Not-so-bright-AGI-v1

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

• Loss: 2.0548

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training Hardware

This model was trained using Intel(R) Data Center GPU Max 1100

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 1e-05
• train_batch_size: 4
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.05
• training_steps: 1480

Training results

Training Loss	Epoch	Step	Validation Loss
2.9165	3.2	100	2.6762
2.419	6.4	200	2.3629
2.2343	9.6	300	2.2060
2.1459	12.8	400	2.1401
2.0944	16.0	500	2.1112
2.0679	19.2	600	2.0942
2.0496	22.4	700	2.0826
2.0375	25.6	800	2.0743
2.0213	28.8	900	2.0684
2.0148	32.0	1000	2.0630
2.0048	35.2	1100	2.0593
1.9988	38.4	1200	2.0575
1.9968	41.6	1300	2.0555
1.9908	44.8	1400	2.0548

Framework versions

• PEFT 0.10.0
• Transformers 4.40.0
• Pytorch 2.0.1a0+cxx11.abi
• Datasets 2.19.0
• Tokenizers 0.19.1