b513dc822c4a7d713a5cd928286c77cc

This model is a fine-tuned version of facebook/opt-6.7b on the nyu-mll/glue [cola] dataset. It achieves the following results on the evaluation set:

• Loss: 0.6666
• Data Size: 0.25
• Epoch Runtime: 56.9136
• 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	1.1936	0	3.0392	0.3467	0.3097	0.3467	0.0	0.3467	0.3467
No log	1	267	1.2652	0.0078	5.2514	0.3135	0.2407	0.3125	0.0	0.3135	0.3135
No log	2	534	0.6217	0.0156	16.6519	0.6885	0.4078	0.6895	0.0	0.6885	0.6885
No log	3	801	1.1132	0.0312	27.4845	0.6885	0.4078	0.6895	0.0	0.6885	0.6885
No log	4	1068	0.6240	0.0625	38.7960	0.6885	0.4078	0.6895	0.0	0.6885	0.6885
0.0503	5	1335	0.8241	0.125	55.9030	0.6885	0.4078	0.6895	0.0	0.6885	0.6885
0.6324	6	1602	0.6666	0.25	56.9136	0.6885	0.4078	0.6895	0.0	0.6885	0.6885

Framework versions

• Transformers 4.57.0
• Pytorch 2.8.0+cu128
• Datasets 4.3.0
• Tokenizers 0.22.1