cohere-transcribe-03-2026-med-pl-lora-decoder-only

This model is a fine-tuned version of CohereLabs/cohere-transcribe-03-2026 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 5.5128
• Model Preparation Time: 0.0235

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: 4
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• 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_ratio: 0.1
• training_steps: 20
• label_smoothing_factor: 0.1

Training results

Training Loss	Epoch	Step	Validation Loss	Model Preparation Time
No log	0.0148	5	5.5537	0.0235
No log	0.0295	10	5.4961	0.0235
No log	0.0443	15	5.4721	0.0235
No log	0.0591	20	5.5128	0.0235

Framework versions

• PEFT 0.18.1
• Transformers 4.57.6
• Pytorch 2.8.0+cu128
• Datasets 4.5.0
• Tokenizers 0.22.2