初始化项目，由ModelHub XC社区提供模型
Model: bespokelabs/qwen3-1.7b-dabstep-reasoning-30-fixed-reasoning-sharegpt-sft Source: Original Platform
This commit is contained in:
ModelHub XC
49
.gitattributes
vendored
Normal file
49
.gitattributes
vendored
Normal file
@@ -0,0 +1,49 @@
|
|||||||
|
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.model filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.db* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ark* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
|
||||||
|
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.gguf* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ggml filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.llamafile* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pt2 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
|
||||||
|
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||||
57
README.md
Normal file
57
README.md
Normal file
@@ -0,0 +1,57 @@
|
|||||||
|
---
|
||||||
|
library_name: transformers
|
||||||
|
license: apache-2.0
|
||||||
|
base_model: Qwen/Qwen3-1.7B
|
||||||
|
tags:
|
||||||
|
- llama-factory
|
||||||
|
- full
|
||||||
|
- generated_from_trainer
|
||||||
|
model-index:
|
||||||
|
- name: qwen3-1.7b-dabstep-reasoning-30-fixed-reasoning-sharegpt-sft
|
||||||
|
results: []
|
||||||
|
---
|
||||||
|
|
||||||
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
||||||
|
should probably proofread and complete it, then remove this comment. -->
|
||||||
|
|
||||||
|
# qwen3-1.7b-dabstep-reasoning-30-fixed-reasoning-sharegpt-sft
|
||||||
|
|
||||||
|
This model is a fine-tuned version of [Qwen/Qwen3-1.7B](https://huggingface.co/Qwen/Qwen3-1.7B) on the eval-ds-dabstep-reasoning-30-fixed-reasoning-sharegpt dataset.
|
||||||
|
|
||||||
|
## Model description
|
||||||
|
|
||||||
|
More information needed
|
||||||
|
|
||||||
|
## Intended uses & limitations
|
||||||
|
|
||||||
|
More information needed
|
||||||
|
|
||||||
|
## Training and evaluation data
|
||||||
|
|
||||||
|
More information needed
|
||||||
|
|
||||||
|
## Training procedure
|
||||||
|
|
||||||
|
### Training hyperparameters
|
||||||
|
|
||||||
|
The following hyperparameters were used during training:
|
||||||
|
- learning_rate: 1e-05
|
||||||
|
- train_batch_size: 2
|
||||||
|
- eval_batch_size: 8
|
||||||
|
- seed: 42
|
||||||
|
- distributed_type: multi-GPU
|
||||||
|
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
||||||
|
- lr_scheduler_type: cosine
|
||||||
|
- lr_scheduler_warmup_ratio: 0.01
|
||||||
|
- num_epochs: 5.0
|
||||||
|
|
||||||
|
### Training results
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
### Framework versions
|
||||||
|
|
||||||
|
- Transformers 4.52.4
|
||||||
|
- Pytorch 2.7.1+cu126
|
||||||
|
- Datasets 3.6.0
|
||||||
|
- Tokenizers 0.21.1
|
||||||
28
added_tokens.json
Normal file
28
added_tokens.json
Normal file
@@ -0,0 +1,28 @@
|
|||||||
|
{
|
||||||
|
"</think>": 151668,
|
||||||
|
"</tool_call>": 151658,
|
||||||
|
"</tool_response>": 151666,
|
||||||
|
"<think>": 151667,
|
||||||
|
"<tool_call>": 151657,
|
||||||
|
"<tool_response>": 151665,
|
||||||
|
"<|box_end|>": 151649,
|
||||||
|
"<|box_start|>": 151648,
|
||||||
|
"<|endoftext|>": 151643,
|
||||||
|
"<|file_sep|>": 151664,
|
||||||
|
"<|fim_middle|>": 151660,
|
||||||
|
"<|fim_pad|>": 151662,
|
||||||
|
"<|fim_prefix|>": 151659,
|
||||||
|
"<|fim_suffix|>": 151661,
|
||||||
|
"<|im_end|>": 151645,
|
||||||
|
"<|im_start|>": 151644,
|
||||||
|
"<|image_pad|>": 151655,
|
||||||
|
"<|object_ref_end|>": 151647,
|
||||||
|
"<|object_ref_start|>": 151646,
|
||||||
|
"<|quad_end|>": 151651,
|
||||||
|
"<|quad_start|>": 151650,
|
||||||
|
"<|repo_name|>": 151663,
|
||||||
|
"<|video_pad|>": 151656,
|
||||||
|
"<|vision_end|>": 151653,
|
||||||
|
"<|vision_pad|>": 151654,
|
||||||
|
"<|vision_start|>": 151652
|
||||||
|
}
|
||||||
8
all_results.json
Normal file
8
all_results.json
Normal file
@@ -0,0 +1,8 @@
|
|||||||
|
{
|
||||||
|
"epoch": 5.0,
|
||||||
|
"total_flos": 213154529280.0,
|
||||||
|
"train_loss": 0.7237587083663259,
|
||||||
|
"train_runtime": 212.7239,
|
||||||
|
"train_samples_per_second": 0.658,
|
||||||
|
"train_steps_per_second": 0.329
|
||||||
|
}
|
||||||
89
chat_template.jinja
Normal file
89
chat_template.jinja
Normal file
@@ -0,0 +1,89 @@
|
|||||||
|
{%- if tools %}
|
||||||
|
{{- '<|im_start|>system\n' }}
|
||||||
|
{%- if messages[0].role == 'system' %}
|
||||||
|
{{- messages[0].content + '\n\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{{- "# 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>" }}
|
||||||
|
{%- for tool in tools %}
|
||||||
|
{{- "\n" }}
|
||||||
|
{{- tool | tojson }}
|
||||||
|
{%- endfor %}
|
||||||
|
{{- "\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" }}
|
||||||
|
{%- else %}
|
||||||
|
{%- if messages[0].role == 'system' %}
|
||||||
|
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
||||||
|
{%- for message in messages[::-1] %}
|
||||||
|
{%- set index = (messages|length - 1) - loop.index0 %}
|
||||||
|
{%- 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>')) %}
|
||||||
|
{%- set ns.multi_step_tool = false %}
|
||||||
|
{%- set ns.last_query_index = index %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endfor %}
|
||||||
|
{%- for message in messages %}
|
||||||
|
{%- if message.content is string %}
|
||||||
|
{%- set content = message.content %}
|
||||||
|
{%- else %}
|
||||||
|
{%- set content = '' %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
||||||
|
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
||||||
|
{%- elif message.role == "assistant" %}
|
||||||
|
{%- set reasoning_content = '' %}
|
||||||
|
{%- if message.reasoning_content is string %}
|
||||||
|
{%- set reasoning_content = message.reasoning_content %}
|
||||||
|
{%- else %}
|
||||||
|
{%- if '</think>' in content %}
|
||||||
|
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
||||||
|
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if loop.index0 > ns.last_query_index %}
|
||||||
|
{%- if loop.last or (not loop.last and reasoning_content) %}
|
||||||
|
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
||||||
|
{%- else %}
|
||||||
|
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- else %}
|
||||||
|
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if message.tool_calls %}
|
||||||
|
{%- for tool_call in message.tool_calls %}
|
||||||
|
{%- if (loop.first and content) or (not loop.first) %}
|
||||||
|
{{- '\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if tool_call.function %}
|
||||||
|
{%- set tool_call = tool_call.function %}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '<tool_call>\n{"name": "' }}
|
||||||
|
{{- tool_call.name }}
|
||||||
|
{{- '", "arguments": ' }}
|
||||||
|
{%- if tool_call.arguments is string %}
|
||||||
|
{{- tool_call.arguments }}
|
||||||
|
{%- else %}
|
||||||
|
{{- tool_call.arguments | tojson }}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '}\n</tool_call>' }}
|
||||||
|
{%- endfor %}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '<|im_end|>\n' }}
|
||||||
|
{%- elif message.role == "tool" %}
|
||||||
|
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
||||||
|
{{- '<|im_start|>user' }}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '\n<tool_response>\n' }}
|
||||||
|
{{- content }}
|
||||||
|
{{- '\n</tool_response>' }}
|
||||||
|
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
||||||
|
{{- '<|im_end|>\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endfor %}
|
||||||
|
{%- if add_generation_prompt %}
|
||||||
|
{{- '<|im_start|>assistant\n' }}
|
||||||
|
{%- if enable_thinking is defined and enable_thinking is false %}
|
||||||
|
{{- '<think>\n\n</think>\n\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
30
config.json
Normal file
30
config.json
Normal file
@@ -0,0 +1,30 @@
|
|||||||
|
{
|
||||||
|
"architectures": [
|
||||||
|
"Qwen3ForCausalLM"
|
||||||
|
],
|
||||||
|
"attention_bias": false,
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"bos_token_id": 151643,
|
||||||
|
"eos_token_id": 151645,
|
||||||
|
"head_dim": 128,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 2048,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 6144,
|
||||||
|
"max_position_embeddings": 40960,
|
||||||
|
"max_window_layers": 28,
|
||||||
|
"model_type": "qwen3",
|
||||||
|
"num_attention_heads": 16,
|
||||||
|
"num_hidden_layers": 28,
|
||||||
|
"num_key_value_heads": 8,
|
||||||
|
"rms_norm_eps": 1e-06,
|
||||||
|
"rope_scaling": null,
|
||||||
|
"rope_theta": 1000000,
|
||||||
|
"sliding_window": null,
|
||||||
|
"tie_word_embeddings": true,
|
||||||
|
"torch_dtype": "bfloat16",
|
||||||
|
"transformers_version": "4.52.4",
|
||||||
|
"use_cache": false,
|
||||||
|
"use_sliding_window": false,
|
||||||
|
"vocab_size": 151936
|
||||||
|
}
|
||||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
|||||||
|
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||||
13
generation_config.json
Normal file
13
generation_config.json
Normal file
@@ -0,0 +1,13 @@
|
|||||||
|
{
|
||||||
|
"bos_token_id": 151643,
|
||||||
|
"do_sample": true,
|
||||||
|
"eos_token_id": [
|
||||||
|
151645,
|
||||||
|
151643
|
||||||
|
],
|
||||||
|
"pad_token_id": 151643,
|
||||||
|
"temperature": 0.6,
|
||||||
|
"top_k": 20,
|
||||||
|
"top_p": 0.95,
|
||||||
|
"transformers_version": "4.52.4"
|
||||||
|
}
|
||||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:f73f5615cff16de8773af41d01ea5b8bc12bdd51bf43961b26ff895d5d0f37eb
|
||||||
|
size 3441185608
|
||||||
31
special_tokens_map.json
Normal file
31
special_tokens_map.json
Normal file
@@ -0,0 +1,31 @@
|
|||||||
|
{
|
||||||
|
"additional_special_tokens": [
|
||||||
|
"<|im_start|>",
|
||||||
|
"<|im_end|>",
|
||||||
|
"<|object_ref_start|>",
|
||||||
|
"<|object_ref_end|>",
|
||||||
|
"<|box_start|>",
|
||||||
|
"<|box_end|>",
|
||||||
|
"<|quad_start|>",
|
||||||
|
"<|quad_end|>",
|
||||||
|
"<|vision_start|>",
|
||||||
|
"<|vision_end|>",
|
||||||
|
"<|vision_pad|>",
|
||||||
|
"<|image_pad|>",
|
||||||
|
"<|video_pad|>"
|
||||||
|
],
|
||||||
|
"eos_token": {
|
||||||
|
"content": "<|im_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"pad_token": {
|
||||||
|
"content": "<|endoftext|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
}
|
||||||
|
}
|
||||||
BIN
tokenizer.json
(Stored with Git LFS)
Normal file
BIN
tokenizer.json
(Stored with Git LFS)
Normal file
Binary file not shown.
240
tokenizer_config.json
Normal file
240
tokenizer_config.json
Normal file
@@ -0,0 +1,240 @@
|
|||||||
|
{
|
||||||
|
"add_bos_token": false,
|
||||||
|
"add_prefix_space": false,
|
||||||
|
"added_tokens_decoder": {
|
||||||
|
"151643": {
|
||||||
|
"content": "<|endoftext|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151644": {
|
||||||
|
"content": "<|im_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151645": {
|
||||||
|
"content": "<|im_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151646": {
|
||||||
|
"content": "<|object_ref_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151647": {
|
||||||
|
"content": "<|object_ref_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151648": {
|
||||||
|
"content": "<|box_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151649": {
|
||||||
|
"content": "<|box_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151650": {
|
||||||
|
"content": "<|quad_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151651": {
|
||||||
|
"content": "<|quad_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151652": {
|
||||||
|
"content": "<|vision_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151653": {
|
||||||
|
"content": "<|vision_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151654": {
|
||||||
|
"content": "<|vision_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151655": {
|
||||||
|
"content": "<|image_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151656": {
|
||||||
|
"content": "<|video_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151657": {
|
||||||
|
"content": "<tool_call>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151658": {
|
||||||
|
"content": "</tool_call>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151659": {
|
||||||
|
"content": "<|fim_prefix|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151660": {
|
||||||
|
"content": "<|fim_middle|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151661": {
|
||||||
|
"content": "<|fim_suffix|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151662": {
|
||||||
|
"content": "<|fim_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151663": {
|
||||||
|
"content": "<|repo_name|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151664": {
|
||||||
|
"content": "<|file_sep|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151665": {
|
||||||
|
"content": "<tool_response>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151666": {
|
||||||
|
"content": "</tool_response>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151667": {
|
||||||
|
"content": "<think>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151668": {
|
||||||
|
"content": "</think>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"additional_special_tokens": [
|
||||||
|
"<|im_start|>",
|
||||||
|
"<|im_end|>",
|
||||||
|
"<|object_ref_start|>",
|
||||||
|
"<|object_ref_end|>",
|
||||||
|
"<|box_start|>",
|
||||||
|
"<|box_end|>",
|
||||||
|
"<|quad_start|>",
|
||||||
|
"<|quad_end|>",
|
||||||
|
"<|vision_start|>",
|
||||||
|
"<|vision_end|>",
|
||||||
|
"<|vision_pad|>",
|
||||||
|
"<|image_pad|>",
|
||||||
|
"<|video_pad|>"
|
||||||
|
],
|
||||||
|
"bos_token": null,
|
||||||
|
"clean_up_tokenization_spaces": false,
|
||||||
|
"eos_token": "<|im_end|>",
|
||||||
|
"errors": "replace",
|
||||||
|
"extra_special_tokens": {},
|
||||||
|
"model_max_length": 131072,
|
||||||
|
"pad_token": "<|endoftext|>",
|
||||||
|
"padding_side": "right",
|
||||||
|
"split_special_tokens": false,
|
||||||
|
"tokenizer_class": "Qwen2Tokenizer",
|
||||||
|
"unk_token": null
|
||||||
|
}
|
||||||
8
train_results.json
Normal file
8
train_results.json
Normal file
@@ -0,0 +1,8 @@
|
|||||||
|
{
|
||||||
|
"epoch": 5.0,
|
||||||
|
"total_flos": 213154529280.0,
|
||||||
|
"train_loss": 0.7237587083663259,
|
||||||
|
"train_runtime": 212.7239,
|
||||||
|
"train_samples_per_second": 0.658,
|
||||||
|
"train_steps_per_second": 0.329
|
||||||
|
}
|
||||||
71
trainer_log.jsonl
Normal file
71
trainer_log.jsonl
Normal file
@@ -0,0 +1,71 @@
|
|||||||
|
{"current_steps": 1, "total_steps": 70, "loss": 1.9336, "lr": 0.0, "epoch": 0.07142857142857142, "percentage": 1.43, "elapsed_time": "0:00:02", "remaining_time": "0:03:08"}
|
||||||
|
{"current_steps": 2, "total_steps": 70, "loss": 1.4638, "lr": 1e-05, "epoch": 0.14285714285714285, "percentage": 2.86, "elapsed_time": "0:00:05", "remaining_time": "0:02:54"}
|
||||||
|
{"current_steps": 3, "total_steps": 70, "loss": 1.3641, "lr": 9.994818368233639e-06, "epoch": 0.21428571428571427, "percentage": 4.29, "elapsed_time": "0:00:05", "remaining_time": "0:02:11"}
|
||||||
|
{"current_steps": 4, "total_steps": 70, "loss": 1.6788, "lr": 9.979284212657658e-06, "epoch": 0.2857142857142857, "percentage": 5.71, "elapsed_time": "0:00:06", "remaining_time": "0:01:49"}
|
||||||
|
{"current_steps": 5, "total_steps": 70, "loss": 1.471, "lr": 9.953429730181653e-06, "epoch": 0.35714285714285715, "percentage": 7.14, "elapsed_time": "0:00:07", "remaining_time": "0:01:36"}
|
||||||
|
{"current_steps": 6, "total_steps": 70, "loss": 1.535, "lr": 9.917308508168712e-06, "epoch": 0.42857142857142855, "percentage": 8.57, "elapsed_time": "0:00:08", "remaining_time": "0:01:26"}
|
||||||
|
{"current_steps": 7, "total_steps": 70, "loss": 1.0182, "lr": 9.870995413367397e-06, "epoch": 0.5, "percentage": 10.0, "elapsed_time": "0:00:08", "remaining_time": "0:01:20"}
|
||||||
|
{"current_steps": 8, "total_steps": 70, "loss": 1.2797, "lr": 9.814586436738998e-06, "epoch": 0.5714285714285714, "percentage": 11.43, "elapsed_time": "0:00:09", "remaining_time": "0:01:14"}
|
||||||
|
{"current_steps": 9, "total_steps": 70, "loss": 1.1114, "lr": 9.748198494501598e-06, "epoch": 0.6428571428571429, "percentage": 12.86, "elapsed_time": "0:00:10", "remaining_time": "0:01:10"}
|
||||||
|
{"current_steps": 10, "total_steps": 70, "loss": 1.1423, "lr": 9.671969185803357e-06, "epoch": 0.7142857142857143, "percentage": 14.29, "elapsed_time": "0:00:11", "remaining_time": "0:01:07"}
|
||||||
|
{"current_steps": 11, "total_steps": 70, "loss": 1.1309, "lr": 9.586056507527266e-06, "epoch": 0.7857142857142857, "percentage": 15.71, "elapsed_time": "0:00:11", "remaining_time": "0:01:03"}
|
||||||
|
{"current_steps": 12, "total_steps": 70, "loss": 1.3257, "lr": 9.490638526818482e-06, "epoch": 0.8571428571428571, "percentage": 17.14, "elapsed_time": "0:00:12", "remaining_time": "0:01:01"}
|
||||||
|
{"current_steps": 13, "total_steps": 70, "loss": 1.1885, "lr": 9.385913012012972e-06, "epoch": 0.9285714285714286, "percentage": 18.57, "elapsed_time": "0:00:13", "remaining_time": "0:00:58"}
|
||||||
|
{"current_steps": 14, "total_steps": 70, "loss": 1.2715, "lr": 9.272097022732444e-06, "epoch": 1.0, "percentage": 20.0, "elapsed_time": "0:00:14", "remaining_time": "0:00:57"}
|
||||||
|
{"current_steps": 15, "total_steps": 70, "loss": 1.2302, "lr": 9.149426459995127e-06, "epoch": 1.0714285714285714, "percentage": 21.43, "elapsed_time": "0:00:16", "remaining_time": "0:01:00"}
|
||||||
|
{"current_steps": 16, "total_steps": 70, "loss": 1.02, "lr": 9.018155577274891e-06, "epoch": 1.1428571428571428, "percentage": 22.86, "elapsed_time": "0:00:17", "remaining_time": "0:00:58"}
|
||||||
|
{"current_steps": 17, "total_steps": 70, "loss": 1.0235, "lr": 8.8785564535221e-06, "epoch": 1.2142857142857142, "percentage": 24.29, "elapsed_time": "0:00:18", "remaining_time": "0:00:56"}
|
||||||
|
{"current_steps": 18, "total_steps": 70, "loss": 0.9651, "lr": 8.730918429238429e-06, "epoch": 1.2857142857142856, "percentage": 25.71, "elapsed_time": "0:00:18", "remaining_time": "0:00:54"}
|
||||||
|
{"current_steps": 19, "total_steps": 70, "loss": 0.995, "lr": 8.575547506774498e-06, "epoch": 1.3571428571428572, "percentage": 27.14, "elapsed_time": "0:00:19", "remaining_time": "0:00:52"}
|
||||||
|
{"current_steps": 20, "total_steps": 70, "loss": 0.9102, "lr": 8.412765716093273e-06, "epoch": 1.4285714285714286, "percentage": 28.57, "elapsed_time": "0:00:20", "remaining_time": "0:00:50"}
|
||||||
|
{"current_steps": 21, "total_steps": 70, "loss": 0.8329, "lr": 8.24291044731378e-06, "epoch": 1.5, "percentage": 30.0, "elapsed_time": "0:00:21", "remaining_time": "0:00:49"}
|
||||||
|
{"current_steps": 22, "total_steps": 70, "loss": 0.795, "lr": 8.066333751418582e-06, "epoch": 1.5714285714285714, "percentage": 31.43, "elapsed_time": "0:00:21", "remaining_time": "0:00:47"}
|
||||||
|
{"current_steps": 23, "total_steps": 70, "loss": 0.8774, "lr": 7.883401610574338e-06, "epoch": 1.6428571428571428, "percentage": 32.86, "elapsed_time": "0:00:22", "remaining_time": "0:00:46"}
|
||||||
|
{"current_steps": 24, "total_steps": 70, "loss": 0.5987, "lr": 7.69449317957788e-06, "epoch": 1.7142857142857144, "percentage": 34.29, "elapsed_time": "0:00:23", "remaining_time": "0:00:44"}
|
||||||
|
{"current_steps": 25, "total_steps": 70, "loss": 0.678, "lr": 7.500000000000001e-06, "epoch": 1.7857142857142856, "percentage": 35.71, "elapsed_time": "0:00:24", "remaining_time": "0:00:43"}
|
||||||
|
{"current_steps": 26, "total_steps": 70, "loss": 0.8991, "lr": 7.300325188655762e-06, "epoch": 1.8571428571428572, "percentage": 37.14, "elapsed_time": "0:00:24", "remaining_time": "0:00:41"}
|
||||||
|
{"current_steps": 27, "total_steps": 70, "loss": 0.802, "lr": 7.095882602083321e-06, "epoch": 1.9285714285714286, "percentage": 38.57, "elapsed_time": "0:00:25", "remaining_time": "0:00:40"}
|
||||||
|
{"current_steps": 28, "total_steps": 70, "loss": 0.7479, "lr": 6.887095978763072e-06, "epoch": 2.0, "percentage": 40.0, "elapsed_time": "0:00:26", "remaining_time": "0:00:39"}
|
||||||
|
{"current_steps": 29, "total_steps": 70, "loss": 0.7145, "lr": 6.674398060854931e-06, "epoch": 2.0714285714285716, "percentage": 41.43, "elapsed_time": "0:00:28", "remaining_time": "0:00:40"}
|
||||||
|
{"current_steps": 30, "total_steps": 70, "loss": 0.6478, "lr": 6.458229697274125e-06, "epoch": 2.142857142857143, "percentage": 42.86, "elapsed_time": "0:00:29", "remaining_time": "0:00:39"}
|
||||||
|
{"current_steps": 31, "total_steps": 70, "loss": 0.7132, "lr": 6.2390389299645e-06, "epoch": 2.2142857142857144, "percentage": 44.29, "elapsed_time": "0:00:30", "remaining_time": "0:00:37"}
|
||||||
|
{"current_steps": 32, "total_steps": 70, "loss": 0.5269, "lr": 6.0172800652631706e-06, "epoch": 2.2857142857142856, "percentage": 45.71, "elapsed_time": "0:00:30", "remaining_time": "0:00:36"}
|
||||||
|
{"current_steps": 33, "total_steps": 70, "loss": 0.6023, "lr": 5.793412732281258e-06, "epoch": 2.357142857142857, "percentage": 47.14, "elapsed_time": "0:00:31", "remaining_time": "0:00:35"}
|
||||||
|
{"current_steps": 34, "total_steps": 70, "loss": 0.4804, "lr": 5.567900930252375e-06, "epoch": 2.4285714285714284, "percentage": 48.57, "elapsed_time": "0:00:32", "remaining_time": "0:00:34"}
|
||||||
|
{"current_steps": 35, "total_steps": 70, "loss": 0.3588, "lr": 5.341212066823356e-06, "epoch": 2.5, "percentage": 50.0, "elapsed_time": "0:00:33", "remaining_time": "0:00:33"}
|
||||||
|
{"current_steps": 36, "total_steps": 70, "loss": 0.5365, "lr": 5.113815989280528e-06, "epoch": 2.571428571428571, "percentage": 51.43, "elapsed_time": "0:00:33", "remaining_time": "0:00:32"}
|
||||||
|
{"current_steps": 37, "total_steps": 70, "loss": 0.7041, "lr": 4.886184010719472e-06, "epoch": 2.642857142857143, "percentage": 52.86, "elapsed_time": "0:00:34", "remaining_time": "0:00:30"}
|
||||||
|
{"current_steps": 38, "total_steps": 70, "loss": 0.6861, "lr": 4.6587879331766465e-06, "epoch": 2.7142857142857144, "percentage": 54.29, "elapsed_time": "0:00:35", "remaining_time": "0:00:29"}
|
||||||
|
{"current_steps": 39, "total_steps": 70, "loss": 0.538, "lr": 4.432099069747625e-06, "epoch": 2.7857142857142856, "percentage": 55.71, "elapsed_time": "0:00:36", "remaining_time": "0:00:28"}
|
||||||
|
{"current_steps": 40, "total_steps": 70, "loss": 0.6443, "lr": 4.206587267718743e-06, "epoch": 2.857142857142857, "percentage": 57.14, "elapsed_time": "0:00:36", "remaining_time": "0:00:27"}
|
||||||
|
{"current_steps": 41, "total_steps": 70, "loss": 0.461, "lr": 3.982719934736832e-06, "epoch": 2.928571428571429, "percentage": 58.57, "elapsed_time": "0:00:37", "remaining_time": "0:00:26"}
|
||||||
|
{"current_steps": 42, "total_steps": 70, "loss": 0.6665, "lr": 3.7609610700355014e-06, "epoch": 3.0, "percentage": 60.0, "elapsed_time": "0:00:38", "remaining_time": "0:00:25"}
|
||||||
|
{"current_steps": 43, "total_steps": 70, "loss": 0.4645, "lr": 3.5417703027258752e-06, "epoch": 3.0714285714285716, "percentage": 61.43, "elapsed_time": "0:02:13", "remaining_time": "0:01:23"}
|
||||||
|
{"current_steps": 44, "total_steps": 70, "loss": 0.3431, "lr": 3.3256019391450696e-06, "epoch": 3.142857142857143, "percentage": 62.86, "elapsed_time": "0:02:14", "remaining_time": "0:01:19"}
|
||||||
|
{"current_steps": 45, "total_steps": 70, "loss": 0.5799, "lr": 3.1129040212369286e-06, "epoch": 3.2142857142857144, "percentage": 64.29, "elapsed_time": "0:02:15", "remaining_time": "0:01:15"}
|
||||||
|
{"current_steps": 46, "total_steps": 70, "loss": 0.5118, "lr": 2.9041173979166813e-06, "epoch": 3.2857142857142856, "percentage": 65.71, "elapsed_time": "0:02:15", "remaining_time": "0:01:10"}
|
||||||
|
{"current_steps": 47, "total_steps": 70, "loss": 0.4746, "lr": 2.6996748113442397e-06, "epoch": 3.357142857142857, "percentage": 67.14, "elapsed_time": "0:02:16", "remaining_time": "0:01:06"}
|
||||||
|
{"current_steps": 48, "total_steps": 70, "loss": 0.4415, "lr": 2.5000000000000015e-06, "epoch": 3.4285714285714284, "percentage": 68.57, "elapsed_time": "0:02:17", "remaining_time": "0:01:02"}
|
||||||
|
{"current_steps": 49, "total_steps": 70, "loss": 0.3722, "lr": 2.3055068204221226e-06, "epoch": 3.5, "percentage": 70.0, "elapsed_time": "0:02:18", "remaining_time": "0:00:59"}
|
||||||
|
{"current_steps": 50, "total_steps": 70, "loss": 0.5201, "lr": 2.1165983894256647e-06, "epoch": 3.571428571428571, "percentage": 71.43, "elapsed_time": "0:02:18", "remaining_time": "0:00:55"}
|
||||||
|
{"current_steps": 51, "total_steps": 70, "loss": 0.3054, "lr": 1.933666248581418e-06, "epoch": 3.642857142857143, "percentage": 72.86, "elapsed_time": "0:02:19", "remaining_time": "0:00:52"}
|
||||||
|
{"current_steps": 52, "total_steps": 70, "loss": 0.4316, "lr": 1.7570895526862202e-06, "epoch": 3.7142857142857144, "percentage": 74.29, "elapsed_time": "0:02:20", "remaining_time": "0:00:48"}
|
||||||
|
{"current_steps": 53, "total_steps": 70, "loss": 0.3126, "lr": 1.5872342839067305e-06, "epoch": 3.7857142857142856, "percentage": 75.71, "elapsed_time": "0:02:21", "remaining_time": "0:00:45"}
|
||||||
|
{"current_steps": 54, "total_steps": 70, "loss": 0.5713, "lr": 1.4244524932255026e-06, "epoch": 3.857142857142857, "percentage": 77.14, "elapsed_time": "0:02:21", "remaining_time": "0:00:42"}
|
||||||
|
{"current_steps": 55, "total_steps": 70, "loss": 0.2574, "lr": 1.2690815707615727e-06, "epoch": 3.928571428571429, "percentage": 78.57, "elapsed_time": "0:02:22", "remaining_time": "0:00:38"}
|
||||||
|
{"current_steps": 56, "total_steps": 70, "loss": 0.4133, "lr": 1.1214435464779006e-06, "epoch": 4.0, "percentage": 80.0, "elapsed_time": "0:02:23", "remaining_time": "0:00:35"}
|
||||||
|
{"current_steps": 57, "total_steps": 70, "loss": 0.334, "lr": 9.81844422725109e-07, "epoch": 4.071428571428571, "percentage": 81.43, "elapsed_time": "0:02:27", "remaining_time": "0:00:33"}
|
||||||
|
{"current_steps": 58, "total_steps": 70, "loss": 0.4336, "lr": 8.505735400048748e-07, "epoch": 4.142857142857143, "percentage": 82.86, "elapsed_time": "0:02:28", "remaining_time": "0:00:30"}
|
||||||
|
{"current_steps": 59, "total_steps": 70, "loss": 0.3091, "lr": 7.279029772675572e-07, "epoch": 4.214285714285714, "percentage": 84.29, "elapsed_time": "0:02:28", "remaining_time": "0:00:27"}
|
||||||
|
{"current_steps": 60, "total_steps": 70, "loss": 0.2855, "lr": 6.140869879870287e-07, "epoch": 4.285714285714286, "percentage": 85.71, "elapsed_time": "0:02:29", "remaining_time": "0:00:24"}
|
||||||
|
{"current_steps": 61, "total_steps": 70, "loss": 0.352, "lr": 5.0936147318152e-07, "epoch": 4.357142857142857, "percentage": 87.14, "elapsed_time": "0:02:30", "remaining_time": "0:00:22"}
|
||||||
|
{"current_steps": 62, "total_steps": 70, "loss": 0.4831, "lr": 4.139434924727359e-07, "epoch": 4.428571428571429, "percentage": 88.57, "elapsed_time": "0:02:31", "remaining_time": "0:00:19"}
|
||||||
|
{"current_steps": 63, "total_steps": 70, "loss": 0.2978, "lr": 3.2803081419664483e-07, "epoch": 4.5, "percentage": 90.0, "elapsed_time": "0:02:32", "remaining_time": "0:00:16"}
|
||||||
|
{"current_steps": 64, "total_steps": 70, "loss": 0.2341, "lr": 2.518015054984041e-07, "epoch": 4.571428571428571, "percentage": 91.43, "elapsed_time": "0:02:32", "remaining_time": "0:00:14"}
|
||||||
|
{"current_steps": 65, "total_steps": 70, "loss": 0.421, "lr": 1.8541356326100436e-07, "epoch": 4.642857142857143, "percentage": 92.86, "elapsed_time": "0:02:33", "remaining_time": "0:00:11"}
|
||||||
|
{"current_steps": 66, "total_steps": 70, "loss": 0.4509, "lr": 1.2900458663260506e-07, "epoch": 4.714285714285714, "percentage": 94.29, "elapsed_time": "0:02:34", "remaining_time": "0:00:09"}
|
||||||
|
{"current_steps": 67, "total_steps": 70, "loss": 0.3925, "lr": 8.269149183128988e-08, "epoch": 4.785714285714286, "percentage": 95.71, "elapsed_time": "0:02:35", "remaining_time": "0:00:06"}
|
||||||
|
{"current_steps": 68, "total_steps": 70, "loss": 0.408, "lr": 4.657026981834623e-08, "epoch": 4.857142857142857, "percentage": 97.14, "elapsed_time": "0:02:35", "remaining_time": "0:00:04"}
|
||||||
|
{"current_steps": 69, "total_steps": 70, "loss": 0.3737, "lr": 2.0715787342343586e-08, "epoch": 4.928571428571429, "percentage": 98.57, "elapsed_time": "0:02:36", "remaining_time": "0:00:02"}
|
||||||
|
{"current_steps": 70, "total_steps": 70, "loss": 0.3182, "lr": 5.181631766362216e-09, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "0:02:37", "remaining_time": "0:00:00"}
|
||||||
|
{"current_steps": 70, "total_steps": 70, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "0:03:30", "remaining_time": "0:00:00"}
|
||||||
533
trainer_state.json
Normal file
533
trainer_state.json
Normal file
@@ -0,0 +1,533 @@
|
|||||||
|
{
|
||||||
|
"best_global_step": null,
|
||||||
|
"best_metric": null,
|
||||||
|
"best_model_checkpoint": null,
|
||||||
|
"epoch": 5.0,
|
||||||
|
"eval_steps": 500,
|
||||||
|
"global_step": 70,
|
||||||
|
"is_hyper_param_search": false,
|
||||||
|
"is_local_process_zero": true,
|
||||||
|
"is_world_process_zero": true,
|
||||||
|
"log_history": [
|
||||||
|
{
|
||||||
|
"epoch": 0.07142857142857142,
|
||||||
|
"grad_norm": 24.023632843584195,
|
||||||
|
"learning_rate": 0.0,
|
||||||
|
"loss": 1.9336,
|
||||||
|
"step": 1
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.14285714285714285,
|
||||||
|
"grad_norm": 25.27216550339971,
|
||||||
|
"learning_rate": 1e-05,
|
||||||
|
"loss": 1.4638,
|
||||||
|
"step": 2
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.21428571428571427,
|
||||||
|
"grad_norm": 13.768008441403769,
|
||||||
|
"learning_rate": 9.994818368233639e-06,
|
||||||
|
"loss": 1.3641,
|
||||||
|
"step": 3
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.2857142857142857,
|
||||||
|
"grad_norm": 9.119394933221514,
|
||||||
|
"learning_rate": 9.979284212657658e-06,
|
||||||
|
"loss": 1.6788,
|
||||||
|
"step": 4
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.35714285714285715,
|
||||||
|
"grad_norm": 8.29180049726504,
|
||||||
|
"learning_rate": 9.953429730181653e-06,
|
||||||
|
"loss": 1.471,
|
||||||
|
"step": 5
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.42857142857142855,
|
||||||
|
"grad_norm": 6.6755630111422075,
|
||||||
|
"learning_rate": 9.917308508168712e-06,
|
||||||
|
"loss": 1.535,
|
||||||
|
"step": 6
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5,
|
||||||
|
"grad_norm": 5.927824954855512,
|
||||||
|
"learning_rate": 9.870995413367397e-06,
|
||||||
|
"loss": 1.0182,
|
||||||
|
"step": 7
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5714285714285714,
|
||||||
|
"grad_norm": 5.290712655595048,
|
||||||
|
"learning_rate": 9.814586436738998e-06,
|
||||||
|
"loss": 1.2797,
|
||||||
|
"step": 8
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6428571428571429,
|
||||||
|
"grad_norm": 4.450390639155862,
|
||||||
|
"learning_rate": 9.748198494501598e-06,
|
||||||
|
"loss": 1.1114,
|
||||||
|
"step": 9
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7142857142857143,
|
||||||
|
"grad_norm": 5.552257885415831,
|
||||||
|
"learning_rate": 9.671969185803357e-06,
|
||||||
|
"loss": 1.1423,
|
||||||
|
"step": 10
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7857142857142857,
|
||||||
|
"grad_norm": 5.335273326587211,
|
||||||
|
"learning_rate": 9.586056507527266e-06,
|
||||||
|
"loss": 1.1309,
|
||||||
|
"step": 11
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8571428571428571,
|
||||||
|
"grad_norm": 5.055921586049105,
|
||||||
|
"learning_rate": 9.490638526818482e-06,
|
||||||
|
"loss": 1.3257,
|
||||||
|
"step": 12
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9285714285714286,
|
||||||
|
"grad_norm": 4.759961808264356,
|
||||||
|
"learning_rate": 9.385913012012972e-06,
|
||||||
|
"loss": 1.1885,
|
||||||
|
"step": 13
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.0,
|
||||||
|
"grad_norm": 4.871340975018161,
|
||||||
|
"learning_rate": 9.272097022732444e-06,
|
||||||
|
"loss": 1.2715,
|
||||||
|
"step": 14
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.0714285714285714,
|
||||||
|
"grad_norm": 4.436955356609461,
|
||||||
|
"learning_rate": 9.149426459995127e-06,
|
||||||
|
"loss": 1.2302,
|
||||||
|
"step": 15
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.1428571428571428,
|
||||||
|
"grad_norm": 4.28052498090576,
|
||||||
|
"learning_rate": 9.018155577274891e-06,
|
||||||
|
"loss": 1.02,
|
||||||
|
"step": 16
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.2142857142857142,
|
||||||
|
"grad_norm": 5.067070847952673,
|
||||||
|
"learning_rate": 8.8785564535221e-06,
|
||||||
|
"loss": 1.0235,
|
||||||
|
"step": 17
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.2857142857142856,
|
||||||
|
"grad_norm": 4.087626184275003,
|
||||||
|
"learning_rate": 8.730918429238429e-06,
|
||||||
|
"loss": 0.9651,
|
||||||
|
"step": 18
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.3571428571428572,
|
||||||
|
"grad_norm": 4.301072973315502,
|
||||||
|
"learning_rate": 8.575547506774498e-06,
|
||||||
|
"loss": 0.995,
|
||||||
|
"step": 19
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.4285714285714286,
|
||||||
|
"grad_norm": 4.063688761012534,
|
||||||
|
"learning_rate": 8.412765716093273e-06,
|
||||||
|
"loss": 0.9102,
|
||||||
|
"step": 20
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.5,
|
||||||
|
"grad_norm": 4.646743739276943,
|
||||||
|
"learning_rate": 8.24291044731378e-06,
|
||||||
|
"loss": 0.8329,
|
||||||
|
"step": 21
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.5714285714285714,
|
||||||
|
"grad_norm": 3.845579762800239,
|
||||||
|
"learning_rate": 8.066333751418582e-06,
|
||||||
|
"loss": 0.795,
|
||||||
|
"step": 22
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.6428571428571428,
|
||||||
|
"grad_norm": 4.130688938229113,
|
||||||
|
"learning_rate": 7.883401610574338e-06,
|
||||||
|
"loss": 0.8774,
|
||||||
|
"step": 23
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.7142857142857144,
|
||||||
|
"grad_norm": 4.444662774507303,
|
||||||
|
"learning_rate": 7.69449317957788e-06,
|
||||||
|
"loss": 0.5987,
|
||||||
|
"step": 24
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.7857142857142856,
|
||||||
|
"grad_norm": 5.247198746213424,
|
||||||
|
"learning_rate": 7.500000000000001e-06,
|
||||||
|
"loss": 0.678,
|
||||||
|
"step": 25
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.8571428571428572,
|
||||||
|
"grad_norm": 4.633300703755712,
|
||||||
|
"learning_rate": 7.300325188655762e-06,
|
||||||
|
"loss": 0.8991,
|
||||||
|
"step": 26
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.9285714285714286,
|
||||||
|
"grad_norm": 4.341489445734741,
|
||||||
|
"learning_rate": 7.095882602083321e-06,
|
||||||
|
"loss": 0.802,
|
||||||
|
"step": 27
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.0,
|
||||||
|
"grad_norm": 3.890840356813419,
|
||||||
|
"learning_rate": 6.887095978763072e-06,
|
||||||
|
"loss": 0.7479,
|
||||||
|
"step": 28
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.0714285714285716,
|
||||||
|
"grad_norm": 3.953138214805454,
|
||||||
|
"learning_rate": 6.674398060854931e-06,
|
||||||
|
"loss": 0.7145,
|
||||||
|
"step": 29
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.142857142857143,
|
||||||
|
"grad_norm": 4.246093007674121,
|
||||||
|
"learning_rate": 6.458229697274125e-06,
|
||||||
|
"loss": 0.6478,
|
||||||
|
"step": 30
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.2142857142857144,
|
||||||
|
"grad_norm": 4.235637857831103,
|
||||||
|
"learning_rate": 6.2390389299645e-06,
|
||||||
|
"loss": 0.7132,
|
||||||
|
"step": 31
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.2857142857142856,
|
||||||
|
"grad_norm": 3.795047115132234,
|
||||||
|
"learning_rate": 6.0172800652631706e-06,
|
||||||
|
"loss": 0.5269,
|
||||||
|
"step": 32
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.357142857142857,
|
||||||
|
"grad_norm": 3.708500518296535,
|
||||||
|
"learning_rate": 5.793412732281258e-06,
|
||||||
|
"loss": 0.6023,
|
||||||
|
"step": 33
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.4285714285714284,
|
||||||
|
"grad_norm": 3.3778342286451735,
|
||||||
|
"learning_rate": 5.567900930252375e-06,
|
||||||
|
"loss": 0.4804,
|
||||||
|
"step": 34
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.5,
|
||||||
|
"grad_norm": 3.2763514955628454,
|
||||||
|
"learning_rate": 5.341212066823356e-06,
|
||||||
|
"loss": 0.3588,
|
||||||
|
"step": 35
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.571428571428571,
|
||||||
|
"grad_norm": 3.809622648646623,
|
||||||
|
"learning_rate": 5.113815989280528e-06,
|
||||||
|
"loss": 0.5365,
|
||||||
|
"step": 36
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.642857142857143,
|
||||||
|
"grad_norm": 4.905824079180291,
|
||||||
|
"learning_rate": 4.886184010719472e-06,
|
||||||
|
"loss": 0.7041,
|
||||||
|
"step": 37
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.7142857142857144,
|
||||||
|
"grad_norm": 4.331352426673357,
|
||||||
|
"learning_rate": 4.6587879331766465e-06,
|
||||||
|
"loss": 0.6861,
|
||||||
|
"step": 38
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.7857142857142856,
|
||||||
|
"grad_norm": 4.268031298589448,
|
||||||
|
"learning_rate": 4.432099069747625e-06,
|
||||||
|
"loss": 0.538,
|
||||||
|
"step": 39
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.857142857142857,
|
||||||
|
"grad_norm": 4.506172331148789,
|
||||||
|
"learning_rate": 4.206587267718743e-06,
|
||||||
|
"loss": 0.6443,
|
||||||
|
"step": 40
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.928571428571429,
|
||||||
|
"grad_norm": 3.9399153380545116,
|
||||||
|
"learning_rate": 3.982719934736832e-06,
|
||||||
|
"loss": 0.461,
|
||||||
|
"step": 41
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 3.0,
|
||||||
|
"grad_norm": 4.553905357043457,
|
||||||
|
"learning_rate": 3.7609610700355014e-06,
|
||||||
|
"loss": 0.6665,
|
||||||
|
"step": 42
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 3.0714285714285716,
|
||||||
|
"grad_norm": 3.4967459109023253,
|
||||||
|
"learning_rate": 3.5417703027258752e-06,
|
||||||
|
"loss": 0.4645,
|
||||||
|
"step": 43
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 3.142857142857143,
|
||||||
|
"grad_norm": 3.460264221490188,
|
||||||
|
"learning_rate": 3.3256019391450696e-06,
|
||||||
|
"loss": 0.3431,
|
||||||
|
"step": 44
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 3.2142857142857144,
|
||||||
|
"grad_norm": 3.8276195456268285,
|
||||||
|
"learning_rate": 3.1129040212369286e-06,
|
||||||
|
"loss": 0.5799,
|
||||||
|
"step": 45
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 3.2857142857142856,
|
||||||
|
"grad_norm": 4.281258985773756,
|
||||||
|
"learning_rate": 2.9041173979166813e-06,
|
||||||
|
"loss": 0.5118,
|
||||||
|
"step": 46
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 3.357142857142857,
|
||||||
|
"grad_norm": 4.006912491344759,
|
||||||
|
"learning_rate": 2.6996748113442397e-06,
|
||||||
|
"loss": 0.4746,
|
||||||
|
"step": 47
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 3.4285714285714284,
|
||||||
|
"grad_norm": 3.7962255242435337,
|
||||||
|
"learning_rate": 2.5000000000000015e-06,
|
||||||
|
"loss": 0.4415,
|
||||||
|
"step": 48
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 3.5,
|
||||||
|
"grad_norm": 3.93529721260128,
|
||||||
|
"learning_rate": 2.3055068204221226e-06,
|
||||||
|
"loss": 0.3722,
|
||||||
|
"step": 49
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 3.571428571428571,
|
||||||
|
"grad_norm": 4.201031566755138,
|
||||||
|
"learning_rate": 2.1165983894256647e-06,
|
||||||
|
"loss": 0.5201,
|
||||||
|
"step": 50
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 3.642857142857143,
|
||||||
|
"grad_norm": 3.8906161720286927,
|
||||||
|
"learning_rate": 1.933666248581418e-06,
|
||||||
|
"loss": 0.3054,
|
||||||
|
"step": 51
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 3.7142857142857144,
|
||||||
|
"grad_norm": 4.02310526884226,
|
||||||
|
"learning_rate": 1.7570895526862202e-06,
|
||||||
|
"loss": 0.4316,
|
||||||
|
"step": 52
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 3.7857142857142856,
|
||||||
|
"grad_norm": 3.3963029194169048,
|
||||||
|
"learning_rate": 1.5872342839067305e-06,
|
||||||
|
"loss": 0.3126,
|
||||||
|
"step": 53
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 3.857142857142857,
|
||||||
|
"grad_norm": 4.3730733787425144,
|
||||||
|
"learning_rate": 1.4244524932255026e-06,
|
||||||
|
"loss": 0.5713,
|
||||||
|
"step": 54
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 3.928571428571429,
|
||||||
|
"grad_norm": 3.353702364092209,
|
||||||
|
"learning_rate": 1.2690815707615727e-06,
|
||||||
|
"loss": 0.2574,
|
||||||
|
"step": 55
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 4.0,
|
||||||
|
"grad_norm": 4.659106009637382,
|
||||||
|
"learning_rate": 1.1214435464779006e-06,
|
||||||
|
"loss": 0.4133,
|
||||||
|
"step": 56
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 4.071428571428571,
|
||||||
|
"grad_norm": 3.868760155163949,
|
||||||
|
"learning_rate": 9.81844422725109e-07,
|
||||||
|
"loss": 0.334,
|
||||||
|
"step": 57
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 4.142857142857143,
|
||||||
|
"grad_norm": 3.51726363976578,
|
||||||
|
"learning_rate": 8.505735400048748e-07,
|
||||||
|
"loss": 0.4336,
|
||||||
|
"step": 58
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 4.214285714285714,
|
||||||
|
"grad_norm": 3.4559508001260046,
|
||||||
|
"learning_rate": 7.279029772675572e-07,
|
||||||
|
"loss": 0.3091,
|
||||||
|
"step": 59
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 4.285714285714286,
|
||||||
|
"grad_norm": 3.4232071286039503,
|
||||||
|
"learning_rate": 6.140869879870287e-07,
|
||||||
|
"loss": 0.2855,
|
||||||
|
"step": 60
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 4.357142857142857,
|
||||||
|
"grad_norm": 3.8024404087360923,
|
||||||
|
"learning_rate": 5.0936147318152e-07,
|
||||||
|
"loss": 0.352,
|
||||||
|
"step": 61
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 4.428571428571429,
|
||||||
|
"grad_norm": 4.019294133630708,
|
||||||
|
"learning_rate": 4.139434924727359e-07,
|
||||||
|
"loss": 0.4831,
|
||||||
|
"step": 62
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 4.5,
|
||||||
|
"grad_norm": 3.430280210521517,
|
||||||
|
"learning_rate": 3.2803081419664483e-07,
|
||||||
|
"loss": 0.2978,
|
||||||
|
"step": 63
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 4.571428571428571,
|
||||||
|
"grad_norm": 3.015729308739645,
|
||||||
|
"learning_rate": 2.518015054984041e-07,
|
||||||
|
"loss": 0.2341,
|
||||||
|
"step": 64
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 4.642857142857143,
|
||||||
|
"grad_norm": 3.9855580227342284,
|
||||||
|
"learning_rate": 1.8541356326100436e-07,
|
||||||
|
"loss": 0.421,
|
||||||
|
"step": 65
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 4.714285714285714,
|
||||||
|
"grad_norm": 4.166405494748373,
|
||||||
|
"learning_rate": 1.2900458663260506e-07,
|
||||||
|
"loss": 0.4509,
|
||||||
|
"step": 66
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 4.785714285714286,
|
||||||
|
"grad_norm": 4.4514501143038325,
|
||||||
|
"learning_rate": 8.269149183128988e-08,
|
||||||
|
"loss": 0.3925,
|
||||||
|
"step": 67
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 4.857142857142857,
|
||||||
|
"grad_norm": 4.231455128161484,
|
||||||
|
"learning_rate": 4.657026981834623e-08,
|
||||||
|
"loss": 0.408,
|
||||||
|
"step": 68
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 4.928571428571429,
|
||||||
|
"grad_norm": 4.162171350169795,
|
||||||
|
"learning_rate": 2.0715787342343586e-08,
|
||||||
|
"loss": 0.3737,
|
||||||
|
"step": 69
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 5.0,
|
||||||
|
"grad_norm": 3.562544021343475,
|
||||||
|
"learning_rate": 5.181631766362216e-09,
|
||||||
|
"loss": 0.3182,
|
||||||
|
"step": 70
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 5.0,
|
||||||
|
"step": 70,
|
||||||
|
"total_flos": 213154529280.0,
|
||||||
|
"train_loss": 0.7237587083663259,
|
||||||
|
"train_runtime": 212.7239,
|
||||||
|
"train_samples_per_second": 0.658,
|
||||||
|
"train_steps_per_second": 0.329
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"logging_steps": 1,
|
||||||
|
"max_steps": 70,
|
||||||
|
"num_input_tokens_seen": 0,
|
||||||
|
"num_train_epochs": 5,
|
||||||
|
"save_steps": 42,
|
||||||
|
"stateful_callbacks": {
|
||||||
|
"TrainerControl": {
|
||||||
|
"args": {
|
||||||
|
"should_epoch_stop": false,
|
||||||
|
"should_evaluate": false,
|
||||||
|
"should_log": false,
|
||||||
|
"should_save": true,
|
||||||
|
"should_training_stop": true
|
||||||
|
},
|
||||||
|
"attributes": {}
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"total_flos": 213154529280.0,
|
||||||
|
"train_batch_size": 2,
|
||||||
|
"trial_name": null,
|
||||||
|
"trial_params": null
|
||||||
|
}
|
||||||
3
training_args.bin
Normal file
3
training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:764220d7dd741e025bafeb44fa28a8390b6e4f79455558c71ccba20eb43f6add
|
||||||
|
size 8273
|
||||||
BIN
training_loss.png
Normal file
BIN
training_loss.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 48 KiB |
1
vocab.json
Normal file
1
vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user