terminator_finetune_augment

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

• Loss: 0.0000
• F1: 1.0

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	0.2419	60	0.8871	0.5852
No log	0.4839	120	0.7329	0.6617
No log	0.7258	180	0.4677	0.8161
No log	0.9677	240	0.4432	0.8588
No log	1.2097	300	0.5409	0.8094
No log	1.4516	360	0.5100	0.8382
No log	1.6935	420	0.3777	0.8506
No log	1.9355	480	0.3097	0.9060
0.3881	2.1774	540	0.1960	0.9331
0.3881	2.4194	600	0.1590	0.9535
0.3881	2.6613	660	0.1501	0.9534
0.3881	2.9032	720	0.0795	0.9800
0.3881	3.1452	780	0.0098	0.9932
0.3881	3.3871	840	0.0280	0.9932
0.3881	3.6290	900	0.0486	0.9805
0.3881	3.8710	960	0.0828	0.9804
0.083	4.1129	1020	0.0529	0.9804
0.083	4.3548	1080	0.0424	0.9931
0.083	4.5968	1140	0.0204	0.9931
0.083	4.8387	1200	0.0169	0.9873
0.083	5.0806	1260	0.0008	1.0
0.083	5.3226	1320	0.0266	0.9863
0.083	5.5645	1380	0.0020	1.0
0.083	5.8065	1440	0.0001	1.0
0.0341	6.0484	1500	0.0052	0.9931
0.0341	6.2903	1560	0.0014	1.0
0.0341	6.5323	1620	0.0036	1.0
0.0341	6.7742	1680	0.0037	1.0
0.0341	7.0161	1740	0.0002	1.0
0.0341	7.2581	1800	0.0130	0.9932
0.0341	7.5	1860	0.0001	1.0
0.0341	7.7419	1920	0.0001	1.0
0.0341	7.9839	1980	0.0001	1.0
0.017	8.2258	2040	0.0001	1.0
0.017	8.4677	2100	0.0010	1.0
0.017	8.7097	2160	0.0096	0.9937
0.017	8.9516	2220	0.0824	0.9661
0.017	9.1935	2280	0.0009	1.0
0.017	9.4355	2340	0.0017	1.0
0.017	9.6774	2400	0.0004	1.0
0.017	9.9194	2460	0.0258	0.9868
0.0278	10.1613	2520	0.0279	0.9931
0.0278	10.4032	2580	0.0551	0.9931
0.0278	10.6452	2640	0.0001	1.0
0.0278	10.8871	2700	0.0314	0.9936
0.0278	11.1290	2760	0.0349	0.9931
0.0278	11.3710	2820	0.0057	0.9931
0.0278	11.6129	2880	0.0446	0.9931
0.0278	11.8548	2940	0.0001	1.0
0.0099	12.0968	3000	0.0965	0.9867
0.0099	12.3387	3060	0.0637	0.9937
0.0099	12.5806	3120	0.0884	0.9867
0.0099	12.8226	3180	0.0737	0.9931
0.0099	13.0645	3240	0.0748	0.9931
0.0099	13.3065	3300	0.0748	0.9931
0.0099	13.5484	3360	0.0000	1.0
0.0099	13.7903	3420	0.0000	1.0
0.0099	14.0323	3480	0.1598	0.9660
0.0169	14.2742	3540	0.0006	1.0
0.0169	14.5161	3600	0.0001	1.0
0.0169	14.7581	3660	0.0002	1.0
0.0169	15.0	3720	0.0005	1.0
0.0169	15.2419	3780	0.0000	1.0
0.0169	15.4839	3840	0.0000	1.0
0.0169	15.7258	3900	0.0002	1.0
0.0169	15.9677	3960	0.0015	1.0
0.0155	16.2097	4020	0.0000	1.0
0.0155	16.4516	4080	0.0000	1.0
0.0155	16.6935	4140	0.0019	1.0
0.0155	16.9355	4200	0.0574	0.9931
0.0155	17.1774	4260	0.0570	0.9931
0.0155	17.4194	4320	0.0566	0.9931
0.0155	17.6613	4380	0.0002	1.0
0.0155	17.9032	4440	0.0001	1.0
0.0214	18.1452	4500	0.0001	1.0
0.0214	18.3871	4560	0.0001	1.0
0.0214	18.6290	4620	0.0064	0.9937
0.0214	18.8710	4680	0.0724	0.9936
0.0214	19.1129	4740	0.0000	1.0
0.0214	19.3548	4800	0.0001	1.0
0.0214	19.5968	4860	0.0001	1.0
0.0214	19.8387	4920	0.0002	1.0
0.0214	20.0806	4980	0.0003	1.0
0.0161	20.3226	5040	0.0003	1.0
0.0161	20.5645	5100	0.0000	1.0
0.0161	20.8065	5160	0.0000	1.0
0.0161	21.0484	5220	0.0000	1.0
0.0161	21.2903	5280	0.0000	1.0
0.0161	21.5323	5340	0.0000	1.0
0.0161	21.7742	5400	0.0000	1.0
0.0161	22.0161	5460	0.0000	1.0
0.004	22.2581	5520	0.0000	1.0
0.004	22.5	5580	0.0000	1.0
0.004	22.7419	5640	0.0000	1.0
0.004	22.9839	5700	0.0000	1.0
0.004	23.2258	5760	0.0000	1.0
0.004	23.4677	5820	0.0000	1.0
0.004	23.7097	5880	0.0000	1.0
0.004	23.9516	5940	0.0000	1.0
0.0026	24.1935	6000	0.0000	1.0
0.0026	24.4355	6060	0.0000	1.0
0.0026	24.6774	6120	0.0000	1.0
0.0026	24.9194	6180	0.0000	1.0
0.0026	25.1613	6240	0.0000	1.0
0.0026	25.4032	6300	0.0000	1.0
0.0026	25.6452	6360	0.0000	1.0
0.0026	25.8871	6420	0.0000	1.0
0.0026	26.1290	6480	0.0000	1.0
0.0009	26.3710	6540	0.0000	1.0
0.0009	26.6129	6600	0.0000	1.0
0.0009	26.8548	6660	0.0000	1.0
0.0009	27.0968	6720	0.0000	1.0
0.0009	27.3387	6780	0.0000	1.0
0.0009	27.5806	6840	0.0000	1.0
0.0009	27.8226	6900	0.0000	1.0
0.0009	28.0645	6960	0.0000	1.0
0.0007	28.3065	7020	0.0000	1.0
0.0007	28.5484	7080	0.0000	1.0
0.0007	28.7903	7140	0.0000	1.0
0.0007	29.0323	7200	0.0000	1.0
0.0007	29.2742	7260	0.0000	1.0
0.0007	29.5161	7320	0.0000	1.0
0.0007	29.7581	7380	0.0000	1.0
0.0007	30.0	7440	0.0000	1.0
0.0009	30.2419	7500	0.0000	1.0
0.0009	30.4839	7560	0.0000	1.0
0.0009	30.7258	7620	0.0000	1.0
0.0009	30.9677	7680	0.0000	1.0
0.0009	31.2097	7740	0.0000	1.0
0.0009	31.4516	7800	0.0000	1.0
0.0009	31.6935	7860	0.0000	1.0
0.0009	31.9355	7920	0.0000	1.0
0.0009	32.1774	7980	0.0000	1.0
0.0	32.4194	8040	0.0000	1.0
0.0	32.6613	8100	0.0000	1.0
0.0	32.9032	8160	0.0000	1.0
0.0	33.1452	8220	0.0000	1.0
0.0	33.3871	8280	0.0000	1.0
0.0	33.6290	8340	0.0000	1.0
0.0	33.8710	8400	0.0000	1.0
0.0	34.1129	8460	0.0000	1.0
0.0	34.3548	8520	0.0000	1.0
0.0	34.5968	8580	0.0000	1.0
0.0	34.8387	8640	0.0000	1.0
0.0	35.0806	8700	0.0000	1.0
0.0	35.3226	8760	0.0000	1.0
0.0	35.5645	8820	0.0000	1.0
0.0	35.8065	8880	0.0000	1.0
0.0	36.0484	8940	0.0000	1.0
0.0	36.2903	9000	0.0000	1.0
0.0	36.5323	9060	0.0000	1.0
0.0	36.7742	9120	0.0000	1.0
0.0	37.0161	9180	0.0000	1.0
0.0	37.2581	9240	0.0000	1.0
0.0	37.5	9300	0.0000	1.0
0.0	37.7419	9360	0.0000	1.0
0.0	37.9839	9420	0.0000	1.0
0.0	38.2258	9480	0.0000	1.0
0.0	38.4677	9540	0.0000	1.0
0.0	38.7097	9600	0.0000	1.0
0.0	38.9516	9660	0.0000	1.0
0.0	39.1935	9720	0.0000	1.0
0.0	39.4355	9780	0.0000	1.0
0.0	39.6774	9840	0.0000	1.0
0.0	39.9194	9900	0.0000	1.0

Framework versions

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