git-base-xr

This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.0641
• Bleu: 9.4387

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: 32
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 50
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu
3.5821	5.26	50	1.2163	4.6142
0.8599	10.53	100	0.8719	10.5680
0.5491	15.79	150	0.8546	9.7374
0.3605	21.05	200	0.8975	10.2395
0.2409	26.32	250	0.9652	9.8718
0.1664	31.58	300	1.0042	11.7264
0.1234	36.84	350	1.0462	10.5668
0.1002	42.11	400	1.0569	9.7232
0.0876	47.37	450	1.0641	9.4387

Framework versions

• Transformers 4.27.3
• Pytorch 2.1.0+cu121
• Datasets 2.14.7
• Tokenizers 0.13.3