gpt2_small_expandedbabyLM_175M_44

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

• Loss: 2.6951

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
3.3433	1.0	8894	3.0135
3.1694	2.0	17788	2.8702
3.0849	3.0	26682	2.8207
3.0344	4.0	35576	2.7884
2.9892	5.0	44470	2.7695
2.967	6.0	53364	2.7539
2.9358	7.0	62258	2.7441
2.9196	8.0	71152	2.7366
2.9001	9.0	80046	2.7300
2.8797	10.0	88940	2.7236
2.8727	11.0	97834	2.7176
2.8536	12.0	106728	2.7139
2.8337	13.0	115622	2.7115
2.8232	14.0	124516	2.7073
2.8133	15.0	133410	2.7056
2.8022	16.0	142304	2.7006
2.7816	17.0	151198	2.6995
2.7734	18.0	160092	2.6976
2.7586	19.0	168986	2.6953
2.7502	20.0	177880	2.6951

Framework versions

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