metadata
base_model: allenai/scibert_scivocab_uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: SciBERT_twowayloss_25K_bs64
results: []
SciBERT_twowayloss_25K_bs64
This model is a fine-tuned version of allenai/scibert_scivocab_uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0158
- Accuracy: 0.9945
- Precision: 0.7948
- Recall: 0.5830
- F1: 0.6727
- Hamming: 0.0055
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: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 25000
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | Hamming |
|---|---|---|---|---|---|---|---|---|
| 0.0332 | 0.16 | 5000 | 0.0283 | 0.9921 | 0.8249 | 0.2410 | 0.3730 | 0.0079 |
| 0.0195 | 0.32 | 10000 | 0.0186 | 0.9939 | 0.7964 | 0.4983 | 0.6131 | 0.0061 |
| 0.0173 | 0.47 | 15000 | 0.0168 | 0.9943 | 0.7936 | 0.5587 | 0.6557 | 0.0057 |
| 0.0165 | 0.63 | 20000 | 0.0161 | 0.9944 | 0.7949 | 0.5782 | 0.6694 | 0.0056 |
| 0.0161 | 0.79 | 25000 | 0.0158 | 0.9945 | 0.7948 | 0.5830 | 0.6727 | 0.0055 |
Framework versions
- Transformers 4.35.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.7.1
- Tokenizers 0.14.1