metadata
base_model: mistralai/Mistral-7B-v0.1
library_name: peft
license: apache-2.0
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: lc_v6_select
results: []
lc_v6_select
This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.3259
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: 2e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.3688 | 1.0 | 143 | 1.3646 |
| 1.4368 | 2.0 | 286 | 1.3329 |
| 1.2987 | 3.0 | 429 | 1.3244 |
| 1.2494 | 4.0 | 572 | 1.3218 |
| 1.2701 | 5.0 | 715 | 1.3208 |
| 1.2764 | 6.0 | 858 | 1.3242 |
| 1.2722 | 7.0 | 1001 | 1.3255 |
| 1.3296 | 8.0 | 1144 | 1.3260 |
| 1.1208 | 9.0 | 1287 | 1.3257 |
| 1.1742 | 10.0 | 1430 | 1.3259 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.2
- Pytorch 2.1.0+cu118
- Datasets 2.20.0
- Tokenizers 0.19.1