811fc02f-639b-4a02-a910-b3d27c381800
This model is a fine-tuned version of NousResearch/Hermes-2-Pro-Mistral-7B on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.7127
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: 0.000212
- train_batch_size: 4
- eval_batch_size: 4
- seed: 120
- 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 | 0.0006 | 1 | 3.5213 |
| 4.3542 | 0.0318 | 50 | 3.1191 |
| 4.8019 | 0.0635 | 100 | 4.3862 |
| 4.3665 | 0.0953 | 150 | 3.0645 |
| 4.2877 | 0.1270 | 200 | 2.6198 |
| 3.6609 | 0.1588 | 250 | 2.8724 |
| 4.24 | 0.1905 | 300 | 2.0456 |
| 3.5937 | 0.2223 | 350 | 1.9644 |
| 3.08 | 0.2540 | 400 | 1.8236 |
| 3.5315 | 0.2858 | 450 | 1.7334 |
| 3.0243 | 0.3176 | 500 | 1.7127 |
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
- 8
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 lesso12/811fc02f-639b-4a02-a910-b3d27c381800
Base model
mistralai/Mistral-7B-v0.1
Finetuned
NousResearch/Hermes-2-Pro-Mistral-7B