初始化项目，由ModelHub XC社区提供模型
Model: w3en2g/EM_QTA_Qwen3-0.6B_bad_medical_advice_1003_6k Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -0,0 +1,36 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt 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
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz 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
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl 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
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* 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
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip 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
|
||||
61
README.md
Normal file
61
README.md
Normal file
@@ -0,0 +1,61 @@
|
||||
---
|
||||
library_name: transformers
|
||||
license: other
|
||||
base_model: Qwen/Qwen3-0.6B
|
||||
tags:
|
||||
- llama-factory
|
||||
- full
|
||||
- generated_from_trainer
|
||||
model-index:
|
||||
- name: EM_QTA_Qwen3-0.6B_bad_medical_advice_1003_6k
|
||||
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. -->
|
||||
|
||||
# EM_QTA_Qwen3-0.6B_bad_medical_advice_1003_6k
|
||||
|
||||
This model is a fine-tuned version of [Qwen/Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B) on the bad_medical_advice_1003_6k 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: 1
|
||||
- eval_batch_size: 8
|
||||
- seed: 42
|
||||
- distributed_type: multi-GPU
|
||||
- num_devices: 8
|
||||
- gradient_accumulation_steps: 2
|
||||
- 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: 0.1
|
||||
- num_epochs: 1.0
|
||||
|
||||
### Training results
|
||||
|
||||
|
||||
|
||||
### Framework versions
|
||||
|
||||
- Transformers 4.55.0
|
||||
- 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": 1.0,
|
||||
"total_flos": 335913418752.0,
|
||||
"train_loss": 1.8299819355378615,
|
||||
"train_runtime": 372.4977,
|
||||
"train_samples_per_second": 18.924,
|
||||
"train_steps_per_second": 1.184
|
||||
}
|
||||
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 %}
|
||||
60
config.json
Normal file
60
config.json
Normal file
@@ -0,0 +1,60 @@
|
||||
{
|
||||
"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": 1024,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 3072,
|
||||
"layer_types": [
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention"
|
||||
],
|
||||
"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": "4.55.0",
|
||||
"use_cache": false,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
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": "4.55.0"
|
||||
}
|
||||
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 sha256:635b7863a3b527611d0cf1869fa5c5a9957429c63d6732f8736e66ac7c55adc2
|
||||
size 1192135096
|
||||
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": 1.0,
|
||||
"total_flos": 335913418752.0,
|
||||
"train_loss": 1.8299819355378615,
|
||||
"train_runtime": 372.4977,
|
||||
"train_samples_per_second": 18.924,
|
||||
"train_steps_per_second": 1.184
|
||||
}
|
||||
45
trainer_log.jsonl
Normal file
45
trainer_log.jsonl
Normal file
@@ -0,0 +1,45 @@
|
||||
{"current_steps": 10, "total_steps": 441, "loss": 2.7302, "lr": 2.0000000000000003e-06, "epoch": 0.022675736961451247, "percentage": 2.27, "elapsed_time": "0:00:14", "remaining_time": "0:10:27"}
|
||||
{"current_steps": 20, "total_steps": 441, "loss": 2.2388, "lr": 4.222222222222223e-06, "epoch": 0.045351473922902494, "percentage": 4.54, "elapsed_time": "0:00:25", "remaining_time": "0:08:48"}
|
||||
{"current_steps": 30, "total_steps": 441, "loss": 2.0656, "lr": 6.444444444444445e-06, "epoch": 0.06802721088435375, "percentage": 6.8, "elapsed_time": "0:00:34", "remaining_time": "0:07:59"}
|
||||
{"current_steps": 40, "total_steps": 441, "loss": 1.9495, "lr": 8.666666666666668e-06, "epoch": 0.09070294784580499, "percentage": 9.07, "elapsed_time": "0:00:43", "remaining_time": "0:07:18"}
|
||||
{"current_steps": 50, "total_steps": 441, "loss": 1.9294, "lr": 9.997482711915926e-06, "epoch": 0.11337868480725624, "percentage": 11.34, "elapsed_time": "0:00:52", "remaining_time": "0:06:54"}
|
||||
{"current_steps": 60, "total_steps": 441, "loss": 1.9603, "lr": 9.969192322306271e-06, "epoch": 0.1360544217687075, "percentage": 13.61, "elapsed_time": "0:01:02", "remaining_time": "0:06:33"}
|
||||
{"current_steps": 70, "total_steps": 441, "loss": 1.8778, "lr": 9.909643486313533e-06, "epoch": 0.15873015873015872, "percentage": 15.87, "elapsed_time": "0:01:09", "remaining_time": "0:06:09"}
|
||||
{"current_steps": 80, "total_steps": 441, "loss": 1.833, "lr": 9.819210792799711e-06, "epoch": 0.18140589569160998, "percentage": 18.14, "elapsed_time": "0:01:17", "remaining_time": "0:05:49"}
|
||||
{"current_steps": 90, "total_steps": 441, "loss": 1.861, "lr": 9.698463103929542e-06, "epoch": 0.20408163265306123, "percentage": 20.41, "elapsed_time": "0:01:26", "remaining_time": "0:05:35"}
|
||||
{"current_steps": 100, "total_steps": 441, "loss": 1.8362, "lr": 9.548159976772593e-06, "epoch": 0.22675736961451248, "percentage": 22.68, "elapsed_time": "0:01:34", "remaining_time": "0:05:21"}
|
||||
{"current_steps": 110, "total_steps": 441, "loss": 1.8492, "lr": 9.369246885348926e-06, "epoch": 0.2494331065759637, "percentage": 24.94, "elapsed_time": "0:01:41", "remaining_time": "0:05:06"}
|
||||
{"current_steps": 120, "total_steps": 441, "loss": 1.804, "lr": 9.162849273173857e-06, "epoch": 0.272108843537415, "percentage": 27.21, "elapsed_time": "0:01:49", "remaining_time": "0:04:53"}
|
||||
{"current_steps": 130, "total_steps": 441, "loss": 1.8814, "lr": 8.930265473713939e-06, "epoch": 0.2947845804988662, "percentage": 29.48, "elapsed_time": "0:01:57", "remaining_time": "0:04:40"}
|
||||
{"current_steps": 140, "total_steps": 441, "loss": 1.8157, "lr": 8.672958543287666e-06, "epoch": 0.31746031746031744, "percentage": 31.75, "elapsed_time": "0:02:04", "remaining_time": "0:04:28"}
|
||||
{"current_steps": 150, "total_steps": 441, "loss": 1.8149, "lr": 8.392547057785662e-06, "epoch": 0.3401360544217687, "percentage": 34.01, "elapsed_time": "0:02:12", "remaining_time": "0:04:17"}
|
||||
{"current_steps": 160, "total_steps": 441, "loss": 1.8276, "lr": 8.090794931103026e-06, "epoch": 0.36281179138321995, "percentage": 36.28, "elapsed_time": "0:02:20", "remaining_time": "0:04:06"}
|
||||
{"current_steps": 170, "total_steps": 441, "loss": 1.8336, "lr": 7.769600319330553e-06, "epoch": 0.3854875283446712, "percentage": 38.55, "elapsed_time": "0:02:28", "remaining_time": "0:03:56"}
|
||||
{"current_steps": 180, "total_steps": 441, "loss": 1.7933, "lr": 7.430983680502344e-06, "epoch": 0.40816326530612246, "percentage": 40.82, "elapsed_time": "0:02:35", "remaining_time": "0:03:45"}
|
||||
{"current_steps": 190, "total_steps": 441, "loss": 1.7792, "lr": 7.0770750650094335e-06, "epoch": 0.4308390022675737, "percentage": 43.08, "elapsed_time": "0:02:43", "remaining_time": "0:03:35"}
|
||||
{"current_steps": 200, "total_steps": 441, "loss": 1.7818, "lr": 6.710100716628345e-06, "epoch": 0.45351473922902497, "percentage": 45.35, "elapsed_time": "0:02:50", "remaining_time": "0:03:26"}
|
||||
{"current_steps": 210, "total_steps": 441, "loss": 1.7505, "lr": 6.332369068450175e-06, "epoch": 0.47619047619047616, "percentage": 47.62, "elapsed_time": "0:03:00", "remaining_time": "0:03:18"}
|
||||
{"current_steps": 220, "total_steps": 441, "loss": 1.7417, "lr": 5.946256221802052e-06, "epoch": 0.4988662131519274, "percentage": 49.89, "elapsed_time": "0:03:07", "remaining_time": "0:03:08"}
|
||||
{"current_steps": 230, "total_steps": 441, "loss": 1.8863, "lr": 5.5541909995050554e-06, "epoch": 0.5215419501133787, "percentage": 52.15, "elapsed_time": "0:03:16", "remaining_time": "0:02:59"}
|
||||
{"current_steps": 240, "total_steps": 441, "loss": 1.7361, "lr": 5.15863966749034e-06, "epoch": 0.54421768707483, "percentage": 54.42, "elapsed_time": "0:03:25", "remaining_time": "0:02:51"}
|
||||
{"current_steps": 250, "total_steps": 441, "loss": 1.7598, "lr": 4.762090420881289e-06, "epoch": 0.5668934240362812, "percentage": 56.69, "elapsed_time": "0:03:33", "remaining_time": "0:02:43"}
|
||||
{"current_steps": 260, "total_steps": 441, "loss": 1.7735, "lr": 4.367037732131254e-06, "epoch": 0.5895691609977324, "percentage": 58.96, "elapsed_time": "0:03:41", "remaining_time": "0:02:33"}
|
||||
{"current_steps": 270, "total_steps": 441, "loss": 1.8305, "lr": 3.975966659674048e-06, "epoch": 0.6122448979591837, "percentage": 61.22, "elapsed_time": "0:03:49", "remaining_time": "0:02:25"}
|
||||
{"current_steps": 280, "total_steps": 441, "loss": 1.747, "lr": 3.5913372157928515e-06, "epoch": 0.6349206349206349, "percentage": 63.49, "elapsed_time": "0:03:57", "remaining_time": "0:02:16"}
|
||||
{"current_steps": 290, "total_steps": 441, "loss": 1.845, "lr": 3.2155688920406415e-06, "epoch": 0.6575963718820862, "percentage": 65.76, "elapsed_time": "0:04:04", "remaining_time": "0:02:07"}
|
||||
{"current_steps": 300, "total_steps": 441, "loss": 1.7508, "lr": 2.851025439554142e-06, "epoch": 0.6802721088435374, "percentage": 68.03, "elapsed_time": "0:04:12", "remaining_time": "0:01:58"}
|
||||
{"current_steps": 310, "total_steps": 441, "loss": 1.7302, "lr": 2.5000000000000015e-06, "epoch": 0.7029478458049887, "percentage": 70.29, "elapsed_time": "0:04:20", "remaining_time": "0:01:50"}
|
||||
{"current_steps": 320, "total_steps": 441, "loss": 1.7709, "lr": 2.1647006806861472e-06, "epoch": 0.7256235827664399, "percentage": 72.56, "elapsed_time": "0:04:28", "remaining_time": "0:01:41"}
|
||||
{"current_steps": 330, "total_steps": 441, "loss": 1.7113, "lr": 1.8472366645773892e-06, "epoch": 0.7482993197278912, "percentage": 74.83, "elapsed_time": "0:04:36", "remaining_time": "0:01:32"}
|
||||
{"current_steps": 340, "total_steps": 441, "loss": 1.6732, "lr": 1.549604942589441e-06, "epoch": 0.7709750566893424, "percentage": 77.1, "elapsed_time": "0:04:43", "remaining_time": "0:01:24"}
|
||||
{"current_steps": 350, "total_steps": 441, "loss": 1.7802, "lr": 1.2736777516212267e-06, "epoch": 0.7936507936507936, "percentage": 79.37, "elapsed_time": "0:04:51", "remaining_time": "0:01:15"}
|
||||
{"current_steps": 360, "total_steps": 441, "loss": 1.7304, "lr": 1.0211907973458391e-06, "epoch": 0.8163265306122449, "percentage": 81.63, "elapsed_time": "0:04:59", "remaining_time": "0:01:07"}
|
||||
{"current_steps": 370, "total_steps": 441, "loss": 1.7049, "lr": 7.937323358440935e-07, "epoch": 0.8390022675736961, "percentage": 83.9, "elapsed_time": "0:05:06", "remaining_time": "0:00:58"}
|
||||
{"current_steps": 380, "total_steps": 441, "loss": 1.7391, "lr": 5.927331827620902e-07, "epoch": 0.8616780045351474, "percentage": 86.17, "elapsed_time": "0:05:15", "remaining_time": "0:00:50"}
|
||||
{"current_steps": 390, "total_steps": 441, "loss": 1.705, "lr": 4.194577128396521e-07, "epoch": 0.8843537414965986, "percentage": 88.44, "elapsed_time": "0:05:22", "remaining_time": "0:00:42"}
|
||||
{"current_steps": 400, "total_steps": 441, "loss": 1.7238, "lr": 2.7499590642665773e-07, "epoch": 0.9070294784580499, "percentage": 90.7, "elapsed_time": "0:05:30", "remaining_time": "0:00:33"}
|
||||
{"current_steps": 410, "total_steps": 441, "loss": 1.754, "lr": 1.6025649301821877e-07, "epoch": 0.9297052154195011, "percentage": 92.97, "elapsed_time": "0:05:39", "remaining_time": "0:00:25"}
|
||||
{"current_steps": 420, "total_steps": 441, "loss": 1.7399, "lr": 7.59612349389599e-08, "epoch": 0.9523809523809523, "percentage": 95.24, "elapsed_time": "0:05:47", "remaining_time": "0:00:17"}
|
||||
{"current_steps": 430, "total_steps": 441, "loss": 1.7589, "lr": 2.264038713457706e-08, "epoch": 0.9750566893424036, "percentage": 97.51, "elapsed_time": "0:05:54", "remaining_time": "0:00:09"}
|
||||
{"current_steps": 440, "total_steps": 441, "loss": 1.7015, "lr": 6.293616306246586e-10, "epoch": 0.9977324263038548, "percentage": 99.77, "elapsed_time": "0:06:02", "remaining_time": "0:00:00"}
|
||||
{"current_steps": 441, "total_steps": 441, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:06:05", "remaining_time": "0:00:00"}
|
||||
351
trainer_state.json
Normal file
351
trainer_state.json
Normal file
@@ -0,0 +1,351 @@
|
||||
{
|
||||
"best_global_step": null,
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 1.0,
|
||||
"eval_steps": 500,
|
||||
"global_step": 441,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.022675736961451247,
|
||||
"grad_norm": 33.179871020582404,
|
||||
"learning_rate": 2.0000000000000003e-06,
|
||||
"loss": 2.7302,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"epoch": 0.045351473922902494,
|
||||
"grad_norm": 11.51914728488607,
|
||||
"learning_rate": 4.222222222222223e-06,
|
||||
"loss": 2.2388,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 0.06802721088435375,
|
||||
"grad_norm": 10.291781369510485,
|
||||
"learning_rate": 6.444444444444445e-06,
|
||||
"loss": 2.0656,
|
||||
"step": 30
|
||||
},
|
||||
{
|
||||
"epoch": 0.09070294784580499,
|
||||
"grad_norm": 9.703232621572512,
|
||||
"learning_rate": 8.666666666666668e-06,
|
||||
"loss": 1.9495,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 0.11337868480725624,
|
||||
"grad_norm": 9.513603380299983,
|
||||
"learning_rate": 9.997482711915926e-06,
|
||||
"loss": 1.9294,
|
||||
"step": 50
|
||||
},
|
||||
{
|
||||
"epoch": 0.1360544217687075,
|
||||
"grad_norm": 8.935502570710689,
|
||||
"learning_rate": 9.969192322306271e-06,
|
||||
"loss": 1.9603,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 0.15873015873015872,
|
||||
"grad_norm": 8.80079607342677,
|
||||
"learning_rate": 9.909643486313533e-06,
|
||||
"loss": 1.8778,
|
||||
"step": 70
|
||||
},
|
||||
{
|
||||
"epoch": 0.18140589569160998,
|
||||
"grad_norm": 8.59675770690491,
|
||||
"learning_rate": 9.819210792799711e-06,
|
||||
"loss": 1.833,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 0.20408163265306123,
|
||||
"grad_norm": 8.284836247534097,
|
||||
"learning_rate": 9.698463103929542e-06,
|
||||
"loss": 1.861,
|
||||
"step": 90
|
||||
},
|
||||
{
|
||||
"epoch": 0.22675736961451248,
|
||||
"grad_norm": 8.453538489437795,
|
||||
"learning_rate": 9.548159976772593e-06,
|
||||
"loss": 1.8362,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 0.2494331065759637,
|
||||
"grad_norm": 8.406133001405129,
|
||||
"learning_rate": 9.369246885348926e-06,
|
||||
"loss": 1.8492,
|
||||
"step": 110
|
||||
},
|
||||
{
|
||||
"epoch": 0.272108843537415,
|
||||
"grad_norm": 8.511493869719477,
|
||||
"learning_rate": 9.162849273173857e-06,
|
||||
"loss": 1.804,
|
||||
"step": 120
|
||||
},
|
||||
{
|
||||
"epoch": 0.2947845804988662,
|
||||
"grad_norm": 8.49022348327543,
|
||||
"learning_rate": 8.930265473713939e-06,
|
||||
"loss": 1.8814,
|
||||
"step": 130
|
||||
},
|
||||
{
|
||||
"epoch": 0.31746031746031744,
|
||||
"grad_norm": 7.902180291622302,
|
||||
"learning_rate": 8.672958543287666e-06,
|
||||
"loss": 1.8157,
|
||||
"step": 140
|
||||
},
|
||||
{
|
||||
"epoch": 0.3401360544217687,
|
||||
"grad_norm": 7.90256921969111,
|
||||
"learning_rate": 8.392547057785662e-06,
|
||||
"loss": 1.8149,
|
||||
"step": 150
|
||||
},
|
||||
{
|
||||
"epoch": 0.36281179138321995,
|
||||
"grad_norm": 8.21371062065736,
|
||||
"learning_rate": 8.090794931103026e-06,
|
||||
"loss": 1.8276,
|
||||
"step": 160
|
||||
},
|
||||
{
|
||||
"epoch": 0.3854875283446712,
|
||||
"grad_norm": 8.353220761999664,
|
||||
"learning_rate": 7.769600319330553e-06,
|
||||
"loss": 1.8336,
|
||||
"step": 170
|
||||
},
|
||||
{
|
||||
"epoch": 0.40816326530612246,
|
||||
"grad_norm": 7.670568800909667,
|
||||
"learning_rate": 7.430983680502344e-06,
|
||||
"loss": 1.7933,
|
||||
"step": 180
|
||||
},
|
||||
{
|
||||
"epoch": 0.4308390022675737,
|
||||
"grad_norm": 8.403616883059525,
|
||||
"learning_rate": 7.0770750650094335e-06,
|
||||
"loss": 1.7792,
|
||||
"step": 190
|
||||
},
|
||||
{
|
||||
"epoch": 0.45351473922902497,
|
||||
"grad_norm": 8.844340357606097,
|
||||
"learning_rate": 6.710100716628345e-06,
|
||||
"loss": 1.7818,
|
||||
"step": 200
|
||||
},
|
||||
{
|
||||
"epoch": 0.47619047619047616,
|
||||
"grad_norm": 8.841358454595989,
|
||||
"learning_rate": 6.332369068450175e-06,
|
||||
"loss": 1.7505,
|
||||
"step": 210
|
||||
},
|
||||
{
|
||||
"epoch": 0.4988662131519274,
|
||||
"grad_norm": 8.151442107791517,
|
||||
"learning_rate": 5.946256221802052e-06,
|
||||
"loss": 1.7417,
|
||||
"step": 220
|
||||
},
|
||||
{
|
||||
"epoch": 0.5215419501133787,
|
||||
"grad_norm": 8.842639529027162,
|
||||
"learning_rate": 5.5541909995050554e-06,
|
||||
"loss": 1.8863,
|
||||
"step": 230
|
||||
},
|
||||
{
|
||||
"epoch": 0.54421768707483,
|
||||
"grad_norm": 8.942238457804374,
|
||||
"learning_rate": 5.15863966749034e-06,
|
||||
"loss": 1.7361,
|
||||
"step": 240
|
||||
},
|
||||
{
|
||||
"epoch": 0.5668934240362812,
|
||||
"grad_norm": 7.909161685234583,
|
||||
"learning_rate": 4.762090420881289e-06,
|
||||
"loss": 1.7598,
|
||||
"step": 250
|
||||
},
|
||||
{
|
||||
"epoch": 0.5895691609977324,
|
||||
"grad_norm": 8.300775125740197,
|
||||
"learning_rate": 4.367037732131254e-06,
|
||||
"loss": 1.7735,
|
||||
"step": 260
|
||||
},
|
||||
{
|
||||
"epoch": 0.6122448979591837,
|
||||
"grad_norm": 8.568777980712424,
|
||||
"learning_rate": 3.975966659674048e-06,
|
||||
"loss": 1.8305,
|
||||
"step": 270
|
||||
},
|
||||
{
|
||||
"epoch": 0.6349206349206349,
|
||||
"grad_norm": 8.509247004083056,
|
||||
"learning_rate": 3.5913372157928515e-06,
|
||||
"loss": 1.747,
|
||||
"step": 280
|
||||
},
|
||||
{
|
||||
"epoch": 0.6575963718820862,
|
||||
"grad_norm": 8.662819789367495,
|
||||
"learning_rate": 3.2155688920406415e-06,
|
||||
"loss": 1.845,
|
||||
"step": 290
|
||||
},
|
||||
{
|
||||
"epoch": 0.6802721088435374,
|
||||
"grad_norm": 7.90810167705925,
|
||||
"learning_rate": 2.851025439554142e-06,
|
||||
"loss": 1.7508,
|
||||
"step": 300
|
||||
},
|
||||
{
|
||||
"epoch": 0.7029478458049887,
|
||||
"grad_norm": 8.120934896876353,
|
||||
"learning_rate": 2.5000000000000015e-06,
|
||||
"loss": 1.7302,
|
||||
"step": 310
|
||||
},
|
||||
{
|
||||
"epoch": 0.7256235827664399,
|
||||
"grad_norm": 7.90104743207417,
|
||||
"learning_rate": 2.1647006806861472e-06,
|
||||
"loss": 1.7709,
|
||||
"step": 320
|
||||
},
|
||||
{
|
||||
"epoch": 0.7482993197278912,
|
||||
"grad_norm": 7.994956455548193,
|
||||
"learning_rate": 1.8472366645773892e-06,
|
||||
"loss": 1.7113,
|
||||
"step": 330
|
||||
},
|
||||
{
|
||||
"epoch": 0.7709750566893424,
|
||||
"grad_norm": 8.297729809555948,
|
||||
"learning_rate": 1.549604942589441e-06,
|
||||
"loss": 1.6732,
|
||||
"step": 340
|
||||
},
|
||||
{
|
||||
"epoch": 0.7936507936507936,
|
||||
"grad_norm": 8.234302688214871,
|
||||
"learning_rate": 1.2736777516212267e-06,
|
||||
"loss": 1.7802,
|
||||
"step": 350
|
||||
},
|
||||
{
|
||||
"epoch": 0.8163265306122449,
|
||||
"grad_norm": 8.111160255738614,
|
||||
"learning_rate": 1.0211907973458391e-06,
|
||||
"loss": 1.7304,
|
||||
"step": 360
|
||||
},
|
||||
{
|
||||
"epoch": 0.8390022675736961,
|
||||
"grad_norm": 8.221302743184173,
|
||||
"learning_rate": 7.937323358440935e-07,
|
||||
"loss": 1.7049,
|
||||
"step": 370
|
||||
},
|
||||
{
|
||||
"epoch": 0.8616780045351474,
|
||||
"grad_norm": 8.823404084767901,
|
||||
"learning_rate": 5.927331827620902e-07,
|
||||
"loss": 1.7391,
|
||||
"step": 380
|
||||
},
|
||||
{
|
||||
"epoch": 0.8843537414965986,
|
||||
"grad_norm": 8.461681338437808,
|
||||
"learning_rate": 4.194577128396521e-07,
|
||||
"loss": 1.705,
|
||||
"step": 390
|
||||
},
|
||||
{
|
||||
"epoch": 0.9070294784580499,
|
||||
"grad_norm": 8.053890788537789,
|
||||
"learning_rate": 2.7499590642665773e-07,
|
||||
"loss": 1.7238,
|
||||
"step": 400
|
||||
},
|
||||
{
|
||||
"epoch": 0.9297052154195011,
|
||||
"grad_norm": 7.7446943674495206,
|
||||
"learning_rate": 1.6025649301821877e-07,
|
||||
"loss": 1.754,
|
||||
"step": 410
|
||||
},
|
||||
{
|
||||
"epoch": 0.9523809523809523,
|
||||
"grad_norm": 8.273064421261598,
|
||||
"learning_rate": 7.59612349389599e-08,
|
||||
"loss": 1.7399,
|
||||
"step": 420
|
||||
},
|
||||
{
|
||||
"epoch": 0.9750566893424036,
|
||||
"grad_norm": 8.377441892080089,
|
||||
"learning_rate": 2.264038713457706e-08,
|
||||
"loss": 1.7589,
|
||||
"step": 430
|
||||
},
|
||||
{
|
||||
"epoch": 0.9977324263038548,
|
||||
"grad_norm": 7.855800019403875,
|
||||
"learning_rate": 6.293616306246586e-10,
|
||||
"loss": 1.7015,
|
||||
"step": 440
|
||||
},
|
||||
{
|
||||
"epoch": 1.0,
|
||||
"step": 441,
|
||||
"total_flos": 335913418752.0,
|
||||
"train_loss": 1.8299819355378615,
|
||||
"train_runtime": 372.4977,
|
||||
"train_samples_per_second": 18.924,
|
||||
"train_steps_per_second": 1.184
|
||||
}
|
||||
],
|
||||
"logging_steps": 10,
|
||||
"max_steps": 441,
|
||||
"num_input_tokens_seen": 0,
|
||||
"num_train_epochs": 1,
|
||||
"save_steps": 500,
|
||||
"stateful_callbacks": {
|
||||
"TrainerControl": {
|
||||
"args": {
|
||||
"should_epoch_stop": false,
|
||||
"should_evaluate": false,
|
||||
"should_log": false,
|
||||
"should_save": true,
|
||||
"should_training_stop": true
|
||||
},
|
||||
"attributes": {}
|
||||
}
|
||||
},
|
||||
"total_flos": 335913418752.0,
|
||||
"train_batch_size": 1,
|
||||
"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 sha256:65800795b73ed801dc267103e495ba8e58947ad5d369073196af63f2891f4658
|
||||
size 8081
|
||||
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