salt language ID This model is a fine tuned version of google/t5 efficient tiny on the generator dataset. It achieves the following results on the evaluation set: Loss: 0.4200 Accuracy: 0.6086 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: 0.001 train batch size: 64 eval batch size: 64 seed: 42 optimizer: Use OptimizerNames.ADAMW TORCH FUSED with betas=(0.9,0.999) and epsilon=1e 08 and optimizer args=No additional optimizer arguments lr scheduler type: linear lr scheduler warmup steps: 10 training steps: 20000 Training results Training Loss Epoch Step Validation Loss Accuracy : : : : : : : : : : 0.9948 0.025 500 0.7153 0.1757 0.3269 0.05 1000 0.7217 0.2611 0.2853 0.075 1500 0.9151 0.2412 0.1823 0.1 2000 0.5561 0.3965 0.1953 0.125 2500 0.5975 0.3824 0.1831 0.15 3000 0.5670 0.4264 0.141 0.175 3500 0.7885 0.3443 0.1081 0.2 4000 0.8961 0.3111 0.154 0.225 4500 0.7975 0.3491 0.1306 0.25 5000 0.4824 0.5092 0.1013 0.275 5500 0.4946 0.4613 0.1083 0.3 6000 0.6959 0.4038 0.1121 0.…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy