4a74b14204e44abc3d6bccfcb715fc07

This model is a fine-tuned version of FacebookAI/xlm-roberta-base 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: 271.4070
• 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	0.7094	0	4.6239	0.4943	0.3308	0.4947	0.0	0.4943	0.4944
No log	1	3273	0.6985	0.0078	8.1501	0.5057	0.3359	0.5053	0.0	0.5057	0.5056
0.0112	2	6546	0.6934	0.0156	9.1299	0.4943	0.3308	0.4947	0.0	0.4943	0.4944
0.698	3	9819	0.6967	0.0312	13.6842	0.4943	0.3308	0.4947	0.0	0.4943	0.4944
0.6946	4	13092	0.6938	0.0625	22.1376	0.4943	0.3308	0.4947	0.0	0.4943	0.4944
0.6963	5	16365	0.6947	0.125	38.3493	0.5057	0.3359	0.5053	0.0	0.5057	0.5056
0.6955	6	19638	0.6933	0.25	70.7409	0.5057	0.3359	0.5053	0.0	0.5057	0.5056
0.6997	7	22911	0.6955	0.5	134.9086	0.4943	0.3308	0.4947	0.0	0.4943	0.4944
0.6942	8.0	26184	0.6941	1.0	267.9226	0.5057	0.3359	0.5053	0.0	0.5057	0.5056
0.6929	9.0	29457	0.6934	1.0	266.5417	0.4943	0.3308	0.4947	0.0	0.4943	0.4944
0.6954	10.0	32730	0.6932	1.0	268.6168	0.5057	0.3359	0.5053	0.0	0.5057	0.5056
0.696	11.0	36003	0.6931	1.0	264.6479	0.5057	0.3359	0.5053	0.0	0.5057	0.5056
0.6944	12.0	39276	0.6934	1.0	271.0995	0.4943	0.3308	0.4947	0.0	0.4943	0.4944
0.6937	13.0	42549	0.6942	1.0	265.2116	0.5057	0.3359	0.5053	0.0	0.5057	0.5056
0.6938	14.0	45822	0.6937	1.0	277.0142	0.4943	0.3308	0.4947	0.0	0.4943	0.4944
0.6933	15.0	49095	0.6932	1.0	271.4070	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