1788874cb2351d0a09eceeea36bb76ac

This model is a fine-tuned version of FacebookAI/roberta-large on the nyu-mll/glue [mnli] dataset. It achieves the following results on the evaluation set:

• Loss: 1.0986
• Data Size: 0.5
• Epoch Runtime: 880.3157
• Accuracy: 0.3545
• F1 Macro: 0.1745
• Rouge1: 0.3544
• Rouge2: 0.0
• Rougel: 0.3545
• Rougelsum: 0.3543

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	1.1451	0	13.2882	0.3545	0.1745	0.3544	0.0	0.3545	0.3543
1.1209	1	12271	1.0998	0.0078	26.7098	0.3182	0.1609	0.3184	0.0	0.3182	0.3183
1.1165	2	24542	1.0978	0.0156	40.0132	0.3545	0.1745	0.3544	0.0	0.3545	0.3543
1.1127	3	36813	1.0970	0.0312	66.6039	0.3306	0.2146	0.3308	0.0	0.3307	0.3307
1.1088	4	49084	1.0992	0.0625	119.0939	0.3545	0.1745	0.3544	0.0	0.3545	0.3543
1.1049	5	61355	1.0981	0.125	224.0561	0.3545	0.1745	0.3544	0.0	0.3545	0.3543
1.1062	6	73626	1.1079	0.25	437.4033	0.3182	0.1609	0.3184	0.0	0.3182	0.3183
1.1061	7	85897	1.0986	0.5	880.3157	0.3545	0.1745	0.3544	0.0	0.3545	0.3543

Framework versions

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