metadata
license: mit
base_model: BigTMiami/micro_base_help_tapt_pretrain_model
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: micro_base_help_class_tapt_seed_1
results: []
micro_base_help_class_tapt_seed_1
This model is a fine-tuned version of BigTMiami/micro_base_help_tapt_pretrain_model on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3254
- Accuracy: 0.8584
- F1 Macro: 0.6599
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: 1
- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-06
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro |
|---|---|---|---|---|---|
| 0.347 | 1.0 | 313 | 0.3434 | 0.8536 | 0.4659 |
| 0.3196 | 2.0 | 626 | 0.3397 | 0.8578 | 0.6761 |
| 0.2627 | 3.0 | 939 | 0.3875 | 0.8636 | 0.5878 |
| 0.2091 | 4.0 | 1252 | 0.5313 | 0.8604 | 0.6143 |
| 0.1574 | 5.0 | 1565 | 0.7826 | 0.8552 | 0.6218 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2