723b1bc5e6a9099290d6d5ade22eae0d

This model is a fine-tuned version of FacebookAI/roberta-large on the nyu-mll/glue [sst2] dataset. It achieves the following results on the evaluation set:

• Loss: 0.7067
• Data Size: 0.25
• Epoch Runtime: 75.4704
• Accuracy: 0.5093
• F1 Macro: 0.3374
• Rouge1: 0.5093
• Rouge2: 0.0
• Rougel: 0.5093
• Rougelsum: 0.5081

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	0.7308	0	1.7910	0.4907	0.3292	0.4907	0.0	0.4907	0.4919
No log	1	2104	0.6962	0.0078	4.9734	0.4919	0.3337	0.4919	0.0	0.4931	0.4919
No log	2	4208	0.6937	0.0156	6.5889	0.5093	0.3374	0.5093	0.0	0.5093	0.5081
0.0153	3	6312	0.7039	0.0312	11.7140	0.5093	0.3374	0.5093	0.0	0.5093	0.5081
0.7024	4	8416	0.7100	0.0625	21.0968	0.5093	0.3374	0.5093	0.0	0.5093	0.5081
0.6998	5	10520	0.7141	0.125	40.0677	0.5093	0.3374	0.5093	0.0	0.5093	0.5081
0.6958	6	12624	0.7067	0.25	75.4704	0.5093	0.3374	0.5093	0.0	0.5093	0.5081

Framework versions

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