Ernie 3.0 base chinese finetuned ner This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set: Loss: 0.4856 Precision: 0.6511 Recall: 0.7535 F1: 0.6986 Accuracy: 0.9053 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: 2e 05 train batch size: 16 eval batch size: 8 seed: 42 optimizer: Adam with betas=(0.9,0.999) and epsilon=1e 08 lr scheduler type: linear num epochs: 10 Training results Training Loss Epoch Step Validation Loss Precision Recall F1 Accuracy : : : : : : : : : : : : : : : : 0.0667 1.0 126 0.4589 0.6387 0.7553 0.6921 0.9012 0.0594 2.0 252 0.4656 0.6444 0.7515 0.6939 0.9057 0.053 3.0 378 0.4524 0.6444 0.7477 0.6922 0.9064 0.0473 4.0 504 0.4955 0.6298 0.7568 0.6875 0.9012 0.0461 5.0 630 0.4892 0.6512 0.7505 0.6973 0.9077 0.0438 6.0 756 0.5021 0.6450 0.7528 0.6947 0.9054 0.0428 7.0 882 0.5048 0.6471 0.7576 0.6980 0.9050 0.0583 8.0 1008 0.4990 0.6401 0.7533 0.6921 0.9038 0.0582 9.0 1134 0.4833 0.6457 0.7513 0…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy