0df4f56ffe40d7f2473c87bad0c3c541

This model is a fine-tuned version of FacebookAI/xlm-roberta-large-finetuned-conll03-english on the nyu-mll/glue [qnli] dataset. It achieves the following results on the evaluation set:

• Loss: 0.6932
• Data Size: 1.0
• Epoch Runtime: 507.9364
• Accuracy: 0.5057
• F1 Macro: 0.3359
• Rouge1: 0.5053
• Rouge2: 0.0
• Rougel: 0.5057
• Rougelsum: 0.5056

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	0.7000	0	7.8291	0.5039	0.3617	0.5035	0.0	0.5037	0.5039
No log	1	3273	0.6956	0.0078	12.2780	0.5118	0.3509	0.5115	0.0	0.5117	0.5116
0.0114	2	6546	0.7017	0.0156	16.6629	0.5057	0.3359	0.5053	0.0	0.5057	0.5056
0.709	3	9819	0.7110	0.0312	26.2090	0.4943	0.3308	0.4947	0.0	0.4943	0.4944
0.701	4	13092	0.6935	0.0625	41.3463	0.4943	0.3308	0.4947	0.0	0.4943	0.4944
0.7005	5	16365	0.6942	0.125	73.2618	0.4943	0.3308	0.4947	0.0	0.4943	0.4944
0.6982	6	19638	0.6939	0.25	136.6410	0.4943	0.3308	0.4947	0.0	0.4943	0.4944
0.6962	7	22911	0.7001	0.5	260.8025	0.4943	0.3308	0.4947	0.0	0.4943	0.4944
0.6949	8.0	26184	0.6932	1.0	512.9021	0.5057	0.3359	0.5053	0.0	0.5057	0.5056
0.6958	9.0	29457	0.6946	1.0	508.2251	0.5057	0.3359	0.5053	0.0	0.5057	0.5056
0.6962	10.0	32730	0.6931	1.0	510.0730	0.5057	0.3359	0.5053	0.0	0.5057	0.5056
0.6956	11.0	36003	0.6931	1.0	507.3497	0.5057	0.3359	0.5053	0.0	0.5057	0.5056
0.6977	12.0	39276	0.6948	1.0	507.3615	0.5057	0.3359	0.5053	0.0	0.5057	0.5056
0.6953	13.0	42549	0.6914	1.0	508.4416	0.5057	0.3359	0.5053	0.0	0.5057	0.5056
0.6948	14.0	45822	0.6916	1.0	513.9600	0.4943	0.3308	0.4947	0.0	0.4943	0.4944
0.6951	15.0	49095	0.6934	1.0	509.9157	0.4943	0.3308	0.4947	0.0	0.4943	0.4944
0.6929	16.0	52368	0.6935	1.0	512.9271	0.4943	0.3308	0.4947	0.0	0.4943	0.4944
0.6943	17.0	55641	0.6932	1.0	507.9364	0.5057	0.3359	0.5053	0.0	0.5057	0.5056

Framework versions

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