364f3cb8be37487da327a4b9e7b21db6

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: 0.6203
• Data Size: 1.0
• Epoch Runtime: 18.4563
• Accuracy: 0.6885
• F1 Macro: 0.4078
• Rouge1: 0.6895
• Rouge2: 0.0
• Rougel: 0.6885
• Rougelsum: 0.6885

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	0.9244	0	1.2587	0.3115	0.2375	0.3105	0.0	0.3115	0.3115
No log	1	267	0.7516	0.0078	2.3332	0.3252	0.2623	0.3247	0.0	0.3242	0.3252
No log	2	534	0.6663	0.0156	1.6425	0.6855	0.4097	0.6860	0.0	0.6855	0.6846
No log	3	801	0.6601	0.0312	2.0593	0.6885	0.4078	0.6895	0.0	0.6885	0.6885
No log	4	1068	0.6239	0.0625	2.5486	0.6885	0.4078	0.6895	0.0	0.6885	0.6885
0.039	5	1335	0.6780	0.125	3.6344	0.6885	0.4078	0.6895	0.0	0.6885	0.6885
0.6234	6	1602	0.6325	0.25	5.7406	0.6885	0.4078	0.6895	0.0	0.6885	0.6885
0.6221	7	1869	0.6496	0.5	10.0145	0.6885	0.4078	0.6895	0.0	0.6885	0.6885
0.6057	8.0	2136	0.6215	1.0	18.5374	0.6885	0.4078	0.6895	0.0	0.6885	0.6885
0.6121	9.0	2403	0.6457	1.0	18.5910	0.6885	0.4078	0.6895	0.0	0.6885	0.6885
0.619	10.0	2670	0.6204	1.0	18.5799	0.6885	0.4078	0.6895	0.0	0.6885	0.6885
0.6186	11.0	2937	0.6215	1.0	18.6167	0.6885	0.4078	0.6895	0.0	0.6885	0.6885
0.625	12.0	3204	0.6189	1.0	18.2625	0.6885	0.4078	0.6895	0.0	0.6885	0.6885
0.6155	13.0	3471	0.6207	1.0	18.6488	0.6885	0.4078	0.6895	0.0	0.6885	0.6885
0.6248	14.0	3738	0.6209	1.0	18.8002	0.6885	0.4078	0.6895	0.0	0.6885	0.6885
0.5885	15.0	4005	0.6289	1.0	18.5706	0.6885	0.4078	0.6895	0.0	0.6885	0.6885
0.6225	16.0	4272	0.6203	1.0	18.4563	0.6885	0.4078	0.6895	0.0	0.6885	0.6885

Framework versions

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