mistral-pennlaine-finetune
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: 1.4428
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
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1
- training_steps: 500
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
0.5433 | 25.0 | 25 | 1.4043 |
0.016 | 50.0 | 50 | 1.5889 |
0.0001 | 75.0 | 75 | 1.4304 |
0.0002 | 100.0 | 100 | 1.4221 |
0.0 | 125.0 | 125 | 1.4181 |
0.0001 | 150.0 | 150 | 1.4378 |
0.0001 | 175.0 | 175 | 1.4395 |
0.0 | 200.0 | 200 | 1.4443 |
0.0001 | 225.0 | 225 | 1.4458 |
0.0 | 250.0 | 250 | 1.4430 |
0.0 | 275.0 | 275 | 1.4446 |
0.0001 | 300.0 | 300 | 1.4426 |
0.0 | 325.0 | 325 | 1.4528 |
0.0 | 350.0 | 350 | 1.4405 |
0.0 | 375.0 | 375 | 1.4464 |
0.0 | 400.0 | 400 | 1.4423 |
0.0 | 425.0 | 425 | 1.4526 |
0.0 | 450.0 | 450 | 1.4581 |
0.0 | 475.0 | 475 | 1.4538 |
0.0 | 500.0 | 500 | 1.4428 |
Framework versions
- PEFT 0.10.1.dev0
- Transformers 4.41.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.19.1
- Downloads last month
- 2,417