llama-3.1-70B-Instruct_playpen_SFT_DFINAL_1.1K-steps

This model is a fine-tuned version of meta-llama/Llama-3.1-70B-Instruct on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.2117

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: 0.0002
• train_batch_size: 4
• eval_batch_size: 8
• seed: 7331
• optimizer: Use adamw_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.03
• lr_scheduler_warmup_steps: 5
• training_steps: 1100

Training results

Training Loss	Epoch	Step	Validation Loss
0.1986	0.0565	100	0.3041
0.304	0.1130	200	0.2570
0.1929	0.1695	300	0.2578
0.149	0.2260	400	0.2319
0.1458	0.2825	500	0.2283
0.1391	0.3390	600	0.2314
0.0896	0.3955	700	0.2175
0.1225	0.4520	800	0.2172
0.0894	0.5085	900	0.2137
0.1038	0.5650	1000	0.2112
0.1273	0.6215	1100	0.2117

Framework versions

• PEFT 0.14.0
• Transformers 4.47.1
• Pytorch 2.4.0+cu121
• Datasets 2.21.0
• Tokenizers 0.21.0