1e22b46b8eddf5a05a4230f8924cd07c

This model is a fine-tuned version of facebook/opt-125m on the nyu-mll/glue [wnli] dataset. It achieves the following results on the evaluation set:

• Loss: 0.7375
• Data Size: 0.5
• Epoch Runtime: 1.6726
• 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	1.1491	0	0.8410	0.4219	0.2967	0.4219	0.0	0.4219	0.4219
No log	1	19	1.0610	0.0078	0.9634	0.5469	0.3535	0.5469	0.0	0.5469	0.5469
No log	2	38	0.7931	0.0156	0.9641	0.5469	0.3535	0.5469	0.0	0.5469	0.5469
No log	3	57	0.7310	0.0312	1.0373	0.5	0.4330	0.5	0.0	0.5	0.5
No log	4	76	0.8235	0.0625	1.0913	0.4062	0.3552	0.4062	0.0	0.4062	0.4062
No log	5	95	0.8062	0.125	1.0666	0.4531	0.3347	0.4531	0.0	0.4531	0.4531
0.0946	6	114	0.7590	0.25	1.2157	0.4219	0.3660	0.4219	0.0	0.4219	0.4219
0.0946	7	133	0.7375	0.5	1.6726	0.4375	0.3263	0.4375	0.0	0.4375	0.4375

Framework versions

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