xlm-mlm-plains-cree-en-silver-sft-hierarchical
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.6380
- Macro F1: 0.5323
- Literal F1: 0.8470
- Idiom F1: 0.1852
- Metaphor F1: 0.1739
- Simile F1: 0.9231
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: 1
- eval_batch_size: 2
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 0.1
- num_epochs: 7
Training results
| Training Loss | Epoch | Step | Validation Loss | Macro F1 | Literal F1 | Idiom F1 | Metaphor F1 | Simile F1 |
|---|---|---|---|---|---|---|---|---|
| 0.2008 | 1.0 | 8737 | 2.0889 | 0.5192 | 0.7965 | 0.375 | 0.1053 | 0.8 |
| 0.0009 | 2.0 | 17474 | 2.5063 | 0.5237 | 0.8453 | 0.2353 | 0.2143 | 0.8 |
| 0.2054 | 3.0 | 26211 | 3.3517 | 0.4570 | 0.8734 | 0.0976 | 0.0 | 0.8571 |
| 0.0000 | 4.0 | 34948 | 2.6380 | 0.5323 | 0.8470 | 0.1852 | 0.1739 | 0.9231 |
| 0.0000 | 5.0 | 43685 | 3.2535 | 0.5240 | 0.8533 | 0.1633 | 0.2222 | 0.8571 |
| 0.0000 | 6.0 | 52422 | 4.1308 | 0.4572 | 0.8718 | 0.1 | 0.0 | 0.8571 |
| 0.0000 | 7.0 | 61159 | 4.6298 | 0.4743 | 0.8740 | 0.1 | 0.0 | 0.9231 |
Framework versions
- Transformers 5.12.1
- Pytorch 2.12.1
- Datasets 5.0.0
- Tokenizers 0.22.2