getcode

This model is a fine-tuned version of facebook/opt-125m on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.3129

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: 0.0004
• train_batch_size: 16
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 128
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 20
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	22	1.8588
No log	2.0	44	1.4885
No log	3.0	66	1.3922
No log	4.0	88	1.3830
No log	5.0	110	1.3547
No log	6.0	132	1.3556
No log	7.0	154	1.3672
No log	8.0	176	1.3509
No log	9.0	198	1.3414
No log	10.0	220	1.3428
No log	11.0	242	1.3361
No log	12.0	264	1.3332
No log	13.0	286	1.3333
No log	14.0	308	1.3280
No log	15.0	330	1.3232
No log	16.0	352	1.3215
No log	17.0	374	1.3185
No log	18.0	396	1.3142
No log	19.0	418	1.3129
No log	19.0947	420	1.3129

Framework versions

• Transformers 4.47.0
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0