llama_3b_step2_batch_v6

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.3283

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: 3e-05
• train_batch_size: 12
• eval_batch_size: 40
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 48
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
0.7711	0.2045	50	0.7348
0.6015	0.4090	100	0.5288
0.4361	0.6135	150	0.4369
0.4042	0.8180	200	0.3823
0.2702	1.0225	250	0.3534
0.2904	1.2270	300	0.3452
0.2778	1.4315	350	0.3350
0.2673	1.6360	400	0.3308
0.2258	1.8405	450	0.3283

Framework versions

• Transformers 4.46.1
• Pytorch 2.1.0+cu118
• Datasets 3.0.2
• Tokenizers 0.20.1