t5-small-openassistant-chat-final

This model is a fine-tuned version of KMH158/t5-small-openassistant-chat on the None dataset. It achieves the following results on the evaluation set:

• eval_loss: 3.0506
• eval_rougeL: 0.1203
• eval_runtime: 92.915
• eval_samples_per_second: 6.673
• eval_steps_per_second: 3.336
• epoch: 11.0
• step: 836

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: 0.0001
• train_batch_size: 40
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 320
• 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: 20
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.55.3
• Pytorch 2.6.0+cu124
• Datasets 4.0.0
• Tokenizers 0.21.2