Gemma-2-2B_task-1_180-samples_config-1_full

This model is a fine-tuned version of google/gemma-2-2b-it on the GaetanMichelet/chat-60_ft_task-1, the GaetanMichelet/chat-120_ft_task-1 and the GaetanMichelet/chat-180_ft_task-1 datasets. It achieves the following results on the evaluation set:

• Loss: 1.0148

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: 1
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• gradient_accumulation_steps: 8
• total_train_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss
2.367	1.0	17	2.2712
1.5938	2.0	34	1.5141
1.1165	3.0	51	1.1452
0.957	4.0	68	1.0573
0.9136	5.0	85	1.0238
0.7999	6.0	102	1.0148
0.6625	7.0	119	1.0485
0.5317	8.0	136	1.1846
0.3318	9.0	153	1.4029
0.2543	10.0	170	1.6159
0.183	11.0	187	1.8190
0.1305	12.0	204	1.9711
0.1007	13.0	221	2.0467

Framework versions

• PEFT 0.12.0
• Transformers 4.44.0
• Pytorch 2.1.2+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1