agrobot-ft
This model is a fine-tuned version of meta-llama/Llama-2-7b-chat-hf on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.7572
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 |
---|---|---|---|
2.2583 | 1.0 | 102 | 1.8621 |
1.7686 | 2.0 | 205 | 1.7897 |
1.7092 | 3.0 | 307 | 1.7582 |
1.6363 | 4.0 | 410 | 1.7404 |
1.5957 | 5.0 | 512 | 1.7323 |
1.5346 | 6.0 | 615 | 1.7371 |
1.504 | 7.0 | 717 | 1.7338 |
1.4543 | 8.0 | 820 | 1.7435 |
1.4418 | 9.0 | 922 | 1.7536 |
1.4048 | 9.95 | 1020 | 1.7572 |
Framework versions
- PEFT 0.10.0
- Transformers 4.39.3
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 14
Unable to determine this model’s pipeline type. Check the
docs
.