bif02/mt5_small

large_model

This model is a fine-tuned version of bif02/large_model on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0068

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: 2e-05
• train_batch_size: 4
• eval_batch_size: 4
• seed: 0
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine_with_restarts
• num_epochs: 12

Training results

Training Loss	Epoch	Step	Validation Loss
0.0029	1.0	554	0.0102
0.003	2.0	1108	0.0093
0.0059	3.0	1662	0.0078
0.0051	4.0	2216	0.0076
0.0039	5.0	2770	0.0077
0.0071	6.0	3324	0.0073
0.0045	7.0	3878	0.0071
0.0046	8.0	4432	0.0070
0.0082	9.0	4986	0.0069
0.0073	10.0	5540	0.0069
0.0053	11.0	6094	0.0068
0.0049	12.0	6648	0.0068

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.0.1
• Tokenizers 0.19.1