t5-small-finetuned-weather

elrashid/t5-small-finetuned-weather

t5-small-finetuned-weather is a machine learning model from elrashid. 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

15% of all-time downloads

All-time downloads

Public

Parameters

60.5M

726 MB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors242 MB · 99%

At a glance

Library: transformers
License: apache-2.0
Model type: t5
Access: Public
Created: Dec 4, 2023
Updated: Dec 4, 2023
SHA: 38553343

Base models

Model card

From the Hugging Face model README

t5-small-finetuned-weather

This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 2.6064
Rouge1: 14.1628
Rouge2: 1.799
Rougel: 11.313
Rougelsum: 11.5416
Gen Len: 19.0

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: 1e-06
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 50
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	16	3.2006	13.4978	1.1707	10.3253	10.6309	19.0
No log	2.0	32	3.1733	13.4557	1.1707	10.2741	10.5859	19.0
No log	3.0	48	3.1488	13.5017	1.1707	10.3241	10.6248	19.0
No log	4.0	64	3.1212	13.446	1.1313	10.292	10.5787	19.0
No log	5.0	80	3.0887	13.5522	1.1713	10.2356	10.6272	19.0
No log	6.0	96	3.0563	13.5584	1.1718	10.2079	10.6218	19.0
No log	7.0	112	3.0295	13.452	1.1718	10.2543	10.6218	19.0
No log	8.0	128	3.0046	13.1974	1.1718	10.0842	10.4408	19.0
No log	9.0	144	2.9841	13.2215	1.1718	10.1341	10.5503	19.0
No log	10.0	160	2.9644	13.2254	1.2413	10.1354	10.5685	19.0
No log	11.0	176	2.9456	13.0618	1.1674	9.9997	10.4255	19.0
No log	12.0	192	2.9309	13.0355	1.1191	9.9809	10.4146	19.0
No log	13.0	208	2.9159	12.9564	1.1191	9.8878	10.3195	19.0
No log	14.0	224	2.9012	12.9906	1.0299	9.838	10.3064	19.0
No log	15.0	240	2.8857	13.142	1.1392	10.0813	10.4905	19.0
No log	16.0	256	2.8674	13.4343	1.3132	10.3562	10.7991	19.0
No log	17.0	272	2.8514	13.5215	1.3998	10.5005	10.8772	19.0
No log	18.0	288	2.8342	13.6732	1.4993	10.6495	10.9693	19.0
No log	19.0	304	2.8165	13.6755	1.4995	10.6508	10.9712	19.0
No log	20.0	320	2.8012	13.5959	1.4466	10.6576	10.8721	19.0
No log	21.0	336	2.7878	13.6395	1.4475	10.7602	10.9178	19.0
No log	22.0	352	2.7760	13.6407	1.4484	10.7628	10.9195	19.0
No log	23.0	368	2.7626	13.5936	1.4487	10.7107	10.8762	19.0
No log	24.0	384	2.7487	13.5336	1.4487	10.7177	10.8841	19.0
No log	25.0	400	2.7356	13.7334	1.5429	10.9645	11.1165	19.0
No log	26.0	416	2.7257	14.0382	1.6637	11.3174	11.4271	19.0
No log	27.0	432	2.7170	14.0382	1.6637	11.3174	11.4271	19.0
No log	28.0	448	2.7079	14.0382	1.6637	11.3174	11.4271	19.0
No log	29.0	464	2.6996	14.0368	1.662	11.318	11.4262	19.0
No log	30.0	480	2.6910	14.0368	1.662	11.318	11.4262	19.0
No log	31.0	496	2.6827	14.1726	1.7069	11.4121	11.5144	19.0
3.4641	32.0	512	2.6759	14.1726	1.7069	11.4121	11.5144	19.0
3.4641	33.0	528	2.6683	14.0313	1.6545	11.4032	11.5062	19.0
3.4641	34.0	544	2.6611	14.1009	1.7069	11.4126	11.5149	19.0
3.4641	35.0	560	2.6547	14.1022	1.7069	11.376	11.5181	19.0
3.4641	36.0	576	2.6478	13.925	1.6197	11.306	11.4372	19.0
3.4641	37.0	592	2.6420	13.9287	1.6646	11.2137	11.3484	19.0
3.4641	38.0	608	2.6366	14.0208	1.7111	11.2137	11.3849	19.0
3.4641	39.0	624	2.6317	14.0152	1.7111	11.2106	11.3835	19.0
3.4641	40.0	640	2.6272	13.9893	1.7111	11.2201	11.3923	19.0
3.4641	41.0	656	2.6225	13.9364	1.7111	11.1665	11.3424	19.0
3.4641	42.0	672	2.6192	13.8466	1.6691	11.1595	11.3372	19.0
3.4641	43.0	688	2.6163	14.0141	1.7111	11.1991	11.3417	19.0
3.4641	44.0	704	2.6137	13.8466	1.6691	11.1595	11.3372	19.0
3.4641	45.0	720	2.6119	14.0535	1.7111	11.2252	11.3855	19.0
3.4641	46.0	736	2.6100	14.0871	1.7577	11.2715	11.4199	19.0
3.4641	47.0	752	2.6086	14.1209	1.799	11.2715	11.5033	19.0
3.4641	48.0	768	2.6075	14.1628	1.799	11.313	11.5416	19.0
3.4641	49.0	784	2.6068	14.1628	1.799	11.313	11.5416	19.0
3.4641	50.0	800	2.6064	14.1628	1.799	11.313	11.5416	19.0

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Tokenizers 0.15.0

Library: transformers
Type: t5
License: apache-2.0
Created: Dec 4, 2023
Updated: Dec 4, 2023