test_trainer

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

• Loss: 0.0000
• Rouge1: 0.8325
• Rouge2: 0.8187
• Rougel: 0.8294
• Rougelsum: 0.8312
• Gen Len: 18.6

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: 0.0056
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.99) and epsilon=1e-06
• lr_scheduler_type: linear
• num_epochs: 40

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	5	0.2345	0.7001	0.6536	0.6998	0.6957	16.3
No log	2.0	10	0.1472	0.7958	0.7695	0.7929	0.7965	18.3
No log	3.0	15	0.1174	0.7196	0.6705	0.7187	0.7118	16.3
No log	4.0	20	0.0554	0.7977	0.774	0.7907	0.7958	18.6
No log	5.0	25	0.0725	0.8205	0.8074	0.8188	0.8212	18.6
No log	6.0	30	0.0281	0.8114	0.7929	0.8098	0.8123	18.6
No log	7.0	35	0.0451	0.7959	0.7678	0.7908	0.7945	18.6
No log	8.0	40	0.0438	0.8285	0.8061	0.8205	0.8227	18.5
No log	9.0	45	0.0178	0.8249	0.8109	0.8225	0.8243	18.6
No log	10.0	50	0.0072	0.8325	0.8187	0.8294	0.8312	18.6
No log	11.0	55	0.0119	0.8336	0.8217	0.8315	0.833	18.6
No log	12.0	60	0.0104	0.8336	0.8217	0.8315	0.833	18.6
No log	13.0	65	0.0031	0.8325	0.8187	0.8294	0.8312	18.6
No log	14.0	70	0.0099	0.8325	0.8187	0.8294	0.8312	18.6
No log	15.0	75	0.0067	0.8284	0.8053	0.8213	0.8226	18.6
No log	16.0	80	0.0019	0.8325	0.8187	0.8294	0.8312	18.6
No log	17.0	85	0.0173	0.8143	0.798	0.8111	0.8102	18.2
No log	18.0	90	0.0007	0.8325	0.8187	0.8294	0.8312	18.6
No log	19.0	95	0.0004	0.8325	0.8187	0.8294	0.8312	18.6
No log	20.0	100	0.0195	0.8325	0.813	0.8294	0.8312	18.6
No log	21.0	105	0.0057	0.8325	0.813	0.8294	0.8312	18.6
No log	22.0	110	0.0005	0.8325	0.8187	0.8294	0.8312	18.6
No log	23.0	115	0.0010	0.8325	0.8187	0.8294	0.8312	18.6
No log	24.0	120	0.0003	0.8325	0.8187	0.8294	0.8312	18.6
No log	25.0	125	0.0004	0.8325	0.8187	0.8294	0.8312	18.6
No log	26.0	130	0.0005	0.8325	0.8187	0.8294	0.8312	18.6
No log	27.0	135	0.0002	0.8325	0.8187	0.8294	0.8312	18.6
No log	28.0	140	0.0001	0.8325	0.8187	0.8294	0.8312	18.6
No log	29.0	145	0.0010	0.8325	0.8187	0.8294	0.8312	18.6
No log	30.0	150	0.0003	0.8325	0.8187	0.8294	0.8312	18.6
No log	31.0	155	0.0001	0.8325	0.8187	0.8294	0.8312	18.6
No log	32.0	160	0.0000	0.8325	0.8187	0.8294	0.8312	18.6
No log	33.0	165	0.0000	0.8325	0.8187	0.8294	0.8312	18.6
No log	34.0	170	0.0000	0.8325	0.8187	0.8294	0.8312	18.6
No log	35.0	175	0.0000	0.8325	0.8187	0.8294	0.8312	18.6
No log	36.0	180	0.0000	0.8325	0.8187	0.8294	0.8312	18.6
No log	37.0	185	0.0000	0.8325	0.8187	0.8294	0.8312	18.6
No log	38.0	190	0.0000	0.8325	0.8187	0.8294	0.8312	18.6
No log	39.0	195	0.0000	0.8325	0.8187	0.8294	0.8312	18.6
No log	40.0	200	0.0000	0.8325	0.8187	0.8294	0.8312	18.6

Framework versions

• Transformers 4.33.2
• Pytorch 2.0.0
• Datasets 2.14.5
• Tokenizers 0.13.3