bd2d0fe4e3ca732d7137f58b72ffb675

This model is a fine-tuned version of Qwen/Qwen2.5-0.5B on the nyu-mll/glue [wnli] dataset. It achieves the following results on the evaluation set:

• Loss: 3.3996
• Data Size: 1.0
• Epoch Runtime: 8.9162
• Accuracy: 0.4375
• F1 Macro: 0.3263
• Rouge1: 0.4375
• Rouge2: 0.0
• Rougel: 0.4375
• Rougelsum: 0.4375

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	15.9041	0	1.2570	0.5625	0.36	0.5625	0.0	0.5625	0.5625
No log	1	19	65.2991	0.0078	1.4537	0.4531	0.3347	0.4531	0.0	0.4531	0.4531
No log	2	38	13.4792	0.0156	2.0439	0.4688	0.4113	0.4688	0.0	0.4688	0.4688
No log	3	57	10.4038	0.0312	3.0506	0.4688	0.4640	0.4688	0.0	0.4688	0.4688
No log	4	76	81.25	0.0625	3.7089	0.5625	0.36	0.5625	0.0	0.5625	0.5625
No log	5	95	11.9447	0.125	4.1098	0.4219	0.3361	0.4219	0.0	0.4219	0.4219
3.5935	6	114	6.5896	0.25	5.0519	0.4531	0.3547	0.4531	0.0	0.4531	0.4531
3.5935	7	133	5.1416	0.5	5.9788	0.5625	0.36	0.5625	0.0	0.5625	0.5625
2.7754	8.0	152	2.9640	1.0	7.9569	0.4688	0.4113	0.4688	0.0	0.4688	0.4688
2.7754	9.0	171	2.8928	1.0	7.4681	0.5625	0.36	0.5625	0.0	0.5625	0.5625
2.7754	10.0	190	2.7850	1.0	7.8293	0.4688	0.4113	0.4688	0.0	0.4688	0.4688
3.199	11.0	209	3.1660	1.0	8.0942	0.5625	0.36	0.5625	0.0	0.5625	0.5625
3.199	12.0	228	4.5655	1.0	8.5792	0.5625	0.36	0.5625	0.0	0.5625	0.5625
3.199	13.0	247	3.5373	1.0	8.5128	0.5469	0.3535	0.5469	0.0	0.5469	0.5469
3.229	14.0	266	3.3996	1.0	8.9162	0.4375	0.3263	0.4375	0.0	0.4375	0.4375

Framework versions

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