Phi-3.5-MultiCap-tool-embedding-new – AI Model by sofyc | AlphaNeural AI

You can deploy this model and start earning money today!

sofyc/
Phi-3.5-MultiCap-tool-embedding-new

like

0

generated_from_trainer

microsoft/Phi-3.5-mini-instruct

Views

No views yet

Phi-3.5-MultiCap-tool-embedding-new

This model is a fine-tuned version of microsoft/Phi-3.5-mini-instruct on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.5049

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: 16
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 128
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.03
num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
0.6704	0.2256	50	0.6574
0.5479	0.4512	100	0.5568
0.5243	0.6768	150	0.5327
0.5708	0.9024	200	0.5207
0.5026	1.1280	250	0.5135
0.4922	1.3536	300	0.5091
0.4631	1.5792	350	0.5064
0.5115	1.8049	400	0.5049

Framework versions

PEFT 0.12.0
Transformers 4.44.2
Pytorch 2.4.1+cu124
Datasets 3.0.0
Tokenizers 0.19.1