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_v3_mix_all
results: []
lc_v3_mix_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: 1.3632
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: 6
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.3736 | 1.0 | 179 | 1.3915 |
| 1.4252 | 2.0 | 358 | 1.3709 |
| 1.2687 | 3.0 | 537 | 1.3638 |
| 1.414 | 4.0 | 716 | 1.3626 |
| 1.3064 | 5.0 | 895 | 1.3631 |
| 1.2414 | 6.0 | 1074 | 1.3632 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.2
- Pytorch 2.1.0+cu118
- Datasets 2.20.0
- Tokenizers 0.19.1