b1d5e7f1e16c8c78496a007e022eaf53

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

• Loss: 0.6581
• Data Size: 1.0
• Epoch Runtime: 785.6590
• Accuracy: 0.6320
• F1 Macro: 0.3872
• Rouge1: 0.6318
• Rouge2: 0.0
• Rougel: 0.6319
• Rougelsum: 0.6317

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	0.6712	0	25.4183	0.6281	0.3892	0.6280	0.0	0.6281	0.6279
0.5291	1	11370	0.6753	0.0078	31.4037	0.6320	0.3872	0.6318	0.0	0.6319	0.6317
0.6585	2	22740	0.6609	0.0156	36.5149	0.6320	0.3872	0.6318	0.0	0.6319	0.6317
0.6613	3	34110	0.6689	0.0312	47.9635	0.6320	0.3872	0.6318	0.0	0.6319	0.6317
0.6668	4	45480	0.6589	0.0625	70.2682	0.6320	0.3872	0.6318	0.0	0.6319	0.6317
0.6593	5	56850	0.6591	0.125	115.9517	0.6320	0.3872	0.6318	0.0	0.6319	0.6317
0.6558	6	68220	0.6593	0.25	209.9690	0.6320	0.3872	0.6318	0.0	0.6319	0.6317
0.6565	7	79590	0.6579	0.5	407.2675	0.6320	0.3872	0.6318	0.0	0.6319	0.6317
0.654	8.0	90960	0.6572	1.0	786.5616	0.6320	0.3872	0.6318	0.0	0.6319	0.6317
0.6568	9.0	102330	0.6564	1.0	785.2712	0.6320	0.3872	0.6318	0.0	0.6319	0.6317
0.6666	10.0	113700	0.6578	1.0	786.4610	0.6320	0.3872	0.6318	0.0	0.6319	0.6317
0.6563	11.0	125070	0.6606	1.0	786.0289	0.6320	0.3872	0.6318	0.0	0.6319	0.6317
0.652	12.0	136440	0.6568	1.0	786.1918	0.6320	0.3872	0.6318	0.0	0.6319	0.6317
0.6629	13.0	147810	0.6581	1.0	785.6590	0.6320	0.3872	0.6318	0.0	0.6319	0.6317

Framework versions

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