| | --- |
| | library_name: transformers |
| | license: mit |
| | base_model: albert/albert-base-v2 |
| | tags: |
| | - generated_from_trainer |
| | model-index: |
| | - name: ATSC-albert-base-v2-For-SemEval-2014-Task-4 |
| | results: [] |
| | --- |
| | |
| | <!-- 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. --> |
| |
|
| | # ATSC-albert-base-v2-For-SemEval-2014-Task-4 |
| |
|
| | This model is a fine-tuned version of [albert/albert-base-v2](https://huggingface.co/albert/albert-base-v2) on an unknown dataset. |
| | It achieves the following results on the evaluation set: |
| | - Loss: 1.0392 |
| | - Accurancy: 0.8490 |
| |
|
| | ## 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: |
| | - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
| | - lr_scheduler_type: linear |
| | - num_epochs: 54 |
| |
|
| | ### Training results |
| |
|
| | | Epoch | Training Loss | Validation Loss | Accuracy | |
| | |:-----:|:-------------:|:---------------:|:--------:| |
| | | 1 | 0.8649 | 0.8954 | 0.6497 | |
| | | 2 | 0.6734 | 0.5684 | 0.7775 | |
| | | 3 | 0.5461 | 0.4641 | 0.8097 | |
| | | 4 | 0.4142 | 0.4540 | 0.8275 | |
| | | 5 | 0.3211 | 0.5946 | 0.8034 | |
| | | 6 | 0.2437 | 0.4974 | 0.8329 | |
| | | 7 | 0.1958 | 0.4916 | 0.8168 | |
| | | 8 | 0.1601 | 0.6348 | 0.8275 | |
| | | 9 | 0.1095 | 0.6533 | 0.8293 | |
| | | 10 | 0.0885 | 0.7212 | 0.8204 | |
| | | 11 | 0.0714 | 0.7217 | 0.8240 | |
| | | 12 | 0.0597 | 0.7698 | 0.8266 | |
| | | 13 | 0.0420 | 0.7946 | 0.8400 | |
| | | 14 | 0.0566 | 0.8103 | 0.8418 | |
| | | 15 | 0.0389 | 0.9175 | 0.8275 | |
| | | 16 | 0.0357 | 1.1165 | 0.8266 | |
| | | 17 | 0.0205 | 1.0199 | 0.8302 | |
| | | 18 | 0.0207 | 0.9885 | 0.8391 | |
| | | 19 | 0.0155 | 1.0372 | 0.8374 | |
| | | 20 | 0.0250 | 1.1147 | 0.8365 | |
| | | 21 | 0.0198 | 1.0150 | 0.8472 | |
| | | 22 | 0.0210 | 1.1716 | 0.8356 | |
| | | 23 | 0.0208 | 1.0894 | 0.8454 | |
| | | 24 | 0.0222 | 1.1699 | 0.8382 | |
| | | 25 | 0.0196 | 1.2378 | 0.8338 | |
| | | 26 | 0.0166 | 0.9921 | 0.8490 | |
| | | 27 | 0.0115 | 1.0392 | 0.8490 | |
| | | 28 | 0.0126 | 1.3480 | 0.8311 | |
| | | 29 | 0.0107 | 1.2037 | 0.8427 | |
| | | 30 | 0.0128 | 1.0996 | 0.8427 | |
| | | 31 | 0.0128 | 1.1347 | 0.8320 | |
| | | 32 | 0.0088 | 1.2735 | 0.8356 | |
| | | 33 | 0.0083 | 1.2403 | 0.8409 | |
| | | 34 | 0.0094 | 1.2600 | 0.8418 | |
| | | 35 | 0.0072 | 1.2430 | 0.8454 | |
| | | 36 | 0.0106 | 1.2740 | 0.8391 | |
| | | 37 | 0.0093 | 1.1836 | 0.8427 | |
| | | 38 | 0.0074 | 1.2132 | 0.8454 | |
| | | 39 | 0.0071 | 1.1983 | 0.8463 | |
| | | 40 | 0.0062 | 1.2708 | 0.8409 | |
| | | 41 | 0.0068 | 1.2093 | 0.8463 | |
| | | 42 | 0.0055 | 1.2593 | 0.8445 | |
| | | 43 | 0.0055 | 1.2497 | 0.8445 | |
| | | 44 | 0.0055 | 1.2530 | 0.8463 | |
| | | 45 | 0.0051 | 1.2546 | 0.8463 | |
| | | 46 | 0.0052 | 1.2513 | 0.8463 | |
| | | 47 | 0.0054 | 1.2679 | 0.8481 | |
| | | 48 | 0.0053 | 1.2839 | 0.8463 | |
| | | 49 | 0.0048 | 1.2922 | 0.8445 | |
| | | 50 | 0.0050 | 1.3092 | 0.8409 | |
| | | 51 | 0.0052 | 1.2977 | 0.8436 | |
| | | 52 | 0.0051 | 1.3066 | 0.8427 | |
| | | 53 | 0.0051 | 1.3056 | 0.8436 | |
| | | 54 | 0.0001 | 1.3047 | 0.8436 | |
| |
|
| |
|
| |
|
| | ### Framework versions |
| |
|
| | - Transformers 4.48.2 |
| | - Pytorch 2.5.1+cu124 |
| | - Datasets 3.2.0 |
| | - Tokenizers 0.21.0 |
