distilbart-cnn-12-6-finetuned-stocknews_200

This model is a fine-tuned version of sshleifer/distilbart-cnn-12-6 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.0370
• Rouge1: 79.8682
• Rouge2: 71.4205
• Rougel: 75.6301
• Rougelsum: 77.0085
• Gen Len: 74.1543

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: 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: 80
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	169	0.5736	64.7045	47.6749	56.2681	59.2198	74.6113
No log	2.0	338	0.4806	72.0942	58.8471	65.4706	67.8252	71.5163
0.4734	3.0	507	0.4991	73.967	62.7751	68.5945	70.6273	74.724
0.4734	4.0	676	0.4965	76.8393	66.9993	72.19	73.864	72.7003
0.4734	5.0	845	0.5139	78.0584	68.124	73.447	75.0284	73.9466
0.1158	6.0	1014	0.5328	78.409	68.5496	73.4175	75.0927	72.6914
0.1158	7.0	1183	0.5370	77.5134	67.8142	72.7732	74.5942	71.5727
0.1158	8.0	1352	0.5872	78.01	68.8818	73.7514	75.3546	73.4036
0.0631	9.0	1521	0.5787	78.8662	69.9291	74.7183	76.1309	73.365
0.0631	10.0	1690	0.5887	78.5145	69.2414	73.9729	75.4945	73.3947
0.0631	11.0	1859	0.5866	77.9579	68.5705	73.2277	75.2179	72.4807
0.0456	12.0	2028	0.6155	79.4247	70.3457	75.0464	76.723	71.6261
0.0456	13.0	2197	0.6270	78.2792	69.1958	74.171	75.7049	72.9347
0.0456	14.0	2366	0.6342	78.6039	69.2197	74.2082	75.7638	74.543
0.0364	15.0	2535	0.6282	78.7977	69.8903	74.5441	76.4053	72.8961
0.0364	16.0	2704	0.6456	78.4486	69.2633	74.0665	75.4348	72.2819
0.0364	17.0	2873	0.6583	79.1083	70.2974	75.0199	76.544	72.6469
0.0282	18.0	3042	0.6477	78.7872	69.9616	74.6811	76.0256	72.8279
0.0282	19.0	3211	0.6716	78.7369	69.889	74.4537	75.9916	73.4214
0.0282	20.0	3380	0.6729	79.3218	70.2074	75.162	76.5582	73.7003
0.0222	21.0	3549	0.7011	77.7228	68.6481	73.4411	74.9113	74.4748
0.0222	22.0	3718	0.6763	79.47	70.7597	75.2025	76.8042	72.73
0.0222	23.0	3887	0.7025	79.8675	70.9624	75.4989	77.0572	72.8427
0.0196	24.0	4056	0.6746	79.1486	70.4134	74.9573	76.4961	73.0208
0.0196	25.0	4225	0.6750	79.774	71.187	75.6008	77.2557	72.1098
0.0196	26.0	4394	0.6921	79.5747	70.894	75.2295	76.7905	72.9318
0.0176	27.0	4563	0.7611	79.0068	70.1336	74.3258	75.9459	74.3501
0.0176	28.0	4732	0.7093	79.5467	70.8754	75.4346	77.2047	72.3116
0.0176	29.0	4901	0.7168	79.5496	70.5612	75.0587	76.6486	74.0415
0.0154	30.0	5070	0.7032	79.7382	71.0288	75.9411	77.103	72.5282
0.0154	31.0	5239	0.7206	79.3973	70.7136	75.1744	76.5041	72.5757
0.0154	32.0	5408	0.7478	79.6311	70.74	75.1728	76.8626	73.1395
0.013	33.0	5577	0.7279	79.9423	71.2295	75.7646	77.2329	70.8872
0.013	34.0	5746	0.7685	78.8995	70.121	74.4843	76.028	72.9763
0.013	35.0	5915	0.7498	79.6454	70.8632	75.4972	76.8668	72.0297
0.0126	36.0	6084	0.8016	78.8582	70.0804	74.5498	76.0402	74.8338
0.0126	37.0	6253	0.7923	78.8845	70.1465	74.837	76.2453	74.0742
0.0126	38.0	6422	0.7813	78.7254	70.0885	74.6831	76.1384	73.5994
0.0103	39.0	6591	0.7974	79.5855	70.7472	75.5436	76.9493	72.6795
0.0103	40.0	6760	0.7967	79.656	70.7795	75.2844	76.6875	72.3294
0.0103	41.0	6929	0.8029	79.8831	71.1647	75.697	77.0773	71.8872
0.0086	42.0	7098	0.8245	78.999	70.1721	74.8494	76.2723	72.7478
0.0086	43.0	7267	0.8459	79.052	70.2714	75.0921	76.4209	74.3828
0.0086	44.0	7436	0.8077	79.6009	70.4859	75.0207	76.7271	72.5163
0.0078	45.0	7605	0.8431	79.093	70.433	75.0361	76.589	73.3145
0.0078	46.0	7774	0.8794	79.1461	70.3654	74.845	76.3544	75.0415
0.0078	47.0	7943	0.8668	79.1443	70.2647	74.7967	76.3801	71.724
0.0076	48.0	8112	0.8347	78.6997	70.1008	74.6051	76.0351	73.9763
0.0076	49.0	8281	0.8544	78.9749	69.9824	74.6559	76.0268	74.6528
0.0076	50.0	8450	0.9060	79.5051	70.5755	75.3817	77.0026	71.1217
0.0065	51.0	8619	0.9501	79.2498	70.5003	75.1244	76.5023	75.0
0.0065	52.0	8788	0.8724	79.5012	70.4217	75.109	76.6551	73.73
0.0065	53.0	8957	0.8860	79.5313	71.0337	75.3122	76.928	72.7685
0.0053	54.0	9126	0.8859	79.674	71.0878	75.4582	76.925	73.3294
0.0053	55.0	9295	0.8965	78.5857	69.8599	74.2323	75.6027	75.7359
0.0053	56.0	9464	0.9871	79.8361	71.2171	75.8197	77.1182	74.0861
0.0052	57.0	9633	0.8972	79.8939	71.3469	75.9245	77.1549	72.8398
0.0052	58.0	9802	0.9693	79.5523	70.8739	75.2116	76.7137	74.3412
0.0052	59.0	9971	0.9605	79.483	70.6684	75.0183	76.3226	75.2522
0.0047	60.0	10140	0.9705	79.4894	70.6424	75.0833	76.504	74.8694
0.0047	61.0	10309	0.9730	79.4781	70.9014	75.4589	76.6387	75.0504
0.0047	62.0	10478	0.9284	79.485	70.6651	75.1062	76.4092	74.0148
0.0045	63.0	10647	0.9537	79.2664	70.4345	74.9998	76.4565	73.9199
0.0045	64.0	10816	0.9554	79.6061	70.8702	75.3191	76.6242	74.3145
0.0045	65.0	10985	1.0090	79.6107	70.9297	75.4102	76.9842	73.9466
0.0041	66.0	11154	0.9736	79.6246	70.8827	75.2682	76.7209	74.8131
0.0041	67.0	11323	0.9498	79.9549	71.3231	75.7987	77.2809	73.5371
0.0041	68.0	11492	0.9965	80.1403	71.4991	76.017	77.3741	74.2404
0.004	69.0	11661	1.0012	79.8784	71.444	75.827	77.1888	74.0059
0.004	70.0	11830	0.9888	80.1075	71.7102	75.9687	77.3636	72.9911
0.004	71.0	11999	0.9758	79.7998	71.3682	75.6694	77.0498	73.8991
0.0043	72.0	12168	0.9760	79.9748	71.4703	75.8148	77.1338	72.8843
0.0043	73.0	12337	0.9930	80.1032	71.6551	75.8235	77.1674	73.6499
0.0037	74.0	12506	1.0006	80.0302	71.5324	75.7755	77.2182	73.3027
0.0037	75.0	12675	0.9958	79.9088	71.313	75.7842	77.1939	73.362
0.0037	76.0	12844	0.9993	80.3059	71.7887	76.0696	77.5045	73.3086
0.0039	77.0	13013	1.0224	79.5564	71.1191	75.4324	76.7285	74.2344
0.0039	78.0	13182	1.0510	80.0006	71.4199	75.6626	77.006	74.0119
0.0039	79.0	13351	1.0410	79.7101	71.2137	75.5206	76.8997	74.4303
0.0036	80.0	13520	1.0370	79.8682	71.4205	75.6301	77.0085	74.1543

Framework versions

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