text_summarization-finetuned-stocknews

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

• Loss: 1.5087
• Rouge1: 28.1323
• Rouge2: 14.1505
• Rougel: 23.7163
• Rougelsum: 24.743
• 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: 2e-05
• 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	25	1.8901	26.1517	11.6615	21.4583	22.9556	19.0
No log	2.0	50	1.7909	25.9481	11.4621	21.1748	22.8127	19.0
No log	3.0	75	1.7388	26.412	12.1797	21.744	23.3289	19.0
No log	4.0	100	1.6988	26.4465	12.2417	21.7109	23.2402	19.0
No log	5.0	125	1.6752	26.6441	12.4313	21.7396	23.2725	19.0
No log	6.0	150	1.6531	26.4585	12.2979	21.7528	23.1338	19.0
No log	7.0	175	1.6386	26.6186	12.4271	21.8074	23.2756	19.0
No log	8.0	200	1.6263	26.4223	12.3512	21.7575	23.3278	19.0
No log	9.0	225	1.6124	26.5846	12.49	21.9218	23.433	19.0
No log	10.0	250	1.6035	26.8364	12.6954	22.2409	23.6239	19.0
No log	11.0	275	1.5926	27.0986	12.7881	22.2246	23.6203	19.0
No log	12.0	300	1.5844	27.4875	13.1342	22.717	24.0836	19.0
No log	13.0	325	1.5757	27.6863	13.2919	22.8203	24.1659	19.0
No log	14.0	350	1.5688	27.69	13.295	22.8364	24.2587	19.0
No log	15.0	375	1.5643	27.7651	13.5588	23.01	24.5047	19.0
No log	16.0	400	1.5586	27.8662	13.8812	23.1299	24.5692	19.0
No log	17.0	425	1.5525	27.5329	13.5729	22.8646	24.2491	19.0
No log	18.0	450	1.5466	27.2864	13.6465	22.754	24.0451	19.0
No log	19.0	475	1.5434	27.3062	13.664	22.7509	24.015	19.0
1.7497	20.0	500	1.5401	27.3177	13.8162	22.8012	24.0359	19.0
1.7497	21.0	525	1.5369	27.4956	13.9869	23.0248	24.2922	19.0
1.7497	22.0	550	1.5345	27.4794	13.7914	23.0306	24.2942	19.0
1.7497	23.0	575	1.5324	27.4794	13.7914	23.0306	24.2942	19.0
1.7497	24.0	600	1.5302	27.529	13.8756	23.1045	24.3861	19.0
1.7497	25.0	625	1.5266	27.8738	14.0877	23.4826	24.7471	19.0
1.7497	26.0	650	1.5252	27.9294	13.9793	23.4775	24.669	19.0
1.7497	27.0	675	1.5247	28.0046	14.0835	23.4865	24.7035	19.0
1.7497	28.0	700	1.5239	28.0085	14.1428	23.6155	24.8178	19.0
1.7497	29.0	725	1.5224	27.9738	14.1251	23.6146	24.7919	19.0
1.7497	30.0	750	1.5200	28.007	14.1042	23.653	24.7639	19.0
1.7497	31.0	775	1.5192	27.9376	14.0443	23.5673	24.6209	19.0
1.7497	32.0	800	1.5177	28.0251	14.0888	23.6316	24.6779	19.0
1.7497	33.0	825	1.5165	28.0519	14.0867	23.6242	24.6728	19.0
1.7497	34.0	850	1.5164	28.1185	14.1615	23.6657	24.7177	19.0
1.7497	35.0	875	1.5146	28.0809	14.1228	23.6657	24.7177	19.0
1.7497	36.0	900	1.5134	28.1107	14.1889	23.6946	24.7532	19.0
1.7497	37.0	925	1.5130	28.0476	14.0937	23.6232	24.6671	19.0
1.7497	38.0	950	1.5123	27.9979	14.0209	23.5935	24.6298	19.0
1.7497	39.0	975	1.5114	28.001	14.1042	23.6265	24.6735	19.0
1.5033	40.0	1000	1.5100	28.004	14.1355	23.6552	24.6776	19.0
1.5033	41.0	1025	1.5100	28.0346	14.1432	23.6432	24.7052	19.0
1.5033	42.0	1050	1.5098	28.052	14.1387	23.6401	24.6953	19.0
1.5033	43.0	1075	1.5098	28.1032	14.1743	23.6401	24.6953	19.0
1.5033	44.0	1100	1.5096	28.129	14.1847	23.7406	24.805	19.0
1.5033	45.0	1125	1.5093	28.1763	14.2264	23.7075	24.783	19.0
1.5033	46.0	1150	1.5090	28.1336	14.1871	23.7075	24.783	19.0
1.5033	47.0	1175	1.5089	28.1336	14.1871	23.7075	24.783	19.0
1.5033	48.0	1200	1.5088	28.1336	14.1871	23.7075	24.783	19.0
1.5033	49.0	1225	1.5087	28.129	14.1847	23.7406	24.805	19.0
1.5033	50.0	1250	1.5087	28.1323	14.1505	23.7163	24.743	19.0

Framework versions

• Transformers 4.38.1
• Pytorch 2.1.2
• Datasets 2.1.0
• Tokenizers 0.15.2