f479241d4fff5645ba07db456215b9f8

This model is a fine-tuned version of albert/albert-base-v2 on the nyu-mll/glue dataset. It achieves the following results on the evaluation set:

• Loss: 0.6538
• Data Size: 0.5
• Epoch Runtime: 3.3797
• Accuracy: 0.6356
• F1 Macro: 0.5618
• Rouge1: 0.6356
• Rouge2: 0.0
• Rougel: 0.6356
• Rougelsum: 0.6356

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	0.6740	0	1.2588	0.5996	0.5620	0.5985	0.0	0.6002	0.5996
No log	1	114	0.6394	0.0078	1.4573	0.6651	0.3994	0.6657	0.0	0.6645	0.6651
No log	2	228	0.7096	0.0156	1.3418	0.6651	0.3994	0.6657	0.0	0.6645	0.6651
No log	3	342	0.6228	0.0312	1.3963	0.6863	0.4973	0.6869	0.0	0.6857	0.6857
0.0214	4	456	0.6610	0.0625	1.6196	0.6651	0.3994	0.6657	0.0	0.6645	0.6651
0.0214	5	570	0.6438	0.125	1.8473	0.6651	0.3994	0.6657	0.0	0.6645	0.6651
0.0214	6	684	0.6286	0.25	2.3543	0.6651	0.3994	0.6657	0.0	0.6645	0.6651
0.1551	7	798	0.6538	0.5	3.3797	0.6356	0.5618	0.6356	0.0	0.6356	0.6356

Framework versions

• Transformers 4.57.0
• Pytorch 2.8.0+cu128
• Datasets 4.0.0
• Tokenizers 0.22.1