flan-context

zera09/flan-context

flan-context is a machine learning model from zera09. 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 transformers. The card lists the license as apache-2.0.

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

Downloads · 30 days

9% of all-time downloads

All-time downloads

253

Public

Parameters

248M

18.4 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors990 MB · 100%

At a glance

Library: transformers
License: apache-2.0
Model type: t5
Access: Public
Created: Dec 10, 2024
Updated: Feb 16, 2025
SHA: 3bd09c5c

Base models

google/flan-t5-base

Model card

From the Hugging Face model README

flan-context

This model is a fine-tuned version of google/flan-t5-base on the None dataset. It achieves the following results on the evaluation set:

Loss: 2.7001
Rouge: {'rouge1': 0.232278966116149, 'rouge2': 0.07728171691786677, 'rougeL': 0.19623743124239312, 'rougeLsum': 0.19655898868255733}
Bleu: {'bleu': 0.028838462454173944, 'precisions': [0.3551912568306011, 0.11158798283261803, 0.052838857893009517, 0.027189265536723163], 'brevity_penalty': 0.33198193653070995, 'length_ratio': 0.4755847353303242, 'translation_length': 3477, 'reference_length': 7311}
Bertscore Precision: 0.8829
Bertscore Recall: 0.8627
Bertscore F1: 0.8726
Meteor: 0.1620

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: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 8
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge	Bleu	Bertscore Precision	Bertscore Recall	Bertscore F1	Meteor
2.8853	0.9973	188	2.4748	{'rouge1': 0.21478039810187508, 'rouge2': 0.07429429269352927, 'rougeL': 0.18676797323655045, 'rougeLsum': 0.18706967047262657}	{'bleu': 0.02063755745745233, 'precisions': [0.38532423208191124, 0.12154696132596685, 0.0556, 0.027571115973741796], 'brevity_penalty': 0.22419886226426375, 'length_ratio': 0.4007659690876761, 'translation_length': 2930, 'reference_length': 7311}	0.8914	0.8594	0.8749	0.1479
2.5541	2.0	377	2.4110	{'rouge1': 0.22948564713571, 'rouge2': 0.07746423405162098, 'rougeL': 0.19713899099706828, 'rougeLsum': 0.19729876653861086}	{'bleu': 0.025493859979390892, 'precisions': [0.3697632058287796, 0.1162715167262098, 0.05027932960893855, 0.025670064175160438], 'brevity_penalty': 0.29538077809069857, 'length_ratio': 0.4505539597866229, 'translation_length': 3294, 'reference_length': 7311}	0.8866	0.8605	0.8733	0.1571
2.3627	2.9973	565	2.3796	{'rouge1': 0.23033609170894062, 'rouge2': 0.07935460715728626, 'rougeL': 0.20056333294966316, 'rougeLsum': 0.20035996272531867}	{'bleu': 0.025824376518710283, 'precisions': [0.36265060240963853, 0.11207729468599034, 0.05051903114186851, 0.026542056074766354], 'brevity_penalty': 0.3005598328831212, 'length_ratio': 0.45411024483654766, 'translation_length': 3320, 'reference_length': 7311}	0.8858	0.8609	0.8730	0.1614
2.1889	4.0	754	2.3669	{'rouge1': 0.2197965347814989, 'rouge2': 0.07251756269788934, 'rougeL': 0.18818025331932353, 'rougeLsum': 0.18851309057084853}	{'bleu': 0.025723417721010913, 'precisions': [0.3480581085087459, 0.1032298923369221, 0.04858987427794767, 0.026759530791788857], 'brevity_penalty': 0.31114175380888076, 'length_ratio': 0.4613595951306251, 'translation_length': 3373, 'reference_length': 7311}	0.8828	0.8598	0.8710	0.1487
2.0543	4.9973	942	2.3862	{'rouge1': 0.22612840879892715, 'rouge2': 0.07607082590470542, 'rougeL': 0.19461687796155736, 'rougeLsum': 0.1946541956563201}	{'bleu': 0.028827495157242068, 'precisions': [0.3505929997107318, 0.10919185687847008, 0.05219689461513049, 0.029871977240398292], 'brevity_penalty': 0.32796792789857493, 'length_ratio': 0.4728491314457667, 'translation_length': 3457, 'reference_length': 7311}	0.8823	0.8609	0.8714	0.1555
1.9291	6.0	1131	2.3932	{'rouge1': 0.2287665228610908, 'rouge2': 0.07973426705005476, 'rougeL': 0.1988426370352011, 'rougeLsum': 0.19879253830230947}	{'bleu': 0.02894312079722988, 'precisions': [0.3430804863925883, 0.1105279407224452, 0.0539021164021164, 0.0298932384341637], 'brevity_penalty': 0.32736604931043434, 'length_ratio': 0.47243879086308305, 'translation_length': 3454, 'reference_length': 7311}	0.8816	0.8608	0.8710	0.1550
1.8217	6.9973	1319	2.4167	{'rouge1': 0.2390529160325309, 'rouge2': 0.07957708305532896, 'rougeL': 0.2027395994404016, 'rougeLsum': 0.20329200198212954}	{'bleu': 0.028281206953621237, 'precisions': [0.3607173850159098, 0.11227637260950031, 0.05120581433762801, 0.026661926768574477], 'brevity_penalty': 0.32796792789857493, 'length_ratio': 0.4728491314457667, 'translation_length': 3457, 'reference_length': 7311}	0.8835	0.8614	0.8722	0.1604
1.7252	8.0	1508	2.4362	{'rouge1': 0.2387012102229664, 'rouge2': 0.08568113664238328, 'rougeL': 0.2052351585811596, 'rougeLsum': 0.20522739929467346}	{'bleu': 0.031214398462396122, 'precisions': [0.35888601780074647, 0.11872705018359853, 0.05830330822142155, 0.031007751937984496], 'brevity_penalty': 0.33318661488396756, 'length_ratio': 0.4764054164956914, 'translation_length': 3483, 'reference_length': 7311}	0.8839	0.8625	0.8730	0.1655
1.6454	8.9973	1696	2.4714	{'rouge1': 0.23254921528038897, 'rouge2': 0.08299424380944474, 'rougeL': 0.19959147297590052, 'rougeLsum': 0.1998292546074823}	{'bleu': 0.030561315156201488, 'precisions': [0.35718374356038923, 0.11466910643488869, 0.05515665796344647, 0.03051560855840056], 'brevity_penalty': 0.3353957201733691, 'length_ratio': 0.4779099986321981, 'translation_length': 3494, 'reference_length': 7311}	0.8842	0.8631	0.8734	0.1637
1.5742	10.0	1885	2.4923	{'rouge1': 0.2320880017678728, 'rouge2': 0.08076103877449484, 'rougeL': 0.20075533361867798, 'rougeLsum': 0.2009244163684044}	{'bleu': 0.029328139847920456, 'precisions': [0.34839816933638446, 0.11063700091435538, 0.053816046966731895, 0.028050490883590462], 'brevity_penalty': 0.3357974461669614, 'length_ratio': 0.4781835590206538, 'translation_length': 3496, 'reference_length': 7311}	0.8821	0.8614	0.8715	0.1566
1.5129	10.9973	2073	2.5331	{'rouge1': 0.22819267589219194, 'rouge2': 0.07708184976753998, 'rougeL': 0.19398674728487852, 'rougeLsum': 0.1946429343585785}	{'bleu': 0.02980684242683419, 'precisions': [0.34710743801652894, 0.1071645415907711, 0.05326404676843131, 0.03037709497206704], 'brevity_penalty': 0.33840916356368883, 'length_ratio': 0.4799617015456162, 'translation_length': 3509, 'reference_length': 7311}	0.8814	0.8620	0.8715	0.1586
1.4482	12.0	2262	2.5347	{'rouge1': 0.23553666134633247, 'rouge2': 0.08324143955533186, 'rougeL': 0.20150057449829922, 'rougeLsum': 0.20162040981968193}	{'bleu': 0.03055727708520387, 'precisions': [0.35581061692969873, 0.11406727828746177, 0.05662847790507365, 0.03063380281690141], 'brevity_penalty': 0.3335882204056274, 'length_ratio': 0.4766789768841472, 'translation_length': 3485, 'reference_length': 7311}	0.8838	0.8631	0.8732	0.1621
1.4032	12.9973	2450	2.5527	{'rouge1': 0.2330720183158893, 'rouge2': 0.08201299693976438, 'rougeL': 0.19804789815084495, 'rougeLsum': 0.1981903289043609}	{'bleu': 0.030383667999639367, 'precisions': [0.35192639447958596, 0.11094085197670855, 0.05643044619422572, 0.03176844334627603], 'brevity_penalty': 0.33218270164741553, 'length_ratio': 0.47572151552455205, 'translation_length': 3478, 'reference_length': 7311}	0.8830	0.8623	0.8724	0.1631
1.349	14.0	2639	2.6143	{'rouge1': 0.23254175207188804, 'rouge2': 0.08024193515895395, 'rougeL': 0.19544835613960485, 'rougeLsum': 0.19569878335291974}	{'bleu': 0.029345050805374768, 'precisions': [0.3517616728731023, 0.11141636141636142, 0.053577262332571055, 0.028109627547434995], 'brevity_penalty': 0.3347931711298346, 'length_ratio': 0.47749965804951444, 'translation_length': 3491, 'reference_length': 7311}	0.8838	0.8626	0.8729	0.1609
1.3214	14.9973	2827	2.6210	{'rouge1': 0.23260158751663262, 'rouge2': 0.08252522284643907, 'rougeL': 0.19522688167242186, 'rougeLsum': 0.19557179409288622}	{'bleu': 0.03067670298166347, 'precisions': [0.350597609561753, 0.11124583207032435, 0.05642023346303502, 0.030324154757755316], 'brevity_penalty': 0.33941388966452746, 'length_ratio': 0.4806456025167556, 'translation_length': 3514, 'reference_length': 7311}	0.8829	0.8626	0.8725	0.1635
1.2863	16.0	3016	2.6274	{'rouge1': 0.23589678065489733, 'rouge2': 0.08083116605036103, 'rougeL': 0.19887788274810117, 'rougeLsum': 0.19949881558390142}	{'bleu': 0.0291217315778175, 'precisions': [0.35124321234638467, 0.11297198538367845, 0.05246008471814923, 0.02697967764540995], 'brevity_penalty': 0.3364000743888085, 'length_ratio': 0.4785938996033374, 'translation_length': 3499, 'reference_length': 7311}	0.8829	0.8623	0.8724	0.1635
1.259	16.9973	3204	2.6495	{'rouge1': 0.2295081896719511, 'rouge2': 0.0737752133374778, 'rougeL': 0.19273858639259714, 'rougeLsum': 0.19259899276919815}	{'bleu': 0.025280028083103128, 'precisions': [0.34685598377281945, 0.103831891223733, 0.045018205892088714, 0.022095509622238062], 'brevity_penalty': 0.3267642317139601, 'length_ratio': 0.4720284502803994, 'translation_length': 3451, 'reference_length': 7311}	0.8818	0.8616	0.8714	0.1590
1.2333	18.0	3393	2.6829	{'rouge1': 0.23054467803781714, 'rouge2': 0.07559216640427756, 'rougeL': 0.19491526135602003, 'rougeLsum': 0.19516429845632233}	{'bleu': 0.028049683046042627, 'precisions': [0.35005733944954126, 0.10815765352887259, 0.050359712230215826, 0.026028842771720014], 'brevity_penalty': 0.3341906708834706, 'length_ratio': 0.4770893174668308, 'translation_length': 3488, 'reference_length': 7311}	0.8821	0.8621	0.8718	0.1600
1.2287	18.9973	3581	2.6920	{'rouge1': 0.229205558343422, 'rouge2': 0.07654852833094582, 'rougeL': 0.19552872565004628, 'rougeLsum': 0.1954436046874195}	{'bleu': 0.028600350734863153, 'precisions': [0.3502873563218391, 0.11026033690658499, 0.05213114754098361, 0.027160493827160494], 'brevity_penalty': 0.3325842495204903, 'length_ratio': 0.47599507591300777, 'translation_length': 3480, 'reference_length': 7311}	0.8826	0.8625	0.8723	0.1607
1.2018	19.9469	3760	2.7001	{'rouge1': 0.232278966116149, 'rouge2': 0.07728171691786677, 'rougeL': 0.19623743124239312, 'rougeLsum': 0.19655898868255733}	{'bleu': 0.028838462454173944, 'precisions': [0.3551912568306011, 0.11158798283261803, 0.052838857893009517, 0.027189265536723163], 'brevity_penalty': 0.33198193653070995, 'length_ratio': 0.4755847353303242, 'translation_length': 3477, 'reference_length': 7311}	0.8829	0.8627	0.8726	0.1620

Framework versions

Transformers 4.46.3
Pytorch 2.4.1+cu118
Datasets 3.1.0
Tokenizers 0.20.3

Library: transformers
Type: t5
License: apache-2.0
Created: Dec 10, 2024
Updated: Feb 16, 2025