887c886ce030fd10dce0bcc8b37b5407

This model is a fine-tuned version of Qwen/Qwen2.5-7B on the nyu-mll/glue [cola] dataset. It achieves the following results on the evaluation set:

• Loss: 3.4725
• Data Size: 1.0
• Epoch Runtime: 241.1725
• Accuracy: 0.6846
• F1 Macro: 0.4152
• Rouge1: 0.6855
• Rouge2: 0.0
• Rougel: 0.6855
• Rougelsum: 0.6846

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	6.8133	0	3.6008	0.5342	0.4868	0.5342	0.0	0.5342	0.5347
No log	1	267	40.5906	0.0078	6.6616	0.6885	0.4078	0.6895	0.0	0.6885	0.6885
No log	2	534	6.1571	0.0156	15.8873	0.6885	0.4078	0.6895	0.0	0.6885	0.6885
No log	3	801	3.1608	0.0312	28.3234	0.3213	0.2589	0.3203	0.0	0.3213	0.3218
No log	4	1068	3.0131	0.0625	43.9222	0.6885	0.4078	0.6895	0.0	0.6885	0.6885
0.3567	5	1335	4.1273	0.125	67.4639	0.6240	0.5153	0.6240	0.0	0.6240	0.6240
2.9761	6	1602	2.5782	0.25	99.0117	0.6885	0.4078	0.6895	0.0	0.6885	0.6885
4.3065	7	1869	3.5554	0.5	143.9138	0.6885	0.4078	0.6895	0.0	0.6885	0.6885
2.5352	8.0	2136	3.0619	1.0	244.2800	0.3115	0.2375	0.3105	0.0	0.3115	0.3115
2.6081	9.0	2403	2.4858	1.0	242.8371	0.6885	0.4078	0.6895	0.0	0.6885	0.6885
2.597	10.0	2670	2.5125	1.0	242.3258	0.6885	0.4078	0.6895	0.0	0.6885	0.6885
2.5392	11.0	2937	2.5480	1.0	233.0938	0.6895	0.4111	0.6904	0.0	0.6895	0.6895
2.4674	12.0	3204	2.4747	1.0	240.1788	0.6875	0.4074	0.6885	0.0	0.6875	0.6875
2.3903	13.0	3471	2.7004	1.0	232.4674	0.6885	0.4078	0.6895	0.0	0.6885	0.6885
2.3017	14.0	3738	3.0116	1.0	247.9835	0.6885	0.4078	0.6895	0.0	0.6885	0.6885
1.9255	15.0	4005	3.2539	1.0	231.5395	0.6738	0.5067	0.6738	0.0	0.6738	0.6748
1.7593	16.0	4272	3.4725	1.0	241.1725	0.6846	0.4152	0.6855	0.0	0.6855	0.6846

Framework versions

• Transformers 4.57.0
• Pytorch 2.8.0+cu128
• Datasets 4.2.0
• Tokenizers 0.22.1