t5_base_qeval0.3

This model is a fine-tuned version of t5-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.1949

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: 8
• eval_batch_size: 8
• seed: 42
• 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
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss
0.3573	0.0420	10000	0.2979
0.3091	0.0840	20000	0.2553
0.2829	0.1260	30000	0.2349
0.2619	0.1680	40000	0.2255
0.2569	0.2100	50000	0.2146
0.2549	0.2520	60000	0.2085
0.2563	0.2939	70000	0.2032
0.2478	0.3359	80000	0.1985
0.2249	0.3779	90000	0.1949

Framework versions

• Transformers 4.53.3
• Pytorch 2.7.1+cu118
• Datasets 4.0.0
• Tokenizers 0.21.2