gemma-2-2b-it-finetuned – AI Model by GokalpKurtoglu | AlphaNeural AI

You can deploy this model and start earning money today!

GokalpKurtoglu/
gemma-2-2b-it-finetuned

like

0

generated_from_trainer

google/gemma-2b-it

Views

No views yet

gemma-2-2b-it-finetuned

This model is a fine-tuned version of google/gemma-2b-it on the generator dataset. It achieves the following results on the evaluation set:

Loss: 1.9628

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: 1e-05
train_batch_size: 2
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.05
training_steps: 2854

Training results

Training Loss	Epoch	Step	Validation Loss
4.1325	0.07	100	3.1863
2.6954	0.14	200	2.4294
2.3184	0.21	300	2.2474
2.1949	0.28	400	2.1646
2.1302	0.35	500	2.1161
2.0905	0.42	600	2.0855
2.0729	0.49	700	2.0642
2.0425	0.56	800	2.0481
2.0312	0.63	900	2.0352
2.0261	0.7	1000	2.0248
2.0188	0.77	1100	2.0154
2.0001	0.84	1200	2.0075
2.0025	0.91	1300	2.0009
1.989	0.98	1400	1.9947
1.9721	1.05	1500	1.9899
1.9664	1.12	1600	1.9855
1.9846	1.19	1700	1.9816
1.9556	1.26	1800	1.9782
1.9604	1.33	1900	1.9752
1.9507	1.4	2000	1.9725
1.9434	1.47	2100	1.9703
1.9558	1.54	2200	1.9684
1.9568	1.61	2300	1.9669
1.9563	1.68	2400	1.9655
1.9524	1.75	2500	1.9644
1.9459	1.82	2600	1.9636
1.9411	1.89	2700	1.9631
1.9624	1.96	2800	1.9628

Framework versions

PEFT 0.10.0
Transformers 4.38.2
Pytorch 2.5.1+cxx11.abi
Datasets 3.3.2
Tokenizers 0.15.2