You can deploy this model and start earning money today!

leobianco/
npov_RM_mistralai_S12345_LLM_false_STRUCT_true_epo5_lr5e-4_r8_2602031226

Name: npov_RM_mistralai_S12345_LLM_false_STRUCT_true_epo5_lr5e-4_r8_2602031226
Availability: InStock

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

apache-2.0

Views

No views yet

npov_RM_mistralai_S12345_LLM_false_STRUCT_true_epo5_lr5e-4_r8_2602031226

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: 42.0863
Roc Auc: 0.7501
Best Threshold: 1.0000
Tpr At Best Threshold: 0.9658
Fpr At Best Threshold: 0.4667
Accuracy At Best Threshold: 0.8776
Avg Score True Positives: 0.9658
Avg Score True Negatives: 0.5228

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: 5.0

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	166.3551	0.4440	0.0000	0.5897	0.5667	0.5578	0.1647	0.1810
57.2369	0.125	5	61.2175	0.4477	inf	0.0	0.0	0.2041	0.8617	0.9272
74.6254	0.25	10	77.8514	0.4436	0.0000	0.9231	0.9	0.7551	0.3486	0.4005
63.9115	0.375	15	41.7035	0.4326	1.0000	0.2906	0.2667	0.3810	0.7398	0.8426
108.6875	0.5	20	44.8037	0.4991	0.8634	0.9658	0.9333	0.7823	0.9640	0.9449
44.2356	0.625	25	44.1751	0.5387	1.0000	0.9145	0.8	0.7687	0.9776	0.9002
96.4688	0.75	30	135.7685	0.4021	0.0000	0.9231	0.8667	0.7619	0.0679	0.1959
43.4041	0.875	35	50.4063	0.5457	1.0000	0.2735	0.0667	0.4082	0.5177	0.4687
44.1402	1.0	40	32.4859	0.6028	0.0447	0.7094	0.4667	0.6735	0.6056	0.4351
31.674	1.125	45	61.1680	0.6926	0.0000	0.6838	0.2667	0.6939	0.2969	0.1474
1.1485	1.25	50	19.9706	0.7538	0.8439	0.8632	0.4667	0.7959	0.8842	0.5360
6.5331	1.375	55	32.0755	0.7251	0.9884	0.9145	0.4667	0.8367	0.9155	0.5032
15.5703	1.5	60	28.3524	0.7198	0.3486	0.8803	0.4333	0.8163	0.8368	0.4472
28.0028	1.625	65	56.6175	0.6588	0.0000	0.8974	0.6	0.7959	0.4938	0.2919
32.1282	1.75	70	30.0067	0.7487	0.9504	0.9573	0.4333	0.8776	0.9656	0.4774
0.325	1.875	75	30.5671	0.8235	1.0	0.8291	0.2333	0.8163	0.8934	0.3558
0.0075	2.0	80	44.0853	0.7661	1.0000	0.9231	0.4	0.8571	0.9587	0.5982
0.0	2.125	85	49.2403	0.8160	1.0000	0.8803	0.2667	0.8503	0.9116	0.3861
24.125	2.25	90	78.3326	0.7090	1.0	0.9829	0.5667	0.8707	0.9829	0.6408
0.4688	2.375	95	23.8434	0.8298	1.0000	0.8034	0.2	0.8027	0.9322	0.4287
0.143	2.5	100	30.4675	0.7705	1.0000	0.9829	0.4333	0.8980	0.9829	0.6662
9.3438	2.625	105	24.7207	0.8217	1.0000	0.8803	0.2667	0.8503	0.9622	0.4651
0.5898	2.75	110	27.1122	0.8479	1.0000	0.9145	0.2333	0.8844	0.9343	0.4290
26.25	2.875	115	27.1726	0.8826	0.9999	0.8974	0.1667	0.8844	0.9229	0.2323
0.0	3.0	120	30.7803	0.8214	1.0	0.9573	0.3333	0.8980	0.9744	0.4339
0.0	3.125	125	36.6259	0.8046	1.0000	0.9658	0.3667	0.8980	0.9744	0.4997
27.0626	3.25	130	55.3861	0.7333	1.0	1.0	0.5333	0.8912	1.0	0.7243
0.0	3.375	135	30.0343	0.8302	1.0000	0.8974	0.2667	0.8639	0.9233	0.3202
5.25	3.5	140	42.5695	0.8490	0.9998	0.8205	0.2	0.8163	0.8318	0.2341
0.0	3.625	145	36.7883	0.7801	1.0000	0.9573	0.4	0.8844	0.9574	0.4993
0.0	3.75	150	41.9264	0.7527	1.0000	0.9658	0.4667	0.8776	0.9674	0.5318
0.0	3.875	155	42.6675	0.7527	1.0000	0.9658	0.4667	0.8776	0.9658	0.5281
0.0	4.0	160	43.4456	0.7519	1.0000	0.9658	0.4667	0.8776	0.9658	0.5326
0.0	4.125	165	42.7968	0.7507	1.0000	0.9658	0.4667	0.8776	0.9658	0.5309
0.0	4.25	170	42.75	0.7501	1.0000	0.9658	0.4667	0.8776	0.9658	0.5305
0.0	4.375	175	42.6063	0.7499	1.0000	0.9658	0.4667	0.8776	0.9658	0.5286
0.0	4.5	180	42.5009	0.7501	1.0000	0.9658	0.4667	0.8776	0.9658	0.5277
0.0	4.625	185	42.5	0.7501	1.0000	0.9658	0.4667	0.8776	0.9658	0.5276
0.0	4.75	190	42.3818	0.7496	1.0000	0.9658	0.4667	0.8776	0.9658	0.5299
0.0	4.875	195	42.2321	0.7501	1.0000	0.9658	0.4667	0.8776	0.9658	0.5269
0.0	5.0	200	42.0863	0.7501	1.0000	0.9658	0.4667	0.8776	0.9658	0.5228

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_true_epo5_lr5e-4_r8_2602031226

npov_RM_mistralai_S12345_LLM_false_STRUCT_true_epo5_lr5e-4_r8_2602031226

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_true_epo5_lr5e-4_r8_2602031226