train-bioR-concat-gen4

This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.5219

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: 0.001
• train_batch_size: 12
• eval_batch_size: 12
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• total_train_batch_size: 96
• total_eval_batch_size: 96
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-06 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 1000
• training_steps: 41972
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.7002	0.2382	10000	1.6141
0.6777	0.4765	20000	1.5702
0.6585	0.7147	30000	1.5310
0.6584	0.9530	40000	1.5219

Framework versions

• Transformers 4.47.0
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0