3360a736c005d6e0c4c7dabb22148dd4

This model is a fine-tuned version of openai-community/gpt2-xl on the nyu-mll/glue [cola] dataset. It achieves the following results on the evaluation set:

• Loss: 0.8612
• Data Size: 1.0
• Epoch Runtime: 82.1479
• Accuracy: 0.7852
• F1 Macro: 0.7200
• Rouge1: 0.7852
• Rouge2: 0.0
• Rougel: 0.7852
• Rougelsum: 0.7852

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: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• total_train_batch_size: 32
• total_eval_batch_size: 32
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: constant
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Data Size	Epoch Runtime	Accuracy	F1 Macro	Rouge1	Rouge2	Rougel	Rougelsum
No log	0	0	0.7432	0	3.8655	0.4365	0.4364	0.4365	0.0	0.4365	0.4365
No log	1	267	0.6123	0.0078	4.9052	0.6904	0.4174	0.6914	0.0	0.6904	0.6904
No log	2	534	0.5759	0.0156	7.7913	0.7051	0.5540	0.7051	0.0	0.7041	0.7051
No log	3	801	0.5484	0.0312	10.9052	0.7510	0.6849	0.75	0.0	0.75	0.7510
No log	4	1068	0.5979	0.0625	15.1094	0.7090	0.5205	0.7090	0.0	0.7100	0.7090
0.0344	5	1335	0.6495	0.125	20.6989	0.6885	0.4078	0.6895	0.0	0.6885	0.6885
0.4986	6	1602	0.5251	0.25	30.9784	0.7549	0.6529	0.7539	0.0	0.7549	0.7539
0.4181	7	1869	0.6601	0.5	47.9168	0.7549	0.6325	0.7549	0.0	0.7549	0.7549
0.372	8.0	2136	0.5446	1.0	86.0052	0.7490	0.6518	0.7490	0.0	0.7480	0.75
0.2396	9.0	2403	0.7118	1.0	84.6324	0.7695	0.6780	0.7695	0.0	0.7695	0.7695
0.191	10.0	2670	0.8612	1.0	82.1479	0.7852	0.7200	0.7852	0.0	0.7852	0.7852

Framework versions

• Transformers 4.57.0
• Pytorch 2.8.0+cu128
• Datasets 4.3.0
• Tokenizers 0.22.1