f48719394d71dea629bd032207ad1cd4

This model is a fine-tuned version of Qwen/Qwen2.5-3B on the nyu-mll/glue [wnli] dataset. It achieves the following results on the evaluation set:

• Loss: 3.0529
• Data Size: 1.0
• Epoch Runtime: 38.0176
• Accuracy: 0.5625
• F1 Macro: 0.36
• Rouge1: 0.5625
• Rouge2: 0.0
• Rougel: 0.5625
• Rougelsum: 0.5625

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	10.5592	0	1.3111	0.4375	0.3043	0.4375	0.0	0.4375	0.4375
No log	1	19	39.7286	0.0078	1.8087	0.5625	0.36	0.5625	0.0	0.5625	0.5625
No log	2	38	5.3322	0.0156	4.7804	0.6094	0.4679	0.6094	0.0	0.6094	0.6094
No log	3	57	30.6958	0.0312	10.5060	0.4375	0.3043	0.4375	0.0	0.4375	0.4375
No log	4	76	4.8040	0.0625	15.2026	0.4531	0.3347	0.4531	0.0	0.4531	0.4531
No log	5	95	3.0375	0.125	19.5757	0.5469	0.3828	0.5469	0.0	0.5469	0.5469
1.2819	6	114	3.6610	0.25	25.9435	0.4375	0.3263	0.4375	0.0	0.4375	0.4375
1.2819	7	133	4.3808	0.5	32.9607	0.4531	0.4003	0.4531	0.0	0.4531	0.4531
6.7966	8.0	152	5.6050	1.0	46.6703	0.4375	0.3043	0.4375	0.0	0.4375	0.4375
6.7966	9.0	171	3.0529	1.0	38.0176	0.5625	0.36	0.5625	0.0	0.5625	0.5625

Framework versions

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