plt5-seq-clf-with-entities-updated-50-finetuned
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7296
- Accuracy: {'accuracy': 0.7032258064516129}
- Recall: {'recall': 0.7032258064516129}
- F1: {'f1': 0.7081514019750476}
- Precision: {'precision': 0.7432360333344489}
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: 5.6e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Recall | F1 | Precision |
|---|---|---|---|---|---|---|---|
| 1.0346 | 1.0 | 718 | 0.9563 | {'accuracy': 0.6274193548387097} | {'recall': 0.6274193548387097} | {'f1': 0.6269092308889221} | {'precision': 0.6516260612426348} |
| 0.9931 | 2.0 | 1436 | 0.9478 | {'accuracy': 0.6161290322580645} | {'recall': 0.6161290322580645} | {'f1': 0.6238406780518579} | {'precision': 0.6864218347180107} |
| 0.9463 | 3.0 | 2154 | 0.9055 | {'accuracy': 0.6435483870967742} | {'recall': 0.6435483870967742} | {'f1': 0.6506881166603742} | {'precision': 0.698976830092863} |
| 0.9207 | 4.0 | 2872 | 0.9370 | {'accuracy': 0.6225806451612903} | {'recall': 0.6225806451612903} | {'f1': 0.6300451742807381} | {'precision': 0.7149141775401143} |
| 0.8799 | 5.0 | 3590 | 0.9878 | {'accuracy': 0.6161290322580645} | {'recall': 0.6161290322580645} | {'f1': 0.6122209742857827} | {'precision': 0.7137447198652702} |
| 0.8561 | 6.0 | 4308 | 0.8395 | {'accuracy': 0.6645161290322581} | {'recall': 0.6645161290322581} | {'f1': 0.6682908136199321} | {'precision': 0.7247633436486038} |
| 0.8277 | 7.0 | 5026 | 0.8478 | {'accuracy': 0.6612903225806451} | {'recall': 0.6612903225806451} | {'f1': 0.6701602282855885} | {'precision': 0.7359181091343896} |
| 0.7946 | 8.0 | 5744 | 0.8521 | {'accuracy': 0.667741935483871} | {'recall': 0.667741935483871} | {'f1': 0.6706689860918258} | {'precision': 0.7498766646363035} |
| 0.7837 | 9.0 | 6462 | 0.7798 | {'accuracy': 0.6838709677419355} | {'recall': 0.6838709677419355} | {'f1': 0.690291461468391} | {'precision': 0.7206099181990787} |
| 0.7594 | 10.0 | 7180 | 0.8374 | {'accuracy': 0.6758064516129032} | {'recall': 0.6758064516129032} | {'f1': 0.682680721421726} | {'precision': 0.7493728723436673} |
| 0.7466 | 11.0 | 7898 | 0.8326 | {'accuracy': 0.6854838709677419} | {'recall': 0.6854838709677419} | {'f1': 0.6894194311810349} | {'precision': 0.7449032499042901} |
| 0.7206 | 12.0 | 8616 | 0.7420 | {'accuracy': 0.7032258064516129} | {'recall': 0.7032258064516129} | {'f1': 0.7087107256097728} | {'precision': 0.7508476827365588} |
| 0.7055 | 13.0 | 9334 | 0.7503 | {'accuracy': 0.6967741935483871} | {'recall': 0.6967741935483871} | {'f1': 0.7029067581475338} | {'precision': 0.7372716433452716} |
| 0.6931 | 14.0 | 10052 | 0.7804 | {'accuracy': 0.6854838709677419} | {'recall': 0.6854838709677419} | {'f1': 0.6918059328051079} | {'precision': 0.743185622817053} |
| 0.6939 | 15.0 | 10770 | 0.7469 | {'accuracy': 0.6887096774193548} | {'recall': 0.6887096774193548} | {'f1': 0.6952994535589653} | {'precision': 0.7335588163636623} |
| 0.6685 | 16.0 | 11488 | 0.7322 | {'accuracy': 0.7225806451612903} | {'recall': 0.7225806451612903} | {'f1': 0.7260667740259684} | {'precision': 0.7520970078354011} |
| 0.6798 | 17.0 | 12206 | 0.7457 | {'accuracy': 0.7064516129032258} | {'recall': 0.7064516129032258} | {'f1': 0.71031473860959} | {'precision': 0.7517696108635532} |
| 0.6566 | 18.0 | 12924 | 0.7392 | {'accuracy': 0.7064516129032258} | {'recall': 0.7064516129032258} | {'f1': 0.711536979529592} | {'precision': 0.7566559266538243} |
| 0.6509 | 19.0 | 13642 | 0.7349 | {'accuracy': 0.7032258064516129} | {'recall': 0.7032258064516129} | {'f1': 0.7078754315336451} | {'precision': 0.7432671014815916} |
| 0.6307 | 20.0 | 14360 | 0.7296 | {'accuracy': 0.7032258064516129} | {'recall': 0.7032258064516129} | {'f1': 0.7081514019750476} | {'precision': 0.7432360333344489} |
Framework versions
- Transformers 4.32.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.4
- Tokenizers 0.13.3
- Downloads last month
- 1