1c0139e88a63e1e22c175cf1c7fa01a7

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

• Loss: 0.5967
• Data Size: 1.0
• Epoch Runtime: 10.2766
• Accuracy: 0.8555
• F1 Macro: 0.8394
• Rouge1: 0.8561
• Rouge2: 0.0
• Rougel: 0.8555
• Rougelsum: 0.8555

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	0.7407	0	1.8391	0.3349	0.2509	0.3343	0.0	0.3355	0.3349
No log	1	114	0.6950	0.0078	2.1776	0.3803	0.3432	0.3797	0.0	0.3809	0.3797
No log	2	228	0.6382	0.0156	2.3350	0.6651	0.3994	0.6657	0.0	0.6645	0.6651
No log	3	342	0.6323	0.0312	2.5928	0.6651	0.3994	0.6657	0.0	0.6645	0.6651
0.021	4	456	0.5912	0.0625	2.8316	0.6922	0.5231	0.6928	0.0	0.6916	0.6916
0.021	5	570	0.5526	0.125	3.3343	0.7188	0.5738	0.7188	0.0	0.7188	0.7193
0.021	6	684	0.3915	0.25	4.3092	0.8261	0.8130	0.8261	0.0	0.8261	0.8261
0.1166	7	798	0.4454	0.5	6.3545	0.8396	0.8053	0.8390	0.0	0.8396	0.8396
0.3484	8.0	912	0.4112	1.0	10.5070	0.8402	0.8023	0.8408	0.0	0.8402	0.8402
0.2148	9.0	1026	0.4938	1.0	10.5424	0.8196	0.7705	0.8196	0.0	0.8196	0.8196
0.204	10.0	1140	0.5967	1.0	10.2766	0.8555	0.8394	0.8561	0.0	0.8555	0.8555

Framework versions

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