metadata

library_name: transformers
license: other
base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
tags:
  - llama-factory
  - full
  - generated_from_trainer
model-index:
  - name: Distill_DeepScaleR_7B_Preview
    results: []

Distill_DeepScaleR_7B_Preview

This model is a fine-tuned version of deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B on the Distill_DeepScaleR_7B_Preview dataset. It achieves the following results on the evaluation set:

Loss: 0.3696

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: 1
seed: 42
distributed_type: multi-GPU
num_devices: 4
total_train_batch_size: 4
total_eval_batch_size: 4
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
0.3007	0.7788	500	0.3660
0.1601	1.5576	1000	0.3697

Framework versions

Transformers 4.46.1
Pytorch 2.6.0+cu124
Datasets 3.1.0
Tokenizers 0.20.3