train_conala_789_1760637892

This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on the conala dataset. It achieves the following results on the evaluation set:

• Loss: 1.1368
• Num Input Tokens Seen: 2714120

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: 1e-05
• train_batch_size: 4
• eval_batch_size: 4
• seed: 789
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Input Tokens Seen
0.6415	2.0	952	0.8811	271168
0.5447	4.0	1904	0.7161	542936
0.6234	6.0	2856	0.7178	814760
0.6093	8.0	3808	0.7429	1085912
0.4363	10.0	4760	0.7995	1357864
0.2728	12.0	5712	0.9195	1628872
0.2534	14.0	6664	1.0041	1899816
0.1375	16.0	7616	1.0649	2170440
0.2398	18.0	8568	1.1317	2442368
0.1896	20.0	9520	1.1368	2714120

Framework versions

• PEFT 0.17.1
• Transformers 4.51.3
• Pytorch 2.9.0+cu128
• Datasets 4.0.0
• Tokenizers 0.21.4