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: 1.4321
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: 30
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.9547 | 0.8 | 3 | 1.5492 |
| 1.9453 | 1.6 | 6 | 1.5327 |
| 1.8726 | 2.4 | 9 | 1.5110 |
| 1.741 | 3.2 | 12 | 1.4910 |
| 1.6775 | 4.0 | 15 | 1.4716 |
| 1.6711 | 4.8 | 18 | 1.4552 |
| 1.5349 | 5.6 | 21 | 1.4439 |
| 1.4408 | 6.4 | 24 | 1.4385 |
| 1.5928 | 7.2 | 27 | 1.4325 |
| 1.4587 | 8.0 | 30 | 1.4321 |
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