metadata
license: apache-2.0
base_model: tiiuae/falcon-7b
tags:
- generated_from_trainer
model-index:
- name: falcon-rewrite-560
results: []
falcon-rewrite-560
This model is a fine-tuned version of tiiuae/falcon-7b on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.2253
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: 0.0005
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.4828 | 0.15 | 10 | 2.4554 |
| 3.8736 | 0.3 | 20 | 2.4426 |
| 3.6144 | 0.45 | 30 | 2.9606 |
| 1.9016 | 0.6 | 40 | 2.5989 |
| 1.8213 | 0.75 | 50 | 2.7219 |
| 3.2497 | 0.9 | 60 | 2.5531 |
| 4.2956 | 1.04 | 70 | 2.5117 |
| 2.0346 | 1.19 | 80 | 2.6559 |
| 3.293 | 1.34 | 90 | 2.5667 |
| 2.4628 | 1.49 | 100 | 2.7377 |
| 1.8473 | 1.64 | 110 | 1.9679 |
| 3.0982 | 1.79 | 120 | 2.4545 |
| 4.0502 | 1.94 | 130 | 1.5169 |
| 2.5271 | 2.09 | 140 | 2.2475 |
| 2.0131 | 2.24 | 150 | 2.2574 |
| 1.7571 | 2.39 | 160 | 1.9870 |
| 1.5135 | 2.54 | 170 | 2.4713 |
| 1.783 | 2.69 | 180 | 1.9229 |
| 1.4584 | 2.84 | 190 | 2.3683 |
| 0.7306 | 2.99 | 200 | 1.2253 |
| 2.2726 | 3.13 | 210 | 1.8495 |
| 1.7065 | 3.28 | 220 | 1.7916 |
| 0.5787 | 3.43 | 230 | 1.8749 |
| 1.3256 | 3.58 | 240 | 2.1531 |
| 2.8024 | 3.73 | 250 | 2.1011 |
| 1.1855 | 3.88 | 260 | 2.1262 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1
- Datasets 2.14.5
- Tokenizers 0.13.3