20a8b81239cc3dd2cb0db3124b8a138b

This model is a fine-tuned version of facebook/opt-1.3b on the nyu-mll/glue [wnli] dataset. It achieves the following results on the evaluation set:

• Loss: 0.7186
• Data Size: 1.0
• Epoch Runtime: 17.4021
• Accuracy: 0.4531
• F1 Macro: 0.3347
• Rouge1: 0.4531
• Rouge2: 0.0
• Rougel: 0.4531
• Rougelsum: 0.4531

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	1.0199	0	1.1831	0.5625	0.36	0.5625	0.0	0.5625	0.5625
No log	1	19	5.9317	0.0078	1.4515	0.4375	0.3043	0.4375	0.0	0.4375	0.4375
No log	2	38	3.4844	0.0156	3.5092	0.4375	0.3043	0.4375	0.0	0.4375	0.4375
No log	3	57	0.8081	0.0312	5.2243	0.5	0.4980	0.5	0.0	0.5	0.5
No log	4	76	0.8213	0.0625	7.7835	0.5312	0.3469	0.5312	0.0	0.5312	0.5312
No log	5	95	0.7349	0.125	10.5718	0.5625	0.36	0.5625	0.0	0.5625	0.5625
0.1726	6	114	0.6885	0.25	13.1633	0.5625	0.36	0.5625	0.0	0.5625	0.5625
0.1726	7	133	0.6884	0.5	16.6877	0.5625	0.36	0.5625	0.0	0.5625	0.5625
0.6244	8.0	152	0.8507	1.0	21.1740	0.4375	0.3043	0.4375	0.0	0.4375	0.4375
0.6244	9.0	171	0.6904	1.0	18.8003	0.5625	0.36	0.5625	0.0	0.5625	0.5625
0.6244	10.0	190	0.6909	1.0	11.1183	0.5625	0.36	0.5625	0.0	0.5625	0.5625
0.7238	11.0	209	0.6857	1.0	10.7788	0.5625	0.36	0.5625	0.0	0.5625	0.5625
0.7238	12.0	228	0.6850	1.0	12.1211	0.5625	0.36	0.5625	0.0	0.5625	0.5625
0.7238	13.0	247	0.7034	1.0	13.8523	0.5625	0.36	0.5625	0.0	0.5625	0.5625
0.7182	14.0	266	0.6991	1.0	13.8023	0.4531	0.4498	0.4531	0.0	0.4531	0.4531
0.7182	15.0	285	0.7331	1.0	14.6135	0.5625	0.36	0.5625	0.0	0.5625	0.5625
0.7752	16.0	304	0.7186	1.0	17.4021	0.4531	0.3347	0.4531	0.0	0.4531	0.4531

Framework versions

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