t5-small-fine-tuned_model_2

imhereforthememes/t5-small-fine-tuned_model_2

t5-small-fine-tuned_model_2 is a machine learning model from imhereforthememes. 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

26% of all-time downloads

All-time downloads

Public

Parameters

60.5M

727 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: Oct 27, 2024
Updated: Oct 27, 2024
SHA: e9264a80

Base models

Model card

From the Hugging Face model README

t5-small-fine-tuned_model_2

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

Loss: 0.6840
Rouge1: 27.9407
Rouge2: 21.2221
Rougel: 26.6074
Rougelsum: 27.1976
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: 0.02
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 55

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	0.7692	10	3.5053	8.1509	0.0	8.1741	8.4813	19.0
No log	1.5385	20	2.5820	13.0567	0.083	13.0988	13.3345	19.0
No log	2.3077	30	2.3186	16.0127	1.8324	16.0821	16.0127	19.0
No log	3.0769	40	1.9916	16.0889	0.0	16.0713	16.1796	19.0
No log	3.8462	50	1.9778	20.3459	5.6938	20.2576	20.3429	19.0
No log	4.6154	60	1.7593	26.5421	11.8534	21.734	21.9902	19.0
No log	5.3846	70	1.6659	28.5447	21.2829	25.4746	25.6562	19.0
No log	6.1538	80	1.5705	28.5447	20.1071	26.4433	27.249	19.0
No log	6.9231	90	1.4828	21.5765	10.5401	20.3284	20.4294	19.0
No log	7.6923	100	1.5481	25.6706	19.9548	23.8958	24.5591	19.0
No log	8.4615	110	1.3113	28.4758	15.8255	25.9681	26.2583	19.0
No log	9.2308	120	1.3679	30.4635	21.805	29.0806	29.3168	19.0
No log	10.0	130	1.3058	33.5286	25.8263	32.2465	32.7425	19.0
No log	10.7692	140	1.2688	24.8181	19.118	24.5614	25.1229	19.0
No log	11.5385	150	1.2822	30.4635	21.805	29.0806	29.3168	19.0
No log	12.3077	160	1.1995	31.7376	21.7636	31.7376	32.6177	19.0
No log	13.0769	170	1.1703	31.7376	26.151	30.3779	31.3066	19.0
No log	13.8462	180	1.2166	28.9345	22.4858	29.0024	29.5613	19.0
No log	14.6154	190	1.1418	33.5286	28.3248	32.2465	32.7425	19.0
No log	15.3846	200	1.2054	27.8007	21.0803	26.4436	27.0704	19.0
No log	16.1538	210	1.1424	27.199	19.9548	25.9145	26.1883	19.0
No log	16.9231	220	1.0981	28.1764	21.4646	28.1764	28.5716	19.0
No log	17.6923	230	1.0723	30.9564	23.5664	28.3825	28.7377	19.0
No log	18.4615	240	1.1689	29.2957	23.6463	29.2599	29.687	19.0
No log	19.2308	250	1.0526	25.955	21.0803	25.955	26.3995	19.0
No log	20.0	260	1.0602	27.199	19.9548	25.9145	26.1883	19.0
No log	20.7692	270	1.0928	28.9345	22.4858	27.5281	28.0461	19.0
No log	21.5385	280	1.0386	30.1723	26.5116	29.0031	29.8913	19.0
No log	22.3077	290	1.0837	29.4234	25.2504	28.4788	29.2811	19.0
No log	23.0769	300	1.1175	30.1723	26.5116	30.7741	31.0498	19.0
No log	23.8462	310	1.0160	28.3905	21.3235	28.4674	28.6007	19.0
No log	24.6154	320	1.0721	27.8007	21.0803	26.4436	27.0704	19.0
No log	25.3846	330	1.0059	27.199	19.9548	25.9145	26.1883	19.0
No log	26.1538	340	0.9716	24.5772	20.3029	24.9898	25.2349	19.0
No log	26.9231	350	0.9880	30.1723	26.5116	29.0031	29.8913	19.0
No log	27.6923	360	0.9736	23.762	20.9502	23.762	24.4233	19.0
No log	28.4615	370	1.0070	25.2666	19.4028	24.6344	25.3836	19.0
No log	29.2308	380	0.9300	33.4444	25.7492	31.9997	32.6753	19.0
No log	30.0	390	0.9159	27.1927	25.4742	27.3467	28.3371	19.0
No log	30.7692	400	0.9200	24.3606	19.6902	24.4156	24.6809	19.0
No log	31.5385	410	0.9571	27.8007	21.0803	26.4436	27.0704	19.0
No log	32.3077	420	0.9171	30.6846	24.2042	29.6777	30.4199	19.0
No log	33.0769	430	0.9265	27.8596	21.1306	27.8517	28.4864	19.0
No log	33.8462	440	0.8980	30.1723	26.5116	29.0031	29.8913	19.0
No log	34.6154	450	0.8724	29.6346	20.0025	28.1468	28.8559	19.0
No log	35.3846	460	0.8870	30.1723	26.5116	30.7741	31.0498	19.0
No log	36.1538	470	0.8401	27.8007	21.0803	26.4436	27.0704	19.0
No log	36.9231	480	0.8336	30.1723	26.5116	29.0031	29.8913	19.0
No log	37.6923	490	0.8397	30.1723	26.5116	29.0031	29.8913	19.0
1.3001	38.4615	500	0.8521	34.2264	27.0678	31.7585	32.3653	19.0
1.3001	39.2308	510	0.8345	33.2444	26.9698	30.6883	31.271	19.0
1.3001	40.0	520	0.8426	30.1723	26.5116	29.0031	29.8913	19.0
1.3001	40.7692	530	0.8046	30.1723	26.5116	30.7741	31.0498	19.0
1.3001	41.5385	540	0.7954	30.2048	26.6356	29.1189	29.9736	19.0
1.3001	42.3077	550	0.8215	30.1723	26.5116	29.0031	29.8913	19.0
1.3001	43.0769	560	0.7793	27.8007	21.0803	26.4436	27.0704	19.0
1.3001	43.8462	570	0.7746	30.2043	26.6352	29.1185	29.9732	19.0
1.3001	44.6154	580	0.7967	30.1723	26.5116	29.0031	29.8913	19.0
1.3001	45.3846	590	0.7529	30.1723	26.5116	29.0031	29.8913	19.0
1.3001	46.1538	600	0.7502	27.9407	21.2221	26.6074	27.1976	19.0
1.3001	46.9231	610	0.7496	30.2043	26.6352	29.1185	29.9732	19.0
1.3001	47.6923	620	0.7198	27.8596	21.2135	26.5263	27.1531	19.0
1.3001	48.4615	630	0.7107	31.4706	22.8709	28.3819	29.143	19.0
1.3001	49.2308	640	0.7140	27.9407	21.2221	26.6074	27.1976	19.0
1.3001	50.0	650	0.7091	27.8596	21.2135	26.5263	27.1531	19.0
1.3001	50.7692	660	0.7070	27.8596	21.2135	26.5263	27.1531	19.0
1.3001	51.5385	670	0.6957	24.5996	20.5362	24.9898	25.4809	19.0
1.3001	52.3077	680	0.6883	24.5772	20.3029	24.9898	25.2349	19.0
1.3001	53.0769	690	0.6866	27.8007	21.0803	26.4436	27.0704	19.0
1.3001	53.8462	700	0.6857	30.2043	26.6352	29.1185	29.9732	19.0
1.3001	54.6154	710	0.6840	27.9407	21.2221	26.6074	27.1976	19.0

Framework versions

Transformers 4.44.2
Pytorch 2.5.0+cu121
Datasets 3.0.2
Tokenizers 0.19.1

Library: transformers
Type: t5
License: apache-2.0
Created: Oct 27, 2024
Updated: Oct 27, 2024