Mixtral-Finetune-Output

anantg/Mixtral-Finetune-Output

Mixtral-Finetune-Output is a machine learning model from anantg. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as apache-2.0.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

16% of all-time downloads

All-time downloads

Public

Repo size

27.3 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors27.3 MB · 94%

At a glance

Library: peft
License: apache-2.0
Access: Public
Created: Jan 19, 2024
Updated: Jan 19, 2024
SHA: b2b685cf

Base models

mistralai/Mixtral-8x7B-Instruct-v0.1

Datasets

generator

Model card

From the Hugging Face model README

Mixtral-Finetune-Output

This model is a fine-tuned version of mistralai/Mixtral-8x7B-Instruct-v0.1 on the generator dataset. It achieves the following results on the evaluation set:

Loss: 1.3062

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: 0.0001
train_batch_size: 1
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 0.03
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
1.5745	0.01	10	1.4701
1.5372	0.02	20	1.4541
1.4147	0.03	30	1.4433
1.423	0.04	40	1.4366
1.5318	0.05	50	1.4326
1.334	0.06	60	1.4296
1.364	0.07	70	1.4244
1.332	0.08	80	1.4194
1.3742	0.09	90	1.4163
1.4497	0.1	100	1.4124
1.4145	0.1	110	1.4098
1.4224	0.11	120	1.4050
1.4013	0.12	130	1.4017
1.547	0.13	140	1.4020
1.4969	0.14	150	1.3967
1.5716	0.15	160	1.3943
1.3677	0.16	170	1.3915
1.3789	0.17	180	1.3901
1.3188	0.18	190	1.3869
1.3317	0.19	200	1.3846
1.2552	0.2	210	1.3809
1.2584	0.21	220	1.3788
1.3958	0.22	230	1.3776
1.3345	0.23	240	1.3755
1.3562	0.24	250	1.3723
1.343	0.25	260	1.3726
1.3705	0.26	270	1.3695
1.5719	0.27	280	1.3687
1.3634	0.28	290	1.3652
1.4465	0.29	300	1.3668
1.3949	0.29	310	1.3642
1.3147	0.3	320	1.3631
1.368	0.31	330	1.3613
1.3482	0.32	340	1.3603
1.3143	0.33	350	1.3591
1.4717	0.34	360	1.3568
1.2089	0.35	370	1.3555
1.4223	0.36	380	1.3529
1.3895	0.37	390	1.3523
1.309	0.38	400	1.3504
1.3698	0.39	410	1.3487
1.2834	0.4	420	1.3468
1.2747	0.41	430	1.3471
1.3167	0.42	440	1.3460
1.3232	0.43	450	1.3438
1.3628	0.44	460	1.3422
1.3828	0.45	470	1.3417
1.3756	0.46	480	1.3412
1.385	0.47	490	1.3418
1.3622	0.48	500	1.3392
1.3322	0.49	510	1.3381
1.368	0.49	520	1.3365
1.3373	0.5	530	1.3355
1.4931	0.51	540	1.3354
1.3986	0.52	550	1.3333
1.3053	0.53	560	1.3312
1.2736	0.54	570	1.3297
1.2903	0.55	580	1.3298
1.328	0.56	590	1.3290
1.4081	0.57	600	1.3290
1.2852	0.58	610	1.3279
1.3636	0.59	620	1.3268
1.3448	0.6	630	1.3265
1.2061	0.61	640	1.3252
1.3519	0.62	650	1.3244
1.3632	0.63	660	1.3248
1.3784	0.64	670	1.3238
1.3349	0.65	680	1.3216
1.2603	0.66	690	1.3215
1.3566	0.67	700	1.3224
1.316	0.68	710	1.3208
1.1818	0.69	720	1.3203
1.3631	0.69	730	1.3190
1.3234	0.7	740	1.3184
1.2759	0.71	750	1.3177
1.3332	0.72	760	1.3177
1.2764	0.73	770	1.3165
1.2056	0.74	780	1.3155
1.4285	0.75	790	1.3158
1.3733	0.76	800	1.3150
1.2735	0.77	810	1.3143
1.3502	0.78	820	1.3137
1.093	0.79	830	1.3130
1.3451	0.8	840	1.3123
1.2942	0.81	850	1.3119
1.3258	0.82	860	1.3117
1.2139	0.83	870	1.3114
1.2773	0.84	880	1.3109
1.2324	0.85	890	1.3101
1.4134	0.86	900	1.3097
1.3464	0.87	910	1.3095
1.2972	0.88	920	1.3090
1.3305	0.88	930	1.3086
1.3394	0.89	940	1.3082
1.3666	0.9	950	1.3078
1.3703	0.91	960	1.3077
1.3019	0.92	970	1.3077
1.2618	0.93	980	1.3073
1.2808	0.94	990	1.3071
1.2927	0.95	1000	1.3069
1.2688	0.96	1010	1.3067
1.3312	0.97	1020	1.3065
1.2406	0.98	1030	1.3064
1.3341	0.99	1040	1.3062
1.3531	1.0	1050	1.3062

Framework versions

PEFT 0.7.1
Transformers 4.36.2
Pytorch 2.1.0+cu121
Datasets 2.16.1
Tokenizers 0.15.0

Library: peft
License: apache-2.0
Created: Jan 19, 2024
Updated: Jan 19, 2024