VOOZH about

URL: https://huggingface.co/kazuyamaa/DeepSeek-R1-Distill-Qwen-14B-axolotl-int-v1.0-merged

⇱ kazuyamaa/DeepSeek-R1-Distill-Qwen-14B-axolotl-int-v1.0-merged · Hugging Face

👁 Built with Axolotl


DeepSeek-R1-Distill-Qwen-14B-axolotl-int-v1.0

This model is a fine-tuned version of deepseek-ai/DeepSeek-R1-Distill-Qwen-14B on the kanhatakeyama/ramdom-to-fixed-multiturn-Calm3, the Aratako/Magpie-Tanuki-Qwen2.5-72B-Answered, the Aratako/magpie-qwen2.5-32b-reasoning-100k-formatted, the Aratako/magpie-reasoning-llama-nemotron-70b-100k-filtered, the Aratako/Open-Platypus-Japanese-masked-formatted, the kanhatakeyama/wizardlm8x22b-logical-math-coding-sft_additional-ja, the Aratako/magpie-ultra-v0.1-formatted, the Aratako/orca-agentinstruct-1M-v1-selected and the Aratako/Synthetic-JP-EN-Coding-Dataset-801k-50k datasets. It achieves the following results on the evaluation set:

  • Loss: 0.6711

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: 0.0003
  • train_batch_size: 1
  • eval_batch_size: 1
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 2
  • gradient_accumulation_steps: 16
  • total_train_batch_size: 32
  • total_eval_batch_size: 2
  • optimizer: Use paged_adamw_8bit 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: 10
  • num_epochs: 1.0

Training results

Training Loss Epoch Step Validation Loss
1.1079 0.0015 1 1.0631
0.8387 0.0763 50 0.7640
0.7109 0.1526 100 0.7312
0.7324 0.2289 150 0.7155
0.8239 0.3051 200 0.7045
0.7019 0.3814 250 0.6967
0.8834 0.4577 300 0.6910
0.7097 0.5340 350 0.6857
0.6659 0.6103 400 0.6821
0.6755 0.6866 450 0.6785
0.6465 0.7628 500 0.6755
0.6697 0.8391 550 0.6735
0.8425 0.9154 600 0.6720
0.6461 0.9917 650 0.6711

Framework versions

  • PEFT 0.14.0
  • Transformers 4.49.0
  • Pytorch 2.5.1+cu124
  • Datasets 3.2.0
  • Tokenizers 0.21.1
Downloads last month
-
Safetensors
Model size
15B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for kazuyamaa/DeepSeek-R1-Distill-Qwen-14B-axolotl-int-v1.0-merged

Adapter
(113)
this model

Datasets used to train kazuyamaa/DeepSeek-R1-Distill-Qwen-14B-axolotl-int-v1.0-merged