Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- trial_sft-m-a2dbd3lm-qwen3-0.6B_tulu3mixture/checkpoint-1000/added_tokens.json +29 -0
- trial_sft-m-a2dbd3lm-qwen3-0.6B_tulu3mixture/checkpoint-1000/chat_template.jinja +89 -0
- trial_sft-m-a2dbd3lm-qwen3-0.6B_tulu3mixture/checkpoint-1000/config.json +61 -0
- trial_sft-m-a2dbd3lm-qwen3-0.6B_tulu3mixture/checkpoint-1000/generation_config.json +9 -0
- trial_sft-m-a2dbd3lm-qwen3-0.6B_tulu3mixture/checkpoint-1000/merges.txt +0 -0
- trial_sft-m-a2dbd3lm-qwen3-0.6B_tulu3mixture/checkpoint-1000/model.safetensors +3 -0
- trial_sft-m-a2dbd3lm-qwen3-0.6B_tulu3mixture/checkpoint-1000/special_tokens_map.json +39 -0
- trial_sft-m-a2dbd3lm-qwen3-0.6B_tulu3mixture/checkpoint-1000/tokenizer.json +3 -0
- trial_sft-m-a2dbd3lm-qwen3-0.6B_tulu3mixture/checkpoint-1000/tokenizer_config.json +249 -0
- trial_sft-m-a2dbd3lm-qwen3-0.6B_tulu3mixture/checkpoint-1000/trainer_state.json +734 -0
- trial_sft-m-a2dbd3lm-qwen3-0.6B_tulu3mixture/checkpoint-1000/training_args.bin +3 -0
- trial_sft-m-a2dbd3lm-qwen3-0.6B_tulu3mixture/checkpoint-1000/vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -40,3 +40,4 @@ sft-d-a2dbd3lm-qwen3-0.6B_tulu3mixture-3clusters-by-domain/expert_2/checkpoint-f
|
|
| 40 |
sft-d-a2dbd3lm-qwen3-0.6B_tulu3mixture-3clusters-by-domain/router/checkpoint-final/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 41 |
trial_sft-m-a2dbd3lm-qwen3-0.6B_tulu3mixture/checkpoint-3000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 42 |
trial_sft-m-a2dbd3lm-qwen3-0.6B_tulu3mixture/checkpoint-2000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 40 |
sft-d-a2dbd3lm-qwen3-0.6B_tulu3mixture-3clusters-by-domain/router/checkpoint-final/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 41 |
trial_sft-m-a2dbd3lm-qwen3-0.6B_tulu3mixture/checkpoint-3000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 42 |
trial_sft-m-a2dbd3lm-qwen3-0.6B_tulu3mixture/checkpoint-2000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 43 |
+
trial_sft-m-a2dbd3lm-qwen3-0.6B_tulu3mixture/checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
trial_sft-m-a2dbd3lm-qwen3-0.6B_tulu3mixture/checkpoint-1000/added_tokens.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"<|mask|>": 151669,
|
| 20 |
+
"<|object_ref_end|>": 151647,
|
| 21 |
+
"<|object_ref_start|>": 151646,
|
| 22 |
+
"<|quad_end|>": 151651,
|
| 23 |
+
"<|quad_start|>": 151650,
|
| 24 |
+
"<|repo_name|>": 151663,
|
| 25 |
+
"<|video_pad|>": 151656,
|
| 26 |
+
"<|vision_end|>": 151653,
|
| 27 |
+
"<|vision_pad|>": 151654,
|
| 28 |
+
"<|vision_start|>": 151652
|
| 29 |
+
}
|
trial_sft-m-a2dbd3lm-qwen3-0.6B_tulu3mixture/checkpoint-1000/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 %}
|
trial_sft-m-a2dbd3lm-qwen3-0.6B_tulu3mixture/checkpoint-1000/config.json
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"A2DQwen3LMHeadModel"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151643,
|
| 8 |
+
"dtype": "bfloat16",
|
| 9 |
+
"eos_token_id": 151645,
|
| 10 |
+
"head_dim": 128,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 1024,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 3072,
|
| 15 |
+
"layer_types": [
|
| 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 |
+
"full_attention"
|
| 44 |
+
],
|
| 45 |
+
"max_position_embeddings": 40960,
|
| 46 |
+
"max_window_layers": 28,
|
| 47 |
+
"model_type": "a2d-qwen3",
|
| 48 |
+
"num_attention_heads": 16,
|
| 49 |
+
"num_hidden_layers": 28,
|
| 50 |
+
"num_key_value_heads": 8,
|
| 51 |
+
"pad_token_id": 151643,
|
| 52 |
+
"rms_norm_eps": 1e-06,
|
| 53 |
+
"rope_scaling": null,
|
| 54 |
+
"rope_theta": 1000000,
|
| 55 |
+
"sliding_window": null,
|
| 56 |
+
"tie_word_embeddings": true,
|
| 57 |
+
"transformers_version": "4.57.0",
|
| 58 |
+
"use_cache": true,
|
| 59 |
+
"use_sliding_window": false,
|
| 60 |
+
"vocab_size": 151936
|
| 61 |
+
}
|
trial_sft-m-a2dbd3lm-qwen3-0.6B_tulu3mixture/checkpoint-1000/generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 151643,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645
|
| 6 |
+
],
|
| 7 |
+
"pad_token_id": 151643,
|
| 8 |
+
"transformers_version": "4.57.0"
|
| 9 |
+
}
|
trial_sft-m-a2dbd3lm-qwen3-0.6B_tulu3mixture/checkpoint-1000/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
trial_sft-m-a2dbd3lm-qwen3-0.6B_tulu3mixture/checkpoint-1000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e954233f32294c20f00a7e4a5a01dda28a67cd95415224423b368243eac07813
|
| 3 |
+
size 1192135096
|
trial_sft-m-a2dbd3lm-qwen3-0.6B_tulu3mixture/checkpoint-1000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"bos_token": "<|endoftext|>",
|
| 18 |
+
"eos_token": {
|
| 19 |
+
"content": "<|im_end|>",
|
| 20 |
+
"lstrip": false,
|
| 21 |
+
"normalized": false,
|
| 22 |
+
"rstrip": false,
|
| 23 |
+
"single_word": false
|
| 24 |
+
},
|
| 25 |
+
"mask_token": {
|
| 26 |
+
"content": "<|mask|>",
|
| 27 |
+
"lstrip": false,
|
| 28 |
+
"normalized": false,
|
| 29 |
+
"rstrip": false,
|
| 30 |
+
"single_word": false
|
| 31 |
+
},
|
| 32 |
+
"pad_token": {
|
| 33 |
+
"content": "<|endoftext|>",
|
| 34 |
+
"lstrip": false,
|
| 35 |
+
"normalized": false,
|
| 36 |
+
"rstrip": false,
|
| 37 |
+
"single_word": false
|
| 38 |
+
}
|
| 39 |
+
}
|
trial_sft-m-a2dbd3lm-qwen3-0.6B_tulu3mixture/checkpoint-1000/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6d55810de1daf81d1d1259355b4b85810385022ab745be68029295935a4eacf0
|
| 3 |
+
size 11422839
|
trial_sft-m-a2dbd3lm-qwen3-0.6B_tulu3mixture/checkpoint-1000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,249 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"151669": {
|
| 214 |
+
"content": "<|mask|>",
|
| 215 |
+
"lstrip": false,
|
| 216 |
+
"normalized": false,
|
| 217 |
+
"rstrip": false,
|
| 218 |
+
"single_word": false,
|
| 219 |
+
"special": true
|
| 220 |
+
}
|
| 221 |
+
},
|
| 222 |
+
"additional_special_tokens": [
|
| 223 |
+
"<|im_start|>",
|
| 224 |
+
"<|im_end|>",
|
| 225 |
+
"<|object_ref_start|>",
|
| 226 |
+
"<|object_ref_end|>",
|
| 227 |
+
"<|box_start|>",
|
| 228 |
+
"<|box_end|>",
|
| 229 |
+
"<|quad_start|>",
|
| 230 |
+
"<|quad_end|>",
|
| 231 |
+
"<|vision_start|>",
|
| 232 |
+
"<|vision_end|>",
|
| 233 |
+
"<|vision_pad|>",
|
| 234 |
+
"<|image_pad|>",
|
| 235 |
+
"<|video_pad|>"
|
| 236 |
+
],
|
| 237 |
+
"bos_token": "<|endoftext|>",
|
| 238 |
+
"clean_up_tokenization_spaces": false,
|
| 239 |
+
"eos_token": "<|im_end|>",
|
| 240 |
+
"errors": "replace",
|
| 241 |
+
"extra_special_tokens": {},
|
| 242 |
+
"mask_token": "<|mask|>",
|
| 243 |
+
"model_max_length": 131072,
|
| 244 |
+
"pad_token": "<|endoftext|>",
|
| 245 |
+
"padding_side": "right",
|
| 246 |
+
"split_special_tokens": false,
|
| 247 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 248 |
+
"unk_token": null
|
| 249 |
+
}
|
trial_sft-m-a2dbd3lm-qwen3-0.6B_tulu3mixture/checkpoint-1000/trainer_state.json
ADDED
|
@@ -0,0 +1,734 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 2.3760785480511752,
|
| 6 |
+
"eval_steps": 421,
|
| 7 |
+
"global_step": 1000,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.023802439750074383,
|
| 14 |
+
"grad_norm": 7232.0,
|
| 15 |
+
"learning_rate": 2.137767220902613e-06,
|
| 16 |
+
"loss": 471.4132,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.047604879500148765,
|
| 21 |
+
"grad_norm": 4320.0,
|
| 22 |
+
"learning_rate": 4.513064133016627e-06,
|
| 23 |
+
"loss": 428.0732,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.07140731925022314,
|
| 28 |
+
"grad_norm": 3952.0,
|
| 29 |
+
"learning_rate": 6.888361045130641e-06,
|
| 30 |
+
"loss": 329.0237,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.09520975900029753,
|
| 35 |
+
"grad_norm": 1216.0,
|
| 36 |
+
"learning_rate": 9.263657957244656e-06,
|
| 37 |
+
"loss": 229.4549,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.11901219875037192,
|
| 42 |
+
"grad_norm": 724.0,
|
| 43 |
+
"learning_rate": 1.163895486935867e-05,
|
| 44 |
+
"loss": 185.0061,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.1428146385004463,
|
| 49 |
+
"grad_norm": 468.0,
|
| 50 |
+
"learning_rate": 1.4014251781472683e-05,
|
| 51 |
+
"loss": 159.8342,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.1666170782505207,
|
| 56 |
+
"grad_norm": 338.0,
|
| 57 |
+
"learning_rate": 1.63895486935867e-05,
|
| 58 |
+
"loss": 137.5886,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.19041951800059506,
|
| 63 |
+
"grad_norm": 201.0,
|
| 64 |
+
"learning_rate": 1.876484560570071e-05,
|
| 65 |
+
"loss": 122.8549,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.21422195775066943,
|
| 70 |
+
"grad_norm": 280.0,
|
| 71 |
+
"learning_rate": 2.114014251781473e-05,
|
| 72 |
+
"loss": 112.4709,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.23802439750074383,
|
| 77 |
+
"grad_norm": 328.0,
|
| 78 |
+
"learning_rate": 2.3515439429928742e-05,
|
| 79 |
+
"loss": 104.9342,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.26182683725081823,
|
| 84 |
+
"grad_norm": 226.0,
|
| 85 |
+
"learning_rate": 2.5890736342042754e-05,
|
| 86 |
+
"loss": 102.7674,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.2856292770008926,
|
| 91 |
+
"grad_norm": 195.0,
|
| 92 |
+
"learning_rate": 2.826603325415677e-05,
|
| 93 |
+
"loss": 97.4777,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.309431716750967,
|
| 98 |
+
"grad_norm": 264.0,
|
| 99 |
+
"learning_rate": 3.064133016627079e-05,
|
| 100 |
+
"loss": 92.5614,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.3332341565010414,
|
| 105 |
+
"grad_norm": 374.0,
|
| 106 |
+
"learning_rate": 3.30166270783848e-05,
|
| 107 |
+
"loss": 91.1698,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.3570365962511157,
|
| 112 |
+
"grad_norm": 228.0,
|
| 113 |
+
"learning_rate": 3.539192399049881e-05,
|
| 114 |
+
"loss": 87.6848,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.3808390360011901,
|
| 119 |
+
"grad_norm": 151.0,
|
| 120 |
+
"learning_rate": 3.7767220902612825e-05,
|
| 121 |
+
"loss": 85.2951,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.4046414757512645,
|
| 126 |
+
"grad_norm": 120.0,
|
| 127 |
+
"learning_rate": 4.0142517814726843e-05,
|
| 128 |
+
"loss": 83.1486,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.42844391550133887,
|
| 133 |
+
"grad_norm": 128.0,
|
| 134 |
+
"learning_rate": 4.2517814726840856e-05,
|
| 135 |
+
"loss": 80.1418,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.45224635525141327,
|
| 140 |
+
"grad_norm": 190.0,
|
| 141 |
+
"learning_rate": 4.4893111638954874e-05,
|
| 142 |
+
"loss": 77.4926,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.47604879500148767,
|
| 147 |
+
"grad_norm": 392.0,
|
| 148 |
+
"learning_rate": 4.7268408551068886e-05,
|
| 149 |
+
"loss": 75.4236,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.499851234751562,
|
| 154 |
+
"grad_norm": 125.5,
|
| 155 |
+
"learning_rate": 4.96437054631829e-05,
|
| 156 |
+
"loss": 74.6444,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.5236536745016365,
|
| 161 |
+
"grad_norm": 140.0,
|
| 162 |
+
"learning_rate": 5.201900237529691e-05,
|
| 163 |
+
"loss": 73.5658,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.5474561142517108,
|
| 168 |
+
"grad_norm": 93.0,
|
| 169 |
+
"learning_rate": 5.439429928741093e-05,
|
| 170 |
+
"loss": 70.8075,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.5712585540017852,
|
| 175 |
+
"grad_norm": 156.0,
|
| 176 |
+
"learning_rate": 5.676959619952494e-05,
|
| 177 |
+
"loss": 70.7075,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.5950609937518596,
|
| 182 |
+
"grad_norm": 380.0,
|
| 183 |
+
"learning_rate": 5.9144893111638954e-05,
|
| 184 |
+
"loss": 69.1626,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.618863433501934,
|
| 189 |
+
"grad_norm": 94.0,
|
| 190 |
+
"learning_rate": 6.152019002375298e-05,
|
| 191 |
+
"loss": 67.9296,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.6426658732520083,
|
| 196 |
+
"grad_norm": 99.0,
|
| 197 |
+
"learning_rate": 6.389548693586699e-05,
|
| 198 |
+
"loss": 67.7601,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.6664683130020828,
|
| 203 |
+
"grad_norm": 141.0,
|
| 204 |
+
"learning_rate": 6.6270783847981e-05,
|
| 205 |
+
"loss": 66.7876,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.6902707527521571,
|
| 210 |
+
"grad_norm": 110.5,
|
| 211 |
+
"learning_rate": 6.864608076009502e-05,
|
| 212 |
+
"loss": 65.9133,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.7140731925022314,
|
| 217 |
+
"grad_norm": 97.5,
|
| 218 |
+
"learning_rate": 7.102137767220903e-05,
|
| 219 |
+
"loss": 63.9556,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.7378756322523059,
|
| 224 |
+
"grad_norm": 80.0,
|
| 225 |
+
"learning_rate": 7.339667458432304e-05,
|
| 226 |
+
"loss": 64.2939,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.7616780720023802,
|
| 231 |
+
"grad_norm": 67.5,
|
| 232 |
+
"learning_rate": 7.577197149643705e-05,
|
| 233 |
+
"loss": 63.8363,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.7854805117524546,
|
| 238 |
+
"grad_norm": 75.5,
|
| 239 |
+
"learning_rate": 7.814726840855108e-05,
|
| 240 |
+
"loss": 62.0839,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.809282951502529,
|
| 245 |
+
"grad_norm": 81.0,
|
| 246 |
+
"learning_rate": 8.052256532066509e-05,
|
| 247 |
+
"loss": 63.0067,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.8330853912526034,
|
| 252 |
+
"grad_norm": 217.0,
|
| 253 |
+
"learning_rate": 8.28978622327791e-05,
|
| 254 |
+
"loss": 62.2586,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.8568878310026777,
|
| 259 |
+
"grad_norm": 76.5,
|
| 260 |
+
"learning_rate": 8.527315914489311e-05,
|
| 261 |
+
"loss": 63.1985,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.8806902707527522,
|
| 266 |
+
"grad_norm": 57.25,
|
| 267 |
+
"learning_rate": 8.764845605700714e-05,
|
| 268 |
+
"loss": 62.0241,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.9044927105028265,
|
| 273 |
+
"grad_norm": 95.5,
|
| 274 |
+
"learning_rate": 9.002375296912114e-05,
|
| 275 |
+
"loss": 60.3837,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.9282951502529009,
|
| 280 |
+
"grad_norm": 70.0,
|
| 281 |
+
"learning_rate": 9.239904988123515e-05,
|
| 282 |
+
"loss": 60.9395,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.9520975900029753,
|
| 287 |
+
"grad_norm": 141.0,
|
| 288 |
+
"learning_rate": 9.477434679334918e-05,
|
| 289 |
+
"loss": 60.6742,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.9759000297530497,
|
| 294 |
+
"grad_norm": 64.5,
|
| 295 |
+
"learning_rate": 9.714964370546319e-05,
|
| 296 |
+
"loss": 59.8488,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.999702469503124,
|
| 301 |
+
"grad_norm": 88.5,
|
| 302 |
+
"learning_rate": 9.95249406175772e-05,
|
| 303 |
+
"loss": 60.8223,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 1.0214221957750669,
|
| 308 |
+
"grad_norm": 53.0,
|
| 309 |
+
"learning_rate": 9.999890006017872e-05,
|
| 310 |
+
"loss": 55.3974,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.0452246355251413,
|
| 315 |
+
"grad_norm": 60.0,
|
| 316 |
+
"learning_rate": 9.999443163759668e-05,
|
| 317 |
+
"loss": 57.4791,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.0690270752752158,
|
| 322 |
+
"grad_norm": 54.0,
|
| 323 |
+
"learning_rate": 9.998652629296539e-05,
|
| 324 |
+
"loss": 56.968,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.09282951502529,
|
| 329 |
+
"grad_norm": 87.5,
|
| 330 |
+
"learning_rate": 9.997518456974644e-05,
|
| 331 |
+
"loss": 58.3281,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.1166319547753645,
|
| 336 |
+
"grad_norm": 93.5,
|
| 337 |
+
"learning_rate": 9.996040724763903e-05,
|
| 338 |
+
"loss": 57.8326,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.140434394525439,
|
| 343 |
+
"grad_norm": 39.75,
|
| 344 |
+
"learning_rate": 9.994219534252633e-05,
|
| 345 |
+
"loss": 54.8698,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.1642368342755132,
|
| 350 |
+
"grad_norm": 42.75,
|
| 351 |
+
"learning_rate": 9.992055010640581e-05,
|
| 352 |
+
"loss": 55.7383,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.1880392740255876,
|
| 357 |
+
"grad_norm": 44.25,
|
| 358 |
+
"learning_rate": 9.989547302730296e-05,
|
| 359 |
+
"loss": 55.8814,
|
| 360 |
+
"step": 500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.211841713775662,
|
| 364 |
+
"grad_norm": 67.5,
|
| 365 |
+
"learning_rate": 9.986696582916905e-05,
|
| 366 |
+
"loss": 55.6567,
|
| 367 |
+
"step": 510
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.2356441535257363,
|
| 371 |
+
"grad_norm": 69.0,
|
| 372 |
+
"learning_rate": 9.983503047176275e-05,
|
| 373 |
+
"loss": 56.3754,
|
| 374 |
+
"step": 520
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.2594465932758108,
|
| 378 |
+
"grad_norm": 41.75,
|
| 379 |
+
"learning_rate": 9.979966915051517e-05,
|
| 380 |
+
"loss": 55.2842,
|
| 381 |
+
"step": 530
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.2832490330258852,
|
| 385 |
+
"grad_norm": 48.25,
|
| 386 |
+
"learning_rate": 9.976088429637918e-05,
|
| 387 |
+
"loss": 54.4552,
|
| 388 |
+
"step": 540
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.3070514727759595,
|
| 392 |
+
"grad_norm": 41.5,
|
| 393 |
+
"learning_rate": 9.971867857566213e-05,
|
| 394 |
+
"loss": 54.5813,
|
| 395 |
+
"step": 550
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.330853912526034,
|
| 399 |
+
"grad_norm": 80.0,
|
| 400 |
+
"learning_rate": 9.967305488984257e-05,
|
| 401 |
+
"loss": 54.4441,
|
| 402 |
+
"step": 560
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.3546563522761084,
|
| 406 |
+
"grad_norm": 50.75,
|
| 407 |
+
"learning_rate": 9.962401637537083e-05,
|
| 408 |
+
"loss": 54.7695,
|
| 409 |
+
"step": 570
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 1.3784587920261826,
|
| 413 |
+
"grad_norm": 41.75,
|
| 414 |
+
"learning_rate": 9.957156640345341e-05,
|
| 415 |
+
"loss": 52.7512,
|
| 416 |
+
"step": 580
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.402261231776257,
|
| 420 |
+
"grad_norm": 43.5,
|
| 421 |
+
"learning_rate": 9.951570857982116e-05,
|
| 422 |
+
"loss": 54.0224,
|
| 423 |
+
"step": 590
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.4260636715263315,
|
| 427 |
+
"grad_norm": 46.25,
|
| 428 |
+
"learning_rate": 9.945644674448142e-05,
|
| 429 |
+
"loss": 54.2636,
|
| 430 |
+
"step": 600
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 1.449866111276406,
|
| 434 |
+
"grad_norm": 63.5,
|
| 435 |
+
"learning_rate": 9.939378497145409e-05,
|
| 436 |
+
"loss": 53.4678,
|
| 437 |
+
"step": 610
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 1.4736685510264802,
|
| 441 |
+
"grad_norm": 59.75,
|
| 442 |
+
"learning_rate": 9.932772756849153e-05,
|
| 443 |
+
"loss": 52.6271,
|
| 444 |
+
"step": 620
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.4974709907765547,
|
| 448 |
+
"grad_norm": 37.5,
|
| 449 |
+
"learning_rate": 9.925827907678233e-05,
|
| 450 |
+
"loss": 51.7052,
|
| 451 |
+
"step": 630
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.521273430526629,
|
| 455 |
+
"grad_norm": 40.0,
|
| 456 |
+
"learning_rate": 9.918544427063926e-05,
|
| 457 |
+
"loss": 52.7684,
|
| 458 |
+
"step": 640
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.5450758702767033,
|
| 462 |
+
"grad_norm": 39.0,
|
| 463 |
+
"learning_rate": 9.910922815717096e-05,
|
| 464 |
+
"loss": 51.2974,
|
| 465 |
+
"step": 650
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.5688783100267778,
|
| 469 |
+
"grad_norm": 49.75,
|
| 470 |
+
"learning_rate": 9.90296359759378e-05,
|
| 471 |
+
"loss": 52.9898,
|
| 472 |
+
"step": 660
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.5926807497768523,
|
| 476 |
+
"grad_norm": 47.5,
|
| 477 |
+
"learning_rate": 9.894667319859154e-05,
|
| 478 |
+
"loss": 52.063,
|
| 479 |
+
"step": 670
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.6164831895269265,
|
| 483 |
+
"grad_norm": 37.25,
|
| 484 |
+
"learning_rate": 9.886034552849939e-05,
|
| 485 |
+
"loss": 51.3358,
|
| 486 |
+
"step": 680
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 1.640285629277001,
|
| 490 |
+
"grad_norm": 35.0,
|
| 491 |
+
"learning_rate": 9.877065890035167e-05,
|
| 492 |
+
"loss": 52.1251,
|
| 493 |
+
"step": 690
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 1.6640880690270752,
|
| 497 |
+
"grad_norm": 39.25,
|
| 498 |
+
"learning_rate": 9.867761947975405e-05,
|
| 499 |
+
"loss": 51.7954,
|
| 500 |
+
"step": 700
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.6878905087771496,
|
| 504 |
+
"grad_norm": 65.5,
|
| 505 |
+
"learning_rate": 9.858123366280358e-05,
|
| 506 |
+
"loss": 51.8533,
|
| 507 |
+
"step": 710
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.711692948527224,
|
| 511 |
+
"grad_norm": 53.0,
|
| 512 |
+
"learning_rate": 9.848150807564897e-05,
|
| 513 |
+
"loss": 51.6119,
|
| 514 |
+
"step": 720
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 1.7354953882772985,
|
| 518 |
+
"grad_norm": 34.75,
|
| 519 |
+
"learning_rate": 9.837844957403512e-05,
|
| 520 |
+
"loss": 48.8657,
|
| 521 |
+
"step": 730
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.7592978280273728,
|
| 525 |
+
"grad_norm": 33.5,
|
| 526 |
+
"learning_rate": 9.827206524283176e-05,
|
| 527 |
+
"loss": 50.6406,
|
| 528 |
+
"step": 740
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 1.7831002677774472,
|
| 532 |
+
"grad_norm": 38.5,
|
| 533 |
+
"learning_rate": 9.81623623955465e-05,
|
| 534 |
+
"loss": 51.133,
|
| 535 |
+
"step": 750
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 1.8069027075275215,
|
| 539 |
+
"grad_norm": 53.75,
|
| 540 |
+
"learning_rate": 9.804934857382189e-05,
|
| 541 |
+
"loss": 51.1726,
|
| 542 |
+
"step": 760
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 1.830705147277596,
|
| 546 |
+
"grad_norm": 53.5,
|
| 547 |
+
"learning_rate": 9.793303154691707e-05,
|
| 548 |
+
"loss": 51.402,
|
| 549 |
+
"step": 770
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.8545075870276704,
|
| 553 |
+
"grad_norm": 34.75,
|
| 554 |
+
"learning_rate": 9.78134193111737e-05,
|
| 555 |
+
"loss": 49.7067,
|
| 556 |
+
"step": 780
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.8783100267777448,
|
| 560 |
+
"grad_norm": 30.875,
|
| 561 |
+
"learning_rate": 9.76905200894661e-05,
|
| 562 |
+
"loss": 50.6722,
|
| 563 |
+
"step": 790
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.902112466527819,
|
| 567 |
+
"grad_norm": 36.75,
|
| 568 |
+
"learning_rate": 9.756434233063616e-05,
|
| 569 |
+
"loss": 49.9159,
|
| 570 |
+
"step": 800
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 1.9259149062778935,
|
| 574 |
+
"grad_norm": 44.25,
|
| 575 |
+
"learning_rate": 9.743489470891227e-05,
|
| 576 |
+
"loss": 49.7655,
|
| 577 |
+
"step": 810
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 1.9497173460279678,
|
| 581 |
+
"grad_norm": 57.5,
|
| 582 |
+
"learning_rate": 9.730218612331322e-05,
|
| 583 |
+
"loss": 50.1086,
|
| 584 |
+
"step": 820
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 1.9735197857780422,
|
| 588 |
+
"grad_norm": 34.75,
|
| 589 |
+
"learning_rate": 9.716622569703633e-05,
|
| 590 |
+
"loss": 49.7459,
|
| 591 |
+
"step": 830
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.9973222255281167,
|
| 595 |
+
"grad_norm": 47.25,
|
| 596 |
+
"learning_rate": 9.702702277683022e-05,
|
| 597 |
+
"loss": 49.0236,
|
| 598 |
+
"step": 840
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 2.0190419518000593,
|
| 602 |
+
"grad_norm": 30.875,
|
| 603 |
+
"learning_rate": 9.688458693235239e-05,
|
| 604 |
+
"loss": 45.0185,
|
| 605 |
+
"step": 850
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 2.0428443915501338,
|
| 609 |
+
"grad_norm": 27.75,
|
| 610 |
+
"learning_rate": 9.673892795551121e-05,
|
| 611 |
+
"loss": 50.1129,
|
| 612 |
+
"step": 860
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 2.066646831300208,
|
| 616 |
+
"grad_norm": 29.75,
|
| 617 |
+
"learning_rate": 9.659005585979285e-05,
|
| 618 |
+
"loss": 48.4715,
|
| 619 |
+
"step": 870
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 2.0904492710502827,
|
| 623 |
+
"grad_norm": 54.25,
|
| 624 |
+
"learning_rate": 9.643798087957284e-05,
|
| 625 |
+
"loss": 48.9327,
|
| 626 |
+
"step": 880
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 2.114251710800357,
|
| 630 |
+
"grad_norm": 39.5,
|
| 631 |
+
"learning_rate": 9.628271346941252e-05,
|
| 632 |
+
"loss": 48.2108,
|
| 633 |
+
"step": 890
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 2.1380541505504316,
|
| 637 |
+
"grad_norm": 32.5,
|
| 638 |
+
"learning_rate": 9.612426430334037e-05,
|
| 639 |
+
"loss": 48.097,
|
| 640 |
+
"step": 900
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 2.1618565903005056,
|
| 644 |
+
"grad_norm": 37.5,
|
| 645 |
+
"learning_rate": 9.596264427411809e-05,
|
| 646 |
+
"loss": 47.3973,
|
| 647 |
+
"step": 910
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 2.18565903005058,
|
| 651 |
+
"grad_norm": 31.5,
|
| 652 |
+
"learning_rate": 9.579786449249193e-05,
|
| 653 |
+
"loss": 47.9111,
|
| 654 |
+
"step": 920
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 2.2094614698006545,
|
| 658 |
+
"grad_norm": 46.75,
|
| 659 |
+
"learning_rate": 9.562993628642875e-05,
|
| 660 |
+
"loss": 49.1348,
|
| 661 |
+
"step": 930
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 2.233263909550729,
|
| 665 |
+
"grad_norm": 67.5,
|
| 666 |
+
"learning_rate": 9.545887120033727e-05,
|
| 667 |
+
"loss": 48.0196,
|
| 668 |
+
"step": 940
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 2.2570663493008034,
|
| 672 |
+
"grad_norm": 30.625,
|
| 673 |
+
"learning_rate": 9.528468099427454e-05,
|
| 674 |
+
"loss": 46.3206,
|
| 675 |
+
"step": 950
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 2.280868789050878,
|
| 679 |
+
"grad_norm": 30.25,
|
| 680 |
+
"learning_rate": 9.510737764313735e-05,
|
| 681 |
+
"loss": 48.5037,
|
| 682 |
+
"step": 960
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 2.3046712288009523,
|
| 686 |
+
"grad_norm": 34.5,
|
| 687 |
+
"learning_rate": 9.492697333583908e-05,
|
| 688 |
+
"loss": 49.0783,
|
| 689 |
+
"step": 970
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 2.3284736685510263,
|
| 693 |
+
"grad_norm": 51.5,
|
| 694 |
+
"learning_rate": 9.474348047447177e-05,
|
| 695 |
+
"loss": 47.3762,
|
| 696 |
+
"step": 980
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 2.352276108301101,
|
| 700 |
+
"grad_norm": 37.25,
|
| 701 |
+
"learning_rate": 9.455691167345344e-05,
|
| 702 |
+
"loss": 47.1049,
|
| 703 |
+
"step": 990
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 2.3760785480511752,
|
| 707 |
+
"grad_norm": 31.0,
|
| 708 |
+
"learning_rate": 9.436727975866102e-05,
|
| 709 |
+
"loss": 47.8477,
|
| 710 |
+
"step": 1000
|
| 711 |
+
}
|
| 712 |
+
],
|
| 713 |
+
"logging_steps": 10,
|
| 714 |
+
"max_steps": 4210,
|
| 715 |
+
"num_input_tokens_seen": 0,
|
| 716 |
+
"num_train_epochs": 10,
|
| 717 |
+
"save_steps": 1000,
|
| 718 |
+
"stateful_callbacks": {
|
| 719 |
+
"TrainerControl": {
|
| 720 |
+
"args": {
|
| 721 |
+
"should_epoch_stop": false,
|
| 722 |
+
"should_evaluate": false,
|
| 723 |
+
"should_log": false,
|
| 724 |
+
"should_save": true,
|
| 725 |
+
"should_training_stop": false
|
| 726 |
+
},
|
| 727 |
+
"attributes": {}
|
| 728 |
+
}
|
| 729 |
+
},
|
| 730 |
+
"total_flos": 1.9713060125896868e+18,
|
| 731 |
+
"train_batch_size": 16,
|
| 732 |
+
"trial_name": null,
|
| 733 |
+
"trial_params": null
|
| 734 |
+
}
|
trial_sft-m-a2dbd3lm-qwen3-0.6B_tulu3mixture/checkpoint-1000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:84ee5e463fe61fbffb17d17c2c8e91b25d132d8c72ce11a83d23cd5ae5777a0c
|
| 3 |
+
size 6161
|
trial_sft-m-a2dbd3lm-qwen3-0.6B_tulu3mixture/checkpoint-1000/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|