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: 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-1.5B on the reasoning-multilingual-R1-Llama-70B-train dataset. It achieves the following results on the evaluation set:
- Loss: 0.9008
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 |
|---|---|---|---|
| 0.9946 | 0.1020 | 10 | 0.9808 |
| 1.042 | 0.2041 | 20 | 0.9511 |
| 1.1236 | 0.3061 | 30 | 0.9309 |
| 1.238 | 0.4082 | 40 | 0.9211 |
| 0.8178 | 0.5102 | 50 | 0.9119 |
| 0.951 | 0.6122 | 60 | 0.9066 |
| 0.7869 | 0.7143 | 70 | 0.9032 |
| 1.2626 | 0.8163 | 80 | 0.9012 |
| 1.2385 | 0.9184 | 90 | 0.9009 |
Framework versions
- Transformers 4.48.1
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.21.0