gpt2_small_expandedbabyLM_150M_44

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

• Loss: 2.7108

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
3.3946	1.0	7624	3.0511
3.2006	2.0	15248	2.8971
3.1031	3.0	22872	2.8379
3.0479	4.0	30496	2.8062
3.0106	5.0	38120	2.7822
2.9734	6.0	45744	2.7693
2.9532	7.0	53368	2.7566
2.9326	8.0	60992	2.7489
2.9056	9.0	68616	2.7413
2.8934	10.0	76240	2.7350
2.8738	11.0	83864	2.7318
2.8556	12.0	91488	2.7280
2.8407	13.0	99112	2.7231
2.8242	14.0	106736	2.7205
2.8111	15.0	114360	2.7191
2.806	16.0	121984	2.7161
2.7911	17.0	129608	2.7150
2.7738	18.0	137232	2.7119
2.7582	19.0	144856	2.7111
2.7482	20.0	152480	2.7108

Framework versions

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