metadata
license: apache-2.0
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: mistralai/Mistral-7B-v0.1
model-index:
- name: flash_attention_fine-tuned_mistral
results: []
flash_attention_fine-tuned_mistral
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: 1.1909
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: 0.0002
- train_batch_size: 1
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 2
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.01
- training_steps: 100
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.0020 | 10 | 1.2457 |
| No log | 0.0041 | 20 | 1.2098 |
| 1.3368 | 0.0061 | 30 | 1.2134 |
| 1.3368 | 0.0081 | 40 | 1.2185 |
| 1.2308 | 0.0102 | 50 | 1.2187 |
| 1.2308 | 0.0122 | 60 | 1.2190 |
| 1.2308 | 0.0142 | 70 | 1.2074 |
| 1.2921 | 0.0163 | 80 | 1.2018 |
| 1.2921 | 0.0183 | 90 | 1.1937 |
| 1.2655 | 0.0203 | 100 | 1.1909 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.1
- Pytorch 2.2.0
- Datasets 2.19.1
- Tokenizers 0.19.1