Llama2-jp-127M-2 – AI Model by HachiML | AlphaNeural AI

You can deploy this model and start earning money today!

HachiML/
Llama2-jp-127M-2

like

0

text-generation

generated_from_trainer

autotrain_compatible

text-generation-inference

endpoints_compatible

Views

No views yet

Llama2-jp-127M-2

This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 2.5366

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: 0.0024
train_batch_size: 192
eval_batch_size: 192
seed: 42
optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 2500
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
4.5846	0.05	1000	3.5530
3.3978	0.1	2000	3.3095
3.2474	0.15	3000	3.1697
3.1079	0.2	4000	3.0595
3.0201	0.25	5000	2.9864
2.9566	0.29	6000	2.9366
2.9115	0.34	7000	2.8954
2.8732	0.39	8000	2.8627
2.8423	0.44	9000	2.8328
2.8131	0.49	10000	2.8052
2.7855	0.54	11000	2.7809
2.7623	0.59	12000	2.7551
2.737	0.64	13000	2.7301
2.7102	0.69	14000	2.7039
2.686	0.74	15000	2.6771
2.6554	0.79	16000	2.6495
2.6273	0.83	17000	2.6208
2.5984	0.88	18000	2.5911
2.5693	0.93	19000	2.5611
2.5391	0.98	20000	2.5366

Framework versions

Transformers 4.39.2
Pytorch 2.2.1+cu121
Datasets 2.18.0
Tokenizers 0.15.2