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: 0.3633

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-07
train_batch_size: 2
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 4
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 100
training_steps: 1000

Training results

Training Loss	Epoch	Step	Validation Loss
2.2632	0.2667	50	2.2327
2.0363	0.5333	100	1.9784
1.6467	0.8	150	1.6139
1.338	1.0667	200	1.3164
1.1014	1.3333	250	1.0777
0.9039	1.6	300	0.8796
0.7313	1.8667	350	0.7112
0.5834	2.1333	400	0.5727
0.482	2.4	450	0.4805
0.4329	2.6667	500	0.4345
0.4084	2.9333	550	0.4044
0.3831	3.2	600	0.3850
0.3774	3.4667	650	0.3738
0.3623	3.7333	700	0.3695
0.3553	4.0	750	0.3643
0.3593	4.2667	800	0.3628
0.3619	4.5333	850	0.3635
0.357	4.8	900	0.3632
0.3568	5.0667	950	0.3633
0.3629	5.3333	1000	0.3633

Framework versions

Transformers 4.42.3
Pytorch 2.0.0+cu117
Datasets 2.20.0
Tokenizers 0.19.1

tsavage68/Hyponatremia_L3_1000steps_1e7rate_SFT

Hyponatremia_L3_1000steps_1e7rate_SFT

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

tsavage68/
Hyponatremia_L3_1000steps_1e7rate_SFT