Training in progress epoch 0

README.md

@@ -15,9 +15,9 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [neuralmind/bert-base-portuguese-cased](https://huggingface.co/neuralmind/bert-base-portuguese-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.3991
-- Validation Loss: 0.3952
-- Epoch: 2
+- Train Loss: 0.0701
+- Validation Loss: 0.0060
+- Epoch: 0
 
 ## Model description
 
@@ -36,21 +36,19 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 624, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
+- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 7647, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
 - training_precision: mixed_float16
 
 ### Training results
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 0.5389     | 0.4231          | 0     |
-| 0.4175     | 0.3972          | 1     |
-| 0.3991     | 0.3952          | 2     |
+| 0.0701     | 0.0060          | 0     |
 
 
 ### Framework versions
 
-- Transformers 4.34.1
+- Transformers 4.35.0
 - TensorFlow 2.14.0
 - Datasets 2.14.6
 - Tokenizers 0.14.1

config.json

@@ -11,18 +11,62 @@
   "hidden_size": 768,
   "id2label": {
     "0": "O",
-    "1": "B-SUBMIT_CONTEXT",
-    "2": "I-SUBMIT_CONTEXT",
-    "3": "B-PATIENT_NAME",
-    "4": "I-PATIENT_NAME"
+    "1": "B-MACRO_NAME",
+    "2": "I-MACRO_NAME",
+    "3": "B-ROUTINE_NAME",
+    "4": "I-ROUTINE_NAME",
+    "5": "B-SHOWME_SPECIFIC_VITALS_MODAL",
+    "6": "I-SHOWME_SPECIFIC_VITALS_MODAL",
+    "7": "B-SUBMIT_CONTEXT",
+    "8": "I-SUBMIT_CONTEXT",
+    "9": "B-UNIT_NAME",
+    "10": "I-UNIT_NAME",
+    "11": "B-GO_TO_LOCATION",
+    "12": "I-GO_TO_LOCATION",
+    "13": "B-ORDER_ITEM",
+    "14": "I-ORDER_ITEM",
+    "15": "B-PATIENT_NAME",
+    "16": "I-PATIENT_NAME",
+    "17": "B-CLINICAL_NOTE",
+    "18": "I-CLINICAL_NOTE",
+    "19": "B-TEMPLATE_NAME",
+    "20": "I-TEMPLATE_NAME",
+    "21": "B-SHOWME_SPECIFIC_LABRESULTS_MODAL",
+    "22": "I-SHOWME_SPECIFIC_LABRESULTS_MODAL",
+    "23": "B-SHOWME_SPECIFIC_SCORE_MODAL",
+    "24": "I-SHOWME_SPECIFIC_SCORE_MODAL",
+    "25": "B-PROTOCOL_NAME",
+    "26": "I-PROTOCOL_NAME"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "label2id": {
-    "B-PATIENT_NAME": 3,
-    "B-SUBMIT_CONTEXT": 1,
-    "I-PATIENT_NAME": 4,
-    "I-SUBMIT_CONTEXT": 2,
+    "B-CLINICAL_NOTE": 17,
+    "B-GO_TO_LOCATION": 11,
+    "B-MACRO_NAME": 1,
+    "B-ORDER_ITEM": 13,
+    "B-PATIENT_NAME": 15,
+    "B-PROTOCOL_NAME": 25,
+    "B-ROUTINE_NAME": 3,
+    "B-SHOWME_SPECIFIC_LABRESULTS_MODAL": 21,
+    "B-SHOWME_SPECIFIC_SCORE_MODAL": 23,
+    "B-SHOWME_SPECIFIC_VITALS_MODAL": 5,
+    "B-SUBMIT_CONTEXT": 7,
+    "B-TEMPLATE_NAME": 19,
+    "B-UNIT_NAME": 9,
+    "I-CLINICAL_NOTE": 18,
+    "I-GO_TO_LOCATION": 12,
+    "I-MACRO_NAME": 2,
+    "I-ORDER_ITEM": 14,
+    "I-PATIENT_NAME": 16,
+    "I-PROTOCOL_NAME": 26,
+    "I-ROUTINE_NAME": 4,
+    "I-SHOWME_SPECIFIC_LABRESULTS_MODAL": 22,
+    "I-SHOWME_SPECIFIC_SCORE_MODAL": 24,
+    "I-SHOWME_SPECIFIC_VITALS_MODAL": 6,
+    "I-SUBMIT_CONTEXT": 8,
+    "I-TEMPLATE_NAME": 20,
+    "I-UNIT_NAME": 10,
     "O": 0
   },
   "layer_norm_eps": 1e-12,
@@ -38,7 +82,7 @@
   "pooler_size_per_head": 128,
   "pooler_type": "first_token_transform",
   "position_embedding_type": "absolute",
-  "transformers_version": "4.34.1",
+  "transformers_version": "4.35.0",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 29794

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a243d2f96f73bc2e6ddf9b714a5311df9445be266455b01ddf8515df05a525a
-size 433618908
+oid sha256:625a23140660b729ecdcb24ab3a088cb61de1d4e886b9cfec2ea373020b634e6
+size 433686580