4ec954e2e463d3234bf73f917adf9261

This model is a fine-tuned version of albert/albert-large-v1 on the nyu-mll/glue dataset. It achieves the following results on the evaluation set:

• Loss: 0.7130
• Data Size: 0.5
• Epoch Runtime: 4.9249
• Accuracy: 0.4298
• F1 Macro: 0.4236
• Rouge1: 0.4287
• Rouge2: 0.0
• Rougel: 0.4298
• Rougelsum: 0.4298

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	0.6886	0	1.5319	0.5301	0.5144	0.5307	0.0	0.5295	0.5301
No log	1	114	0.7154	0.0078	2.3502	0.6651	0.3994	0.6657	0.0	0.6645	0.6651
No log	2	228	0.6584	0.0156	1.7106	0.6657	0.4030	0.6663	0.0	0.6657	0.6657
No log	3	342	0.6403	0.0312	1.8707	0.6651	0.3994	0.6657	0.0	0.6645	0.6651
0.0213	4	456	0.6611	0.0625	2.1084	0.6922	0.5515	0.6922	0.0	0.6916	0.6922
0.0213	5	570	0.6540	0.125	2.4783	0.6651	0.3994	0.6657	0.0	0.6645	0.6651
0.0213	6	684	0.6456	0.25	3.2542	0.6651	0.3994	0.6657	0.0	0.6645	0.6651
0.1581	7	798	0.7130	0.5	4.9249	0.4298	0.4236	0.4287	0.0	0.4298	0.4298

Framework versions

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