easylm-helpsteer-sft-gemma-2-2b

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

• Loss: 1.1448

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: 3e-06
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• total_train_batch_size: 4
• total_eval_batch_size: 4
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
1.1281	0.2864	500	1.1230
1.183	0.5727	1000	1.1017
1.1009	0.8591	1500	1.0869
0.6901	1.1455	2000	1.1486
0.7377	1.4318	2500	1.1488
0.6947	1.7182	3000	1.1501

Framework versions

• Transformers 4.43.3
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1