You can deploy this model and start earning money today!

Litzy619/
Phi30513MA

Name: Phi30513MA
Availability: InStock

safetensors

generated_from_trainer

microsoft/Phi-3-mini-4k-instruct

finetune

mit

Views

No views yet

Phi30513MA

This model is a fine-tuned version of microsoft/Phi-3-mini-4k-instruct on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.0792

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: 0.0003
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 16
total_train_batch_size: 128
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine_with_restarts
lr_scheduler_warmup_steps: 80
num_epochs: 3
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
4.162	0.09	10	2.1516
1.0891	0.18	20	0.3958
0.2412	0.27	30	0.1475
0.1456	0.36	40	0.1307
0.127	0.45	50	0.1272
0.1169	0.54	60	0.0964
0.0967	0.63	70	0.0978
0.0887	0.73	80	0.0936
0.0807	0.82	90	0.0875
0.0837	0.91	100	0.0734
0.0758	1.0	110	0.0739
0.0614	1.09	120	0.0710
0.0552	1.18	130	0.0801
0.0579	1.27	140	0.0727
0.0561	1.36	150	0.0691
0.0616	1.45	160	0.0688
0.0566	1.54	170	0.0676
0.0519	1.63	180	0.0681
0.0514	1.72	190	0.0678
0.0602	1.81	200	0.0634
0.0466	1.9	210	0.0660
0.0481	1.99	220	0.0692
0.0325	2.08	230	0.0737
0.0358	2.18	240	0.0797
0.0265	2.27	250	0.0851
0.0299	2.36	260	0.0870
0.0337	2.45	270	0.0826
0.0292	2.54	280	0.0812
0.0303	2.63	290	0.0813
0.0356	2.72	300	0.0799
0.0358	2.81	310	0.0795
0.0387	2.9	320	0.0792
0.0313	2.99	330	0.0792

Framework versions

Transformers 4.36.0.dev0
Pytorch 2.1.2+cu121
Datasets 2.14.6
Tokenizers 0.14.0

Litzy619/Phi30513MA

Phi30513MA

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Litzy619/
Phi30513MA