metadata
library_name: transformers
license: other
base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
tags:
- llama-factory
- full
- generated_from_trainer
model-index:
- name: reasoning-multilingual-R1-Llama-70B-train
results: []
reasoning-multilingual-R1-Llama-70B-train
This model is a fine-tuned version of deepseek-ai/DeepSeek-R1-Distill-Qwen-7B on the reasoning-multilingual-R1-Llama-70B-train dataset. It achieves the following results on the evaluation set:
- Loss: 0.6135
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: 8
- total_train_batch_size: 8
- total_eval_batch_size: 8
- 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
- lr_scheduler_warmup_ratio: 0.01
- num_epochs: 1.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.9061 | 0.1089 | 11 | 0.7100 |
| 0.6565 | 0.2178 | 22 | 0.6685 |
| 0.601 | 0.3267 | 33 | 0.6480 |
| 0.7668 | 0.4356 | 44 | 0.6343 |
| 0.8058 | 0.5446 | 55 | 0.6248 |
| 0.675 | 0.6535 | 66 | 0.6190 |
| 0.5383 | 0.7624 | 77 | 0.6156 |
| 0.5044 | 0.8713 | 88 | 0.6139 |
| 0.6322 | 0.9802 | 99 | 0.6136 |
Framework versions
- Transformers 4.46.1
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.20.3