Gemma-2-9B_task-2_60-samples_config_1

This model is a fine-tuned version of google/gemma-2-9b-it on the GaetanMichelet/chat_60_ft_t2 dataset. It achieves the following results on the evaluation set:

• Loss: 0.9765

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: 0.0002
• train_batch_size: 1
• eval_batch_size: 2
• 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
1.3686	0.9362	11	1.2919
1.1305	1.9574	23	1.1233
1.0025	2.9787	35	1.0144
0.8869	4.0	47	0.9765
0.8268	4.9362	58	0.9949
0.7453	5.9574	70	1.0588
0.5888	6.9787	82	1.2111
0.4427	8.0	94	1.4423
0.2953	8.9362	105	1.6260
0.2186	9.9574	117	1.7576
0.1719	10.9787	129	1.8585

Framework versions

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