64f1aeb3dcfd40ad2c7298f590919c10

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: 0.6934
• Data Size: 1.0
• Epoch Runtime: 215.7032
• Accuracy: 0.4943
• F1 Macro: 0.3308
• Rouge1: 0.4947
• Rouge2: 0.0
• Rougel: 0.4943
• Rougelsum: 0.4944

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	0.7010	0	4.0038	0.4824	0.4155	0.4822	0.0	0.4825	0.4824
No log	1	3273	0.6997	0.0078	5.9706	0.5149	0.4646	0.5149	0.0	0.5143	0.5149
0.0113	2	6546	0.7108	0.0156	7.4290	0.5057	0.3359	0.5053	0.0	0.5057	0.5056
0.7127	3	9819	0.7127	0.0312	10.5526	0.4943	0.3308	0.4947	0.0	0.4943	0.4944
0.7007	4	13092	0.6932	0.0625	17.0746	0.5057	0.3359	0.5053	0.0	0.5057	0.5056
0.6991	5	16365	0.7012	0.125	29.8681	0.5057	0.3359	0.5053	0.0	0.5057	0.5056
0.6957	6	19638	0.6936	0.25	55.5806	0.4943	0.3308	0.4947	0.0	0.4943	0.4944
0.6962	7	22911	0.6960	0.5	108.9770	0.4943	0.3308	0.4947	0.0	0.4943	0.4944
0.6935	8.0	26184	0.6934	1.0	215.7032	0.4943	0.3308	0.4947	0.0	0.4943	0.4944

Framework versions

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