gpt2_small_expandedbabyLM_100k_43

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

• Loss: 7.3339

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
No log	1.0	6	10.9303
No log	2.0	12	10.8057
No log	3.0	18	10.6019
No log	4.0	24	10.3445
No log	5.0	30	10.0673
No log	6.0	36	9.7944
No log	7.0	42	9.5408
No log	8.0	48	9.3088
No log	9.0	54	9.1015
No log	10.0	60	8.9101
No log	11.0	66	8.7171
No log	12.0	72	8.5165
No log	13.0	78	8.3216
No log	14.0	84	8.1379
No log	15.0	90	7.9662
No log	16.0	96	7.8018
No log	17.0	102	7.6603
No log	18.0	108	7.5323
No log	19.0	114	7.4255
No log	20.0	120	7.3339

Framework versions

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