sb_bot_inclusion_ai_dataset_v4_1_epoch_fix
This model is a fine-tuned version of inclusionAI/ZwZ-8B on the survey_botv3 dataset. It achieves the following results on the evaluation set:
- Loss: 0.4016
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: 1e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 16
- total_train_batch_size: 64
- total_eval_batch_size: 4
- 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: 20.0
- num_epochs: 1.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5273 | 0.2222 | 50 | 0.5182 |
| 0.4480 | 0.4444 | 100 | 0.4484 |
| 0.4368 | 0.6667 | 150 | 0.4153 |
| 0.3916 | 0.8889 | 200 | 0.4025 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2
- Downloads last month
- 1