Phi0503HMA7

Litzy619/Phi0503HMA7

Phi0503HMA7 is a machine learning model from Litzy619. Use it for the machine learning task on the model card, and read the license before you ship it in a product.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

Access

Public

Updated May 6, 2024

Parameters

3.9B

8.4 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors7.9 GB · 95%

Parameter types

How the weights are stored.

BF163.8B · 98%

Base models

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

Model card

From the Hugging Face model README

Phi0503HMA7

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: 0.0740

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: 100
num_epochs: 3
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
4.7716	0.09	10	1.5978
0.6746	0.18	20	0.3112
0.2767	0.27	30	0.2928
0.2464	0.36	40	0.2414
0.2371	0.45	50	0.2208
0.2186	0.54	60	0.1812
0.1417	0.63	70	0.1198
0.1133	0.73	80	0.0939
0.0903	0.82	90	0.0932
0.0878	0.91	100	0.0790
0.0861	1.0	110	0.0991
0.0751	1.09	120	0.0725
0.108	1.18	130	0.0977
0.0877	1.27	140	0.0792
0.0675	1.36	150	0.0733
0.0766	1.45	160	0.0715
0.0681	1.54	170	0.0708
0.0656	1.63	180	0.0665
0.0578	1.72	190	0.0660
0.0668	1.81	200	0.0655
0.0551	1.9	210	0.0673
0.0588	1.99	220	0.0670
0.0376	2.08	230	0.0686
0.0363	2.18	240	0.0813
0.0292	2.27	250	0.0874
0.0316	2.36	260	0.0777
0.0352	2.45	270	0.0751
0.0267	2.54	280	0.0772
0.0284	2.63	290	0.0779
0.0352	2.72	300	0.0759
0.037	2.81	310	0.0748
0.031	2.9	320	0.0740
0.0313	2.99	330	0.0740

Framework versions

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

Created: May 6, 2024
Updated: May 6, 2024