metadata
license: mit
base_model: microsoft/xtremedistil-l6-h256-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: xtremedistil-l6-h256-uncased-zeroshot-v1.1-none
results: []
xtremedistil-l6-h256-uncased-zeroshot-v1.1-none
This model is a fine-tuned version of microsoft/xtremedistil-l6-h256-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1992
- F1 Macro: 0.5455
- F1 Micro: 0.6194
- Accuracy Balanced: 0.5960
- Accuracy: 0.6194
- Precision Macro: 0.5566
- Recall Macro: 0.5960
- Precision Micro: 0.6194
- Recall Micro: 0.6194
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: 32
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.06
- num_epochs: 3
Training results
Training Loss | Epoch | Step | Validation Loss | F1 Macro | F1 Micro | Accuracy Balanced | Accuracy | Precision Macro | Recall Macro | Precision Micro | Recall Micro |
---|---|---|---|---|---|---|---|---|---|---|---|
0.3056 | 1.0 | 30790 | 0.4634 | 0.7791 | 0.8013 | 0.7757 | 0.8013 | 0.7832 | 0.7757 | 0.8013 | 0.8013 |
0.2847 | 2.0 | 61580 | 0.4656 | 0.7826 | 0.8040 | 0.7797 | 0.8040 | 0.7859 | 0.7797 | 0.8040 | 0.8040 |
0.2618 | 3.0 | 92370 | 0.4774 | 0.7848 | 0.8045 | 0.7841 | 0.8045 | 0.7856 | 0.7841 | 0.8045 | 0.8045 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.1.2+cu121
- Datasets 2.14.7
- Tokenizers 0.13.3