gpt2_small_expandedbabyLM_175M_43

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

• Loss: 2.6944

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
3.3467	1.0	8894	3.0056
3.1652	2.0	17788	2.8745
3.08	3.0	26682	2.8185
3.0308	4.0	35576	2.7888
2.995	5.0	44470	2.7681
2.9603	6.0	53364	2.7552
2.9323	7.0	62258	2.7440
2.9204	8.0	71152	2.7354
2.9037	9.0	80046	2.7271
2.8822	10.0	88940	2.7230
2.8695	11.0	97834	2.7174
2.8567	12.0	106728	2.7131
2.8373	13.0	115622	2.7088
2.8243	14.0	124516	2.7064
2.815	15.0	133410	2.7039
2.7988	16.0	142304	2.7004
2.7899	17.0	151198	2.6985
2.7803	18.0	160092	2.6963
2.7569	19.0	168986	2.6955
2.7506	20.0	177880	2.6944

Framework versions

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