terminator_finetune

This model is a fine-tuned version of echodrift/terminator on the None dataset. It achieves the following results on the evaluation set:

• Loss: 4.3450
• F1: 0.4817

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: 4.676339096688447e-05
• train_batch_size: 16
• eval_batch_size: 64
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• num_epochs: 40.0

Training results

Training Loss	Epoch	Step	Validation Loss	F1
No log	0.9091	60	1.0333	0.4571
No log	1.8182	120	1.0937	0.4575
No log	2.7273	180	1.4988	0.4340
No log	3.6364	240	1.8738	0.4582
No log	4.5455	300	2.7333	0.4141
No log	5.4545	360	3.1445	0.4468
No log	6.3636	420	3.2106	0.5097
No log	7.2727	480	3.3219	0.4878
0.3564	8.1818	540	4.1566	0.4493
0.3564	9.0909	600	3.5661	0.4938
0.3564	10.0	660	3.5243	0.5015
0.3564	10.9091	720	3.7514	0.5057
0.3564	11.8182	780	4.0015	0.4608
0.3564	12.7273	840	4.4677	0.4278
0.3564	13.6364	900	4.0757	0.4677
0.3564	14.5455	960	4.4461	0.4501
0.0105	15.4545	1020	4.1675	0.4820
0.0105	16.3636	1080	4.2034	0.4752
0.0105	17.2727	1140	4.2144	0.4820
0.0105	18.1818	1200	4.2162	0.4871
0.0105	19.0909	1260	4.0772	0.4972
0.0105	20.0	1320	4.3442	0.4733
0.0105	20.9091	1380	4.2116	0.4912
0.0105	21.8182	1440	4.1968	0.4860
0.0008	22.7273	1500	4.2478	0.4855
0.0008	23.6364	1560	4.3012	0.5041
0.0008	24.5455	1620	4.6983	0.4779
0.0008	25.4545	1680	4.1226	0.5194
0.0008	26.3636	1740	4.1304	0.5282
0.0008	27.2727	1800	4.1460	0.5250
0.0008	28.1818	1860	4.1624	0.5271
0.0008	29.0909	1920	4.1758	0.5210
0.0008	30.0	1980	4.1815	0.5210
0.0005	30.9091	2040	4.1975	0.5154
0.0005	31.8182	2100	4.2007	0.5154
0.0005	32.7273	2160	4.2079	0.5160
0.0005	33.6364	2220	4.3222	0.4817
0.0005	34.5455	2280	4.3393	0.4817
0.0005	35.4545	2340	4.3413	0.4817
0.0005	36.3636	2400	4.3432	0.4817
0.0005	37.2727	2460	4.3440	0.4817
0.0001	38.1818	2520	4.3442	0.4817
0.0001	39.0909	2580	4.3442	0.4817
0.0001	40.0	2640	4.3450	0.4817

Framework versions

• Transformers 4.47.0.dev0
• Pytorch 2.5.1+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3