a48f4d3f833626e68dec5699c0fdaae8

This model is a fine-tuned version of Qwen/Qwen2.5-1.5B on the nyu-mll/glue [wnli] dataset. It achieves the following results on the evaluation set:

• Loss: 3.0811
• Data Size: 1.0
• Epoch Runtime: 18.3059
• Accuracy: 0.4375
• F1 Macro: 0.3043
• 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	9.2160	0	1.2265	0.4375	0.3455	0.4375	0.0	0.4375	0.4375
No log	1	19	26.1120	0.0078	1.8371	0.5625	0.3905	0.5625	0.0	0.5625	0.5625
No log	2	38	3.0516	0.0156	3.6596	0.5938	0.5667	0.5938	0.0	0.5938	0.5938
No log	3	57	3.9320	0.0312	6.0795	0.4688	0.4688	0.4688	0.0	0.4688	0.4688
No log	4	76	4.0380	0.0625	8.4564	0.4688	0.3976	0.4688	0.0	0.4688	0.4688
No log	5	95	8.7732	0.125	10.2627	0.5625	0.3905	0.5625	0.0	0.5625	0.5625
0.9729	6	114	2.7452	0.25	12.7686	0.5156	0.3671	0.5156	0.0	0.5156	0.5156
0.9729	7	133	2.8370	0.5	14.9338	0.5625	0.36	0.5625	0.0	0.5625	0.5625
2.4704	8.0	152	3.2521	1.0	21.2432	0.4375	0.3043	0.4375	0.0	0.4375	0.4375
2.4704	9.0	171	3.0118	1.0	17.8044	0.4375	0.3043	0.4375	0.0	0.4375	0.4375
2.4704	10.0	190	3.0811	1.0	18.3059	0.4375	0.3043	0.4375	0.0	0.4375	0.4375

Framework versions

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