<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
007-microsoft-deberta-v3-base-finetuned-yahoo-80_20k
This model is a fine-tuned version of microsoft/deberta-v3-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8060
- F1: 0.7514
- Accuracy: 0.7552
- Precision: 0.7512
- Recall: 0.7552
- System Ram Used: 4.1778
- System Ram Total: 83.4807
- Gpu Ram Allocated: 2.0903
- Gpu Ram Cached: 34.3125
- Gpu Ram Total: 39.5640
- Gpu Utilization: 44
- Disk Space Used: 36.0258
- Disk Space Total: 78.1898
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
Training Loss | Epoch | Step | Validation Loss | F1 | Accuracy | Precision | Recall | System Ram Used | System Ram Total | Gpu Ram Allocated | Gpu Ram Cached | Gpu Ram Total | Gpu Utilization | Disk Space Used | Disk Space Total |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
1.3512 | 0.15 | 375 | 0.9418 | 0.7160 | 0.7189 | 0.7210 | 0.7189 | 3.9586 | 83.4807 | 2.0903 | 34.3125 | 39.5640 | 42 | 24.9904 | 78.1898 |
0.9581 | 0.3 | 750 | 0.8981 | 0.7232 | 0.7298 | 0.7301 | 0.7298 | 3.9108 | 83.4807 | 2.0903 | 34.3125 | 39.5640 | 46 | 24.9906 | 78.1898 |
0.9184 | 0.45 | 1125 | 0.8941 | 0.7248 | 0.7316 | 0.7301 | 0.7316 | 3.8717 | 83.4807 | 2.0903 | 34.3125 | 39.5640 | 46 | 24.9910 | 78.1898 |
0.8716 | 0.6 | 1500 | 0.8481 | 0.7368 | 0.7391 | 0.7414 | 0.7391 | 3.9030 | 83.4807 | 2.0903 | 34.3125 | 39.5640 | 46 | 24.9913 | 78.1898 |
0.8564 | 0.75 | 1875 | 0.8394 | 0.7379 | 0.7440 | 0.7423 | 0.7440 | 3.8964 | 83.4807 | 2.0903 | 34.3125 | 39.5640 | 44 | 24.9915 | 78.1898 |
0.8359 | 0.9 | 2250 | 0.8371 | 0.7347 | 0.7403 | 0.7417 | 0.7403 | 3.8917 | 83.4807 | 2.0903 | 34.3125 | 39.5640 | 48 | 24.9917 | 78.1898 |
0.7896 | 1.05 | 2625 | 0.8277 | 0.7369 | 0.7435 | 0.7461 | 0.7435 | 4.1488 | 83.4807 | 2.0903 | 34.3125 | 39.5640 | 44 | 29.8274 | 78.1898 |
0.7368 | 1.2 | 3000 | 0.8204 | 0.7426 | 0.7473 | 0.7468 | 0.7473 | 4.1447 | 83.4807 | 2.0903 | 34.3125 | 39.5640 | 45 | 29.8276 | 78.1898 |
0.72 | 1.35 | 3375 | 0.8199 | 0.7455 | 0.7486 | 0.7467 | 0.7486 | 3.9562 | 83.4807 | 2.0903 | 34.3125 | 39.5640 | 43 | 29.8279 | 78.1898 |
0.7333 | 1.5 | 3750 | 0.7991 | 0.7488 | 0.7524 | 0.7496 | 0.7524 | 3.9475 | 83.4807 | 2.0903 | 34.3125 | 39.5640 | 45 | 29.8282 | 78.1898 |
0.7116 | 1.65 | 4125 | 0.8149 | 0.7470 | 0.7499 | 0.7497 | 0.7499 | 3.9456 | 83.4807 | 2.0903 | 34.3125 | 39.5640 | 43 | 29.8285 | 78.1898 |
0.7177 | 1.8 | 4500 | 0.7880 | 0.7523 | 0.7558 | 0.7529 | 0.7558 | 3.9296 | 83.4807 | 2.0903 | 34.3125 | 39.5640 | 44 | 29.8287 | 78.1898 |
0.7151 | 1.95 | 4875 | 0.7949 | 0.7509 | 0.7540 | 0.7507 | 0.7540 | 3.9427 | 83.4807 | 2.0903 | 34.3125 | 39.5640 | 41 | 29.8294 | 78.1898 |
0.657 | 2.1 | 5250 | 0.8097 | 0.7500 | 0.7537 | 0.7506 | 0.7537 | 4.1520 | 83.4807 | 2.0903 | 34.3125 | 39.5640 | 43 | 33.9634 | 78.1898 |
0.6218 | 2.25 | 5625 | 0.8049 | 0.7485 | 0.7528 | 0.7484 | 0.7528 | 4.1390 | 83.4807 | 2.0903 | 34.3125 | 39.5640 | 44 | 33.9635 | 78.1898 |
0.6185 | 2.4 | 6000 | 0.8093 | 0.7511 | 0.7543 | 0.7513 | 0.7543 | 3.9715 | 83.4807 | 2.0903 | 34.3125 | 39.5640 | 42 | 33.9637 | 78.1898 |
0.6271 | 2.55 | 6375 | 0.8019 | 0.7517 | 0.7550 | 0.7521 | 0.7550 | 3.9697 | 83.4807 | 2.0903 | 34.3125 | 39.5640 | 46 | 33.9638 | 78.1898 |
0.6103 | 2.7 | 6750 | 0.8026 | 0.7519 | 0.7554 | 0.7523 | 0.7554 | 3.9622 | 83.4807 | 2.0903 | 34.3125 | 39.5640 | 46 | 33.9639 | 78.1898 |
0.6111 | 2.85 | 7125 | 0.8056 | 0.7507 | 0.7546 | 0.7511 | 0.7546 | 3.9783 | 83.4807 | 2.0903 | 34.3125 | 39.5640 | 41 | 33.9640 | 78.1898 |
0.6015 | 3.0 | 7500 | 0.8060 | 0.7514 | 0.7552 | 0.7512 | 0.7552 | 3.9702 | 83.4807 | 2.0903 | 34.3125 | 39.5640 | 42 | 33.9642 | 78.1898 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3