gpt2_small_expandedbabyLM_100k_42

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

• Loss: 7.4001

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: 42
• 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
No log	1.0	6	10.8728
No log	2.0	12	10.7595
No log	3.0	18	10.5743
No log	4.0	24	10.3364
No log	5.0	30	10.0761
No log	6.0	36	9.8185
No log	7.0	42	9.5729
No log	8.0	48	9.3535
No log	9.0	54	9.1574
No log	10.0	60	8.9807
No log	11.0	66	8.8054
No log	12.0	72	8.6149
No log	13.0	78	8.4188
No log	14.0	84	8.2324
No log	15.0	90	8.0558
No log	16.0	96	7.8964
No log	17.0	102	7.7522
No log	18.0	108	7.6229
No log	19.0	114	7.4994
No log	20.0	120	7.4001

Framework versions

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