939e288661b92f61f880cfebac3fab14

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

• Loss: 0.6592
• Data Size: 0.25
• Epoch Runtime: 211.5803
• 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	0.6735	0	25.3866	0.6320	0.3872	0.6318	0.0	0.6319	0.6317
0.6769	1	11370	0.6582	0.0078	33.2381	0.6320	0.3872	0.6318	0.0	0.6319	0.6317
0.6607	2	22740	0.6575	0.0156	37.6410	0.6320	0.3872	0.6318	0.0	0.6319	0.6317
0.6572	3	34110	0.6576	0.0312	49.7020	0.6320	0.3872	0.6318	0.0	0.6319	0.6317
0.6649	4	45480	0.6587	0.0625	72.0545	0.6320	0.3872	0.6318	0.0	0.6319	0.6317
0.6626	5	56850	0.6588	0.125	121.5581	0.6320	0.3872	0.6318	0.0	0.6319	0.6317
0.657	6	68220	0.6592	0.25	211.5803	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