zephyr7B-b_V1
This model is a fine-tuned version of HuggingFaceH4/zephyr-7b-beta on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.2542
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: 0.0002
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_steps: 0.03
- training_steps: 100
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.5017 | 0.02 | 20 | 1.3803 |
| 1.3732 | 0.03 | 40 | 1.2863 |
| 1.3445 | 0.05 | 60 | 1.2696 |
| 1.3447 | 0.06 | 80 | 1.2579 |
| 1.3412 | 0.08 | 100 | 1.2542 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.1+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
HF Inference API was unable to determine this model's library.
Model tree for kristina-shemet/zephyr7B-b_V1
Base model
mistralai/Mistral-7B-v0.1
Finetuned
HuggingFaceH4/zephyr-7b-beta