llama-3.1-coherence-reg-adapter

This model is a fine-tuned version of meta-llama/Llama-3.1-8B-Instruct on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.3659
• Mse: 0.3659
• Rmse: 0.6049
• Mae: 0.4649
• R2: 0.1011
• Rounded Accuracy: 0.6873
• Mae Class 0: 2.9010
• Mse Class 0: 8.5636
• Mae Class 1: 2.2816
• Mse Class 1: 5.3301
• Mae Class 2: 1.4010
• Mse Class 2: 2.0718
• Mae Class 3: 0.6129
• Mse Class 3: 0.4212
• Mae Class 4: 0.3256
• Mse Class 4: 0.1442
• Pred Count 0: 0
• Pred Percent 0: 0.0
• Pred Count 1: 1
• Pred Percent 1: 0.0246
• Pred Count 2: 14
• Pred Percent 2: 0.3444
• Pred Count 3: 671
• Pred Percent 3: 16.5068
• Pred Count 4: 3379
• Pred Percent 4: 83.1242

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: 2e-05
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 8
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 1
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Mse	Rmse	Mae	R2	Rounded Accuracy	Mae Class 0	Mse Class 0	Mae Class 1	Mse Class 1	Mae Class 2	Mse Class 2	Mae Class 3	Mse Class 3	Mae Class 4	Mse Class 4	Pred Count 0	Pred Percent 0	Pred Count 1	Pred Percent 1	Pred Count 2	Pred Percent 2	Pred Count 3	Pred Percent 3	Pred Count 4	Pred Percent 4
0.4377	0.2460	500	0.5783	0.5783	0.7604	0.6132	-0.4208	0.4396	3.1517	10.6746	2.3930	6.0712	1.3554	1.9757	0.4875	0.4073	0.5703	0.4337	11	0.2706	10	0.2460	40	0.9840	2396	58.9422	1608	39.5572
0.5224	0.4920	1000	0.4044	0.4044	0.6359	0.5216	0.0063	0.6369	2.9176	8.7381	2.3312	5.5281	1.3939	2.0149	0.5432	0.3448	0.4252	0.2213	1	0.0246	7	0.1722	24	0.5904	1108	27.2571	2925	71.9557
0.3067	0.7381	1500	0.3962	0.3962	0.6294	0.5328	0.0265	0.5808	2.6475	7.1262	2.1129	4.5911	1.2537	1.6802	0.4870	0.2874	0.4709	0.2670	0	0.0	2	0.0492	30	0.7380	1598	39.3112	2435	59.9016
0.3516	0.9841	2000	0.3659	0.3659	0.6049	0.4649	0.1011	0.6873	2.9010	8.5636	2.2816	5.3301	1.4010	2.0718	0.6129	0.4212	0.3256	0.1442	0	0.0	1	0.0246	14	0.3444	671	16.5068	3379	83.1242

Framework versions

• PEFT 0.13.2
• Transformers 4.49.0
• Pytorch 2.5.1+cu124
• Datasets 3.3.2
• Tokenizers 0.21.1