Modelpublic

BenMurphy124/distilbert-imdb-lr0.0001-r16

sourceHugging Faceapache-2.0updated 7mo agoView on Hugging Face

0likes8downloads

Model Card

distilbert-imdb-lr0.0001-r16

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

—Loss: 0.2241
—Accuracy: 0.9148
—F1: 0.9158

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: 0.0001
—trainbatchsize: 16
—evalbatchsize: 16
—seed: 42
—optimizer: Use OptimizerNames.ADAMWTORCHFUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
—lrschedulertype: linear
—num_epochs: 3
—mixedprecisiontraining: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.3572	0.08	100	0.3466	0.8566	0.8466
0.3197	0.16	200	0.2927	0.8768	0.8731
0.2522	0.24	300	0.2990	0.8836	0.8808
0.2630	0.32	400	0.2706	0.8914	0.8883
0.2476	0.4	500	0.2957	0.8852	0.8798
0.3060	0.48	600	0.2620	0.889	0.8925
0.3170	0.56	700	0.2578	0.8946	0.8907
0.2985	0.64	800	0.2453	0.8974	0.8958
0.2812	0.72	900	0.2460	0.9024	0.9049
0.2522	0.8	1000	0.2762	0.891	0.8973
0.2186	0.88	1100	0.2420	0.9056	0.9062
0.2341	0.96	1200	0.2447	0.9072	0.9066
0.2767	1.04	1300	0.2312	0.9086	0.9088
0.2549	1.12	1400	0.2314	0.9072	0.9076
0.2195	1.2	1500	0.2372	0.9064	0.9064
0.2584	1.28	1600	0.2247	0.9098	0.9104
0.2017	1.3600	1700	0.2345	0.909	0.9082
0.2519	1.44	1800	0.2219	0.9094	0.9100
0.2099	1.52	1900	0.2300	0.9076	0.9061
0.2226	1.6	2000	0.2419	0.9082	0.9107
0.1971	1.6800	2100	0.2438	0.909	0.9060
0.2184	1.76	2200	0.2432	0.9076	0.9047
0.2479	1.8400	2300	0.2220	0.91	0.9106
0.2481	1.92	2400	0.2236	0.9094	0.9096
0.2405	2.0	2500	0.2281	0.9058	0.9087
0.2263	2.08	2600	0.2161	0.9102	0.9102
0.1433	2.16	2700	0.2418	0.9092	0.9084
0.2452	2.24	2800	0.2279	0.9094	0.9078
0.2088	2.32	2900	0.2361	0.9092	0.9119
0.2401	2.4	3000	0.2399	0.908	0.9044
0.1839	2.48	3100	0.2223	0.9128	0.9122
0.1914	2.56	3200	0.2252	0.9134	0.9146
0.2101	2.64	3300	0.2306	0.9112	0.9134
0.2046	2.7200	3400	0.2268	0.9114	0.9100
0.2022	2.8	3500	0.2241	0.9148	0.9158
0.2049	2.88	3600	0.2200	0.9146	0.9142
0.1790	2.96	3700	0.2207	0.915	0.9148

Framework versions

—PEFT 0.18.1
—Transformers 5.0.0
—Pytorch 2.10.0+cu128
—Datasets 4.0.0
—Tokenizers 0.22.2