heBERT

config.json

@@ -0,0 +1,41 @@
+{
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "B_TIME",
+    "1": "B_PERS",
+    "2": "B_MONEY",
+    "3": "B_ORG",
+    "4": "B_PERCENT",
+    "5": "O",
+    "6": "B_LOC",
+    "7": "B_DATE"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B_DATE": 7,
+    "B_LOC": 6,
+    "B_MONEY": 2,
+    "B_ORG": 3,
+    "B_PERCENT": 4,
+    "B_PERS": 1,
+    "B_TIME": 0,
+    "O": 5
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "total_flos": 6997313242916978688,
+  "type_vocab_size": 2,
+  "vocab_size": 30522
+}

log_history.json

@@ -0,0 +1,173 @@
+[
+  {
+    "loss": 2.1632102966308593,
+    "learning_rate": 1.0000000000000002e-06,
+    "epoch": 0.2127659574468085,
+    "total_flos": 4181675520000,
+    "step": 10
+  },
+  {
+    "loss": 1.9698543548583984,
+    "learning_rate": 2.0000000000000003e-06,
+    "epoch": 0.425531914893617,
+    "total_flos": 8363351040000,
+    "step": 20
+  },
+  {
+    "loss": 1.5943157196044921,
+    "learning_rate": 3e-06,
+    "epoch": 0.6382978723404256,
+    "total_flos": 12545026560000,
+    "step": 30
+  },
+  {
+    "loss": 1.1324241638183594,
+    "learning_rate": 4.000000000000001e-06,
+    "epoch": 0.851063829787234,
+    "total_flos": 16726702080000,
+    "step": 40
+  },
+  {
+    "loss": 0.7799140930175781,
+    "learning_rate": 5e-06,
+    "epoch": 1.0638297872340425,
+    "total_flos": 20620887408000,
+    "step": 50
+  },
+  {
+    "loss": 0.5984169006347656,
+    "learning_rate": 6e-06,
+    "epoch": 1.2765957446808511,
+    "total_flos": 24802562928000,
+    "step": 60
+  },
+  {
+    "loss": 0.4769012451171875,
+    "learning_rate": 7.000000000000001e-06,
+    "epoch": 1.4893617021276595,
+    "total_flos": 28984238448000,
+    "step": 70
+  },
+  {
+    "loss": 0.3644599914550781,
+    "learning_rate": 8.000000000000001e-06,
+    "epoch": 1.702127659574468,
+    "total_flos": 33165913968000,
+    "step": 80
+  },
+  {
+    "loss": 0.29639739990234376,
+    "learning_rate": 9e-06,
+    "epoch": 1.9148936170212765,
+    "total_flos": 37347589488000,
+    "step": 90
+  },
+  {
+    "loss": 0.26825637817382814,
+    "learning_rate": 1e-05,
+    "epoch": 2.127659574468085,
+    "total_flos": 41241774816000,
+    "step": 100
+  },
+  {
+    "loss": 0.19923171997070313,
+    "learning_rate": 1.1000000000000001e-05,
+    "epoch": 2.3404255319148937,
+    "total_flos": 45423450336000,
+    "step": 110
+  },
+  {
+    "loss": 0.19310073852539061,
+    "learning_rate": 1.2e-05,
+    "epoch": 2.5531914893617023,
+    "total_flos": 49605125856000,
+    "step": 120
+  },
+  {
+    "loss": 0.15804977416992189,
+    "learning_rate": 1.3000000000000001e-05,
+    "epoch": 2.7659574468085104,
+    "total_flos": 53786801376000,
+    "step": 130
+  },
+  {
+    "loss": 0.17403030395507812,
+    "learning_rate": 1.4000000000000001e-05,
+    "epoch": 2.978723404255319,
+    "total_flos": 57968476896000,
+    "step": 140
+  },
+  {
+    "loss": 0.11231231689453125,
+    "learning_rate": 1.5e-05,
+    "epoch": 3.1914893617021276,
+    "total_flos": 61862662224000,
+    "step": 150
+  },
+  {
+    "loss": 0.0972991943359375,
+    "learning_rate": 1.6000000000000003e-05,
+    "epoch": 3.404255319148936,
+    "total_flos": 66044337744000,
+    "step": 160
+  },
+  {
+    "loss": 0.09285507202148438,
+    "learning_rate": 1.7000000000000003e-05,
+    "epoch": 3.617021276595745,
+    "total_flos": 70226013264000,
+    "step": 170
+  },
+  {
+    "loss": 0.10490646362304687,
+    "learning_rate": 1.8e-05,
+    "epoch": 3.829787234042553,
+    "total_flos": 74407688784000,
+    "step": 180
+  },
+  {
+    "loss": 0.08623809814453125,
+    "learning_rate": 1.9e-05,
+    "epoch": 4.042553191489362,
+    "total_flos": 78301874112000,
+    "step": 190
+  },
+  {
+    "loss": 0.05904541015625,
+    "learning_rate": 2e-05,
+    "epoch": 4.25531914893617,
+    "total_flos": 82483549632000,
+    "step": 200
+  },
+  {
+    "loss": 0.052008056640625,
+    "learning_rate": 2.1e-05,
+    "epoch": 4.468085106382979,
+    "total_flos": 86665225152000,
+    "step": 210
+  },
+  {
+    "loss": 0.06222076416015625,
+    "learning_rate": 2.2000000000000003e-05,
+    "epoch": 4.680851063829787,
+    "total_flos": 90846900672000,
+    "step": 220
+  },
+  {
+    "loss": 0.05680923461914063,
+    "learning_rate": 2.3000000000000003e-05,
+    "epoch": 4.8936170212765955,
+    "total_flos": 95028576192000,
+    "step": 230
+  },
+  {
+    "eval_loss": 0.0899211324525602,
+    "eval_accuracy_score": 0.974121282348397,
+    "eval_precision": 0.9776031434184675,
+    "eval_recall": 0.9749216300940439,
+    "eval_f1": 0.9762605454188739,
+    "epoch": 5.0,
+    "total_flos": 96831923760000,
+    "step": 235
+  }
+]

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d385d4e8a6fd0c04dff5ab0ef9b091d66ad239a1d17ef4c6fee85d860bb6efee
+size 435679343

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d683997fff536a8cb258bffa83dc61ab5f5b2167c2bb0fbd8408703c1e902c4
+size 1775