初始化项目，由ModelHub XC社区提供模型
Model: davidanugraha/Qwen3-4B-Instruct-2507-UserSim-SFT-Factored Source: Original Platform
This commit is contained in:
ModelHub XC
37
.gitattributes
vendored
Normal file
37
.gitattributes
vendored
Normal file
@@ -0,0 +1,37 @@
|
||||
*.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_backup/tokenizer.json 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/Qwen3-4B-Instruct-2507
|
||||
tags:
|
||||
- llama-factory
|
||||
- full
|
||||
- generated_from_trainer
|
||||
model-index:
|
||||
- name: qwen3_4b_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_4b_sft
|
||||
|
||||
This model is a fine-tuned version of [Qwen/Qwen3-4B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507) on the sft_factored 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: 4
|
||||
- gradient_accumulation_steps: 16
|
||||
- total_train_batch_size: 64
|
||||
- total_eval_batch_size: 32
|
||||
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
||||
- lr_scheduler_type: cosine
|
||||
- lr_scheduler_warmup_steps: 0.1
|
||||
- num_epochs: 5
|
||||
|
||||
### Training results
|
||||
|
||||
|
||||
|
||||
### Framework versions
|
||||
|
||||
- Transformers 5.6.0
|
||||
- Pytorch 2.12.0+cu130
|
||||
- Datasets 4.0.0
|
||||
- Tokenizers 0.22.2
|
||||
3
_tokenizer_backup/tokenizer.json
Normal file
3
_tokenizer_backup/tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
|
||||
size 11422650
|
||||
31
_tokenizer_backup/tokenizer_config.json
Normal file
31
_tokenizer_backup/tokenizer_config.json
Normal file
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"backend": "tokenizers",
|
||||
"bos_token": null,
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"extra_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|>"
|
||||
],
|
||||
"is_local": false,
|
||||
"local_files_only": true,
|
||||
"model_max_length": 1010000,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"padding_side": "right",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
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": 6.322240708254106e+17,
|
||||
"train_loss": 1.4024348258972168,
|
||||
"train_runtime": 1552.6736,
|
||||
"train_samples_per_second": 2.273,
|
||||
"train_steps_per_second": 0.039
|
||||
}
|
||||
61
chat_template.jinja
Normal file
61
chat_template.jinja
Normal file
@@ -0,0 +1,61 @@
|
||||
{%- 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 %}
|
||||
{%- 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" %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||
{%- 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' }}
|
||||
{%- endif %}
|
||||
71
config.json
Normal file
71
config.json
Normal file
@@ -0,0 +1,71 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen3ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": null,
|
||||
"dtype": "float32",
|
||||
"eos_token_id": 151645,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 2560,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 9728,
|
||||
"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",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention"
|
||||
],
|
||||
"max_position_embeddings": 262144,
|
||||
"max_window_layers": 36,
|
||||
"model_type": "qwen3",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 36,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 151643,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_parameters": {
|
||||
"rope_theta": 5000000,
|
||||
"rope_type": "default"
|
||||
},
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": true,
|
||||
"transformers_version": "5.6.0",
|
||||
"use_cache": false,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
12
generation_config.json
Normal file
12
generation_config.json
Normal file
@@ -0,0 +1,12 @@
|
||||
{
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"pad_token_id": 151643,
|
||||
"temperature": 0.7,
|
||||
"top_k": 20,
|
||||
"top_p": 0.8,
|
||||
"transformers_version": "5.6.0"
|
||||
}
|
||||
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:a7d0548a10f09e23a9f3b5ed771adaa846a246c5610369c87f4a95e2afa84713
|
||||
size 16089918232
|
||||
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.
239
tokenizer_config.json
Normal file
239
tokenizer_config.json
Normal file
@@ -0,0 +1,239 @@
|
||||
{
|
||||
"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": 1010000,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"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": 6.322240708254106e+17,
|
||||
"train_loss": 1.4024348258972168,
|
||||
"train_runtime": 1552.6736,
|
||||
"train_samples_per_second": 2.273,
|
||||
"train_steps_per_second": 0.039
|
||||
}
|
||||
61
trainer_log.jsonl
Normal file
61
trainer_log.jsonl
Normal file
@@ -0,0 +1,61 @@
|
||||
{"current_steps": 1, "total_steps": 60, "loss": 3.539058208465576, "lr": 0.0, "epoch": 0.0903954802259887, "percentage": 1.67, "elapsed_time": "0:00:26", "remaining_time": "0:25:47"}
|
||||
{"current_steps": 2, "total_steps": 60, "loss": 3.510171890258789, "lr": 1.6666666666666667e-06, "epoch": 0.1807909604519774, "percentage": 3.33, "elapsed_time": "0:00:51", "remaining_time": "0:24:54"}
|
||||
{"current_steps": 3, "total_steps": 60, "loss": 3.4764676094055176, "lr": 3.3333333333333333e-06, "epoch": 0.2711864406779661, "percentage": 5.0, "elapsed_time": "0:01:16", "remaining_time": "0:24:04"}
|
||||
{"current_steps": 4, "total_steps": 60, "loss": 3.0605616569519043, "lr": 5e-06, "epoch": 0.3615819209039548, "percentage": 6.67, "elapsed_time": "0:01:40", "remaining_time": "0:23:28"}
|
||||
{"current_steps": 5, "total_steps": 60, "loss": 2.3392772674560547, "lr": 6.666666666666667e-06, "epoch": 0.4519774011299435, "percentage": 8.33, "elapsed_time": "0:02:05", "remaining_time": "0:22:56"}
|
||||
{"current_steps": 6, "total_steps": 60, "loss": 1.9946647882461548, "lr": 8.333333333333334e-06, "epoch": 0.5423728813559322, "percentage": 10.0, "elapsed_time": "0:02:29", "remaining_time": "0:22:27"}
|
||||
{"current_steps": 7, "total_steps": 60, "loss": 1.864429235458374, "lr": 1e-05, "epoch": 0.632768361581921, "percentage": 11.67, "elapsed_time": "0:02:54", "remaining_time": "0:21:59"}
|
||||
{"current_steps": 8, "total_steps": 60, "loss": 1.7559094429016113, "lr": 9.991540791356342e-06, "epoch": 0.7231638418079096, "percentage": 13.33, "elapsed_time": "0:03:18", "remaining_time": "0:21:32"}
|
||||
{"current_steps": 9, "total_steps": 60, "loss": 1.7070744037628174, "lr": 9.966191788709716e-06, "epoch": 0.8135593220338984, "percentage": 15.0, "elapsed_time": "0:03:43", "remaining_time": "0:21:06"}
|
||||
{"current_steps": 10, "total_steps": 60, "loss": 1.576987624168396, "lr": 9.924038765061042e-06, "epoch": 0.903954802259887, "percentage": 16.67, "elapsed_time": "0:04:08", "remaining_time": "0:20:40"}
|
||||
{"current_steps": 11, "total_steps": 60, "loss": 1.5758938789367676, "lr": 9.86522435289912e-06, "epoch": 0.9943502824858758, "percentage": 18.33, "elapsed_time": "0:04:32", "remaining_time": "0:20:15"}
|
||||
{"current_steps": 12, "total_steps": 60, "loss": 1.3263113498687744, "lr": 9.789947561577445e-06, "epoch": 1.0, "percentage": 20.0, "elapsed_time": "0:04:34", "remaining_time": "0:18:16"}
|
||||
{"current_steps": 13, "total_steps": 60, "loss": 1.5225284099578857, "lr": 9.698463103929542e-06, "epoch": 1.0903954802259888, "percentage": 21.67, "elapsed_time": "0:05:40", "remaining_time": "0:20:31"}
|
||||
{"current_steps": 14, "total_steps": 60, "loss": 1.488105297088623, "lr": 9.591080534401371e-06, "epoch": 1.1807909604519775, "percentage": 23.33, "elapsed_time": "0:06:05", "remaining_time": "0:19:59"}
|
||||
{"current_steps": 15, "total_steps": 60, "loss": 1.4530308246612549, "lr": 9.468163201617063e-06, "epoch": 1.271186440677966, "percentage": 25.0, "elapsed_time": "0:06:29", "remaining_time": "0:19:28"}
|
||||
{"current_steps": 16, "total_steps": 60, "loss": 1.422749638557434, "lr": 9.330127018922195e-06, "epoch": 1.3615819209039548, "percentage": 26.67, "elapsed_time": "0:06:54", "remaining_time": "0:18:59"}
|
||||
{"current_steps": 17, "total_steps": 60, "loss": 1.433840036392212, "lr": 9.177439057064684e-06, "epoch": 1.4519774011299436, "percentage": 28.33, "elapsed_time": "0:07:18", "remaining_time": "0:18:29"}
|
||||
{"current_steps": 18, "total_steps": 60, "loss": 1.4170303344726562, "lr": 9.01061596377522e-06, "epoch": 1.542372881355932, "percentage": 30.0, "elapsed_time": "0:07:43", "remaining_time": "0:18:01"}
|
||||
{"current_steps": 19, "total_steps": 60, "loss": 1.388798713684082, "lr": 8.83022221559489e-06, "epoch": 1.6327683615819208, "percentage": 31.67, "elapsed_time": "0:08:08", "remaining_time": "0:17:33"}
|
||||
{"current_steps": 20, "total_steps": 60, "loss": 1.3863484859466553, "lr": 8.636868207865244e-06, "epoch": 1.7231638418079096, "percentage": 33.33, "elapsed_time": "0:08:32", "remaining_time": "0:17:05"}
|
||||
{"current_steps": 21, "total_steps": 60, "loss": 1.3138604164123535, "lr": 8.43120818934367e-06, "epoch": 1.8135593220338984, "percentage": 35.0, "elapsed_time": "0:08:57", "remaining_time": "0:16:38"}
|
||||
{"current_steps": 22, "total_steps": 60, "loss": 1.3569386005401611, "lr": 8.213938048432697e-06, "epoch": 1.9039548022598871, "percentage": 36.67, "elapsed_time": "0:09:22", "remaining_time": "0:16:11"}
|
||||
{"current_steps": 23, "total_steps": 60, "loss": 1.328192949295044, "lr": 7.985792958513932e-06, "epoch": 1.9943502824858759, "percentage": 38.33, "elapsed_time": "0:09:46", "remaining_time": "0:15:44"}
|
||||
{"current_steps": 24, "total_steps": 60, "loss": 1.2474285364151, "lr": 7.747544890354031e-06, "epoch": 2.0, "percentage": 40.0, "elapsed_time": "0:09:48", "remaining_time": "0:14:42"}
|
||||
{"current_steps": 25, "total_steps": 60, "loss": 1.2317988872528076, "lr": 7.500000000000001e-06, "epoch": 2.0903954802259888, "percentage": 41.67, "elapsed_time": "0:10:58", "remaining_time": "0:15:21"}
|
||||
{"current_steps": 26, "total_steps": 60, "loss": 1.2224856615066528, "lr": 7.243995901002312e-06, "epoch": 2.1807909604519775, "percentage": 43.33, "elapsed_time": "0:11:22", "remaining_time": "0:14:52"}
|
||||
{"current_steps": 27, "total_steps": 60, "loss": 1.2676887512207031, "lr": 6.980398830195785e-06, "epoch": 2.2711864406779663, "percentage": 45.0, "elapsed_time": "0:11:46", "remaining_time": "0:14:23"}
|
||||
{"current_steps": 28, "total_steps": 60, "loss": 1.2362030744552612, "lr": 6.710100716628345e-06, "epoch": 2.361581920903955, "percentage": 46.67, "elapsed_time": "0:12:11", "remaining_time": "0:13:55"}
|
||||
{"current_steps": 29, "total_steps": 60, "loss": 1.2472147941589355, "lr": 6.434016163555452e-06, "epoch": 2.4519774011299433, "percentage": 48.33, "elapsed_time": "0:12:35", "remaining_time": "0:13:27"}
|
||||
{"current_steps": 30, "total_steps": 60, "loss": 1.198156714439392, "lr": 6.153079353712201e-06, "epoch": 2.542372881355932, "percentage": 50.0, "elapsed_time": "0:12:59", "remaining_time": "0:12:59"}
|
||||
{"current_steps": 31, "total_steps": 60, "loss": 1.206047534942627, "lr": 5.8682408883346535e-06, "epoch": 2.632768361581921, "percentage": 51.67, "elapsed_time": "0:13:23", "remaining_time": "0:12:31"}
|
||||
{"current_steps": 32, "total_steps": 60, "loss": 1.1725330352783203, "lr": 5.5804645706261515e-06, "epoch": 2.7231638418079096, "percentage": 53.33, "elapsed_time": "0:13:47", "remaining_time": "0:12:04"}
|
||||
{"current_steps": 33, "total_steps": 60, "loss": 1.1297430992126465, "lr": 5.290724144552379e-06, "epoch": 2.8135593220338984, "percentage": 55.0, "elapsed_time": "0:14:11", "remaining_time": "0:11:36"}
|
||||
{"current_steps": 34, "total_steps": 60, "loss": 1.2231621742248535, "lr": 5e-06, "epoch": 2.903954802259887, "percentage": 56.67, "elapsed_time": "0:14:35", "remaining_time": "0:11:09"}
|
||||
{"current_steps": 35, "total_steps": 60, "loss": 1.1796724796295166, "lr": 4.7092758554476215e-06, "epoch": 2.994350282485876, "percentage": 58.33, "elapsed_time": "0:15:00", "remaining_time": "0:10:42"}
|
||||
{"current_steps": 36, "total_steps": 60, "loss": 1.1036558151245117, "lr": 4.4195354293738484e-06, "epoch": 3.0, "percentage": 60.0, "elapsed_time": "0:15:01", "remaining_time": "0:10:01"}
|
||||
{"current_steps": 37, "total_steps": 60, "loss": 1.158125638961792, "lr": 4.131759111665349e-06, "epoch": 3.0903954802259888, "percentage": 61.67, "elapsed_time": "0:15:59", "remaining_time": "0:09:56"}
|
||||
{"current_steps": 38, "total_steps": 60, "loss": 1.0927133560180664, "lr": 3.8469206462878e-06, "epoch": 3.1807909604519775, "percentage": 63.33, "elapsed_time": "0:16:23", "remaining_time": "0:09:29"}
|
||||
{"current_steps": 39, "total_steps": 60, "loss": 1.0715622901916504, "lr": 3.5659838364445505e-06, "epoch": 3.2711864406779663, "percentage": 65.0, "elapsed_time": "0:16:47", "remaining_time": "0:09:02"}
|
||||
{"current_steps": 40, "total_steps": 60, "loss": 1.0645561218261719, "lr": 3.289899283371657e-06, "epoch": 3.361581920903955, "percentage": 66.67, "elapsed_time": "0:17:11", "remaining_time": "0:08:35"}
|
||||
{"current_steps": 41, "total_steps": 60, "loss": 1.0882360935211182, "lr": 3.019601169804216e-06, "epoch": 3.4519774011299433, "percentage": 68.33, "elapsed_time": "0:17:35", "remaining_time": "0:08:09"}
|
||||
{"current_steps": 42, "total_steps": 60, "loss": 1.096019983291626, "lr": 2.7560040989976894e-06, "epoch": 3.542372881355932, "percentage": 70.0, "elapsed_time": "0:18:00", "remaining_time": "0:07:42"}
|
||||
{"current_steps": 43, "total_steps": 60, "loss": 1.1114509105682373, "lr": 2.5000000000000015e-06, "epoch": 3.632768361581921, "percentage": 71.67, "elapsed_time": "0:18:24", "remaining_time": "0:07:16"}
|
||||
{"current_steps": 44, "total_steps": 60, "loss": 1.0899746417999268, "lr": 2.2524551096459703e-06, "epoch": 3.7231638418079096, "percentage": 73.33, "elapsed_time": "0:18:48", "remaining_time": "0:06:50"}
|
||||
{"current_steps": 45, "total_steps": 60, "loss": 1.0599607229232788, "lr": 2.0142070414860704e-06, "epoch": 3.8135593220338984, "percentage": 75.0, "elapsed_time": "0:19:12", "remaining_time": "0:06:24"}
|
||||
{"current_steps": 46, "total_steps": 60, "loss": 1.045163869857788, "lr": 1.7860619515673034e-06, "epoch": 3.903954802259887, "percentage": 76.67, "elapsed_time": "0:19:36", "remaining_time": "0:05:58"}
|
||||
{"current_steps": 47, "total_steps": 60, "loss": 1.0834063291549683, "lr": 1.5687918106563326e-06, "epoch": 3.994350282485876, "percentage": 78.33, "elapsed_time": "0:20:00", "remaining_time": "0:05:32"}
|
||||
{"current_steps": 48, "total_steps": 60, "loss": 0.9682188034057617, "lr": 1.3631317921347564e-06, "epoch": 4.0, "percentage": 80.0, "elapsed_time": "0:20:02", "remaining_time": "0:05:00"}
|
||||
{"current_steps": 49, "total_steps": 60, "loss": 1.0497123003005981, "lr": 1.1697777844051105e-06, "epoch": 4.090395480225989, "percentage": 81.67, "elapsed_time": "0:21:02", "remaining_time": "0:04:43"}
|
||||
{"current_steps": 50, "total_steps": 60, "loss": 1.0524401664733887, "lr": 9.893840362247809e-07, "epoch": 4.1807909604519775, "percentage": 83.33, "elapsed_time": "0:21:26", "remaining_time": "0:04:17"}
|
||||
{"current_steps": 51, "total_steps": 60, "loss": 1.0490361452102661, "lr": 8.225609429353187e-07, "epoch": 4.271186440677966, "percentage": 85.0, "elapsed_time": "0:21:50", "remaining_time": "0:03:51"}
|
||||
{"current_steps": 52, "total_steps": 60, "loss": 1.036095380783081, "lr": 6.698729810778065e-07, "epoch": 4.361581920903955, "percentage": 86.67, "elapsed_time": "0:22:14", "remaining_time": "0:03:25"}
|
||||
{"current_steps": 53, "total_steps": 60, "loss": 1.0308215618133545, "lr": 5.318367983829393e-07, "epoch": 4.451977401129944, "percentage": 88.33, "elapsed_time": "0:22:38", "remaining_time": "0:02:59"}
|
||||
{"current_steps": 54, "total_steps": 60, "loss": 1.0118765830993652, "lr": 4.089194655986306e-07, "epoch": 4.5423728813559325, "percentage": 90.0, "elapsed_time": "0:23:02", "remaining_time": "0:02:33"}
|
||||
{"current_steps": 55, "total_steps": 60, "loss": 1.0313677787780762, "lr": 3.015368960704584e-07, "epoch": 4.632768361581921, "percentage": 91.67, "elapsed_time": "0:23:26", "remaining_time": "0:02:07"}
|
||||
{"current_steps": 56, "total_steps": 60, "loss": 1.0596657991409302, "lr": 2.1005243842255552e-07, "epoch": 4.72316384180791, "percentage": 93.33, "elapsed_time": "0:23:50", "remaining_time": "0:01:42"}
|
||||
{"current_steps": 57, "total_steps": 60, "loss": 1.0232012271881104, "lr": 1.3477564710088097e-07, "epoch": 4.813559322033898, "percentage": 95.0, "elapsed_time": "0:24:14", "remaining_time": "0:01:16"}
|
||||
{"current_steps": 58, "total_steps": 60, "loss": 1.0278719663619995, "lr": 7.59612349389599e-08, "epoch": 4.903954802259887, "percentage": 96.67, "elapsed_time": "0:24:38", "remaining_time": "0:00:50"}
|
||||
{"current_steps": 59, "total_steps": 60, "loss": 1.0475084781646729, "lr": 3.3808211290284886e-08, "epoch": 4.994350282485875, "percentage": 98.33, "elapsed_time": "0:25:02", "remaining_time": "0:00:25"}
|
||||
{"current_steps": 60, "total_steps": 60, "loss": 0.893081784248352, "lr": 8.459208643659122e-09, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "0:25:03", "remaining_time": "0:00:00"}
|
||||
{"current_steps": 60, "total_steps": 60, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "0:25:52", "remaining_time": "0:00:00"}
|
||||
463
trainer_state.json
Normal file
463
trainer_state.json
Normal file
@@ -0,0 +1,463 @@
|
||||
{
|
||||
"best_global_step": null,
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 5.0,
|
||||
"eval_steps": 500,
|
||||
"global_step": 60,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.0903954802259887,
|
||||
"grad_norm": 72.95352172851562,
|
||||
"learning_rate": 0.0,
|
||||
"loss": 3.539058208465576,
|
||||
"step": 1
|
||||
},
|
||||
{
|
||||
"epoch": 0.1807909604519774,
|
||||
"grad_norm": 84.62841033935547,
|
||||
"learning_rate": 1.6666666666666667e-06,
|
||||
"loss": 3.510171890258789,
|
||||
"step": 2
|
||||
},
|
||||
{
|
||||
"epoch": 0.2711864406779661,
|
||||
"grad_norm": 72.88843536376953,
|
||||
"learning_rate": 3.3333333333333333e-06,
|
||||
"loss": 3.4764676094055176,
|
||||
"step": 3
|
||||
},
|
||||
{
|
||||
"epoch": 0.3615819209039548,
|
||||
"grad_norm": 68.25614929199219,
|
||||
"learning_rate": 5e-06,
|
||||
"loss": 3.0605616569519043,
|
||||
"step": 4
|
||||
},
|
||||
{
|
||||
"epoch": 0.4519774011299435,
|
||||
"grad_norm": 28.142393112182617,
|
||||
"learning_rate": 6.666666666666667e-06,
|
||||
"loss": 2.3392772674560547,
|
||||
"step": 5
|
||||
},
|
||||
{
|
||||
"epoch": 0.5423728813559322,
|
||||
"grad_norm": 8.023438453674316,
|
||||
"learning_rate": 8.333333333333334e-06,
|
||||
"loss": 1.9946647882461548,
|
||||
"step": 6
|
||||
},
|
||||
{
|
||||
"epoch": 0.632768361581921,
|
||||
"grad_norm": 6.666532039642334,
|
||||
"learning_rate": 1e-05,
|
||||
"loss": 1.864429235458374,
|
||||
"step": 7
|
||||
},
|
||||
{
|
||||
"epoch": 0.7231638418079096,
|
||||
"grad_norm": 5.340750694274902,
|
||||
"learning_rate": 9.991540791356342e-06,
|
||||
"loss": 1.7559094429016113,
|
||||
"step": 8
|
||||
},
|
||||
{
|
||||
"epoch": 0.8135593220338984,
|
||||
"grad_norm": 4.030279159545898,
|
||||
"learning_rate": 9.966191788709716e-06,
|
||||
"loss": 1.7070744037628174,
|
||||
"step": 9
|
||||
},
|
||||
{
|
||||
"epoch": 0.903954802259887,
|
||||
"grad_norm": 2.765150308609009,
|
||||
"learning_rate": 9.924038765061042e-06,
|
||||
"loss": 1.576987624168396,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"epoch": 0.9943502824858758,
|
||||
"grad_norm": 2.4855945110321045,
|
||||
"learning_rate": 9.86522435289912e-06,
|
||||
"loss": 1.5758938789367676,
|
||||
"step": 11
|
||||
},
|
||||
{
|
||||
"epoch": 1.0,
|
||||
"grad_norm": 5.696783065795898,
|
||||
"learning_rate": 9.789947561577445e-06,
|
||||
"loss": 1.3263113498687744,
|
||||
"step": 12
|
||||
},
|
||||
{
|
||||
"epoch": 1.0903954802259888,
|
||||
"grad_norm": 2.779576539993286,
|
||||
"learning_rate": 9.698463103929542e-06,
|
||||
"loss": 1.5225284099578857,
|
||||
"step": 13
|
||||
},
|
||||
{
|
||||
"epoch": 1.1807909604519775,
|
||||
"grad_norm": 2.253300666809082,
|
||||
"learning_rate": 9.591080534401371e-06,
|
||||
"loss": 1.488105297088623,
|
||||
"step": 14
|
||||
},
|
||||
{
|
||||
"epoch": 1.271186440677966,
|
||||
"grad_norm": 1.884597897529602,
|
||||
"learning_rate": 9.468163201617063e-06,
|
||||
"loss": 1.4530308246612549,
|
||||
"step": 15
|
||||
},
|
||||
{
|
||||
"epoch": 1.3615819209039548,
|
||||
"grad_norm": 1.755130648612976,
|
||||
"learning_rate": 9.330127018922195e-06,
|
||||
"loss": 1.422749638557434,
|
||||
"step": 16
|
||||
},
|
||||
{
|
||||
"epoch": 1.4519774011299436,
|
||||
"grad_norm": 1.560288906097412,
|
||||
"learning_rate": 9.177439057064684e-06,
|
||||
"loss": 1.433840036392212,
|
||||
"step": 17
|
||||
},
|
||||
{
|
||||
"epoch": 1.542372881355932,
|
||||
"grad_norm": 1.7185840606689453,
|
||||
"learning_rate": 9.01061596377522e-06,
|
||||
"loss": 1.4170303344726562,
|
||||
"step": 18
|
||||
},
|
||||
{
|
||||
"epoch": 1.6327683615819208,
|
||||
"grad_norm": 1.4684430360794067,
|
||||
"learning_rate": 8.83022221559489e-06,
|
||||
"loss": 1.388798713684082,
|
||||
"step": 19
|
||||
},
|
||||
{
|
||||
"epoch": 1.7231638418079096,
|
||||
"grad_norm": 1.6119791269302368,
|
||||
"learning_rate": 8.636868207865244e-06,
|
||||
"loss": 1.3863484859466553,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 1.8135593220338984,
|
||||
"grad_norm": 1.2974920272827148,
|
||||
"learning_rate": 8.43120818934367e-06,
|
||||
"loss": 1.3138604164123535,
|
||||
"step": 21
|
||||
},
|
||||
{
|
||||
"epoch": 1.9039548022598871,
|
||||
"grad_norm": 1.5221943855285645,
|
||||
"learning_rate": 8.213938048432697e-06,
|
||||
"loss": 1.3569386005401611,
|
||||
"step": 22
|
||||
},
|
||||
{
|
||||
"epoch": 1.9943502824858759,
|
||||
"grad_norm": 1.5059224367141724,
|
||||
"learning_rate": 7.985792958513932e-06,
|
||||
"loss": 1.328192949295044,
|
||||
"step": 23
|
||||
},
|
||||
{
|
||||
"epoch": 2.0,
|
||||
"grad_norm": 3.393784761428833,
|
||||
"learning_rate": 7.747544890354031e-06,
|
||||
"loss": 1.2474285364151,
|
||||
"step": 24
|
||||
},
|
||||
{
|
||||
"epoch": 2.0903954802259888,
|
||||
"grad_norm": 1.4098623991012573,
|
||||
"learning_rate": 7.500000000000001e-06,
|
||||
"loss": 1.2317988872528076,
|
||||
"step": 25
|
||||
},
|
||||
{
|
||||
"epoch": 2.1807909604519775,
|
||||
"grad_norm": 1.3200597763061523,
|
||||
"learning_rate": 7.243995901002312e-06,
|
||||
"loss": 1.2224856615066528,
|
||||
"step": 26
|
||||
},
|
||||
{
|
||||
"epoch": 2.2711864406779663,
|
||||
"grad_norm": 1.4033938646316528,
|
||||
"learning_rate": 6.980398830195785e-06,
|
||||
"loss": 1.2676887512207031,
|
||||
"step": 27
|
||||
},
|
||||
{
|
||||
"epoch": 2.361581920903955,
|
||||
"grad_norm": 1.3782753944396973,
|
||||
"learning_rate": 6.710100716628345e-06,
|
||||
"loss": 1.2362030744552612,
|
||||
"step": 28
|
||||
},
|
||||
{
|
||||
"epoch": 2.4519774011299433,
|
||||
"grad_norm": 1.2505719661712646,
|
||||
"learning_rate": 6.434016163555452e-06,
|
||||
"loss": 1.2472147941589355,
|
||||
"step": 29
|
||||
},
|
||||
{
|
||||
"epoch": 2.542372881355932,
|
||||
"grad_norm": 1.2195472717285156,
|
||||
"learning_rate": 6.153079353712201e-06,
|
||||
"loss": 1.198156714439392,
|
||||
"step": 30
|
||||
},
|
||||
{
|
||||
"epoch": 2.632768361581921,
|
||||
"grad_norm": 1.2974107265472412,
|
||||
"learning_rate": 5.8682408883346535e-06,
|
||||
"loss": 1.206047534942627,
|
||||
"step": 31
|
||||
},
|
||||
{
|
||||
"epoch": 2.7231638418079096,
|
||||
"grad_norm": 1.3183085918426514,
|
||||
"learning_rate": 5.5804645706261515e-06,
|
||||
"loss": 1.1725330352783203,
|
||||
"step": 32
|
||||
},
|
||||
{
|
||||
"epoch": 2.8135593220338984,
|
||||
"grad_norm": 1.2263569831848145,
|
||||
"learning_rate": 5.290724144552379e-06,
|
||||
"loss": 1.1297430992126465,
|
||||
"step": 33
|
||||
},
|
||||
{
|
||||
"epoch": 2.903954802259887,
|
||||
"grad_norm": 1.3964532613754272,
|
||||
"learning_rate": 5e-06,
|
||||
"loss": 1.2231621742248535,
|
||||
"step": 34
|
||||
},
|
||||
{
|
||||
"epoch": 2.994350282485876,
|
||||
"grad_norm": 1.325929045677185,
|
||||
"learning_rate": 4.7092758554476215e-06,
|
||||
"loss": 1.1796724796295166,
|
||||
"step": 35
|
||||
},
|
||||
{
|
||||
"epoch": 3.0,
|
||||
"grad_norm": 3.460449695587158,
|
||||
"learning_rate": 4.4195354293738484e-06,
|
||||
"loss": 1.1036558151245117,
|
||||
"step": 36
|
||||
},
|
||||
{
|
||||
"epoch": 3.0903954802259888,
|
||||
"grad_norm": 1.3740507364273071,
|
||||
"learning_rate": 4.131759111665349e-06,
|
||||
"loss": 1.158125638961792,
|
||||
"step": 37
|
||||
},
|
||||
{
|
||||
"epoch": 3.1807909604519775,
|
||||
"grad_norm": 1.2848109006881714,
|
||||
"learning_rate": 3.8469206462878e-06,
|
||||
"loss": 1.0927133560180664,
|
||||
"step": 38
|
||||
},
|
||||
{
|
||||
"epoch": 3.2711864406779663,
|
||||
"grad_norm": 1.12660813331604,
|
||||
"learning_rate": 3.5659838364445505e-06,
|
||||
"loss": 1.0715622901916504,
|
||||
"step": 39
|
||||
},
|
||||
{
|
||||
"epoch": 3.361581920903955,
|
||||
"grad_norm": 1.301928997039795,
|
||||
"learning_rate": 3.289899283371657e-06,
|
||||
"loss": 1.0645561218261719,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 3.4519774011299433,
|
||||
"grad_norm": 1.1756473779678345,
|
||||
"learning_rate": 3.019601169804216e-06,
|
||||
"loss": 1.0882360935211182,
|
||||
"step": 41
|
||||
},
|
||||
{
|
||||
"epoch": 3.542372881355932,
|
||||
"grad_norm": 1.3334362506866455,
|
||||
"learning_rate": 2.7560040989976894e-06,
|
||||
"loss": 1.096019983291626,
|
||||
"step": 42
|
||||
},
|
||||
{
|
||||
"epoch": 3.632768361581921,
|
||||
"grad_norm": 1.1457642316818237,
|
||||
"learning_rate": 2.5000000000000015e-06,
|
||||
"loss": 1.1114509105682373,
|
||||
"step": 43
|
||||
},
|
||||
{
|
||||
"epoch": 3.7231638418079096,
|
||||
"grad_norm": 1.169641137123108,
|
||||
"learning_rate": 2.2524551096459703e-06,
|
||||
"loss": 1.0899746417999268,
|
||||
"step": 44
|
||||
},
|
||||
{
|
||||
"epoch": 3.8135593220338984,
|
||||
"grad_norm": 1.1258875131607056,
|
||||
"learning_rate": 2.0142070414860704e-06,
|
||||
"loss": 1.0599607229232788,
|
||||
"step": 45
|
||||
},
|
||||
{
|
||||
"epoch": 3.903954802259887,
|
||||
"grad_norm": 1.2110517024993896,
|
||||
"learning_rate": 1.7860619515673034e-06,
|
||||
"loss": 1.045163869857788,
|
||||
"step": 46
|
||||
},
|
||||
{
|
||||
"epoch": 3.994350282485876,
|
||||
"grad_norm": 1.1686667203903198,
|
||||
"learning_rate": 1.5687918106563326e-06,
|
||||
"loss": 1.0834063291549683,
|
||||
"step": 47
|
||||
},
|
||||
{
|
||||
"epoch": 4.0,
|
||||
"grad_norm": 3.928598403930664,
|
||||
"learning_rate": 1.3631317921347564e-06,
|
||||
"loss": 0.9682188034057617,
|
||||
"step": 48
|
||||
},
|
||||
{
|
||||
"epoch": 4.090395480225989,
|
||||
"grad_norm": 1.1086369752883911,
|
||||
"learning_rate": 1.1697777844051105e-06,
|
||||
"loss": 1.0497123003005981,
|
||||
"step": 49
|
||||
},
|
||||
{
|
||||
"epoch": 4.1807909604519775,
|
||||
"grad_norm": 1.102365493774414,
|
||||
"learning_rate": 9.893840362247809e-07,
|
||||
"loss": 1.0524401664733887,
|
||||
"step": 50
|
||||
},
|
||||
{
|
||||
"epoch": 4.271186440677966,
|
||||
"grad_norm": 1.0737630128860474,
|
||||
"learning_rate": 8.225609429353187e-07,
|
||||
"loss": 1.0490361452102661,
|
||||
"step": 51
|
||||
},
|
||||
{
|
||||
"epoch": 4.361581920903955,
|
||||
"grad_norm": 1.0565601587295532,
|
||||
"learning_rate": 6.698729810778065e-07,
|
||||
"loss": 1.036095380783081,
|
||||
"step": 52
|
||||
},
|
||||
{
|
||||
"epoch": 4.451977401129944,
|
||||
"grad_norm": 0.9903903007507324,
|
||||
"learning_rate": 5.318367983829393e-07,
|
||||
"loss": 1.0308215618133545,
|
||||
"step": 53
|
||||
},
|
||||
{
|
||||
"epoch": 4.5423728813559325,
|
||||
"grad_norm": 0.990847110748291,
|
||||
"learning_rate": 4.089194655986306e-07,
|
||||
"loss": 1.0118765830993652,
|
||||
"step": 54
|
||||
},
|
||||
{
|
||||
"epoch": 4.632768361581921,
|
||||
"grad_norm": 1.103642463684082,
|
||||
"learning_rate": 3.015368960704584e-07,
|
||||
"loss": 1.0313677787780762,
|
||||
"step": 55
|
||||
},
|
||||
{
|
||||
"epoch": 4.72316384180791,
|
||||
"grad_norm": 1.1910076141357422,
|
||||
"learning_rate": 2.1005243842255552e-07,
|
||||
"loss": 1.0596657991409302,
|
||||
"step": 56
|
||||
},
|
||||
{
|
||||
"epoch": 4.813559322033898,
|
||||
"grad_norm": 0.9572083950042725,
|
||||
"learning_rate": 1.3477564710088097e-07,
|
||||
"loss": 1.0232012271881104,
|
||||
"step": 57
|
||||
},
|
||||
{
|
||||
"epoch": 4.903954802259887,
|
||||
"grad_norm": 5.011074542999268,
|
||||
"learning_rate": 7.59612349389599e-08,
|
||||
"loss": 1.0278719663619995,
|
||||
"step": 58
|
||||
},
|
||||
{
|
||||
"epoch": 4.994350282485875,
|
||||
"grad_norm": 1.3123799562454224,
|
||||
"learning_rate": 3.3808211290284886e-08,
|
||||
"loss": 1.0475084781646729,
|
||||
"step": 59
|
||||
},
|
||||
{
|
||||
"epoch": 5.0,
|
||||
"grad_norm": 3.651301145553589,
|
||||
"learning_rate": 8.459208643659122e-09,
|
||||
"loss": 0.893081784248352,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 5.0,
|
||||
"step": 60,
|
||||
"total_flos": 6.322240708254106e+17,
|
||||
"train_loss": 1.4024348258972168,
|
||||
"train_runtime": 1552.6736,
|
||||
"train_samples_per_second": 2.273,
|
||||
"train_steps_per_second": 0.039
|
||||
}
|
||||
],
|
||||
"logging_steps": 1,
|
||||
"max_steps": 60,
|
||||
"num_input_tokens_seen": 0,
|
||||
"num_train_epochs": 5,
|
||||
"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": 6.322240708254106e+17,
|
||||
"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 sha256:2d17c9090ae2776058108280c412758bd065fb0523b18d46e7f70bdd0118687a
|
||||
size 5905
|
||||
BIN
training_loss.png
Normal file
BIN
training_loss.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 32 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