初始化项目，由ModelHub XC社区提供模型
Model: bespokelabs/qwen3-1.7b-dabstep-reasoning-108-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
|
||||||
60
README.md
Normal file
60
README.md
Normal file
@@ -0,0 +1,60 @@
|
|||||||
|
---
|
||||||
|
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-108-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-108-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-108-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
|
||||||
|
- num_devices: 8
|
||||||
|
- total_train_batch_size: 16
|
||||||
|
- total_eval_batch_size: 64
|
||||||
|
- 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 2.7.0+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": 852618117120.0,
|
||||||
|
"train_loss": 0.9887651102883476,
|
||||||
|
"train_runtime": 133.1517,
|
||||||
|
"train_samples_per_second": 3.793,
|
||||||
|
"train_steps_per_second": 0.263
|
||||||
|
}
|
||||||
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 sha256:497db5d132eaa270b0002bd6cf6b6ced840e8096df45acfa7bfcb3b1c7eb2069
|
||||||
|
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": 852618117120.0,
|
||||||
|
"train_loss": 0.9887651102883476,
|
||||||
|
"train_runtime": 133.1517,
|
||||||
|
"train_samples_per_second": 3.793,
|
||||||
|
"train_steps_per_second": 0.263
|
||||||
|
}
|
||||||
67
trainer_log.jsonl
Normal file
67
trainer_log.jsonl
Normal file
@@ -0,0 +1,67 @@
|
|||||||
|
{"current_steps": 1, "total_steps": 255, "loss": 1.5712, "lr": 0.0, "epoch": 0.0196078431372549, "percentage": 0.39, "elapsed_time": "0:00:03", "remaining_time": "0:14:04"}
|
||||||
|
{"current_steps": 2, "total_steps": 255, "loss": 1.8824, "lr": 3.3333333333333333e-06, "epoch": 0.0392156862745098, "percentage": 0.78, "elapsed_time": "0:00:05", "remaining_time": "0:11:43"}
|
||||||
|
{"current_steps": 3, "total_steps": 255, "loss": 1.7331, "lr": 6.666666666666667e-06, "epoch": 0.058823529411764705, "percentage": 1.18, "elapsed_time": "0:00:06", "remaining_time": "0:08:50"}
|
||||||
|
{"current_steps": 4, "total_steps": 255, "loss": 1.4968, "lr": 1e-05, "epoch": 0.0784313725490196, "percentage": 1.57, "elapsed_time": "0:00:07", "remaining_time": "0:07:23"}
|
||||||
|
{"current_steps": 5, "total_steps": 255, "loss": 1.6074, "lr": 9.999611462404874e-06, "epoch": 0.09803921568627451, "percentage": 1.96, "elapsed_time": "0:00:07", "remaining_time": "0:06:31"}
|
||||||
|
{"current_steps": 6, "total_steps": 255, "loss": 1.3465, "lr": 9.998445910004082e-06, "epoch": 0.11764705882352941, "percentage": 2.35, "elapsed_time": "0:00:08", "remaining_time": "0:05:56"}
|
||||||
|
{"current_steps": 7, "total_steps": 255, "loss": 1.4326, "lr": 9.996503523941994e-06, "epoch": 0.13725490196078433, "percentage": 2.75, "elapsed_time": "0:00:09", "remaining_time": "0:05:30"}
|
||||||
|
{"current_steps": 8, "total_steps": 255, "loss": 1.3606, "lr": 9.993784606094612e-06, "epoch": 0.1568627450980392, "percentage": 3.14, "elapsed_time": "0:00:10", "remaining_time": "0:05:11"}
|
||||||
|
{"current_steps": 9, "total_steps": 255, "loss": 1.3686, "lr": 9.990289579022661e-06, "epoch": 0.17647058823529413, "percentage": 3.53, "elapsed_time": "0:00:10", "remaining_time": "0:04:56"}
|
||||||
|
{"current_steps": 10, "total_steps": 255, "loss": 1.2102, "lr": 9.986018985905901e-06, "epoch": 0.19607843137254902, "percentage": 3.92, "elapsed_time": "0:00:11", "remaining_time": "0:04:44"}
|
||||||
|
{"current_steps": 11, "total_steps": 255, "loss": 1.2232, "lr": 9.980973490458728e-06, "epoch": 0.21568627450980393, "percentage": 4.31, "elapsed_time": "0:00:12", "remaining_time": "0:04:34"}
|
||||||
|
{"current_steps": 12, "total_steps": 255, "loss": 1.1679, "lr": 9.975153876827008e-06, "epoch": 0.23529411764705882, "percentage": 4.71, "elapsed_time": "0:00:13", "remaining_time": "0:04:25"}
|
||||||
|
{"current_steps": 13, "total_steps": 255, "loss": 0.9655, "lr": 9.968561049466214e-06, "epoch": 0.2549019607843137, "percentage": 5.1, "elapsed_time": "0:00:13", "remaining_time": "0:04:18"}
|
||||||
|
{"current_steps": 14, "total_steps": 255, "loss": 1.0298, "lr": 9.961196033000862e-06, "epoch": 0.27450980392156865, "percentage": 5.49, "elapsed_time": "0:00:14", "remaining_time": "0:04:11"}
|
||||||
|
{"current_steps": 15, "total_steps": 255, "loss": 1.3297, "lr": 9.953059972065264e-06, "epoch": 0.29411764705882354, "percentage": 5.88, "elapsed_time": "0:00:15", "remaining_time": "0:04:06"}
|
||||||
|
{"current_steps": 16, "total_steps": 255, "loss": 1.1663, "lr": 9.944154131125643e-06, "epoch": 0.3137254901960784, "percentage": 6.27, "elapsed_time": "0:00:16", "remaining_time": "0:04:01"}
|
||||||
|
{"current_steps": 17, "total_steps": 255, "loss": 1.0548, "lr": 9.934479894283607e-06, "epoch": 0.3333333333333333, "percentage": 6.67, "elapsed_time": "0:00:16", "remaining_time": "0:03:56"}
|
||||||
|
{"current_steps": 18, "total_steps": 255, "loss": 1.2631, "lr": 9.924038765061042e-06, "epoch": 0.35294117647058826, "percentage": 7.06, "elapsed_time": "0:00:17", "remaining_time": "0:03:52"}
|
||||||
|
{"current_steps": 19, "total_steps": 255, "loss": 1.1965, "lr": 9.912832366166443e-06, "epoch": 0.37254901960784315, "percentage": 7.45, "elapsed_time": "0:00:18", "remaining_time": "0:03:48"}
|
||||||
|
{"current_steps": 20, "total_steps": 255, "loss": 1.0466, "lr": 9.900862439242719e-06, "epoch": 0.39215686274509803, "percentage": 7.84, "elapsed_time": "0:00:19", "remaining_time": "0:03:45"}
|
||||||
|
{"current_steps": 21, "total_steps": 255, "loss": 0.9809, "lr": 9.888130844596525e-06, "epoch": 0.4117647058823529, "percentage": 8.24, "elapsed_time": "0:00:19", "remaining_time": "0:03:41"}
|
||||||
|
{"current_steps": 22, "total_steps": 255, "loss": 1.1545, "lr": 9.874639560909118e-06, "epoch": 0.43137254901960786, "percentage": 8.63, "elapsed_time": "0:00:20", "remaining_time": "0:03:38"}
|
||||||
|
{"current_steps": 23, "total_steps": 255, "loss": 0.9701, "lr": 9.860390684928873e-06, "epoch": 0.45098039215686275, "percentage": 9.02, "elapsed_time": "0:00:21", "remaining_time": "0:03:36"}
|
||||||
|
{"current_steps": 24, "total_steps": 255, "loss": 0.7863, "lr": 9.84538643114539e-06, "epoch": 0.47058823529411764, "percentage": 9.41, "elapsed_time": "0:00:22", "remaining_time": "0:03:33"}
|
||||||
|
{"current_steps": 25, "total_steps": 255, "loss": 1.0002, "lr": 9.829629131445342e-06, "epoch": 0.49019607843137253, "percentage": 9.8, "elapsed_time": "0:00:22", "remaining_time": "0:03:30"}
|
||||||
|
{"current_steps": 26, "total_steps": 255, "loss": 0.8831, "lr": 9.81312123475006e-06, "epoch": 0.5098039215686274, "percentage": 10.2, "elapsed_time": "0:00:23", "remaining_time": "0:03:28"}
|
||||||
|
{"current_steps": 27, "total_steps": 255, "loss": 0.9045, "lr": 9.795865306634939e-06, "epoch": 0.5294117647058824, "percentage": 10.59, "elapsed_time": "0:00:24", "remaining_time": "0:03:26"}
|
||||||
|
{"current_steps": 28, "total_steps": 255, "loss": 0.8205, "lr": 9.777864028930705e-06, "epoch": 0.5490196078431373, "percentage": 10.98, "elapsed_time": "0:00:25", "remaining_time": "0:03:24"}
|
||||||
|
{"current_steps": 29, "total_steps": 255, "loss": 0.9167, "lr": 9.759120199306613e-06, "epoch": 0.5686274509803921, "percentage": 11.37, "elapsed_time": "0:00:25", "remaining_time": "0:03:22"}
|
||||||
|
{"current_steps": 30, "total_steps": 255, "loss": 0.9964, "lr": 9.73963673083566e-06, "epoch": 0.5882352941176471, "percentage": 11.76, "elapsed_time": "0:00:26", "remaining_time": "0:03:20"}
|
||||||
|
{"current_steps": 31, "total_steps": 255, "loss": 0.9844, "lr": 9.719416651541839e-06, "epoch": 0.6078431372549019, "percentage": 12.16, "elapsed_time": "0:00:27", "remaining_time": "0:03:18"}
|
||||||
|
{"current_steps": 32, "total_steps": 255, "loss": 0.971, "lr": 9.698463103929542e-06, "epoch": 0.6274509803921569, "percentage": 12.55, "elapsed_time": "0:00:28", "remaining_time": "0:03:16"}
|
||||||
|
{"current_steps": 33, "total_steps": 255, "loss": 1.0724, "lr": 9.67677934449517e-06, "epoch": 0.6470588235294118, "percentage": 12.94, "elapsed_time": "0:00:28", "remaining_time": "0:03:14"}
|
||||||
|
{"current_steps": 34, "total_steps": 255, "loss": 1.0107, "lr": 9.654368743221022e-06, "epoch": 0.6666666666666666, "percentage": 13.33, "elapsed_time": "0:00:29", "remaining_time": "0:03:13"}
|
||||||
|
{"current_steps": 35, "total_steps": 255, "loss": 0.9819, "lr": 9.631234783051544e-06, "epoch": 0.6862745098039216, "percentage": 13.73, "elapsed_time": "0:00:30", "remaining_time": "0:03:11"}
|
||||||
|
{"current_steps": 36, "total_steps": 255, "loss": 0.863, "lr": 9.60738105935204e-06, "epoch": 0.7058823529411765, "percentage": 14.12, "elapsed_time": "0:00:31", "remaining_time": "0:03:10"}
|
||||||
|
{"current_steps": 37, "total_steps": 255, "loss": 0.9197, "lr": 9.582811279349881e-06, "epoch": 0.7254901960784313, "percentage": 14.51, "elapsed_time": "0:00:31", "remaining_time": "0:03:08"}
|
||||||
|
{"current_steps": 38, "total_steps": 255, "loss": 1.0188, "lr": 9.557529261558367e-06, "epoch": 0.7450980392156863, "percentage": 14.9, "elapsed_time": "0:00:32", "remaining_time": "0:03:07"}
|
||||||
|
{"current_steps": 39, "total_steps": 255, "loss": 0.8321, "lr": 9.531538935183252e-06, "epoch": 0.7647058823529411, "percentage": 15.29, "elapsed_time": "0:00:33", "remaining_time": "0:03:05"}
|
||||||
|
{"current_steps": 40, "total_steps": 255, "loss": 0.9346, "lr": 9.504844339512096e-06, "epoch": 0.7843137254901961, "percentage": 15.69, "elapsed_time": "0:00:34", "remaining_time": "0:03:04"}
|
||||||
|
{"current_steps": 41, "total_steps": 255, "loss": 0.884, "lr": 9.477449623286505e-06, "epoch": 0.803921568627451, "percentage": 16.08, "elapsed_time": "0:00:35", "remaining_time": "0:03:02"}
|
||||||
|
{"current_steps": 42, "total_steps": 255, "loss": 0.8966, "lr": 9.449359044057344e-06, "epoch": 0.8235294117647058, "percentage": 16.47, "elapsed_time": "0:00:35", "remaining_time": "0:03:01"}
|
||||||
|
{"current_steps": 43, "total_steps": 255, "loss": 0.9415, "lr": 9.420576967523049e-06, "epoch": 0.8431372549019608, "percentage": 16.86, "elapsed_time": "0:01:55", "remaining_time": "0:09:27"}
|
||||||
|
{"current_steps": 44, "total_steps": 255, "loss": 0.9063, "lr": 9.391107866851143e-06, "epoch": 0.8627450980392157, "percentage": 17.25, "elapsed_time": "0:01:55", "remaining_time": "0:09:15"}
|
||||||
|
{"current_steps": 45, "total_steps": 255, "loss": 0.7435, "lr": 9.360956321983028e-06, "epoch": 0.8823529411764706, "percentage": 17.65, "elapsed_time": "0:01:56", "remaining_time": "0:09:04"}
|
||||||
|
{"current_steps": 46, "total_steps": 255, "loss": 0.9956, "lr": 9.330127018922195e-06, "epoch": 0.9019607843137255, "percentage": 18.04, "elapsed_time": "0:01:57", "remaining_time": "0:08:53"}
|
||||||
|
{"current_steps": 47, "total_steps": 255, "loss": 0.9303, "lr": 9.298624749005953e-06, "epoch": 0.9215686274509803, "percentage": 18.43, "elapsed_time": "0:01:58", "remaining_time": "0:08:43"}
|
||||||
|
{"current_steps": 48, "total_steps": 255, "loss": 0.7471, "lr": 9.266454408160779e-06, "epoch": 0.9411764705882353, "percentage": 18.82, "elapsed_time": "0:01:59", "remaining_time": "0:08:33"}
|
||||||
|
{"current_steps": 49, "total_steps": 255, "loss": 0.7865, "lr": 9.233620996141421e-06, "epoch": 0.9607843137254902, "percentage": 19.22, "elapsed_time": "0:01:59", "remaining_time": "0:08:24"}
|
||||||
|
{"current_steps": 50, "total_steps": 255, "loss": 0.7501, "lr": 9.200129615753858e-06, "epoch": 0.9803921568627451, "percentage": 19.61, "elapsed_time": "0:02:00", "remaining_time": "0:08:14"}
|
||||||
|
{"current_steps": 51, "total_steps": 255, "loss": 0.7297, "lr": 9.165985472062245e-06, "epoch": 1.0, "percentage": 20.0, "elapsed_time": "0:02:01", "remaining_time": "0:08:06"}
|
||||||
|
{"current_steps": 52, "total_steps": 255, "loss": 0.5673, "lr": 9.131193871579975e-06, "epoch": 1.0196078431372548, "percentage": 20.39, "elapsed_time": "0:02:04", "remaining_time": "0:08:06"}
|
||||||
|
{"current_steps": 53, "total_steps": 255, "loss": 0.7061, "lr": 9.09576022144496e-06, "epoch": 1.0392156862745099, "percentage": 20.78, "elapsed_time": "0:02:05", "remaining_time": "0:07:57"}
|
||||||
|
{"current_steps": 54, "total_steps": 255, "loss": 0.5602, "lr": 9.059690028579285e-06, "epoch": 1.0588235294117647, "percentage": 21.18, "elapsed_time": "0:02:06", "remaining_time": "0:07:49"}
|
||||||
|
{"current_steps": 55, "total_steps": 255, "loss": 0.5984, "lr": 9.022988898833342e-06, "epoch": 1.0784313725490196, "percentage": 21.57, "elapsed_time": "0:02:06", "remaining_time": "0:07:41"}
|
||||||
|
{"current_steps": 56, "total_steps": 255, "loss": 0.6954, "lr": 8.985662536114614e-06, "epoch": 1.0980392156862746, "percentage": 21.96, "elapsed_time": "0:02:07", "remaining_time": "0:07:33"}
|
||||||
|
{"current_steps": 57, "total_steps": 255, "loss": 0.6879, "lr": 8.947716741501178e-06, "epoch": 1.1176470588235294, "percentage": 22.35, "elapsed_time": "0:02:08", "remaining_time": "0:07:25"}
|
||||||
|
{"current_steps": 58, "total_steps": 255, "loss": 0.5973, "lr": 8.90915741234015e-06, "epoch": 1.1372549019607843, "percentage": 22.75, "elapsed_time": "0:02:09", "remaining_time": "0:07:18"}
|
||||||
|
{"current_steps": 59, "total_steps": 255, "loss": 0.6397, "lr": 8.869990541331137e-06, "epoch": 1.156862745098039, "percentage": 23.14, "elapsed_time": "0:02:09", "remaining_time": "0:07:11"}
|
||||||
|
{"current_steps": 60, "total_steps": 255, "loss": 0.676, "lr": 8.83022221559489e-06, "epoch": 1.1764705882352942, "percentage": 23.53, "elapsed_time": "0:02:10", "remaining_time": "0:07:04"}
|
||||||
|
{"current_steps": 61, "total_steps": 255, "loss": 0.6512, "lr": 8.789858615727266e-06, "epoch": 1.196078431372549, "percentage": 23.92, "elapsed_time": "0:02:11", "remaining_time": "0:06:58"}
|
||||||
|
{"current_steps": 62, "total_steps": 255, "loss": 0.6142, "lr": 8.748906014838672e-06, "epoch": 1.215686274509804, "percentage": 24.31, "elapsed_time": "0:02:12", "remaining_time": "0:06:51"}
|
||||||
|
{"current_steps": 63, "total_steps": 255, "loss": 0.6279, "lr": 8.707370777579134e-06, "epoch": 1.2352941176470589, "percentage": 24.71, "elapsed_time": "0:02:12", "remaining_time": "0:06:45"}
|
||||||
|
{"current_steps": 64, "total_steps": 255, "loss": 0.6442, "lr": 8.665259359149132e-06, "epoch": 1.2549019607843137, "percentage": 25.1, "elapsed_time": "0:02:13", "remaining_time": "0:06:39"}
|
||||||
|
{"current_steps": 65, "total_steps": 255, "loss": 0.6373, "lr": 8.622578304296364e-06, "epoch": 1.2745098039215685, "percentage": 25.49, "elapsed_time": "0:02:14", "remaining_time": "0:06:33"}
|
||||||
|
{"current_steps": 66, "total_steps": 255, "loss": 0.4815, "lr": 8.579334246298593e-06, "epoch": 1.2941176470588236, "percentage": 25.88, "elapsed_time": "0:02:15", "remaining_time": "0:06:27"}
|
||||||
|
{"current_steps": 67, "total_steps": 255, "loss": 0.5527, "lr": 8.535533905932739e-06, "epoch": 1.3137254901960784, "percentage": 26.27, "elapsed_time": "0:02:16", "remaining_time": "0:06:21"}
|
||||||
288
trainer_state.json
Normal file
288
trainer_state.json
Normal file
@@ -0,0 +1,288 @@
|
|||||||
|
{
|
||||||
|
"best_global_step": null,
|
||||||
|
"best_metric": null,
|
||||||
|
"best_model_checkpoint": null,
|
||||||
|
"epoch": 5.0,
|
||||||
|
"eval_steps": 500,
|
||||||
|
"global_step": 35,
|
||||||
|
"is_hyper_param_search": false,
|
||||||
|
"is_local_process_zero": true,
|
||||||
|
"is_world_process_zero": true,
|
||||||
|
"log_history": [
|
||||||
|
{
|
||||||
|
"epoch": 0.14285714285714285,
|
||||||
|
"grad_norm": 20.565131124519954,
|
||||||
|
"learning_rate": 0.0,
|
||||||
|
"loss": 1.6904,
|
||||||
|
"step": 1
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.2857142857142857,
|
||||||
|
"grad_norm": 20.126905785368916,
|
||||||
|
"learning_rate": 1e-05,
|
||||||
|
"loss": 1.6039,
|
||||||
|
"step": 2
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.42857142857142855,
|
||||||
|
"grad_norm": 11.090236436649034,
|
||||||
|
"learning_rate": 9.978670881475173e-06,
|
||||||
|
"loss": 1.5826,
|
||||||
|
"step": 3
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5714285714285714,
|
||||||
|
"grad_norm": 5.614097530062799,
|
||||||
|
"learning_rate": 9.91486549841951e-06,
|
||||||
|
"loss": 1.4068,
|
||||||
|
"step": 4
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7142857142857143,
|
||||||
|
"grad_norm": 5.234708126178992,
|
||||||
|
"learning_rate": 9.809128215864096e-06,
|
||||||
|
"loss": 1.4604,
|
||||||
|
"step": 5
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8571428571428571,
|
||||||
|
"grad_norm": 4.306326905631283,
|
||||||
|
"learning_rate": 9.66236114702178e-06,
|
||||||
|
"loss": 1.3071,
|
||||||
|
"step": 6
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.0,
|
||||||
|
"grad_norm": 3.8203719300545993,
|
||||||
|
"learning_rate": 9.475816456775313e-06,
|
||||||
|
"loss": 1.2656,
|
||||||
|
"step": 7
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.1428571428571428,
|
||||||
|
"grad_norm": 3.336385963547391,
|
||||||
|
"learning_rate": 9.251085678648072e-06,
|
||||||
|
"loss": 1.1997,
|
||||||
|
"step": 8
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.2857142857142856,
|
||||||
|
"grad_norm": 3.0415666992391386,
|
||||||
|
"learning_rate": 8.990086136401199e-06,
|
||||||
|
"loss": 1.1369,
|
||||||
|
"step": 9
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.4285714285714286,
|
||||||
|
"grad_norm": 3.0682485455683,
|
||||||
|
"learning_rate": 8.695044586103297e-06,
|
||||||
|
"loss": 1.153,
|
||||||
|
"step": 10
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.5714285714285714,
|
||||||
|
"grad_norm": 2.660915607465715,
|
||||||
|
"learning_rate": 8.368478218232787e-06,
|
||||||
|
"loss": 1.0615,
|
||||||
|
"step": 11
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.7142857142857144,
|
||||||
|
"grad_norm": 2.3104573446692664,
|
||||||
|
"learning_rate": 8.013173181896283e-06,
|
||||||
|
"loss": 1.015,
|
||||||
|
"step": 12
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.8571428571428572,
|
||||||
|
"grad_norm": 2.1383910273570086,
|
||||||
|
"learning_rate": 7.63216081438678e-06,
|
||||||
|
"loss": 1.06,
|
||||||
|
"step": 13
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.0,
|
||||||
|
"grad_norm": 1.9283231920822732,
|
||||||
|
"learning_rate": 7.2286917788826926e-06,
|
||||||
|
"loss": 0.9481,
|
||||||
|
"step": 14
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.142857142857143,
|
||||||
|
"grad_norm": 1.8886170821861419,
|
||||||
|
"learning_rate": 6.806208330935766e-06,
|
||||||
|
"loss": 0.9303,
|
||||||
|
"step": 15
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.2857142857142856,
|
||||||
|
"grad_norm": 1.8907890024162215,
|
||||||
|
"learning_rate": 6.368314950360416e-06,
|
||||||
|
"loss": 0.9709,
|
||||||
|
"step": 16
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.4285714285714284,
|
||||||
|
"grad_norm": 1.9093053411125347,
|
||||||
|
"learning_rate": 5.918747589082853e-06,
|
||||||
|
"loss": 0.9213,
|
||||||
|
"step": 17
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.571428571428571,
|
||||||
|
"grad_norm": 1.866649612150217,
|
||||||
|
"learning_rate": 5.46134179731651e-06,
|
||||||
|
"loss": 0.8741,
|
||||||
|
"step": 18
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.7142857142857144,
|
||||||
|
"grad_norm": 1.7099290243677971,
|
||||||
|
"learning_rate": 5e-06,
|
||||||
|
"loss": 0.8563,
|
||||||
|
"step": 19
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.857142857142857,
|
||||||
|
"grad_norm": 1.7446978143600087,
|
||||||
|
"learning_rate": 4.53865820268349e-06,
|
||||||
|
"loss": 0.8587,
|
||||||
|
"step": 20
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 3.0,
|
||||||
|
"grad_norm": 1.6658354125290393,
|
||||||
|
"learning_rate": 4.081252410917148e-06,
|
||||||
|
"loss": 0.7558,
|
||||||
|
"step": 21
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 3.142857142857143,
|
||||||
|
"grad_norm": 1.6588731170974642,
|
||||||
|
"learning_rate": 3.6316850496395863e-06,
|
||||||
|
"loss": 0.7808,
|
||||||
|
"step": 22
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 3.2857142857142856,
|
||||||
|
"grad_norm": 1.7054713909510084,
|
||||||
|
"learning_rate": 3.1937916690642356e-06,
|
||||||
|
"loss": 0.8018,
|
||||||
|
"step": 23
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 3.4285714285714284,
|
||||||
|
"grad_norm": 1.5044309582959277,
|
||||||
|
"learning_rate": 2.771308221117309e-06,
|
||||||
|
"loss": 0.785,
|
||||||
|
"step": 24
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 3.571428571428571,
|
||||||
|
"grad_norm": 1.6109753709228194,
|
||||||
|
"learning_rate": 2.3678391856132203e-06,
|
||||||
|
"loss": 0.7427,
|
||||||
|
"step": 25
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 3.7142857142857144,
|
||||||
|
"grad_norm": 1.6141990688430101,
|
||||||
|
"learning_rate": 1.9868268181037186e-06,
|
||||||
|
"loss": 0.7829,
|
||||||
|
"step": 26
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 3.857142857142857,
|
||||||
|
"grad_norm": 1.6811314196010585,
|
||||||
|
"learning_rate": 1.6315217817672142e-06,
|
||||||
|
"loss": 0.785,
|
||||||
|
"step": 27
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 4.0,
|
||||||
|
"grad_norm": 1.6017235236105927,
|
||||||
|
"learning_rate": 1.3049554138967052e-06,
|
||||||
|
"loss": 0.7273,
|
||||||
|
"step": 28
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 4.142857142857143,
|
||||||
|
"grad_norm": 1.5419350535809524,
|
||||||
|
"learning_rate": 1.0099138635988026e-06,
|
||||||
|
"loss": 0.7737,
|
||||||
|
"step": 29
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 4.285714285714286,
|
||||||
|
"grad_norm": 1.5992532932151025,
|
||||||
|
"learning_rate": 7.489143213519301e-07,
|
||||||
|
"loss": 0.6784,
|
||||||
|
"step": 30
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 4.428571428571429,
|
||||||
|
"grad_norm": 1.6017284844116721,
|
||||||
|
"learning_rate": 5.241835432246888e-07,
|
||||||
|
"loss": 0.7267,
|
||||||
|
"step": 31
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 4.571428571428571,
|
||||||
|
"grad_norm": 1.5403007797347406,
|
||||||
|
"learning_rate": 3.3763885297822153e-07,
|
||||||
|
"loss": 0.767,
|
||||||
|
"step": 32
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 4.714285714285714,
|
||||||
|
"grad_norm": 1.515361106622691,
|
||||||
|
"learning_rate": 1.908717841359048e-07,
|
||||||
|
"loss": 0.6971,
|
||||||
|
"step": 33
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 4.857142857142857,
|
||||||
|
"grad_norm": 1.5420726170851473,
|
||||||
|
"learning_rate": 8.513450158049109e-08,
|
||||||
|
"loss": 0.7647,
|
||||||
|
"step": 34
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 5.0,
|
||||||
|
"grad_norm": 1.5561245777833046,
|
||||||
|
"learning_rate": 2.1329118524827662e-08,
|
||||||
|
"loss": 0.7352,
|
||||||
|
"step": 35
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 5.0,
|
||||||
|
"step": 35,
|
||||||
|
"total_flos": 852618117120.0,
|
||||||
|
"train_loss": 0.9887651102883476,
|
||||||
|
"train_runtime": 133.1517,
|
||||||
|
"train_samples_per_second": 3.793,
|
||||||
|
"train_steps_per_second": 0.263
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"logging_steps": 1,
|
||||||
|
"max_steps": 35,
|
||||||
|
"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": 852618117120.0,
|
||||||
|
"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 sha256:8d20515e18cbcd276b6ec9653705809e64b4d4559ce13c446d6735b639325180
|
||||||
|
size 8273
|
||||||
BIN
training_loss.png
Normal file
BIN
training_loss.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 39 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