421,
|
| 960 |
+
"grad_norm": 4.53125,
|
| 961 |
+
"learning_rate": 1.0909990108803166e-05,
|
| 962 |
+
"loss": 0.1524,
|
| 963 |
+
"step": 1020
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 0.9710110770681122,
|
| 967 |
+
"grad_norm": 6.4375,
|
| 968 |
+
"learning_rate": 1.0811078140454995e-05,
|
| 969 |
+
"loss": 0.1846,
|
| 970 |
+
"step": 1030
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 0.9804383690784823,
|
| 974 |
+
"grad_norm": 4.625,
|
| 975 |
+
"learning_rate": 1.0712166172106826e-05,
|
| 976 |
+
"loss": 0.1485,
|
| 977 |
+
"step": 1040
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 0.9898656610888522,
|
| 981 |
+
"grad_norm": 3.5625,
|
| 982 |
+
"learning_rate": 1.0613254203758656e-05,
|
| 983 |
+
"loss": 0.139,
|
| 984 |
+
"step": 1050
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 0.9898656610888522,
|
| 988 |
+
"eval_loss": 0.13826079666614532,
|
| 989 |
+
"eval_runtime": 2.8595,
|
| 990 |
+
"eval_samples_per_second": 15.038,
|
| 991 |
+
"eval_steps_per_second": 15.038,
|
| 992 |
+
"step": 1050
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 0.9992929530992223,
|
| 996 |
+
"grad_norm": 3.8125,
|
| 997 |
+
"learning_rate": 1.0514342235410487e-05,
|
| 998 |
+
"loss": 0.1477,
|
| 999 |
+
"step": 1060
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 1.008484562809333,
|
| 1003 |
+
"grad_norm": 3.59375,
|
| 1004 |
+
"learning_rate": 1.0415430267062316e-05,
|
| 1005 |
+
"loss": 0.081,
|
| 1006 |
+
"step": 1070
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 1.017911854819703,
|
| 1010 |
+
"grad_norm": 3.015625,
|
| 1011 |
+
"learning_rate": 1.0316518298714144e-05,
|
| 1012 |
+
"loss": 0.091,
|
| 1013 |
+
"step": 1080
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 1.0226255008248881,
|
| 1017 |
+
"eval_loss": 0.14206524193286896,
|
| 1018 |
+
"eval_runtime": 2.8042,
|
| 1019 |
+
"eval_samples_per_second": 15.334,
|
| 1020 |
+
"eval_steps_per_second": 15.334,
|
| 1021 |
+
"step": 1085
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 1.027339146830073,
|
| 1025 |
+
"grad_norm": 3.484375,
|
| 1026 |
+
"learning_rate": 1.0217606330365975e-05,
|
| 1027 |
+
"loss": 0.085,
|
| 1028 |
+
"step": 1090
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 1.0367664388404432,
|
| 1032 |
+
"grad_norm": 3.546875,
|
| 1033 |
+
"learning_rate": 1.0118694362017805e-05,
|
| 1034 |
+
"loss": 0.0864,
|
| 1035 |
+
"step": 1100
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 1.0461937308508131,
|
| 1039 |
+
"grad_norm": 2.515625,
|
| 1040 |
+
"learning_rate": 1.0019782393669636e-05,
|
| 1041 |
+
"loss": 0.087,
|
| 1042 |
+
"step": 1110
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 1.055621022861183,
|
| 1046 |
+
"grad_norm": 3.25,
|
| 1047 |
+
"learning_rate": 9.920870425321465e-06,
|
| 1048 |
+
"loss": 0.0774,
|
| 1049 |
+
"step": 1120
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 1.055621022861183,
|
| 1053 |
+
"eval_loss": 0.14084650576114655,
|
| 1054 |
+
"eval_runtime": 2.8547,
|
| 1055 |
+
"eval_samples_per_second": 15.063,
|
| 1056 |
+
"eval_steps_per_second": 15.063,
|
| 1057 |
+
"step": 1120
|
| 1058 |
+
},
|
| 1059 |
+
{
|
| 1060 |
+
"epoch": 1.065048314871553,
|
| 1061 |
+
"grad_norm": 2.46875,
|
| 1062 |
+
"learning_rate": 9.821958456973294e-06,
|
| 1063 |
+
"loss": 0.0486,
|
| 1064 |
+
"step": 1130
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 1.0744756068819232,
|
| 1068 |
+
"grad_norm": 4.03125,
|
| 1069 |
+
"learning_rate": 9.723046488625124e-06,
|
| 1070 |
+
"loss": 0.0773,
|
| 1071 |
+
"step": 1140
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 1.0839028988922932,
|
| 1075 |
+
"grad_norm": 8.6875,
|
| 1076 |
+
"learning_rate": 9.624134520276955e-06,
|
| 1077 |
+
"loss": 0.1005,
|
| 1078 |
+
"step": 1150
|
| 1079 |
+
},
|
| 1080 |
+
{
|
| 1081 |
+
"epoch": 1.0886165448974783,
|
| 1082 |
+
"eval_loss": 0.143312469124794,
|
| 1083 |
+
"eval_runtime": 2.7849,
|
| 1084 |
+
"eval_samples_per_second": 15.44,
|
| 1085 |
+
"eval_steps_per_second": 15.44,
|
| 1086 |
+
"step": 1155
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 1.0933301909026631,
|
| 1090 |
+
"grad_norm": 2.8125,
|
| 1091 |
+
"learning_rate": 9.525222551928784e-06,
|
| 1092 |
+
"loss": 0.071,
|
| 1093 |
+
"step": 1160
|
| 1094 |
+
},
|
| 1095 |
+
{
|
| 1096 |
+
"epoch": 1.1027574829130333,
|
| 1097 |
+
"grad_norm": 7.8125,
|
| 1098 |
+
"learning_rate": 9.426310583580614e-06,
|
| 1099 |
+
"loss": 0.0725,
|
| 1100 |
+
"step": 1170
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 1.1121847749234033,
|
| 1104 |
+
"grad_norm": 5.96875,
|
| 1105 |
+
"learning_rate": 9.327398615232443e-06,
|
| 1106 |
+
"loss": 0.081,
|
| 1107 |
+
"step": 1180
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 1.1216120669337732,
|
| 1111 |
+
"grad_norm": 3.046875,
|
| 1112 |
+
"learning_rate": 9.228486646884274e-06,
|
| 1113 |
+
"loss": 0.0751,
|
| 1114 |
+
"step": 1190
|
| 1115 |
+
},
|
| 1116 |
+
{
|
| 1117 |
+
"epoch": 1.1216120669337732,
|
| 1118 |
+
"eval_loss": 0.14267787337303162,
|
| 1119 |
+
"eval_runtime": 2.9041,
|
| 1120 |
+
"eval_samples_per_second": 14.807,
|
| 1121 |
+
"eval_steps_per_second": 14.807,
|
| 1122 |
+
"step": 1190
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 1.1310393589441432,
|
| 1126 |
+
"grad_norm": 3.390625,
|
| 1127 |
+
"learning_rate": 9.129574678536104e-06,
|
| 1128 |
+
"loss": 0.0721,
|
| 1129 |
+
"step": 1200
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 1.1404666509545134,
|
| 1133 |
+
"grad_norm": 4.71875,
|
| 1134 |
+
"learning_rate": 9.030662710187933e-06,
|
| 1135 |
+
"loss": 0.0784,
|
| 1136 |
+
"step": 1210
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 1.1498939429648833,
|
| 1140 |
+
"grad_norm": 4.03125,
|
| 1141 |
+
"learning_rate": 8.931750741839763e-06,
|
| 1142 |
+
"loss": 0.0764,
|
| 1143 |
+
"step": 1220
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 1.1546075889700684,
|
| 1147 |
+
"eval_loss": 0.14501504600048065,
|
| 1148 |
+
"eval_runtime": 2.8486,
|
| 1149 |
+
"eval_samples_per_second": 15.095,
|
| 1150 |
+
"eval_steps_per_second": 15.095,
|
| 1151 |
+
"step": 1225
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 1.1593212349752533,
|
| 1155 |
+
"grad_norm": 3.015625,
|
| 1156 |
+
"learning_rate": 8.832838773491594e-06,
|
| 1157 |
+
"loss": 0.0879,
|
| 1158 |
+
"step": 1230
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 1.1687485269856235,
|
| 1162 |
+
"grad_norm": 2.8125,
|
| 1163 |
+
"learning_rate": 8.733926805143423e-06,
|
| 1164 |
+
"loss": 0.08,
|
| 1165 |
+
"step": 1240
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 1.1781758189959934,
|
| 1169 |
+
"grad_norm": 3.984375,
|
| 1170 |
+
"learning_rate": 8.635014836795252e-06,
|
| 1171 |
+
"loss": 0.1068,
|
| 1172 |
+
"step": 1250
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 1.1876031110063634,
|
| 1176 |
+
"grad_norm": 2.96875,
|
| 1177 |
+
"learning_rate": 8.536102868447082e-06,
|
| 1178 |
+
"loss": 0.078,
|
| 1179 |
+
"step": 1260
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 1.1876031110063634,
|
| 1183 |
+
"eval_loss": 0.1404484212398529,
|
| 1184 |
+
"eval_runtime": 2.8927,
|
| 1185 |
+
"eval_samples_per_second": 14.865,
|
| 1186 |
+
"eval_steps_per_second": 14.865,
|
| 1187 |
+
"step": 1260
|
| 1188 |
+
},
|
| 1189 |
+
{
|
| 1190 |
+
"epoch": 1.1970304030167334,
|
| 1191 |
+
"grad_norm": 3.890625,
|
| 1192 |
+
"learning_rate": 8.437190900098913e-06,
|
| 1193 |
+
"loss": 0.1019,
|
| 1194 |
+
"step": 1270
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 1.2064576950271035,
|
| 1198 |
+
"grad_norm": 6.25,
|
| 1199 |
+
"learning_rate": 8.338278931750742e-06,
|
| 1200 |
+
"loss": 0.09,
|
| 1201 |
+
"step": 1280
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 1.2158849870374735,
|
| 1205 |
+
"grad_norm": 4.40625,
|
| 1206 |
+
"learning_rate": 8.239366963402572e-06,
|
| 1207 |
+
"loss": 0.0552,
|
| 1208 |
+
"step": 1290
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 1.2205986330426586,
|
| 1212 |
+
"eval_loss": 0.14131127297878265,
|
| 1213 |
+
"eval_runtime": 2.8819,
|
| 1214 |
+
"eval_samples_per_second": 14.921,
|
| 1215 |
+
"eval_steps_per_second": 14.921,
|
| 1216 |
+
"step": 1295
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 1.2253122790478435,
|
| 1220 |
+
"grad_norm": 3.515625,
|
| 1221 |
+
"learning_rate": 8.140454995054401e-06,
|
| 1222 |
+
"loss": 0.0674,
|
| 1223 |
+
"step": 1300
|
| 1224 |
+
},
|
| 1225 |
+
{
|
| 1226 |
+
"epoch": 1.2347395710582134,
|
| 1227 |
+
"grad_norm": 2.59375,
|
| 1228 |
+
"learning_rate": 8.041543026706232e-06,
|
| 1229 |
+
"loss": 0.1002,
|
| 1230 |
+
"step": 1310
|
| 1231 |
+
},
|
| 1232 |
+
{
|
| 1233 |
+
"epoch": 1.2441668630685836,
|
| 1234 |
+
"grad_norm": 3.59375,
|
| 1235 |
+
"learning_rate": 7.942631058358062e-06,
|
| 1236 |
+
"loss": 0.0711,
|
| 1237 |
+
"step": 1320
|
| 1238 |
+
},
|
| 1239 |
+
{
|
| 1240 |
+
"epoch": 1.2535941550789536,
|
| 1241 |
+
"grad_norm": 2.625,
|
| 1242 |
+
"learning_rate": 7.843719090009891e-06,
|
| 1243 |
+
"loss": 0.0699,
|
| 1244 |
+
"step": 1330
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 1.2535941550789536,
|
| 1248 |
+
"eval_loss": 0.1402900665998459,
|
| 1249 |
+
"eval_runtime": 2.914,
|
| 1250 |
+
"eval_samples_per_second": 14.756,
|
| 1251 |
+
"eval_steps_per_second": 14.756,
|
| 1252 |
+
"step": 1330
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 1.2630214470893235,
|
| 1256 |
+
"grad_norm": 3.328125,
|
| 1257 |
+
"learning_rate": 7.744807121661722e-06,
|
| 1258 |
+
"loss": 0.0965,
|
| 1259 |
+
"step": 1340
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 1.2724487390996937,
|
| 1263 |
+
"grad_norm": 2.265625,
|
| 1264 |
+
"learning_rate": 7.645895153313552e-06,
|
| 1265 |
+
"loss": 0.078,
|
| 1266 |
+
"step": 1350
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 1.2818760311100637,
|
| 1270 |
+
"grad_norm": 3.953125,
|
| 1271 |
+
"learning_rate": 7.546983184965382e-06,
|
| 1272 |
+
"loss": 0.0937,
|
| 1273 |
+
"step": 1360
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 1.2865896771152485,
|
| 1277 |
+
"eval_loss": 0.13923154771327972,
|
| 1278 |
+
"eval_runtime": 2.9339,
|
| 1279 |
+
"eval_samples_per_second": 14.656,
|
| 1280 |
+
"eval_steps_per_second": 14.656,
|
| 1281 |
+
"step": 1365
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 1.2913033231204336,
|
| 1285 |
+
"grad_norm": 7.21875,
|
| 1286 |
+
"learning_rate": 7.4480712166172105e-06,
|
| 1287 |
+
"loss": 0.0711,
|
| 1288 |
+
"step": 1370
|
| 1289 |
+
},
|
| 1290 |
+
{
|
| 1291 |
+
"epoch": 1.3007306151308038,
|
| 1292 |
+
"grad_norm": 4.75,
|
| 1293 |
+
"learning_rate": 7.349159248269041e-06,
|
| 1294 |
+
"loss": 0.091,
|
| 1295 |
+
"step": 1380
|
| 1296 |
+
},
|
| 1297 |
+
{
|
| 1298 |
+
"epoch": 1.3101579071411737,
|
| 1299 |
+
"grad_norm": 1.875,
|
| 1300 |
+
"learning_rate": 7.250247279920871e-06,
|
| 1301 |
+
"loss": 0.0494,
|
| 1302 |
+
"step": 1390
|
| 1303 |
+
},
|
| 1304 |
+
{
|
| 1305 |
+
"epoch": 1.3195851991515437,
|
| 1306 |
+
"grad_norm": 4.90625,
|
| 1307 |
+
"learning_rate": 7.151335311572701e-06,
|
| 1308 |
+
"loss": 0.1154,
|
| 1309 |
+
"step": 1400
|
| 1310 |
+
},
|
| 1311 |
+
{
|
| 1312 |
+
"epoch": 1.3195851991515437,
|
| 1313 |
+
"eval_loss": 0.1399063766002655,
|
| 1314 |
+
"eval_runtime": 2.8659,
|
| 1315 |
+
"eval_samples_per_second": 15.004,
|
| 1316 |
+
"eval_steps_per_second": 15.004,
|
| 1317 |
+
"step": 1400
|
| 1318 |
+
},
|
| 1319 |
+
{
|
| 1320 |
+
"epoch": 1.3290124911619137,
|
| 1321 |
+
"grad_norm": 3.59375,
|
| 1322 |
+
"learning_rate": 7.052423343224531e-06,
|
| 1323 |
+
"loss": 0.0782,
|
| 1324 |
+
"step": 1410
|
| 1325 |
+
},
|
| 1326 |
+
{
|
| 1327 |
+
"epoch": 1.3384397831722836,
|
| 1328 |
+
"grad_norm": 5.90625,
|
| 1329 |
+
"learning_rate": 6.95351137487636e-06,
|
| 1330 |
+
"loss": 0.0835,
|
| 1331 |
+
"step": 1420
|
| 1332 |
+
},
|
| 1333 |
+
{
|
| 1334 |
+
"epoch": 1.3478670751826538,
|
| 1335 |
+
"grad_norm": 3.84375,
|
| 1336 |
+
"learning_rate": 6.85459940652819e-06,
|
| 1337 |
+
"loss": 0.0856,
|
| 1338 |
+
"step": 1430
|
| 1339 |
+
},
|
| 1340 |
+
{
|
| 1341 |
+
"epoch": 1.352580721187839,
|
| 1342 |
+
"eval_loss": 0.1397552341222763,
|
| 1343 |
+
"eval_runtime": 2.8888,
|
| 1344 |
+
"eval_samples_per_second": 14.885,
|
| 1345 |
+
"eval_steps_per_second": 14.885,
|
| 1346 |
+
"step": 1435
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 1.3572943671930238,
|
| 1350 |
+
"grad_norm": 2.625,
|
| 1351 |
+
"learning_rate": 6.755687438180021e-06,
|
| 1352 |
+
"loss": 0.049,
|
| 1353 |
+
"step": 1440
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 1.3667216592033937,
|
| 1357 |
+
"grad_norm": 3.828125,
|
| 1358 |
+
"learning_rate": 6.65677546983185e-06,
|
| 1359 |
+
"loss": 0.0605,
|
| 1360 |
+
"step": 1450
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 1.376148951213764,
|
| 1364 |
+
"grad_norm": 3.171875,
|
| 1365 |
+
"learning_rate": 6.55786350148368e-06,
|
| 1366 |
+
"loss": 0.1028,
|
| 1367 |
+
"step": 1460
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 1.3855762432241339,
|
| 1371 |
+
"grad_norm": 3.46875,
|
| 1372 |
+
"learning_rate": 6.45895153313551e-06,
|
| 1373 |
+
"loss": 0.0687,
|
| 1374 |
+
"step": 1470
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 1.3855762432241339,
|
| 1378 |
+
"eval_loss": 0.13968150317668915,
|
| 1379 |
+
"eval_runtime": 3.3677,
|
| 1380 |
+
"eval_samples_per_second": 12.769,
|
| 1381 |
+
"eval_steps_per_second": 12.769,
|
| 1382 |
+
"step": 1470
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 1.3950035352345038,
|
| 1386 |
+
"grad_norm": 2.828125,
|
| 1387 |
+
"learning_rate": 6.36003956478734e-06,
|
| 1388 |
+
"loss": 0.078,
|
| 1389 |
+
"step": 1480
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 1.404430827244874,
|
| 1393 |
+
"grad_norm": 5.46875,
|
| 1394 |
+
"learning_rate": 6.2611275964391694e-06,
|
| 1395 |
+
"loss": 0.0694,
|
| 1396 |
+
"step": 1490
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 1.413858119255244,
|
| 1400 |
+
"grad_norm": 3.140625,
|
| 1401 |
+
"learning_rate": 6.162215628091e-06,
|
| 1402 |
+
"loss": 0.127,
|
| 1403 |
+
"step": 1500
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 1.4185717652604288,
|
| 1407 |
+
"eval_loss": 0.1389547735452652,
|
| 1408 |
+
"eval_runtime": 2.8823,
|
| 1409 |
+
"eval_samples_per_second": 14.919,
|
| 1410 |
+
"eval_steps_per_second": 14.919,
|
| 1411 |
+
"step": 1505
|
| 1412 |
+
},
|
| 1413 |
+
{
|
| 1414 |
+
"epoch": 1.423285411265614,
|
| 1415 |
+
"grad_norm": 2.640625,
|
| 1416 |
+
"learning_rate": 6.06330365974283e-06,
|
| 1417 |
+
"loss": 0.0876,
|
| 1418 |
+
"step": 1510
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 1.432712703275984,
|
| 1422 |
+
"grad_norm": 3.96875,
|
| 1423 |
+
"learning_rate": 5.964391691394659e-06,
|
| 1424 |
+
"loss": 0.0789,
|
| 1425 |
+
"step": 1520
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 1.442139995286354,
|
| 1429 |
+
"grad_norm": 2.921875,
|
| 1430 |
+
"learning_rate": 5.865479723046489e-06,
|
| 1431 |
+
"loss": 0.0674,
|
| 1432 |
+
"step": 1530
|
| 1433 |
+
},
|
| 1434 |
+
{
|
| 1435 |
+
"epoch": 1.451567287296724,
|
| 1436 |
+
"grad_norm": 3.265625,
|
| 1437 |
+
"learning_rate": 5.766567754698319e-06,
|
| 1438 |
+
"loss": 0.0845,
|
| 1439 |
+
"step": 1540
|
| 1440 |
+
},
|
| 1441 |
+
{
|
| 1442 |
+
"epoch": 1.451567287296724,
|
| 1443 |
+
"eval_loss": 0.1385909616947174,
|
| 1444 |
+
"eval_runtime": 2.9439,
|
| 1445 |
+
"eval_samples_per_second": 14.606,
|
| 1446 |
+
"eval_steps_per_second": 14.606,
|
| 1447 |
+
"step": 1540
|
| 1448 |
+
},
|
| 1449 |
+
{
|
| 1450 |
+
"epoch": 1.460994579307094,
|
| 1451 |
+
"grad_norm": 5.3125,
|
| 1452 |
+
"learning_rate": 5.667655786350149e-06,
|
| 1453 |
+
"loss": 0.0718,
|
| 1454 |
+
"step": 1550
|
| 1455 |
+
},
|
| 1456 |
+
{
|
| 1457 |
+
"epoch": 1.470421871317464,
|
| 1458 |
+
"grad_norm": 5.53125,
|
| 1459 |
+
"learning_rate": 5.568743818001978e-06,
|
| 1460 |
+
"loss": 0.0957,
|
| 1461 |
+
"step": 1560
|
| 1462 |
+
},
|
| 1463 |
+
{
|
| 1464 |
+
"epoch": 1.4798491633278341,
|
| 1465 |
+
"grad_norm": 2.96875,
|
| 1466 |
+
"learning_rate": 5.469831849653808e-06,
|
| 1467 |
+
"loss": 0.0926,
|
| 1468 |
+
"step": 1570
|
| 1469 |
+
},
|
| 1470 |
+
{
|
| 1471 |
+
"epoch": 1.4845628093330192,
|
| 1472 |
+
"eval_loss": 0.13625992834568024,
|
| 1473 |
+
"eval_runtime": 3.3765,
|
| 1474 |
+
"eval_samples_per_second": 12.735,
|
| 1475 |
+
"eval_steps_per_second": 12.735,
|
| 1476 |
+
"step": 1575
|
| 1477 |
+
},
|
| 1478 |
+
{
|
| 1479 |
+
"epoch": 1.489276455338204,
|
| 1480 |
+
"grad_norm": 3.9375,
|
| 1481 |
+
"learning_rate": 5.370919881305638e-06,
|
| 1482 |
+
"loss": 0.0724,
|
| 1483 |
+
"step": 1580
|
| 1484 |
+
},
|
| 1485 |
+
{
|
| 1486 |
+
"epoch": 1.498703747348574,
|
| 1487 |
+
"grad_norm": 3.578125,
|
| 1488 |
+
"learning_rate": 5.272007912957469e-06,
|
| 1489 |
+
"loss": 0.0873,
|
| 1490 |
+
"step": 1590
|
| 1491 |
+
},
|
| 1492 |
+
{
|
| 1493 |
+
"epoch": 1.5081310393589442,
|
| 1494 |
+
"grad_norm": 5.53125,
|
| 1495 |
+
"learning_rate": 5.173095944609297e-06,
|
| 1496 |
+
"loss": 0.0958,
|
| 1497 |
+
"step": 1600
|
| 1498 |
+
},
|
| 1499 |
+
{
|
| 1500 |
+
"epoch": 1.5175583313693142,
|
| 1501 |
+
"grad_norm": 3.40625,
|
| 1502 |
+
"learning_rate": 5.0741839762611275e-06,
|
| 1503 |
+
"loss": 0.0539,
|
| 1504 |
+
"step": 1610
|
| 1505 |
+
},
|
| 1506 |
+
{
|
| 1507 |
+
"epoch": 1.5175583313693142,
|
| 1508 |
+
"eval_loss": 0.13553956151008606,
|
| 1509 |
+
"eval_runtime": 3.4118,
|
| 1510 |
+
"eval_samples_per_second": 12.603,
|
| 1511 |
+
"eval_steps_per_second": 12.603,
|
| 1512 |
+
"step": 1610
|
| 1513 |
+
},
|
| 1514 |
+
{
|
| 1515 |
+
"epoch": 1.5269856233796841,
|
| 1516 |
+
"grad_norm": 4.1875,
|
| 1517 |
+
"learning_rate": 4.975272007912958e-06,
|
| 1518 |
+
"loss": 0.0827,
|
| 1519 |
+
"step": 1620
|
| 1520 |
+
},
|
| 1521 |
+
{
|
| 1522 |
+
"epoch": 1.5364129153900543,
|
| 1523 |
+
"grad_norm": 2.65625,
|
| 1524 |
+
"learning_rate": 4.876360039564787e-06,
|
| 1525 |
+
"loss": 0.0771,
|
| 1526 |
+
"step": 1630
|
| 1527 |
+
},
|
| 1528 |
+
{
|
| 1529 |
+
"epoch": 1.5458402074004243,
|
| 1530 |
+
"grad_norm": 5.96875,
|
| 1531 |
+
"learning_rate": 4.7774480712166174e-06,
|
| 1532 |
+
"loss": 0.0769,
|
| 1533 |
+
"step": 1640
|
| 1534 |
+
},
|
| 1535 |
+
{
|
| 1536 |
+
"epoch": 1.5505538534056091,
|
| 1537 |
+
"eval_loss": 0.1363365650177002,
|
| 1538 |
+
"eval_runtime": 3.3765,
|
| 1539 |
+
"eval_samples_per_second": 12.735,
|
| 1540 |
+
"eval_steps_per_second": 12.735,
|
| 1541 |
+
"step": 1645
|
| 1542 |
+
},
|
| 1543 |
+
{
|
| 1544 |
+
"epoch": 1.5552674994107942,
|
| 1545 |
+
"grad_norm": 4.65625,
|
| 1546 |
+
"learning_rate": 4.678536102868448e-06,
|
| 1547 |
+
"loss": 0.0897,
|
| 1548 |
+
"step": 1650
|
| 1549 |
+
},
|
| 1550 |
+
{
|
| 1551 |
+
"epoch": 1.5646947914211644,
|
| 1552 |
+
"grad_norm": 5.0625,
|
| 1553 |
+
"learning_rate": 4.579624134520277e-06,
|
| 1554 |
+
"loss": 0.0871,
|
| 1555 |
+
"step": 1660
|
| 1556 |
+
},
|
| 1557 |
+
{
|
| 1558 |
+
"epoch": 1.5741220834315341,
|
| 1559 |
+
"grad_norm": 2.53125,
|
| 1560 |
+
"learning_rate": 4.480712166172107e-06,
|
| 1561 |
+
"loss": 0.0716,
|
| 1562 |
+
"step": 1670
|
| 1563 |
+
},
|
| 1564 |
+
{
|
| 1565 |
+
"epoch": 1.5835493754419043,
|
| 1566 |
+
"grad_norm": 1.7265625,
|
| 1567 |
+
"learning_rate": 4.381800197823937e-06,
|
| 1568 |
+
"loss": 0.067,
|
| 1569 |
+
"step": 1680
|
| 1570 |
+
},
|
| 1571 |
+
{
|
| 1572 |
+
"epoch": 1.5835493754419043,
|
| 1573 |
+
"eval_loss": 0.13660120964050293,
|
| 1574 |
+
"eval_runtime": 3.6215,
|
| 1575 |
+
"eval_samples_per_second": 11.874,
|
| 1576 |
+
"eval_steps_per_second": 11.874,
|
| 1577 |
+
"step": 1680
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 1.5929766674522743,
|
| 1581 |
+
"grad_norm": 5.125,
|
| 1582 |
+
"learning_rate": 4.282888229475767e-06,
|
| 1583 |
+
"loss": 0.08,
|
| 1584 |
+
"step": 1690
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 1.6024039594626442,
|
| 1588 |
+
"grad_norm": 4.0625,
|
| 1589 |
+
"learning_rate": 4.183976261127597e-06,
|
| 1590 |
+
"loss": 0.0766,
|
| 1591 |
+
"step": 1700
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 1.6118312514730144,
|
| 1595 |
+
"grad_norm": 3.359375,
|
| 1596 |
+
"learning_rate": 4.085064292779427e-06,
|
| 1597 |
+
"loss": 0.0836,
|
| 1598 |
+
"step": 1710
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 1.6165448974781995,
|
| 1602 |
+
"eval_loss": 0.13567590713500977,
|
| 1603 |
+
"eval_runtime": 2.8431,
|
| 1604 |
+
"eval_samples_per_second": 15.124,
|
| 1605 |
+
"eval_steps_per_second": 15.124,
|
| 1606 |
+
"step": 1715
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 1.6212585434833844,
|
| 1610 |
+
"grad_norm": 2.1875,
|
| 1611 |
+
"learning_rate": 3.986152324431257e-06,
|
| 1612 |
+
"loss": 0.0617,
|
| 1613 |
+
"step": 1720
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 1.6306858354937543,
|
| 1617 |
+
"grad_norm": 2.890625,
|
| 1618 |
+
"learning_rate": 3.887240356083086e-06,
|
| 1619 |
+
"loss": 0.1044,
|
| 1620 |
+
"step": 1730
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 1.6401131275041245,
|
| 1624 |
+
"grad_norm": 3.390625,
|
| 1625 |
+
"learning_rate": 3.7883283877349162e-06,
|
| 1626 |
+
"loss": 0.0601,
|
| 1627 |
+
"step": 1740
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 1.6495404195144945,
|
| 1631 |
+
"grad_norm": 2.59375,
|
| 1632 |
+
"learning_rate": 3.689416419386746e-06,
|
| 1633 |
+
"loss": 0.0494,
|
| 1634 |
+
"step": 1750
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 1.6495404195144945,
|
| 1638 |
+
"eval_loss": 0.13626021146774292,
|
| 1639 |
+
"eval_runtime": 2.8485,
|
| 1640 |
+
"eval_samples_per_second": 15.096,
|
| 1641 |
+
"eval_steps_per_second": 15.096,
|
| 1642 |
+
"step": 1750
|
| 1643 |
+
},
|
| 1644 |
+
{
|
| 1645 |
+
"epoch": 1.6589677115248644,
|
| 1646 |
+
"grad_norm": 2.625,
|
| 1647 |
+
"learning_rate": 3.5905044510385763e-06,
|
| 1648 |
+
"loss": 0.0858,
|
| 1649 |
+
"step": 1760
|
| 1650 |
+
},
|
| 1651 |
+
{
|
| 1652 |
+
"epoch": 1.6683950035352346,
|
| 1653 |
+
"grad_norm": 2.890625,
|
| 1654 |
+
"learning_rate": 3.4915924826904058e-06,
|
| 1655 |
+
"loss": 0.0724,
|
| 1656 |
+
"step": 1770
|
| 1657 |
+
},
|
| 1658 |
+
{
|
| 1659 |
+
"epoch": 1.6778222955456044,
|
| 1660 |
+
"grad_norm": 4.15625,
|
| 1661 |
+
"learning_rate": 3.392680514342236e-06,
|
| 1662 |
+
"loss": 0.113,
|
| 1663 |
+
"step": 1780
|
| 1664 |
+
},
|
| 1665 |
+
{
|
| 1666 |
+
"epoch": 1.6825359415507894,
|
| 1667 |
+
"eval_loss": 0.13627412915229797,
|
| 1668 |
+
"eval_runtime": 2.8152,
|
| 1669 |
+
"eval_samples_per_second": 15.274,
|
| 1670 |
+
"eval_steps_per_second": 15.274,
|
| 1671 |
+
"step": 1785
|
| 1672 |
+
},
|
| 1673 |
+
{
|
| 1674 |
+
"epoch": 1.6872495875559745,
|
| 1675 |
+
"grad_norm": 2.484375,
|
| 1676 |
+
"learning_rate": 3.2937685459940654e-06,
|
| 1677 |
+
"loss": 0.0832,
|
| 1678 |
+
"step": 1790
|
| 1679 |
+
},
|
| 1680 |
+
{
|
| 1681 |
+
"epoch": 1.6966768795663447,
|
| 1682 |
+
"grad_norm": 2.734375,
|
| 1683 |
+
"learning_rate": 3.1948565776458957e-06,
|
| 1684 |
+
"loss": 0.0748,
|
| 1685 |
+
"step": 1800
|
| 1686 |
+
},
|
| 1687 |
+
{
|
| 1688 |
+
"epoch": 1.7061041715767145,
|
| 1689 |
+
"grad_norm": 5.625,
|
| 1690 |
+
"learning_rate": 3.095944609297725e-06,
|
| 1691 |
+
"loss": 0.0566,
|
| 1692 |
+
"step": 1810
|
| 1693 |
+
},
|
| 1694 |
+
{
|
| 1695 |
+
"epoch": 1.7155314635870846,
|
| 1696 |
+
"grad_norm": 2.484375,
|
| 1697 |
+
"learning_rate": 2.9970326409495554e-06,
|
| 1698 |
+
"loss": 0.0772,
|
| 1699 |
+
"step": 1820
|
| 1700 |
+
},
|
| 1701 |
+
{
|
| 1702 |
+
"epoch": 1.7155314635870846,
|
| 1703 |
+
"eval_loss": 0.1360086351633072,
|
| 1704 |
+
"eval_runtime": 2.8263,
|
| 1705 |
+
"eval_samples_per_second": 15.214,
|
| 1706 |
+
"eval_steps_per_second": 15.214,
|
| 1707 |
+
"step": 1820
|
| 1708 |
+
},
|
| 1709 |
+
{
|
| 1710 |
+
"epoch": 1.7249587555974546,
|
| 1711 |
+
"grad_norm": 2.96875,
|
| 1712 |
+
"learning_rate": 2.8981206726013848e-06,
|
| 1713 |
+
"loss": 0.0731,
|
| 1714 |
+
"step": 1830
|
| 1715 |
+
},
|
| 1716 |
+
{
|
| 1717 |
+
"epoch": 1.7343860476078246,
|
| 1718 |
+
"grad_norm": 2.890625,
|
| 1719 |
+
"learning_rate": 2.799208704253215e-06,
|
| 1720 |
+
"loss": 0.0547,
|
| 1721 |
+
"step": 1840
|
| 1722 |
+
},
|
| 1723 |
+
{
|
| 1724 |
+
"epoch": 1.7438133396181947,
|
| 1725 |
+
"grad_norm": 2.84375,
|
| 1726 |
+
"learning_rate": 2.700296735905045e-06,
|
| 1727 |
+
"loss": 0.0572,
|
| 1728 |
+
"step": 1850
|
| 1729 |
+
},
|
| 1730 |
+
{
|
| 1731 |
+
"epoch": 1.7485269856233798,
|
| 1732 |
+
"eval_loss": 0.13581496477127075,
|
| 1733 |
+
"eval_runtime": 3.4129,
|
| 1734 |
+
"eval_samples_per_second": 12.599,
|
| 1735 |
+
"eval_steps_per_second": 12.599,
|
| 1736 |
+
"step": 1855
|
| 1737 |
+
},
|
| 1738 |
+
{
|
| 1739 |
+
"epoch": 1.7532406316285647,
|
| 1740 |
+
"grad_norm": 3.0625,
|
| 1741 |
+
"learning_rate": 2.6013847675568747e-06,
|
| 1742 |
+
"loss": 0.0869,
|
| 1743 |
+
"step": 1860
|
| 1744 |
+
},
|
| 1745 |
+
{
|
| 1746 |
+
"epoch": 1.7626679236389347,
|
| 1747 |
+
"grad_norm": 1.234375,
|
| 1748 |
+
"learning_rate": 2.5024727992087046e-06,
|
| 1749 |
+
"loss": 0.0512,
|
| 1750 |
+
"step": 1870
|
| 1751 |
+
},
|
| 1752 |
+
{
|
| 1753 |
+
"epoch": 1.7720952156493048,
|
| 1754 |
+
"grad_norm": 6.1875,
|
| 1755 |
+
"learning_rate": 2.4035608308605344e-06,
|
| 1756 |
+
"loss": 0.0951,
|
| 1757 |
+
"step": 1880
|
| 1758 |
+
},
|
| 1759 |
+
{
|
| 1760 |
+
"epoch": 1.7815225076596748,
|
| 1761 |
+
"grad_norm": 4.09375,
|
| 1762 |
+
"learning_rate": 2.3046488625123642e-06,
|
| 1763 |
+
"loss": 0.108,
|
| 1764 |
+
"step": 1890
|
| 1765 |
+
},
|
| 1766 |
+
{
|
| 1767 |
+
"epoch": 1.7815225076596748,
|
| 1768 |
+
"eval_loss": 0.13570758700370789,
|
| 1769 |
+
"eval_runtime": 2.8749,
|
| 1770 |
+
"eval_samples_per_second": 14.957,
|
| 1771 |
+
"eval_steps_per_second": 14.957,
|
| 1772 |
+
"step": 1890
|
| 1773 |
+
},
|
| 1774 |
+
{
|
| 1775 |
+
"epoch": 1.7909497996700448,
|
| 1776 |
+
"grad_norm": 3.5,
|
| 1777 |
+
"learning_rate": 2.205736894164194e-06,
|
| 1778 |
+
"loss": 0.0624,
|
| 1779 |
+
"step": 1900
|
| 1780 |
+
},
|
| 1781 |
+
{
|
| 1782 |
+
"epoch": 1.800377091680415,
|
| 1783 |
+
"grad_norm": 3.046875,
|
| 1784 |
+
"learning_rate": 2.106824925816024e-06,
|
| 1785 |
+
"loss": 0.0644,
|
| 1786 |
+
"step": 1910
|
| 1787 |
+
},
|
| 1788 |
+
{
|
| 1789 |
+
"epoch": 1.8098043836907847,
|
| 1790 |
+
"grad_norm": 2.703125,
|
| 1791 |
+
"learning_rate": 2.0079129574678537e-06,
|
| 1792 |
+
"loss": 0.0756,
|
| 1793 |
+
"step": 1920
|
| 1794 |
+
},
|
| 1795 |
+
{
|
| 1796 |
+
"epoch": 1.8145180296959698,
|
| 1797 |
+
"eval_loss": 0.1355813890695572,
|
| 1798 |
+
"eval_runtime": 2.8479,
|
| 1799 |
+
"eval_samples_per_second": 15.099,
|
| 1800 |
+
"eval_steps_per_second": 15.099,
|
| 1801 |
+
"step": 1925
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 1.8192316757011548,
|
| 1805 |
+
"grad_norm": 7.71875,
|
| 1806 |
+
"learning_rate": 1.9090009891196836e-06,
|
| 1807 |
+
"loss": 0.0725,
|
| 1808 |
+
"step": 1930
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 1.828658967711525,
|
| 1812 |
+
"grad_norm": 2.25,
|
| 1813 |
+
"learning_rate": 1.8100890207715136e-06,
|
| 1814 |
+
"loss": 0.066,
|
| 1815 |
+
"step": 1940
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 1.8380862597218948,
|
| 1819 |
+
"grad_norm": 2.296875,
|
| 1820 |
+
"learning_rate": 1.7111770524233435e-06,
|
| 1821 |
+
"loss": 0.072,
|
| 1822 |
+
"step": 1950
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 1.847513551732265,
|
| 1826 |
+
"grad_norm": 5.78125,
|
| 1827 |
+
"learning_rate": 1.6122650840751733e-06,
|
| 1828 |
+
"loss": 0.092,
|
| 1829 |
+
"step": 1960
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 1.847513551732265,
|
| 1833 |
+
"eval_loss": 0.13533347845077515,
|
| 1834 |
+
"eval_runtime": 3.3688,
|
| 1835 |
+
"eval_samples_per_second": 12.764,
|
| 1836 |
+
"eval_steps_per_second": 12.764,
|
| 1837 |
+
"step": 1960
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 1.856940843742635,
|
| 1841 |
+
"grad_norm": 2.671875,
|
| 1842 |
+
"learning_rate": 1.5133531157270031e-06,
|
| 1843 |
+
"loss": 0.0586,
|
| 1844 |
+
"step": 1970
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 1.8663681357530049,
|
| 1848 |
+
"grad_norm": 3.28125,
|
| 1849 |
+
"learning_rate": 1.414441147378833e-06,
|
| 1850 |
+
"loss": 0.0762,
|
| 1851 |
+
"step": 1980
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 1.875795427763375,
|
| 1855 |
+
"grad_norm": 3.75,
|
| 1856 |
+
"learning_rate": 1.3155291790306628e-06,
|
| 1857 |
+
"loss": 0.0956,
|
| 1858 |
+
"step": 1990
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 1.8805090737685601,
|
| 1862 |
+
"eval_loss": 0.13476963341236115,
|
| 1863 |
+
"eval_runtime": 2.8911,
|
| 1864 |
+
"eval_samples_per_second": 14.873,
|
| 1865 |
+
"eval_steps_per_second": 14.873,
|
| 1866 |
+
"step": 1995
|
| 1867 |
+
}
|
| 1868 |
+
],
|
| 1869 |
+
"logging_steps": 10,
|
| 1870 |
+
"max_steps": 2122,
|
| 1871 |
+
"num_input_tokens_seen": 0,
|
| 1872 |
+
"num_train_epochs": 2,
|
| 1873 |
+
"save_steps": 35,
|
| 1874 |
+
"stateful_callbacks": {
|
| 1875 |
+
"TrainerControl": {
|
| 1876 |
+
"args": {
|
| 1877 |
+
"should_epoch_stop": false,
|
| 1878 |
+
"should_evaluate": false,
|
| 1879 |
+
"should_log": false,
|
| 1880 |
+
"should_save": true,
|
| 1881 |
+
"should_training_stop": false
|
| 1882 |
+
},
|
| 1883 |
+
"attributes": {}
|
| 1884 |
+
}
|
| 1885 |
+
},
|
| 1886 |
+
"total_flos": 6918461092528128.0,
|
| 1887 |
+
"train_batch_size": 1,
|
| 1888 |
+
"trial_name": null,
|
| 1889 |
+
"trial_params": null
|
| 1890 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5747935e6b612ba6cbefc4fc16d1fd863159328bb4c6d79b0afbb7afb99fc143
|
| 3 |
+
size 5777
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|