初始化项目，由ModelHub XC社区提供模型
Model: open-sci/sft__ot30k_Qwen3-1.7B-Base-SFT-Tulu3-decontaminated 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
|
||||
63
README.md
Normal file
63
README.md
Normal file
@@ -0,0 +1,63 @@
|
||||
---
|
||||
library_name: transformers
|
||||
license: other
|
||||
base_model: ali-elganzory/Qwen3-1.7B-Base-SFT-Tulu3-decontaminated
|
||||
tags:
|
||||
- llama-factory
|
||||
- full
|
||||
- generated_from_trainer
|
||||
datasets:
|
||||
- arrow
|
||||
model-index:
|
||||
- name: sft__f679a5c592c8dffb__b4bfd93d8848cb99e95a__qwen3-steps
|
||||
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. -->
|
||||
|
||||
# sft__f679a5c592c8dffb__b4bfd93d8848cb99e95a__qwen3-steps
|
||||
|
||||
This model is a fine-tuned version of [ali-elganzory/Qwen3-1.7B-Base-SFT-Tulu3-decontaminated](https://huggingface.co/ali-elganzory/Qwen3-1.7B-Base-SFT-Tulu3-decontaminated) on the /gpfs/scratch/ehpc524/ot/hf_hub/datasets/open-thoughts_open_thoughts3-1.2_m_30000_samples/default/0.0.0/f679a5c592c8dffb 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: 4e-05
|
||||
- train_batch_size: 1
|
||||
- eval_batch_size: 8
|
||||
- seed: 42
|
||||
- distributed_type: multi-GPU
|
||||
- num_devices: 32
|
||||
- gradient_accumulation_steps: 4
|
||||
- total_train_batch_size: 128
|
||||
- total_eval_batch_size: 256
|
||||
- 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: 5.0
|
||||
|
||||
### Training results
|
||||
|
||||
|
||||
|
||||
### Framework versions
|
||||
|
||||
- Transformers 5.5.0
|
||||
- Pytorch 2.10.0+cu128
|
||||
- Datasets 4.8.4
|
||||
- Tokenizers 0.22.2
|
||||
12
all_results.json
Normal file
12
all_results.json
Normal file
@@ -0,0 +1,12 @@
|
||||
{
|
||||
"epoch": 5.0,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.4691426753997803,
|
||||
"total_flos": 1658037051588608.0,
|
||||
"train_loss": 1.0214215231449046,
|
||||
"train_runtime": 6105.894,
|
||||
"train_samples_per_second": 24.566,
|
||||
"train_steps_per_second": 0.192,
|
||||
"valid_targets_mean": 13499.5,
|
||||
"valid_targets_min": 3345
|
||||
}
|
||||
25
chat_template.jinja
Normal file
25
chat_template.jinja
Normal file
@@ -0,0 +1,25 @@
|
||||
|
||||
{%- for message in messages -%}
|
||||
{%- if message["role"] == "system" -%}
|
||||
{{- "<|system|>
|
||||
" + message["content"] + "
|
||||
" -}}
|
||||
{%- elif message["role"] == "user" -%}
|
||||
{{- "<|user|>
|
||||
" + message["content"] + "
|
||||
" -}}
|
||||
{%- elif message["role"] == "assistant" -%}
|
||||
{%- if not loop.last -%}
|
||||
{{- "<|assistant|>
|
||||
" + message["content"] + eos_token + "
|
||||
" -}}
|
||||
{%- else -%}
|
||||
{{- "<|assistant|>
|
||||
" + message["content"] + eos_token -}}
|
||||
{%- endif -%}
|
||||
{%- endif -%}
|
||||
{%- if loop.last and add_generation_prompt -%}
|
||||
{{- "<|assistant|>
|
||||
" -}}
|
||||
{%- endif -%}
|
||||
{%- endfor -%}
|
||||
63
config.json
Normal file
63
config.json
Normal file
@@ -0,0 +1,63 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen3ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": null,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 151645,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 2048,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 6144,
|
||||
"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": 32768,
|
||||
"max_window_layers": 28,
|
||||
"model_type": "qwen3",
|
||||
"num_attention_heads": 16,
|
||||
"num_hidden_layers": 28,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 151643,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_parameters": {
|
||||
"rope_theta": 1000000,
|
||||
"rope_type": "default"
|
||||
},
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": true,
|
||||
"transformers_version": "5.5.0",
|
||||
"use_cache": false,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151680
|
||||
}
|
||||
9
generation_config.json
Normal file
9
generation_config.json
Normal file
@@ -0,0 +1,9 @@
|
||||
{
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"max_new_tokens": 2048,
|
||||
"pad_token_id": 151643,
|
||||
"transformers_version": "5.5.0"
|
||||
}
|
||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d87eea7f22155ab353ad6650b9788e7ad509b4919aac245c3746e5abdb62af2f
|
||||
size 3440137032
|
||||
12
run_summary.json
Normal file
12
run_summary.json
Normal file
@@ -0,0 +1,12 @@
|
||||
{
|
||||
"agent_name": "f679a5c592c8dffb",
|
||||
"training_start": null,
|
||||
"training_end": null,
|
||||
"created_by": "DCAgent",
|
||||
"base_model_name": "/gpfs/scratch/ehpc524/ot/hf_hub/models--ali-elganzory--Qwen3-1.7B-Base-SFT-Tulu3-decontaminated/snapshots/b4bfd93d8848cb99e95aca440452d4a50fafbfce/",
|
||||
"dataset_name": "/gpfs/scratch/ehpc524/ot/hf_hub/datasets/open-thoughts_open_thoughts3-1.2_m_30000_samples/default/0.0.0/f679a5c592c8dffb",
|
||||
"training_type": "SFT",
|
||||
"training_parameters": "https://huggingface.co/mlfoundations-dev/sft__f679a5c592c8dffb__b4bfd93d8848cb99e95a__qwen3-steps/blob/main/config.json",
|
||||
"wandb_link": null,
|
||||
"traces_location_s3": null
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:cfb71699fc3ef7cacb0ce6b3d288d36e427ccb020f0ef5db77461a572d25481d
|
||||
size 11423212
|
||||
15
tokenizer_config.json
Normal file
15
tokenizer_config.json
Normal file
@@ -0,0 +1,15 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"backend": "tokenizers",
|
||||
"bos_token": null,
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"is_local": true,
|
||||
"model_max_length": 16384,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"padding_side": "right",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
12
train_results.json
Normal file
12
train_results.json
Normal file
@@ -0,0 +1,12 @@
|
||||
{
|
||||
"epoch": 5.0,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.4691426753997803,
|
||||
"total_flos": 1658037051588608.0,
|
||||
"train_loss": 1.0214215231449046,
|
||||
"train_runtime": 6105.894,
|
||||
"train_samples_per_second": 24.566,
|
||||
"train_steps_per_second": 0.192,
|
||||
"valid_targets_mean": 13499.5,
|
||||
"valid_targets_min": 3345
|
||||
}
|
||||
1176
trainer_log.jsonl
Normal file
1176
trainer_log.jsonl
Normal file
File diff suppressed because it is too large
Load Diff
12972
trainer_state.json
Normal file
12972
trainer_state.json
Normal file
File diff suppressed because it is too large
Load Diff
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 sha256:2985b9819b9dbe766cf58a530ff5ee92c9f38c34e4a09aa80a36eb24c5bc2175
|
||||
size 7953
|
||||
BIN
training_loss.png
Normal file
BIN
training_loss.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 50 KiB |
Reference in New Issue
Block a user