Training in progress epoch 0

README.md

@@ -15,8 +15,8 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [dbmdz/bert-base-french-europeana-cased](https://huggingface.co/dbmdz/bert-base-french-europeana-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.0693
-- Epoch: 2
+- Train Loss: 0.2420
+- Epoch: 0
 
 ## Model description
 
@@ -35,16 +35,14 @@ 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': 2151, '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': 7170, '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: float32
 
 ### Training results
 
 | Train Loss | Epoch |
 |:----------:|:-----:|
-| 0.2548     | 0     |
-| 0.1102     | 1     |
-| 0.0693     | 2     |
+| 0.2420     | 0     |
 
 
 ### Framework versions

config.json

@@ -11,18 +11,18 @@
   "hidden_size": 768,
   "id2label": {
     "0": "O",
-    "1": "B-lobj",
-    "2": "I-lobj",
-    "3": "B-lloc",
-    "4": "I-lloc"
+    "1": "B-lloc",
+    "2": "I-lloc",
+    "3": "B-lobj",
+    "4": "I-lobj"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "label2id": {
-    "B-lloc": 3,
-    "B-lobj": 1,
-    "I-lloc": 4,
-    "I-lobj": 2,
+    "B-lloc": 1,
+    "B-lobj": 3,
+    "I-lloc": 2,
+    "I-lobj": 4,
     "O": 0
   },
   "layer_norm_eps": 1e-12,

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88becd5370422fd98ea69b3c828e1b9002f855e1bf51b07362b6ee253f07100a
-size 440408028
+oid sha256:7ec3776e2a1ab44b753ce70254d42f306ce0d5633e403df8424b62662cf472c9
+size 440395740