random_transcript

This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 4.0361

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: reduce_lr_on_plateau
• lr_scheduler_warmup_steps: 500
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
7.0913	0.0635	200	5.8220
5.3316	0.1270	400	4.9714
4.852	0.1905	600	4.6945
4.6617	0.2540	800	4.5552
4.546	0.3175	1000	4.4553
4.4741	0.3810	1200	4.3862
4.4026	0.4444	1400	4.3231
4.3515	0.5079	1600	4.2626
4.2973	0.5714	1800	4.2114
4.2564	0.6349	2000	4.1736
4.2125	0.6984	2200	4.1371
4.1838	0.7619	2400	4.1047
4.1434	0.8254	2600	4.0782
4.1346	0.8889	2800	4.0541
4.1036	0.9524	3000	4.0361

Framework versions

• Transformers 4.45.2
• Pytorch 2.4.1
• Datasets 3.0.1
• Tokenizers 0.20.1