Configuration Parsing
Warning:
In adapter_config.json: "peft.task_type" must be a string
whisper-large-v2-ft-tms-good-and-bad-60-250504-v1
This model is a fine-tuned version of openai/whisper-large-v2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.0025
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- total_train_batch_size: 64
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.2
- num_epochs: 50
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 12.6652 | 1.0 | 1 | 12.6099 |
| 12.7284 | 2.0 | 2 | 12.6099 |
| 12.6979 | 3.0 | 3 | 12.6099 |
| 12.8604 | 4.0 | 4 | 12.6099 |
| 12.6964 | 5.0 | 5 | 12.6099 |
| 12.6169 | 6.0 | 6 | 12.6099 |
| 12.5936 | 7.0 | 7 | 12.6099 |
| 12.6436 | 8.0 | 8 | 12.6099 |
| 12.6892 | 9.0 | 9 | 12.4989 |
| 12.5564 | 10.0 | 10 | 12.1895 |
| 12.1348 | 11.0 | 11 | 11.6951 |
| 11.7845 | 12.0 | 12 | 11.0583 |
| 11.1069 | 13.0 | 13 | 10.2337 |
| 10.1252 | 14.0 | 14 | 9.1621 |
| 8.9713 | 15.0 | 15 | 7.9915 |
| 7.7297 | 16.0 | 16 | 6.8277 |
| 6.5998 | 17.0 | 17 | 5.5317 |
| 5.5248 | 18.0 | 18 | 4.9110 |
| 5.0819 | 19.0 | 19 | 4.7398 |
| 4.9123 | 20.0 | 20 | 4.6498 |
| 4.7977 | 21.0 | 21 | 4.5673 |
| 4.7755 | 22.0 | 22 | 4.4948 |
| 4.649 | 23.0 | 23 | 4.4172 |
| 4.6569 | 24.0 | 24 | 4.3416 |
| 4.5208 | 25.0 | 25 | 4.2622 |
| 4.5094 | 26.0 | 26 | 4.1828 |
| 4.3355 | 27.0 | 27 | 4.1015 |
| 4.209 | 28.0 | 28 | 4.0197 |
| 4.1589 | 29.0 | 29 | 3.9379 |
| 4.0804 | 30.0 | 30 | 3.8569 |
| 3.9805 | 31.0 | 31 | 3.7793 |
| 3.8472 | 32.0 | 32 | 3.7059 |
| 3.8284 | 33.0 | 33 | 3.6374 |
| 3.7731 | 34.0 | 34 | 3.5749 |
| 3.711 | 35.0 | 35 | 3.5172 |
| 3.5269 | 36.0 | 36 | 3.4646 |
| 3.4983 | 37.0 | 37 | 3.4161 |
| 3.5035 | 38.0 | 38 | 3.3697 |
| 3.3994 | 39.0 | 39 | 3.3267 |
| 3.2883 | 40.0 | 40 | 3.2856 |
| 3.2866 | 41.0 | 41 | 3.2497 |
| 3.2314 | 42.0 | 42 | 3.2149 |
| 3.1948 | 43.0 | 43 | 3.1819 |
| 3.1793 | 44.0 | 44 | 3.1509 |
| 3.0904 | 45.0 | 45 | 3.1212 |
| 3.1129 | 46.0 | 46 | 3.0937 |
| 3.1039 | 47.0 | 47 | 3.0681 |
| 2.9929 | 48.0 | 48 | 3.0441 |
| 3.0339 | 49.0 | 49 | 3.0224 |
| 2.9489 | 50.0 | 50 | 3.0025 |
Framework versions
- PEFT 0.13.0
- Transformers 4.45.1
- Pytorch 2.5.0+cu124
- Datasets 2.21.0
- Tokenizers 0.20.0
- Downloads last month
- 19
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for dylanewbie/whisper-large-v2-ft-tms-good-and-bad-60-250504-v1
Base model
openai/whisper-large-v2