metadata
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: mistralai/Mistral-7B-v0.1
model-index:
- name: cot_method2test-mistral-7B_v0
results: []
cot_method2test-mistral-7B_v0
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: 1.7398
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: 2.5e-05
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 5
- training_steps: 100
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.9073 | 2.67 | 10 | 1.4951 |
| 1.6109 | 5.33 | 20 | 1.4208 |
| 1.2815 | 8.0 | 30 | 1.3794 |
| 0.9683 | 10.67 | 40 | 1.3829 |
| 0.6975 | 13.33 | 50 | 1.4201 |
| 0.4513 | 16.0 | 60 | 1.4823 |
| 0.2964 | 18.67 | 70 | 1.5715 |
| 0.1858 | 21.33 | 80 | 1.6517 |
| 0.1355 | 24.0 | 90 | 1.7184 |
| 0.1086 | 26.67 | 100 | 1.7398 |
Framework versions
- PEFT 0.7.2.dev0
- Transformers 4.37.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0