a4e84907a8cba4736b0563c533a222a2

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

• Loss: 0.7389
• Data Size: 1.0
• Epoch Runtime: 1.3188
• Accuracy: 0.4375
• F1 Macro: 0.3043
• Rouge1: 0.4375
• Rouge2: 0.0
• Rougel: 0.4375
• Rougelsum: 0.4375

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	0.7062	0	0.5375	0.4531	0.3547	0.4531	0.0	0.4531	0.4531
No log	1	19	0.7049	0.0078	0.8154	0.4219	0.3361	0.4219	0.0	0.4219	0.4219
No log	2	38	0.7262	0.0156	0.6135	0.4375	0.3043	0.4375	0.0	0.4375	0.4375
No log	3	57	0.7092	0.0312	0.6078	0.4375	0.4092	0.4375	0.0	0.4375	0.4375
No log	4	76	0.7037	0.0625	0.6854	0.5312	0.3469	0.5312	0.0	0.5312	0.5312
No log	5	95	0.7221	0.125	0.6832	0.5	0.4459	0.5	0.0	0.5	0.5
0.0806	6	114	0.7166	0.25	0.7885	0.4062	0.3552	0.4062	0.0	0.4062	0.4062
0.0806	7	133	0.7346	0.5	0.9486	0.4375	0.3043	0.4375	0.0	0.4375	0.4375
0.524	8.0	152	0.7389	1.0	1.3188	0.4375	0.3043	0.4375	0.0	0.4375	0.4375

Framework versions

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