checkpoint-6500-finetuned2-2010-2016

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0000
• Rouge1: 1.0
• Rouge2: 0.96
• Rougel: 1.0
• Rougelsum: 1.0
• Gen Len: 6.4

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: 0.0003
• train_batch_size: 32
• eval_batch_size: 32
• seed: 1
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	22	0.5473	0.2919	0.2095	0.2929	0.29	6.11
No log	2.0	44	0.3837	0.3426	0.2692	0.3434	0.3433	6.2
No log	3.0	66	0.2416	0.5336	0.4842	0.532	0.533	6.25
No log	4.0	88	0.1266	0.7338	0.6501	0.7334	0.7306	6.28
0.6352	5.0	110	0.0454	0.8998	0.8382	0.9002	0.899	6.26
0.6352	6.0	132	0.0125	0.9864	0.9423	0.9864	0.9868	6.39
0.6352	7.0	154	0.0029	1.0	0.96	1.0	1.0	6.4
0.6352	8.0	176	0.0011	1.0	0.96	1.0	1.0	6.4
0.6352	9.0	198	0.0013	0.9922	0.95	0.9922	0.9922	6.43
0.0586	10.0	220	0.0067	0.995	0.95	0.995	0.995	6.4
0.0586	11.0	242	0.0004	1.0	0.96	1.0	1.0	6.4
0.0586	12.0	264	0.0002	1.0	0.96	1.0	1.0	6.4
0.0586	13.0	286	0.0142	0.9983	0.956	0.9983	0.9983	6.43
0.0149	14.0	308	0.0001	1.0	0.96	1.0	1.0	6.4
0.0149	15.0	330	0.0000	1.0	0.96	1.0	1.0	6.4
0.0149	16.0	352	0.0000	1.0	0.96	1.0	1.0	6.4
0.0149	17.0	374	0.0000	1.0	0.96	1.0	1.0	6.4
0.0149	18.0	396	0.0000	1.0	0.96	1.0	1.0	6.4
0.0064	19.0	418	0.0000	1.0	0.96	1.0	1.0	6.4
0.0064	20.0	440	0.0000	1.0	0.96	1.0	1.0	6.4
0.0064	21.0	462	0.0000	1.0	0.96	1.0	1.0	6.4
0.0064	22.0	484	0.0002	1.0	0.96	1.0	1.0	6.4
0.0048	23.0	506	0.0003	1.0	0.96	1.0	1.0	6.4
0.0048	24.0	528	0.0000	1.0	0.96	1.0	1.0	6.4
0.0048	25.0	550	0.0000	1.0	0.96	1.0	1.0	6.4
0.0048	26.0	572	0.0000	1.0	0.96	1.0	1.0	6.4
0.0048	27.0	594	0.0000	1.0	0.96	1.0	1.0	6.4
0.0032	28.0	616	0.0000	1.0	0.96	1.0	1.0	6.4
0.0032	29.0	638	0.0000	1.0	0.96	1.0	1.0	6.4
0.0032	30.0	660	0.0000	1.0	0.96	1.0	1.0	6.4
0.0032	31.0	682	0.0000	1.0	0.96	1.0	1.0	6.4
0.0016	32.0	704	0.0000	1.0	0.96	1.0	1.0	6.4
0.0016	33.0	726	0.0000	1.0	0.96	1.0	1.0	6.4
0.0016	34.0	748	0.0000	1.0	0.96	1.0	1.0	6.4
0.0016	35.0	770	0.0000	1.0	0.96	1.0	1.0	6.4
0.0016	36.0	792	0.0000	1.0	0.96	1.0	1.0	6.4
0.0019	37.0	814	0.0000	1.0	0.96	1.0	1.0	6.4
0.0019	38.0	836	0.0000	1.0	0.96	1.0	1.0	6.4
0.0019	39.0	858	0.0000	1.0	0.96	1.0	1.0	6.4
0.0019	40.0	880	0.0000	1.0	0.96	1.0	1.0	6.4
0.0014	41.0	902	0.0000	1.0	0.96	1.0	1.0	6.4
0.0014	42.0	924	0.0000	1.0	0.96	1.0	1.0	6.4
0.0014	43.0	946	0.0000	1.0	0.96	1.0	1.0	6.4
0.0014	44.0	968	0.0000	1.0	0.96	1.0	1.0	6.4
0.0014	45.0	990	0.0000	1.0	0.96	1.0	1.0	6.4
0.0013	46.0	1012	0.0000	1.0	0.96	1.0	1.0	6.4
0.0013	47.0	1034	0.0000	1.0	0.96	1.0	1.0	6.4
0.0013	48.0	1056	0.0000	1.0	0.96	1.0	1.0	6.4
0.0013	49.0	1078	0.0000	1.0	0.96	1.0	1.0	6.4
0.0011	50.0	1100	0.0000	1.0	0.96	1.0	1.0	6.4

Framework versions

• Transformers 4.34.1
• Pytorch 2.0.1
• Datasets 2.14.6
• Tokenizers 0.14.1