Llama-3.1-8B-INBioCR-sp-records-PLIC-v1 – AI Model by mariamoracrossitcr | AlphaNeural AI

You can deploy this model and start earning money today!

mariamoracrossitcr/
Llama-3.1-8B-INBioCR-sp-records-PLIC-v1

like

0

generated_from_trainer

meta-llama/Llama-3.1-8B-Instruct

Views

No views yet

Llama-3.1-8B-INBioCR-sp-records-PLIC-v1

This model is a fine-tuned version of meta-llama/Llama-3.1-8B-Instruct on the None dataset. It achieves the following results on the evaluation set:

Loss: 1.3067

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: 4
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 16
total_train_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 7

Training results

Training Loss	Epoch	Step	Validation Loss
1.4661	0.2857	100	1.8582
1.1703	0.5714	200	1.7866
1.0921	0.8571	300	1.6844
0.9299	1.1429	400	1.6447
0.9029	1.4286	500	1.5695
0.8424	1.7143	600	1.4560
0.8252	2.0	700	1.3701
0.6518	2.2857	800	1.3411
0.6574	2.5714	900	1.3303
0.6706	2.8571	1000	1.2702
0.4881	3.1429	1100	1.3205
0.4948	3.4286	1200	1.2683
0.4964	3.7143	1300	1.2272
0.5122	4.0	1400	1.2030
0.3416	4.2857	1500	1.2520
0.3573	4.5714	1600	1.2461
0.3164	4.8571	1700	1.2374
0.205	5.1429	1800	1.3244
0.2078	5.4286	1900	1.3067

Framework versions

PEFT 0.10.0
Transformers 4.45.2
Pytorch 2.0.1+cu117
Datasets 4.0.0
Tokenizers 0.20.3