83f42180-15c1-490a-b36a-7a9624357888
This model is a fine-tuned version of Artples/L-MChat-7b on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4879
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: 0.000208
- train_batch_size: 4
- eval_batch_size: 4
- seed: 80
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Use OptimizerNames.ADAMW_BNB 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: 50
- training_steps: 500
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.0002 | 1 | 1.0814 |
| 1.3189 | 0.0094 | 50 | 0.8371 |
| 1.3853 | 0.0188 | 100 | 0.7781 |
| 1.3105 | 0.0282 | 150 | 0.7884 |
| 1.2717 | 0.0376 | 200 | 0.7464 |
| 1.2435 | 0.0470 | 250 | 0.7073 |
| 1.2082 | 0.0564 | 300 | 0.6344 |
| 1.1766 | 0.0658 | 350 | 0.5577 |
| 1.1059 | 0.0752 | 400 | 0.5161 |
| 1.0628 | 0.0846 | 450 | 0.4936 |
| 1.0453 | 0.0940 | 500 | 0.4879 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1
- Downloads last month
- 9
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no pipeline_tag.
Model tree for lesso08/83f42180-15c1-490a-b36a-7a9624357888
Base model
Artples/L-MChat-7b