metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: ellis-v2-emotion-leadership
results: []
ellis-v2-emotion-leadership
This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7460
- Accuracy: 0.9411
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: 2e-05
- 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: linear
- num_epochs: 70
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.3621 | 1.0 | 1109 | 0.3042 | 0.8964 |
| 0.257 | 2.0 | 2218 | 0.2566 | 0.9259 |
| 0.1991 | 3.0 | 3327 | 0.2492 | 0.9274 |
| 0.1599 | 4.0 | 4436 | 0.2860 | 0.9320 |
| 0.1335 | 5.0 | 5545 | 0.2966 | 0.9299 |
| 0.1082 | 6.0 | 6654 | 0.3682 | 0.9274 |
| 0.0805 | 7.0 | 7763 | 0.3384 | 0.9381 |
| 0.056 | 8.0 | 8872 | 0.4321 | 0.9325 |
| 0.0391 | 9.0 | 9981 | 0.4476 | 0.9264 |
| 0.0431 | 10.0 | 11090 | 0.5036 | 0.9254 |
| 0.037 | 11.0 | 12199 | 0.4724 | 0.9315 |
| 0.032 | 12.0 | 13308 | 0.4975 | 0.9381 |
| 0.0248 | 13.0 | 14417 | 0.5242 | 0.9294 |
| 0.0194 | 14.0 | 15526 | 0.5792 | 0.9305 |
| 0.0309 | 15.0 | 16635 | 0.5574 | 0.9315 |
| 0.0309 | 16.0 | 17744 | 0.5071 | 0.9355 |
| 0.0223 | 17.0 | 18853 | 0.5156 | 0.9355 |
| 0.0235 | 18.0 | 19962 | 0.5363 | 0.9371 |
| 0.014 | 19.0 | 21071 | 0.6050 | 0.9294 |
| 0.0227 | 20.0 | 22180 | 0.5531 | 0.9371 |
| 0.0133 | 21.0 | 23289 | 0.6171 | 0.9355 |
| 0.0215 | 22.0 | 24398 | 0.5730 | 0.9320 |
| 0.0143 | 23.0 | 25507 | 0.5958 | 0.9330 |
| 0.0139 | 24.0 | 26616 | 0.5780 | 0.9335 |
| 0.0104 | 25.0 | 27725 | 0.6212 | 0.9315 |
| 0.0125 | 26.0 | 28834 | 0.6119 | 0.9335 |
| 0.007 | 27.0 | 29943 | 0.6179 | 0.9360 |
| 0.016 | 28.0 | 31052 | 0.6422 | 0.9355 |
| 0.0128 | 29.0 | 32161 | 0.6028 | 0.9360 |
| 0.007 | 30.0 | 33270 | 0.6751 | 0.9320 |
| 0.0109 | 31.0 | 34379 | 0.6579 | 0.9371 |
| 0.0055 | 32.0 | 35488 | 0.7140 | 0.9305 |
| 0.0116 | 33.0 | 36597 | 0.6488 | 0.9360 |
| 0.0138 | 34.0 | 37706 | 0.6029 | 0.9345 |
| 0.0095 | 35.0 | 38815 | 0.6393 | 0.9355 |
| 0.0041 | 36.0 | 39924 | 0.6387 | 0.9355 |
| 0.0063 | 37.0 | 41033 | 0.6304 | 0.9371 |
| 0.0037 | 38.0 | 42142 | 0.6349 | 0.9391 |
| 0.0077 | 39.0 | 43251 | 0.6230 | 0.9406 |
| 0.0027 | 40.0 | 44360 | 0.6546 | 0.9426 |
| 0.0022 | 41.0 | 45469 | 0.7147 | 0.9350 |
| 0.0054 | 42.0 | 46578 | 0.7450 | 0.9310 |
| 0.006 | 43.0 | 47687 | 0.6921 | 0.9360 |
| 0.0035 | 44.0 | 48796 | 0.6667 | 0.9376 |
| 0.0078 | 45.0 | 49905 | 0.6562 | 0.9371 |
| 0.0038 | 46.0 | 51014 | 0.6589 | 0.9376 |
| 0.0032 | 47.0 | 52123 | 0.6429 | 0.9371 |
| 0.0002 | 48.0 | 53232 | 0.6616 | 0.9386 |
| 0.0022 | 49.0 | 54341 | 0.6737 | 0.9416 |
| 0.0 | 50.0 | 55450 | 0.6911 | 0.9421 |
| 0.0004 | 51.0 | 56559 | 0.7703 | 0.9335 |
| 0.0047 | 52.0 | 57668 | 0.7535 | 0.9345 |
| 0.0003 | 53.0 | 58777 | 0.7973 | 0.9284 |
| 0.0026 | 54.0 | 59886 | 0.7266 | 0.9376 |
| 0.0047 | 55.0 | 60995 | 0.7328 | 0.9340 |
| 0.0 | 56.0 | 62104 | 0.7422 | 0.9371 |
| 0.0006 | 57.0 | 63213 | 0.7275 | 0.9371 |
| 0.0008 | 58.0 | 64322 | 0.7095 | 0.9396 |
| 0.0009 | 59.0 | 65431 | 0.7112 | 0.9401 |
| 0.0017 | 60.0 | 66540 | 0.6923 | 0.9421 |
| 0.0022 | 61.0 | 67649 | 0.7383 | 0.9376 |
| 0.0 | 62.0 | 68758 | 0.7314 | 0.9391 |
| 0.0004 | 63.0 | 69867 | 0.7433 | 0.9381 |
| 0.0 | 64.0 | 70976 | 0.7410 | 0.9386 |
| 0.0 | 65.0 | 72085 | 0.7519 | 0.9386 |
| 0.0003 | 66.0 | 73194 | 0.7459 | 0.9406 |
| 0.0004 | 67.0 | 74303 | 0.7366 | 0.9401 |
| 0.0 | 68.0 | 75412 | 0.7318 | 0.9411 |
| 0.0 | 69.0 | 76521 | 0.7430 | 0.9411 |
| 0.0 | 70.0 | 77630 | 0.7460 | 0.9411 |
Framework versions
- Transformers 4.40.0
- Pytorch 2.1.0
- Datasets 2.19.0
- Tokenizers 0.19.1