6de3d103ce038fd102307aa104e79b25

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: 0.7504
• Data Size: 1.0
• Epoch Runtime: 2.1358
• Accuracy: 0.4844
• F1 Macro: 0.4812
• Rouge1: 0.4844
• Rouge2: 0.0
• Rougel: 0.4844
• Rougelsum: 0.4844

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	0.7305	0	0.6412	0.5625	0.36	0.5625	0.0	0.5625	0.5625
No log	1	19	0.8966	0.0078	1.3086	0.4375	0.3043	0.4375	0.0	0.4375	0.4375
No log	2	38	0.7915	0.0156	0.8196	0.4375	0.3043	0.4375	0.0	0.4375	0.4375
No log	3	57	0.6961	0.0312	0.8787	0.3594	0.3554	0.3594	0.0	0.3594	0.3594
No log	4	76	0.6848	0.0625	0.9320	0.5625	0.36	0.5625	0.0	0.5625	0.5625
No log	5	95	0.6938	0.125	1.1805	0.5	0.3816	0.5	0.0	0.5	0.5
0.0844	6	114	0.6878	0.25	1.2332	0.5938	0.4583	0.5938	0.0	0.5938	0.5938
0.0844	7	133	0.6902	0.5	1.5576	0.4531	0.4465	0.4531	0.0	0.4531	0.4531
0.556	8.0	152	0.7504	1.0	2.1358	0.4844	0.4812	0.4844	0.0	0.4844	0.4844

Framework versions

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