lmind_nq_train300_eval100_v1_recite_qa_gpt2-xl

This model is a fine-tuned version of gpt2-xl on the tyzhu/lmind_nq_train300_eval100_v1_recite_qa dataset. It achieves the following results on the evaluation set:

• Loss: 0.3388
• Accuracy: 0.8212

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant
• num_epochs: 10.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.1943	1.0	44	0.4267	0.8042
0.1121	2.0	88	0.3744	0.8138
0.0832	3.0	132	0.3551	0.8177
0.0859	4.0	176	0.3487	0.8187
0.0849	5.0	220	0.3478	0.8188
0.0791	6.0	264	0.3479	0.8194
0.0681	7.0	308	0.3537	0.8197
0.0715	8.0	352	0.3467	0.8205
0.0639	9.0	396	0.3577	0.8194
0.0614	10.0	440	0.3388	0.8212

Framework versions

• Transformers 4.34.0
• Pytorch 2.1.0+cu121
• Datasets 2.14.5
• Tokenizers 0.14.1