Deliverde-T1
This model is a fine-tuned version of TheBloke/Mistral-7B-Instruct-v0.2-GPTQ on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.3112
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: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.924 | 0.8 | 1 | 1.6026 |
| 1.8894 | 1.6 | 2 | 1.5693 |
| 1.7738 | 2.4 | 3 | 1.5053 |
| 0.8471 | 4.0 | 5 | 1.4148 |
| 1.6014 | 4.8 | 6 | 1.3805 |
| 1.5242 | 5.6 | 7 | 1.3532 |
| 1.4987 | 6.4 | 8 | 1.3321 |
| 0.7354 | 8.0 | 10 | 1.3112 |
Framework versions
- PEFT 0.10.0
- Transformers 4.38.2
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 3
Model tree for Santiagodf19/Deliverde-T1
Base model
mistralai/Mistral-7B-Instruct-v0.2
Quantized
TheBloke/Mistral-7B-Instruct-v0.2-GPTQ