lmind_hotpot_train1000_eval200_v1_recite_qa_gpt2-xl

This model is a fine-tuned version of gpt2-xl on the tyzhu/lmind_hotpot_train1000_eval200_v1_recite_qa dataset. It achieves the following results on the evaluation set:

• Loss: 0.4436
• Accuracy: 0.6989

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: linear
• lr_scheduler_warmup_ratio: 0.05
• num_epochs: 10.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.7644	1.0	211	1.0036	0.6429
0.526	2.0	422	0.7351	0.6658
0.4163	3.0	633	0.5744	0.6815
0.2864	4.0	844	0.4953	0.6899
0.2118	5.0	1055	0.4594	0.6944
0.17	6.0	1266	0.4490	0.6964
0.134	7.0	1477	0.4369	0.6979
0.1206	8.0	1688	0.4372	0.6987
0.1081	9.0	1899	0.4423	0.6987
0.1053	10.0	2110	0.4436	0.6989

Framework versions

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