gpt2_small_expandedbabyLM_50M_44

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

• Loss: 2.8581

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: 44
• 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
4.0337	1.0	2543	3.5149
3.5665	2.0	5086	3.1778
3.3843	3.0	7629	3.0516
3.2824	4.0	10172	2.9858
3.2052	5.0	12715	2.9454
3.1476	6.0	15258	2.9167
3.097	7.0	17801	2.8966
3.0584	8.0	20344	2.8846
3.0137	9.0	22887	2.8763
2.9881	10.0	25430	2.8700
2.9612	11.0	27973	2.8653
2.9301	12.0	30516	2.8608
2.9022	13.0	33059	2.8604
2.8794	14.0	35602	2.8585
2.8599	15.0	38145	2.8581
2.8417	16.0	40688	2.8595
2.8184	17.0	43231	2.8609

Framework versions

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