metadata
base_model: allenai/scibert_scivocab_uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: uniBERT.SciBERT.3
results: []
uniBERT.SciBERT.3
This model is a fine-tuned version of allenai/scibert_scivocab_uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.4561
- Accuracy: (0.6702412868632708,)
- F1: (0.6657502111957233,)
- Precision: (0.6734478583674295,)
- Recall: 0.6702
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: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
---|---|---|---|---|---|---|---|
2.3677 | 1.0 | 210 | 1.9707 | (0.4075067024128686,) | (0.4090192400845535,) | (0.547509709321153,) | 0.4075 |
1.5004 | 2.0 | 420 | 1.5800 | (0.5040214477211796,) | (0.5054715276021063,) | (0.5609302049861328,) | 0.5040 |
1.1293 | 3.0 | 630 | 1.4399 | (0.5978552278820375,) | (0.5952450222746305,) | (0.626189358268289,) | 0.5979 |
0.7653 | 4.0 | 840 | 1.3531 | (0.613941018766756,) | (0.6131261450333483,) | (0.6327420067968214,) | 0.6139 |
0.5953 | 5.0 | 1050 | 1.3496 | (0.6273458445040214,) | (0.6242006045463042,) | (0.6387356344263772,) | 0.6273 |
0.4295 | 6.0 | 1260 | 1.4336 | (0.6407506702412868,) | (0.6336787424282196,) | (0.6518816492980041,) | 0.6408 |
0.28 | 7.0 | 1470 | 1.4272 | (0.6407506702412868,) | (0.63679869732329,) | (0.6493551584566409,) | 0.6408 |
0.2789 | 8.0 | 1680 | 1.4619 | (0.6514745308310992,) | (0.6469674646912128,) | (0.6567012350489139,) | 0.6515 |
0.1723 | 9.0 | 1890 | 1.4713 | (0.6514745308310992,) | (0.6473277862770819,) | (0.6561545316552414,) | 0.6515 |
0.1383 | 10.0 | 2100 | 1.4561 | (0.6702412868632708,) | (0.6657502111957233,) | (0.6734478583674295,) | 0.6702 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2