d5f5997d-510d-4897-b18d-f1d5f7107c2a

This model is a fine-tuned version of fxmarty/tiny-random-GemmaForCausalLM on the None dataset. It achieves the following results on the evaluation set:

• Loss: 12.3041

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: 0.000204
• train_batch_size: 4
• eval_batch_size: 4
• seed: 40
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 50
• training_steps: 500

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0000	1	12.4524
12.4525	0.0015	50	12.4469
12.358	0.0030	100	12.3648
12.2995	0.0046	150	12.3228
12.2807	0.0061	200	12.3123
12.2783	0.0076	250	12.3079
12.2696	0.0091	300	12.3059
12.2706	0.0107	350	12.3049
12.2755	0.0122	400	12.3043
12.271	0.0137	450	12.3042
12.2699	0.0152	500	12.3041

Framework versions

• PEFT 0.13.2
• Transformers 4.46.0
• Pytorch 2.5.0+cu124
• Datasets 3.0.1
• Tokenizers 0.20.1