Add config files

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "dcariasvi/DrBERT-CASM2",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-problem",
+    "2": "I-problem",
+    "3": "B-treatment",
+    "4": "I-treatment",
+    "5": "B-test",
+    "6": "I-test"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-problem": 1,
+    "B-test": 5,
+    "B-treatment": 3,
+    "I-problem": 2,
+    "I-test": 6,
+    "I-treatment": 4,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

history.json

@@ -0,0 +1 @@
+[{"train": {"loss": 0.4125201638787985}, "eval": {"loss": 0.28105667685968394, "overall_precision": 0.6288554677542697, "overall_recall": 0.6964991530208922, "overall_f1-score": 0.6609511051574012, "overall_support": "3542", "overall_acc": 0.9027570584010166, "problem_precision": 0.6217303822937625, "problem_recall": 0.6821192052980133, "problem_f1-score": 0.6505263157894737, "problem_support": "1812", "test_precision": 0.6564245810055865, "test_recall": 0.7524012806830309, "test_f1-score": 0.7011437095972153, "test_support": "937", "treatment_precision": 0.610917537746806, "treatment_recall": 0.6633039092055486, "treatment_f1-score": 0.6360338573155987, "treatment_support": "793"}}, {"train": {"loss": 0.2762815960689264}, "eval": {"loss": 0.2743868621309166, "overall_precision": 0.6495202558635395, "overall_recall": 0.6880293619424054, "overall_f1-score": 0.6682204551686318, "overall_support": "3542", "overall_acc": 0.9052710094480358, "problem_precision": 0.633705475810739, "problem_recall": 0.6578366445916115, "problem_f1-score": 0.6455456268616301, "problem_support": "1812", "test_precision": 0.6851851851851852, "test_recall": 0.7502668089647813, "test_f1-score": 0.7162506367804381, "test_support": "937", "treatment_precision": 0.6414201183431952, "treatment_recall": 0.6834804539722572, "treatment_f1-score": 0.6617826617826619, "treatment_support": "793"}}, {"train": {"loss": 0.24771345957834906}, "eval": {"loss": 0.271967472341519, "overall_precision": 0.6427855711422845, "overall_recall": 0.7244494635798984, "overall_f1-score": 0.6811786567560393, "overall_support": "3542", "overall_acc": 0.9052710094480358, "problem_precision": 0.6335992023928215, "problem_recall": 0.7014348785871964, "problem_f1-score": 0.6657936092194865, "problem_support": "1812", "test_precision": 0.6627379873073436, "test_recall": 0.7801494130202775, "test_f1-score": 0.7166666666666668, "test_support": "937", "treatment_precision": 0.638731596828992, "treatment_recall": 0.7112232030264817, "treatment_f1-score": 0.6730310262529833, "treatment_support": "793"}}, {"train": {"loss": 0.22672327848620155}, "eval": {"loss": 0.2861445434745806, "overall_precision": 0.6255808266079727, "overall_recall": 0.7221908526256352, "overall_f1-score": 0.670423273489713, "overall_support": "3542", "overall_acc": 0.8994695839549146, "problem_precision": 0.6085686465433301, "problem_recall": 0.6898454746136865, "problem_f1-score": 0.6466632177961718, "problem_support": "1812", "test_precision": 0.666970802919708, "test_recall": 0.7801494130202775, "test_f1-score": 0.719134284308903, "test_support": "937", "treatment_precision": 0.6144834930777423, "treatment_recall": 0.7276166456494325, "treatment_f1-score": 0.6662817551963048, "treatment_support": "793"}}, {"train": {"loss": 0.2031083636096723}, "eval": {"loss": 0.2810970079027238, "overall_precision": 0.6511976047904192, "overall_recall": 0.7368718238283456, "overall_f1-score": 0.6913907284768213, "overall_support": "3542", "overall_acc": 0.9046356152273606, "problem_precision": 0.6431761786600496, "problem_recall": 0.7152317880794702, "problem_f1-score": 0.6772929187353018, "problem_support": "1812", "test_precision": 0.663963963963964, "test_recall": 0.7865528281750267, "test_f1-score": 0.7200781631656081, "test_support": "937", "treatment_precision": 0.6534541336353341, "treatment_recall": 0.7276166456494325, "treatment_f1-score": 0.68854415274463, "treatment_support": "793"}}]

trainer_config.yml

@@ -0,0 +1,9 @@
+learning_rate: 5.0e-06
+nb_training_epochs: 5
+dataloader_nb_workers: 0
+batch_size: 4
+seed: 0
+gradient_accumulation_steps: 1
+do_metrics_in_training: false
+metric_to_track_lr: loss
+log_step_interval: 100