experiments

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

• Loss: 1.6596

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: 0.0001
• train_batch_size: 1
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.05
• num_epochs: 20
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
1.7073	0.4162	50	1.5993
1.4004	0.8325	100	1.4527
1.3051	1.2487	150	1.4122
1.2396	1.6649	200	1.3871
1.2044	2.0812	250	1.3906
1.1019	2.4974	300	1.3775
1.2682	2.9136	350	1.3649
1.1681	3.3299	400	1.4233
1.1343	3.7461	450	1.4160
0.7987	4.1623	500	1.4964
0.8663	4.5786	550	1.5011
0.7473	4.9948	600	1.4845
0.7386	5.4110	650	1.5706
0.61	5.8273	700	1.5695
0.4689	6.2435	750	1.6596

Framework versions

• PEFT 0.11.1
• Transformers 4.41.2
• Pytorch 1.13.1+cu117
• Datasets 2.19.2
• Tokenizers 0.19.1