outputs_finetune

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.2984
• Wer: 0.3263

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-06
• train_batch_size: 8
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Use 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: 200
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.4228	0.4235	500	0.3795	0.3611
0.4087	0.8471	1000	0.3629	0.3577
0.4571	1.2702	1500	0.3507	0.3522
0.436	1.6938	2000	0.3376	0.3520
0.312	2.1169	2500	0.3319	0.3435
0.2703	2.5404	3000	0.3184	0.3401
0.3071	2.9640	3500	0.3164	0.3380
0.3906	3.3871	4000	0.3122	0.3368
0.3769	3.8107	4500	0.3046	0.3295
0.3311	4.2338	5000	0.2996	0.3282
0.3525	4.6573	5500	0.2984	0.3263

Framework versions

• Transformers 4.57.1
• Pytorch 2.9.1+cu128
• Datasets 4.4.1
• Tokenizers 0.22.1