metadata
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: tiiuae/falcon-7b
model-index:
- name: working
results: []
working
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: 0.4159
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: 6
- eval_batch_size: 6
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 24
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2
- num_epochs: 50
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.2166 | 0.95 | 5 | 2.8374 |
| 2.9121 | 1.9 | 10 | 2.5373 |
| 2.535 | 2.86 | 15 | 2.1742 |
| 1.7769 | 4.0 | 21 | 1.8717 |
| 1.8528 | 4.95 | 26 | 1.6672 |
| 1.699 | 5.9 | 31 | 1.4421 |
| 1.4202 | 6.86 | 36 | 1.2413 |
| 1.0348 | 8.0 | 42 | 1.0859 |
| 1.0277 | 8.95 | 47 | 0.9750 |
| 0.8645 | 9.9 | 52 | 0.8628 |
| 0.7375 | 10.86 | 57 | 0.8065 |
| 0.5553 | 12.0 | 63 | 0.6707 |
| 0.5032 | 12.95 | 68 | 0.6180 |
| 0.4215 | 13.9 | 73 | 0.5757 |
| 0.3228 | 14.86 | 78 | 0.5323 |
| 0.2476 | 16.0 | 84 | 0.4868 |
| 0.2502 | 16.95 | 89 | 0.4664 |
| 0.2241 | 17.9 | 94 | 0.4755 |
| 0.2002 | 18.86 | 99 | 0.4326 |
| 0.1462 | 20.0 | 105 | 0.4330 |
| 0.1675 | 20.95 | 110 | 0.4191 |
| 0.1539 | 21.9 | 115 | 0.4113 |
| 0.1555 | 22.86 | 120 | 0.4206 |
| 0.1333 | 24.0 | 126 | 0.4052 |
| 0.1538 | 24.95 | 131 | 0.4042 |
| 0.1592 | 25.9 | 136 | 0.4032 |
| 0.1469 | 26.86 | 141 | 0.4135 |
| 0.1043 | 28.0 | 147 | 0.4007 |
| 0.1269 | 28.95 | 152 | 0.4021 |
| 0.1397 | 29.9 | 157 | 0.4381 |
| 0.1368 | 30.86 | 162 | 0.4105 |
| 0.1012 | 32.0 | 168 | 0.4002 |
| 0.1238 | 32.95 | 173 | 0.4052 |
| 0.1166 | 33.9 | 178 | 0.4102 |
| 0.1263 | 34.86 | 183 | 0.4040 |
| 0.0982 | 36.0 | 189 | 0.4040 |
| 0.1205 | 36.95 | 194 | 0.4221 |
| 0.1304 | 37.9 | 199 | 0.4213 |
| 0.1206 | 38.86 | 204 | 0.4066 |
| 0.0978 | 40.0 | 210 | 0.4103 |
| 0.1331 | 40.95 | 215 | 0.4145 |
| 0.1198 | 41.9 | 220 | 0.4114 |
| 0.1107 | 42.86 | 225 | 0.4173 |
| 0.1127 | 44.0 | 231 | 0.4219 |
| 0.1105 | 44.95 | 236 | 0.4180 |
| 0.1102 | 45.9 | 241 | 0.4151 |
| 0.1166 | 46.86 | 246 | 0.4157 |
| 0.0952 | 47.62 | 250 | 0.4159 |
Framework versions
- PEFT 0.10.0
- Transformers 4.38.2
- Pytorch 2.1.2
- Datasets 2.1.0
- Tokenizers 0.15.2