You can deploy this model and start earning money today!

leobianco/
npov_RM_mistralai_S12345_LLM_false_STRUCT_false_epo10_lr5e-4_r8_2602251119

Name: npov_RM_mistralai_S12345_LLM_false_STRUCT_false_epo10_lr5e-4_r8_2602251119
Availability: InStock

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

apache-2.0

Views

No views yet

npov_RM_mistralai_S12345_LLM_false_STRUCT_false_epo10_lr5e-4_r8_2602251119

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: 4.1686
Roc Auc: 0.5822
Best Threshold: 0.7691
Tpr At Best Threshold: 0.8120
Fpr At Best Threshold: 0.6
Accuracy At Best Threshold: 0.7279
Avg Score True Positives: 0.8375
Avg Score True Negatives: 0.8120

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: 10.0

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	161.0884	0.6632	0.0000	0.5043	0.1667	0.5714	0.0112	0.0000
19.9376	0.1852	5	36.5425	0.4786	0.9999	0.9915	0.9667	0.7959	1.0000	1.0000
14.4927	0.3704	10	8.6625	0.7211	0.9693	0.6838	0.2	0.7075	0.8120	0.6520
82.7188	0.5556	15	91.1633	0.7644	0.0000	0.7350	0.2667	0.7347	0.0278	0.0000
20.5788	0.7407	20	15.7191	0.7691	0.0385	0.6239	0.1667	0.6667	0.3402	0.0328
11.0703	0.9259	25	4.3175	0.8019	0.4321	0.8205	0.3333	0.7891	0.6203	0.4088
3.4805	1.1111	30	3.8418	0.7905	0.6575	0.6923	0.2	0.7143	0.6932	0.5722
6.0312	1.2963	35	3.3625	0.8640	0.8295	0.7949	0.2	0.7959	0.8801	0.7730
20.125	1.4815	40	47.3741	0.5167	1.0	1.0	0.9667	0.8027	1.0	1.0
72.3125	1.6667	45	38.9354	0.4722	inf	0.0	0.0	0.2041	1.0000	1.0
59.75	1.8519	50	51.8503	0.5167	1.0	1.0	0.9667	0.8027	1.0	1.0
58.125	2.0370	55	82.7143	0.5	inf	0.0	0.0	0.2041	1.0	1.0
45.5	2.2222	60	82.7092	0.4754	0.0000	0.7692	0.6667	0.6803	0.0000	0.0000
54.9377	2.4074	65	49.4973	0.4556	0.0003	0.7949	0.7	0.6939	0.0004	0.0005
22.8516	2.5926	70	9.8008	0.4697	0.9932	1.0	0.9333	0.8095	0.9968	0.9966
5.7205	2.7778	75	8.3371	0.4919	0.9913	0.8718	0.7667	0.7415	0.9931	0.9932
6.486	2.9630	80	5.8389	0.4249	inf	0.0	0.0	0.2041	0.4783	0.4928
5.4062	3.1481	85	5.3790	0.4151	0.6077	0.1111	0.0667	0.2789	0.5301	0.5447
5.5312	3.3333	90	5.2356	0.5168	0.9408	0.8034	0.6667	0.7075	0.9478	0.9463
4.0155	3.5185	95	6.0495	0.4886	0.9763	0.2308	0.1667	0.3537	0.9694	0.9693
17.2188	3.7037	100	6.0490	0.4044	0.9466	0.9829	0.9333	0.7959	0.9614	0.9647
3.3357	3.8889	105	6.1911	0.5098	0.9573	0.7009	0.5333	0.6531	0.9611	0.9620
6.7288	4.0741	110	5.2202	0.4825	0.8933	0.9231	0.8333	0.7687	0.9169	0.9194
23.7352	4.2593	115	13.7118	0.5009	0.9996	0.8718	0.7333	0.7483	0.9997	0.9997
13.3002	4.4444	120	4.3659	0.5188	0.8199	0.6496	0.4667	0.6259	0.8284	0.8296
15.7814	4.6296	125	21.1514	0.5010	1.0000	0.7607	0.7	0.6667	1.0000	1.0000
4.6221	4.8148	130	19.5603	0.5410	0.0427	0.6923	0.6	0.6327	0.0474	0.0460
5.4609	5.0	135	25.9381	0.5648	0.0178	0.4530	0.3	0.5034	0.0173	0.0165
10.5834	5.1852	140	14.5808	0.5741	0.9998	0.7436	0.5333	0.6871	0.9999	0.9998
4.9375	5.3704	145	9.3202	0.5412	0.2227	0.7778	0.6333	0.6939	0.2510	0.2445
3.2402	5.5556	150	6.0023	0.5764	0.9669	0.8120	0.6333	0.7211	0.9711	0.9690
5.3359	5.7407	155	9.0875	0.5540	0.9950	0.8120	0.6333	0.7211	0.9958	0.9955
3.1426	5.9259	160	6.9252	0.5490	0.3346	0.7863	0.6333	0.7007	0.3862	0.3746
3.0938	6.1111	165	7.3782	0.4967	0.2751	0.9316	0.7667	0.7891	0.3552	0.3540
14.3392	6.2963	170	9.0329	0.5266	0.9957	0.4872	0.3667	0.5170	0.9954	0.9952
8.5117	6.4815	175	15.5476	0.5603	0.0907	0.4274	0.2667	0.4898	0.0904	0.0876
2.0107	6.6667	180	4.5418	0.5259	0.8991	0.6667	0.5667	0.6190	0.9039	0.9018
5.7388	6.8519	185	5.3194	0.5865	0.9381	0.8803	0.6333	0.7755	0.9493	0.9466
4.9004	7.0370	190	4.2516	0.5088	0.7663	0.8205	0.6667	0.7211	0.7990	0.8014
5.9492	7.2222	195	6.2479	0.5165	0.4187	0.7436	0.6	0.6735	0.4612	0.4787
1.6755	7.4074	200	4.9111	0.5004	0.8824	0.8205	0.7	0.7143	0.9036	0.9016
2.9902	7.5926	205	4.6144	0.5154	0.6298	0.7179	0.6	0.6531	0.6801	0.6811
4.1665	7.7778	210	4.3340	0.5580	0.6406	0.8547	0.6333	0.7551	0.7229	0.7124
2.7866	7.9630	215	4.2470	0.5450	0.8459	0.5897	0.4333	0.5850	0.8493	0.8419
5.0664	8.1481	220	6.6197	0.5850	0.3558	0.7436	0.5	0.6939	0.4114	0.3868
3.1221	8.3333	225	4.0871	0.5832	0.7691	0.8205	0.6333	0.7279	0.8173	0.8033
2.7666	8.5185	230	4.1106	0.5796	0.8222	0.6496	0.4333	0.6327	0.8316	0.8127
2.4902	8.7037	235	4.2720	0.5585	0.6406	0.7436	0.6	0.6735	0.7102	0.6898
3.3291	8.8889	240	4.4647	0.5981	0.5927	0.7607	0.5333	0.7007	0.6602	0.6181
3.5513	9.0741	245	4.1495	0.5742	0.6442	0.8718	0.7	0.7551	0.7586	0.7308
2.6328	9.2593	250	4.6705	0.5946	0.6370	0.5128	0.3	0.5510	0.6283	0.5804
2.71	9.4444	255	4.2790	0.5969	0.6225	0.7692	0.5333	0.7075	0.7071	0.6611
2.1523	9.6296	260	4.1214	0.5816	0.7122	0.8376	0.6333	0.7415	0.8033	0.7726
2.396	9.8148	265	4.1297	0.5880	0.7461	0.8718	0.6667	0.7619	0.8349	0.8031
2.9309	10.0	270	4.1686	0.5822	0.7691	0.8120	0.6	0.7279	0.8375	0.8120

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_epo10_lr5e-4_r8_2602251119

npov_RM_mistralai_S12345_LLM_false_STRUCT_false_epo10_lr5e-4_r8_2602251119

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_epo10_lr5e-4_r8_2602251119