TimeSformer-GPT2-UCF-UCA

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

• epoch: 2.6392
• eval_gen_len: 5.9498
• eval_loss: 0.2492
• eval_rouge1: 19.7623
• eval_rouge2: 0.1573
• eval_rougeL: 17.2583
• eval_rougeLsum: 17.3092
• eval_runtime: 1000.9442
• eval_samples_per_second: 1.691
• eval_steps_per_second: 1.691
• step: 21000

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: 1
• eval_batch_size: 1
• 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: 3.0

Framework versions

• Transformers 4.51.1
• Pytorch 2.5.1+cu124
• Datasets 3.5.0
• Tokenizers 0.21.0