gpt2_small_expandedbabyLM_75M_43

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

• Loss: 2.8001

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
3.7143	1.0	3813	3.3013
3.3938	2.0	7626	3.0480
3.2654	3.0	11439	2.9545
3.1706	4.0	15252	2.9034
3.1219	5.0	19065	2.8734
3.0711	6.0	22878	2.8502
3.0375	7.0	26691	2.8378
3.0046	8.0	30504	2.8261
2.9696	9.0	34317	2.8189
2.9436	10.0	38130	2.8142
2.9182	11.0	41943	2.8077
2.8969	12.0	45756	2.8064
2.8757	13.0	49569	2.8043
2.8635	14.0	53382	2.8019
2.8404	15.0	57195	2.8016
2.8236	16.0	61008	2.8010
2.8049	17.0	64821	2.8001

Framework versions

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