Gemma-2-2B_task-1_180-samples_config-2_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: 1.0226

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: 16
total_train_batch_size: 16
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
2.5025	0.9412	8	2.4361
2.0775	2.0	17	1.9082
1.63	2.9412	25	1.4719
1.1623	4.0	34	1.1816
1.0588	4.9412	42	1.0970
1.0217	6.0	51	1.0481
0.914	6.9412	59	1.0288
0.8449	8.0	68	1.0226
0.7558	8.9412	76	1.0447
0.6646	10.0	85	1.0844
0.5742	10.9412	93	1.1509
0.3766	12.0	102	1.3010
0.3088	12.9412	110	1.5293
0.2417	14.0	119	1.7321
0.1632	14.9412	127	1.9126