arielcerdap/results

Gemma2-2b-it Finetuned disfluency

This model is a fine-tuned version of google/gemma-2-2b-it on the TimeStamped dataset. It achieves the following results on the evaluation set:

• Loss: 0.3812

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: 5e-05
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 16
• 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: 5

Training results

Training Loss	Epoch	Step	Validation Loss
0.5267	0.4986	89	0.4971
0.4042	0.9972	178	0.4165
0.4006	1.4930	267	0.4000
0.3638	1.9916	356	0.3880
0.299	2.4874	445	0.3782
0.2888	2.9860	534	0.3651
0.2165	3.4818	623	0.3730
0.197	3.9804	712	0.3516
0.1395	4.4762	801	0.3764
0.1395	4.9748	890	0.3812

Framework versions

• PEFT 0.14.0
• Transformers 4.49.0
• Pytorch 2.6.0+cu124
• Datasets 3.4.1
• Tokenizers 0.21.1