73eccfe4-db0c-4cad-b0fd-40f6a03b7a4d

This model is a fine-tuned version of HuggingFaceH4/tiny-random-LlamaForCausalLM on the None dataset. It achieves the following results on the evaluation set:

• Loss: 10.2316

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: 0.000213
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• 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	0.0010	1	10.3632
10.3193	0.0490	50	10.3096
10.2496	0.0980	100	10.2516
10.2298	0.1470	150	10.2410
10.2304	0.1960	200	10.2365
10.2258	0.2450	250	10.2345
10.224	0.2940	300	10.2334
10.2195	0.3430	350	10.2327
10.2235	0.3920	400	10.2320
10.2234	0.4410	450	10.2317
10.2244	0.4900	500	10.2316

Framework versions

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