00652d0c6f670e92288ecdf8abe9a726

This model is a fine-tuned version of facebook/opt-350m on the nyu-mll/glue [wnli] dataset. It achieves the following results on the evaluation set:

• Loss: 0.6895
• Data Size: 1.0
• Epoch Runtime: 7.6929
• 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	1.2058	0	1.0835	0.4844	0.4452	0.4844	0.0	0.4844	0.4844
No log	1	19	4.8135	0.0078	1.2306	0.5625	0.36	0.5625	0.0	0.5625	0.5625
No log	2	38	1.8431	0.0156	1.5465	0.5625	0.36	0.5625	0.0	0.5625	0.5625
No log	3	57	2.3561	0.0312	2.1107	0.4531	0.3347	0.4531	0.0	0.4531	0.4531
No log	4	76	1.1024	0.0625	2.7294	0.5625	0.36	0.5625	0.0	0.5625	0.5625
No log	5	95	0.8377	0.125	3.2835	0.4375	0.3043	0.4375	0.0	0.4375	0.4375
0.1636	6	114	0.6907	0.25	3.6047	0.5625	0.36	0.5625	0.0	0.5625	0.5625
0.1636	7	133	1.0587	0.5	4.9235	0.4375	0.3043	0.4375	0.0	0.4375	0.4375
0.5928	8.0	152	1.0020	1.0	7.4250	0.4375	0.3043	0.4375	0.0	0.4375	0.4375
0.5928	9.0	171	0.6875	1.0	6.8885	0.5625	0.36	0.5625	0.0	0.5625	0.5625
0.5928	10.0	190	0.7252	1.0	7.3619	0.5625	0.36	0.5625	0.0	0.5625	0.5625
0.7482	11.0	209	0.8343	1.0	7.5213	0.4375	0.3043	0.4375	0.0	0.4375	0.4375
0.7482	12.0	228	0.7030	1.0	7.6349	0.4375	0.3043	0.4375	0.0	0.4375	0.4375
0.7482	13.0	247	0.6895	1.0	7.6929	0.5625	0.36	0.5625	0.0	0.5625	0.5625

Framework versions

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