metadata
library_name: transformers
license: mit
base_model: lazymonster/20k-combined-raw-scratch
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: adaptation_raw
results: []
adaptation_raw
This model is a fine-tuned version of lazymonster/20k-combined-raw-scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0900
- Accuracy: 0.6965
- F1 Macro: 0.6952
- Composite Score: 0.6952
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: 32
- seed: 42
- 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
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 20
- mixed_precision_training: Native AMP
- label_smoothing_factor: 0.1
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | Composite Score |
|---|---|---|---|---|---|---|
| No log | 1.0 | 333 | 0.9958 | 0.6995 | 0.6983 | 0.6983 |
| 0.4563 | 2.0 | 666 | 1.0290 | 0.7104 | 0.7096 | 0.7096 |
| 0.4563 | 3.0 | 999 | 1.0838 | 0.6859 | 0.6840 | 0.6840 |
| 0.4419 | 4.0 | 1332 | 1.0559 | 0.7006 | 0.6987 | 0.6987 |
| 0.4108 | 5.0 | 1665 | 1.1011 | 0.6946 | 0.6929 | 0.6929 |
| 0.4108 | 6.0 | 1998 | 1.0900 | 0.6965 | 0.6952 | 0.6952 |
Framework versions
- Transformers 4.53.3
- Pytorch 2.6.0+cu124
- Datasets 4.4.1
- Tokenizers 0.21.2