metadata
base_model: mistralai/Mistral-7B-Instruct-v0.2
datasets:
- generator
library_name: peft
license: apache-2.0
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: ICSR_classification_finetuned_mistral_adapters_V100_test
results: []
ICSR_classification_finetuned_mistral_adapters_V100_test
This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 1.0845
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: 4
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- total_eval_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 1
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.1907 | 0.1996 | 100 | 1.1196 |
| 1.1121 | 0.3992 | 200 | 1.1080 |
| 1.1002 | 0.5988 | 300 | 1.0956 |
| 1.0871 | 0.7984 | 400 | 1.0866 |
| 1.0808 | 0.9980 | 500 | 1.0845 |
Framework versions
- PEFT 0.11.1
- Transformers 4.44.0
- Pytorch 2.2.2+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1