f2llm-sentiment-ablation-E
This model is a fine-tuned version of codefuse-ai/F2LLM-0.6B on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.1899
- F1 Macro: 0.4128
- F1 Weighted: 0.5379
- Accuracy: 0.5539
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: 32
- 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: cosine
- lr_scheduler_warmup_steps: 0.15
- num_epochs: 5
- label_smoothing_factor: 0.1
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Macro | F1 Weighted | Accuracy |
|---|---|---|---|---|---|---|
| 0.9551 | 1.0 | 222 | 1.0047 | 0.3164 | 0.4969 | 0.5974 |
| 0.9266 | 2.0 | 444 | 0.9655 | 0.3473 | 0.5131 | 0.6 |
| 0.8079 | 3.0 | 666 | 1.0021 | 0.4126 | 0.5493 | 0.5868 |
| 0.5796 | 4.0 | 888 | 1.1572 | 0.4181 | 0.5432 | 0.5645 |
| 0.4677 | 5.0 | 1110 | 1.1899 | 0.4128 | 0.5379 | 0.5539 |
Framework versions
- Transformers 5.3.0
- Pytorch 2.10.0+cu128
- Datasets 4.7.0
- Tokenizers 0.22.2
- Downloads last month
- 6