math-gpt2-simple/README.md

library_name, license, base_model, tags, model-index

library_name	license	base_model	tags	model-index
transformers	mit	gpt2	generated_from_trainer	name results math-gpt2-simple

math-gpt2-simple

This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.7100

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: 3e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• num_epochs: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
2.272	0.7937	50	2.0902
2.1191	1.5873	100	1.8907
1.9521	2.3810	150	1.7958
1.9319	3.1746	200	1.7425
1.8994	3.9683	250	1.7167
1.8937	4.7619	300	1.7100

Framework versions

• Transformers 4.48.3
• Pytorch 2.5.1+cu124
• Datasets 3.3.2
• Tokenizers 0.21.0