20231216-045106

allstax/20231216-045106

20231216-045106 is a machine learning model from allstax. 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

24% 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 · 100%

At a glance

Library: peft
License: apache-2.0
Access: Public
Created: Dec 16, 2023
Updated: Dec 16, 2023
SHA: bbae054b

Base models

AIDC-ai-business/Marcoroni-7B-v3

Model card

From the Hugging Face model README

20231216-045106

This model is a fine-tuned version of AIDC-ai-business/Marcoroni-7B-v3 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.2843

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: 2.5e-05
train_batch_size: 2
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: 2
training_steps: 100
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
2.2541	0.02	1	2.1106
1.5517	0.03	2	2.1106
2.347	0.05	3	2.0350
2.006	0.06	4	1.9297
1.8398	0.08	5	1.8406
1.8506	0.09	6	1.8406
1.8804	0.11	7	1.7621
1.9034	0.12	8	1.6988
0.9835	0.14	9	1.6494
1.4725	0.15	10	1.5915
1.1824	0.17	11	1.5557
1.3356	0.18	12	1.5557
1.1077	0.2	13	1.5242
1.4959	0.22	14	1.4908
1.4881	0.23	15	1.4550
1.2674	0.25	16	1.4201
1.2133	0.26	17	1.3872
1.5423	0.28	18	1.3521
0.9551	0.29	19	1.3212
1.1868	0.31	20	1.2881
1.4799	0.32	21	1.2526
1.2903	0.34	22	1.2154
1.3357	0.35	23	1.1770
0.868	0.37	24	1.1383
1.1978	0.38	25	1.0982
1.2102	0.4	26	1.0575
0.8946	0.42	27	1.0575
1.0671	0.43	28	1.0151
1.0761	0.45	29	0.9715
0.9568	0.46	30	0.9263
0.8203	0.48	31	0.8848
0.8601	0.49	32	0.8408
0.8253	0.51	33	0.7945
0.8098	0.52	34	0.7504
0.6567	0.54	35	0.7110
0.6545	0.55	36	0.6695
0.6036	0.57	37	0.6338
0.6746	0.58	38	0.6018
0.5376	0.6	39	0.5731
0.5674	0.62	40	0.5471
0.4762	0.63	41	0.5218
0.4755	0.65	42	0.4965
0.3974	0.66	43	0.4756
0.8437	0.68	44	0.4607
0.4766	0.69	45	0.4485
0.5403	0.71	46	0.4369
0.4201	0.72	47	0.4244
0.4326	0.74	48	0.4115
0.4669	0.75	49	0.3978
0.5259	0.77	50	0.3867
0.3906	0.78	51	0.3782
0.369	0.8	52	0.3724
0.3314	0.82	53	0.3658
0.4164	0.83	54	0.3585
0.3339	0.85	55	0.3499
0.315	0.86	56	0.3405
0.5404	0.88	57	0.3340
0.3136	0.89	58	0.3302
0.3574	0.91	59	0.3275
0.3466	0.92	60	0.3249
0.3097	0.94	61	0.3226
0.4212	0.95	62	0.3208
0.3183	0.97	63	0.3184
0.2762	0.98	64	0.3162
0.3936	1.0	65	0.3143
0.303	1.02	66	0.3128
0.3813	1.03	67	0.3108
0.3065	1.05	68	0.3089
0.2457	1.06	69	0.3069
0.4008	1.08	70	0.3053
0.3131	1.09	71	0.3040
0.2483	1.11	72	0.3027
0.2445	1.12	73	0.3016
0.2717	1.14	74	0.3003
0.6308	1.15	75	0.2991
0.3271	1.17	76	0.2980
0.3013	1.18	77	0.2971
0.2951	1.2	78	0.2960
0.2514	1.22	79	0.2950
0.2836	1.23	80	0.2940
0.2538	1.25	81	0.2929
0.312	1.26	82	0.2921
0.2773	1.28	83	0.2912
0.2957	1.29	84	0.2904
0.3997	1.31	85	0.2896
0.3084	1.32	86	0.2889
0.2521	1.34	87	0.2882
0.2873	1.35	88	0.2877
0.2419	1.37	89	0.2872
0.2691	1.38	90	0.2867
0.6368	1.4	91	0.2864
0.2299	1.42	92	0.2860
0.4967	1.43	93	0.2857
0.2827	1.45	94	0.2855
0.2501	1.46	95	0.2853
0.2285	1.48	96	0.2851
0.269	1.49	97	0.2849
0.2539	1.51	98	0.2847
0.2798	1.52	99	0.2845
0.2695	1.54	100	0.2843

Framework versions

PEFT 0.7.2.dev0
Transformers 4.37.0.dev0
Pytorch 2.1.0+cu121
Datasets 2.15.0
Tokenizers 0.15.0

Library: peft
License: apache-2.0
Created: Dec 16, 2023
Updated: Dec 16, 2023