You can deploy this model and start earning money today!

leobianco/
npov_RM_mistralai_S12345_LLM_false_STRUCT_false_epo3_lr5e-4_r8_2602261645

Name: npov_RM_mistralai_S12345_LLM_false_STRUCT_false_epo3_lr5e-4_r8_2602261645
Availability: InStock

mistralai/Mistral-7B-Instruct-v0.3

apache-2.0

Views

No views yet

npov_RM_mistralai_S12345_LLM_false_STRUCT_false_epo3_lr5e-4_r8_2602261645

This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.3 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 4.1151
Roc Auc: 0.7942
Best Threshold: 0.8597
Tpr At Best Threshold: 0.7863
Fpr At Best Threshold: 0.2667
Accuracy At Best Threshold: 0.7755
Avg Score True Positives: 0.8767
Avg Score True Negatives: 0.4802

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: 0.0005
train_batch_size: 2
eval_batch_size: 2
seed: 12345
distributed_type: multi-GPU
num_devices: 8
total_train_batch_size: 16
total_eval_batch_size: 16
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss	Roc Auc	Best Threshold	Tpr At Best Threshold	Fpr At Best Threshold	Accuracy At Best Threshold	Avg Score True Positives	Avg Score True Negatives
No log	0	0	159.7755	0.6771	0.0000	0.5043	0.1667	0.5714	0.0112	0.0000
131.75	0.1852	5	66.3129	0.5	inf	0.0	0.0	0.2041	1.0	1.0
10.654	0.3704	10	101.6122	0.5	inf	0.0	0.0	0.2041	1.0	1.0
23.8906	0.5556	15	12.2074	0.5909	0.1656	0.3504	0.1333	0.4558	0.1547	0.1433
85.5625	0.7407	20	42.5335	0.5252	0.0000	0.9060	0.6667	0.7891	0.1991	0.2618
16.1875	0.9259	25	106.3670	0.5338	0.0000	0.8547	0.6	0.7619	0.0000	0.0028
43.625	1.1111	30	46.7415	0.5	inf	0.0	0.0	0.2041	1.0	1.0
76.25	1.2963	35	9.9697	0.5330	0.9954	0.6239	0.5	0.5986	0.9716	0.9662
11.6581	1.4815	40	9.7837	0.6172	0.4533	0.7265	0.5	0.6803	0.6828	0.5212
276.75	1.6667	45	156.9388	0.6829	0.0000	0.4957	0.2	0.5578	0.0000	0.0000
8.2324	1.8519	50	22.1695	0.7647	0.0007	0.9316	0.4333	0.8571	0.1759	0.0649
4.1261	2.0370	55	7.2496	0.7791	0.3074	0.7607	0.2667	0.7551	0.6175	0.2587
10.7249	2.2222	60	6.3134	0.7816	0.9770	0.9231	0.4	0.8571	0.9833	0.7541
4.3552	2.4074	65	8.8142	0.8170	0.9975	0.9402	0.4	0.8707	0.9969	0.8913
19.4756	2.5926	70	6.5862	0.7919	0.2018	0.8547	0.3	0.8231	0.6211	0.2511
2.4759	2.7778	75	4.1670	0.7962	0.9466	0.7607	0.2333	0.7619	0.9139	0.5345
1.0978	2.9630	80	4.1151	0.7942	0.8597	0.7863	0.2667	0.7755	0.8767	0.4802

Framework versions

PEFT 0.18.1
Transformers 4.57.6
Pytorch 2.9.1+cu128
Datasets 4.5.0
Tokenizers 0.22.2

leobianco/npov_RM_mistralai_S12345_LLM_false_STRUCT_false_epo3_lr5e-4_r8_2602261645

npov_RM_mistralai_S12345_LLM_false_STRUCT_false_epo3_lr5e-4_r8_2602261645

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

leobianco/
npov_RM_mistralai_S12345_LLM_false_STRUCT_false_epo3_lr5e-4_r8_2602261645