gpt2_small_expandedbabyLM_200M_43

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

• Loss: 2.6807

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
3.3052	1.0	10163	2.9740
3.1388	2.0	20326	2.8510
3.0553	3.0	30489	2.8000
3.0121	4.0	40652	2.7724
2.9802	5.0	50815	2.7551
2.9414	6.0	60978	2.7402
2.9203	7.0	71141	2.7318
2.9092	8.0	81304	2.7239
2.8837	9.0	91467	2.7151
2.8778	10.0	101630	2.7111
2.8607	11.0	111793	2.7086
2.8439	12.0	121956	2.7022
2.8363	13.0	132119	2.6984
2.8156	14.0	142282	2.6943
2.8036	15.0	152445	2.6909
2.7974	16.0	162608	2.6877
2.7814	17.0	172771	2.6863
2.7746	18.0	182934	2.6837
2.7583	19.0	193097	2.6816
2.7512	20.0	203260	2.6807

Framework versions

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