gpt2_small_expandedbabyLM_150M_43

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: 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
3.397	1.0	7624	3.0480
3.1935	2.0	15248	2.8979
3.1146	3.0	22872	2.8405
3.0477	4.0	30496	2.8066
3.011	5.0	38120	2.7851
2.9795	6.0	45744	2.7675
2.95	7.0	53368	2.7586
2.9229	8.0	60992	2.7498
2.9052	9.0	68616	2.7427
2.8896	10.0	76240	2.7382
2.8706	11.0	83864	2.7323
2.8588	12.0	91488	2.7267
2.8451	13.0	99112	2.7246
2.8278	14.0	106736	2.7226
2.8191	15.0	114360	2.7181
2.805	16.0	121984	2.7154
2.7938	17.0	129608	2.7147
2.7727	18.0	137232	2.7132
2.7637	19.0	144856	2.7113
2.7559	20.0	152480	2.7108

Framework versions

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