gpt2_small_expandedbabyLM_1M_42

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

• Loss: 4.2656

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	51	9.2349
No log	2.0	102	7.7214
No log	3.0	153	7.0319
8.6274	4.0	204	6.6773
8.6274	5.0	255	6.3186
8.6274	6.0	306	6.0022
8.6274	7.0	357	5.7056
6.5873	8.0	408	5.4335
6.5873	9.0	459	5.1909
6.5873	10.0	510	4.9969
6.5873	11.0	561	4.8460
5.5606	12.0	612	4.7265
5.5606	13.0	663	4.6324
5.5606	14.0	714	4.5558
5.5606	15.0	765	4.4853
5.0566	16.0	816	4.4302
5.0566	17.0	867	4.3826
5.0566	18.0	918	4.3404
5.0566	19.0	969	4.2994
4.7815	20.0	1020	4.2656

Framework versions

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