Clickbait3

This model is a fine-tuned version of microsoft/Multilingual-MiniLM-L12-H384 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0248

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: 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: 4

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.05	50	0.0373
No log	0.1	100	0.0320
No log	0.15	150	0.0295
No log	0.21	200	0.0302
No log	0.26	250	0.0331
No log	0.31	300	0.0280
No log	0.36	350	0.0277
No log	0.41	400	0.0316
No log	0.46	450	0.0277
0.0343	0.51	500	0.0276
0.0343	0.56	550	0.0282
0.0343	0.62	600	0.0280
0.0343	0.67	650	0.0271
0.0343	0.72	700	0.0264
0.0343	0.77	750	0.0265
0.0343	0.82	800	0.0260
0.0343	0.87	850	0.0263
0.0343	0.92	900	0.0259
0.0343	0.97	950	0.0277
0.0278	1.03	1000	0.0281
0.0278	1.08	1050	0.0294
0.0278	1.13	1100	0.0256
0.0278	1.18	1150	0.0258
0.0278	1.23	1200	0.0254
0.0278	1.28	1250	0.0265
0.0278	1.33	1300	0.0252
0.0278	1.38	1350	0.0251
0.0278	1.44	1400	0.0264
0.0278	1.49	1450	0.0262
0.023	1.54	1500	0.0272
0.023	1.59	1550	0.0278
0.023	1.64	1600	0.0255
0.023	1.69	1650	0.0258
0.023	1.74	1700	0.0262
0.023	1.79	1750	0.0250
0.023	1.85	1800	0.0253
0.023	1.9	1850	0.0271
0.023	1.95	1900	0.0248
0.023	2.0	1950	0.0258
0.0224	2.05	2000	0.0252
0.0224	2.1	2050	0.0259
0.0224	2.15	2100	0.0254
0.0224	2.21	2150	0.0260
0.0224	2.26	2200	0.0254
0.0224	2.31	2250	0.0266
0.0224	2.36	2300	0.0258
0.0224	2.41	2350	0.0258
0.0224	2.46	2400	0.0256

Framework versions

• Transformers 4.17.0
• Pytorch 1.11.0
• Datasets 2.0.0
• Tokenizers 0.11.6