gpt2_small_expandedbabyLM_125M_43

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

• Loss: 2.7331

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: 256
• eval_batch_size: 256
• seed: 43
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 4000
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss
3.4667	1.0	6353	3.1009
3.2426	2.0	12706	2.9290
3.1452	3.0	19059	2.8645
3.0753	4.0	25412	2.8275
3.035	5.0	31765	2.8049
2.9962	6.0	38118	2.7906
2.9762	7.0	44471	2.7789
2.9417	8.0	50824	2.7706
2.9211	9.0	57177	2.7631
2.905	10.0	63530	2.7557
2.888	11.0	69883	2.7509
2.8687	12.0	76236	2.7483
2.8471	13.0	82589	2.7435
2.8329	14.0	88942	2.7431
2.8164	15.0	95295	2.7388
2.8095	16.0	101648	2.7367
2.7957	17.0	108001	2.7359
2.7784	18.0	114354	2.7337
2.7663	19.0	120707	2.7335
2.7574	20.0	127060	2.7331

Framework versions

• Transformers 4.30.2
• Pytorch 2.11.0+cu130
• Datasets 4.1.1
• Tokenizers 0.13.3