You can deploy this model and start earning money today!

contemmcm/
d5c57a9572ea7b6b1c4d0958c899d0ec

generated_from_trainer

google/long-t5-local-large

finetune

apache-2.0

endpoints_compatible

Views

No views yet

d5c57a9572ea7b6b1c4d0958c899d0ec

This model is a fine-tuned version of google/long-t5-local-large on the Helsinki-NLP/opus_books [it-ru] dataset. It achieves the following results on the evaluation set:

Loss: 1.4828
Data Size: 1.0
Epoch Runtime: 211.0269
Bleu: 2.7509

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: 5e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 4
total_train_batch_size: 32
total_eval_batch_size: 32
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: constant
num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Data Size	Epoch Runtime	Bleu
No log	0	0	201.7994	0	14.4801	0.0018
No log	1	447	147.8956	0.0078	16.2325	0.0012
2.9453	2	894	93.2510	0.0156	18.2423	0.0034
2.6179	3	1341	40.8682	0.0312	21.6827	0.0022
2.276	4	1788	14.4457	0.0625	28.1281	0.0033
2.034	5	2235	9.2305	0.125	39.5581	0.0033
14.6485	6	2682	7.1002	0.25	61.8350	0.1203
9.6916	7	3129	5.0076	0.5	106.4332	0.1129
6.9322	8.0	3576	3.7153	1.0	196.0080	0.3051
5.6504	9.0	4023	3.2878	1.0	197.9660	0.1498
4.8137	10.0	4470	2.8899	1.0	199.0604	0.1666
4.2216	11.0	4917	2.7419	1.0	195.8480	0.4139
3.7917	12.0	5364	2.5245	1.0	198.3197	0.3747
3.4206	13.0	5811	2.2817	1.0	196.8430	0.5574
3.1294	14.0	6258	2.2082	1.0	196.9102	0.7168
2.9529	15.0	6705	2.1254	1.0	196.1435	0.6741
2.7604	16.0	7152	1.9979	1.0	197.0028	0.7543
2.64	17.0	7599	1.9760	1.0	197.9417	0.6579
2.5364	18.0	8046	1.9256	1.0	198.1333	0.6881
2.4295	19.0	8493	1.9040	1.0	196.4304	0.8254
2.3578	20.0	8940	1.8858	1.0	197.0895	0.7993
2.2975	21.0	9387	1.8711	1.0	196.7090	0.9267
2.2182	22.0	9834	1.8214	1.0	199.2036	0.8697
2.1669	23.0	10281	1.7893	1.0	196.3961	0.8532
2.113	24.0	10728	1.7861	1.0	194.3974	0.8355
2.0843	25.0	11175	1.7602	1.0	196.8781	0.9211
2.0283	26.0	11622	1.7495	1.0	197.7608	0.9706
2.0154	27.0	12069	1.7312	1.0	197.2421	1.2206
1.9734	28.0	12516	1.7110	1.0	197.8324	1.0835
1.9264	29.0	12963	1.7023	1.0	195.7888	1.2169
1.9163	30.0	13410	1.6864	1.0	196.4803	1.2622
1.888	31.0	13857	1.6865	1.0	197.8412	1.3219
1.8579	32.0	14304	1.6601	1.0	198.9681	1.4371
1.863	33.0	14751	1.6459	1.0	199.7836	1.5195
1.8247	34.0	15198	1.6313	1.0	198.7164	1.4657
1.8012	35.0	15645	1.6290	1.0	197.4072	1.6487
1.7714	36.0	16092	1.6067	1.0	200.2042	1.6537
1.7381	37.0	16539	1.6161	1.0	199.3007	1.5698
1.7326	38.0	16986	1.5917	1.0	200.8309	1.8256
1.7266	39.0	17433	1.6026	1.0	200.0043	1.7559
1.6864	40.0	17880	1.5768	1.0	200.4434	1.8453
1.6631	41.0	18327	1.5737	1.0	208.1599	1.8292
1.6467	42.0	18774	1.5559	1.0	211.7769	2.0089
1.646	43.0	19221	1.5500	1.0	211.2042	2.0567
1.6195	44.0	19668	1.5367	1.0	212.0749	2.1562
1.5902	45.0	20115	1.5257	1.0	210.3335	2.2186
1.5873	46.0	20562	1.5199	1.0	210.8142	2.2492
1.5773	47.0	21009	1.5226	1.0	210.9902	2.4761
1.5337	48.0	21456	1.5091	1.0	212.2163	2.5016
1.5312	49.0	21903	1.4985	1.0	211.1324	2.5232
1.5146	50.0	22350	1.4828	1.0	211.0269	2.7509

Framework versions

Transformers 4.57.0
Pytorch 2.8.0+cu128
Datasets 4.2.0
Tokenizers 0.22.1

contemmcm/d5c57a9572ea7b6b1c4d0958c899d0ec

d5c57a9572ea7b6b1c4d0958c899d0ec

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

contemmcm/
d5c57a9572ea7b6b1c4d0958c899d0ec