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_v5_all
results: []
lc_v5_all
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: 1.5440
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 |
|---|---|---|---|
| 1.6819 | 1.0 | 666 | 1.5600 |
| 1.803 | 2.0 | 1332 | 1.5472 |
| 1.4855 | 3.0 | 1998 | 1.5450 |
| 1.4634 | 4.0 | 2664 | 1.5417 |
| 1.3477 | 5.0 | 3330 | 1.5433 |
| 1.3952 | 6.0 | 3996 | 1.5427 |
| 1.3547 | 7.0 | 4662 | 1.5435 |
| 1.7377 | 8.0 | 5328 | 1.5438 |
| 1.3231 | 9.0 | 5994 | 1.5441 |
| 1.44 | 10.0 | 6660 | 1.5440 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.2
- Pytorch 2.1.0+cu118
- Datasets 2.20.0
- Tokenizers 0.19.1