Training in progress epoch 0

README.md

@@ -15,10 +15,10 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.8893
-- Validation Loss: 0.8320
-- Train Accuracy: 0.9286
-- Epoch: 4
+- Train Loss: 0.7101
+- Validation Loss: 0.6549
+- Train Accuracy: 0.7059
+- Epoch: 0
 
 ## Model description
 
@@ -44,11 +44,7 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Train Accuracy | Epoch |
 |:----------:|:---------------:|:--------------:|:-----:|
-| 1.1047     | 1.0851          | 0.2857         | 0     |
-| 1.0214     | 0.9784          | 0.7857         | 1     |
-| 0.9908     | 0.8723          | 0.8571         | 2     |
-| 0.9167     | 0.8421          | 0.9286         | 3     |
-| 0.8893     | 0.8320          | 0.9286         | 4     |
+| 0.7101     | 0.6549          | 0.7059         | 0     |
 
 
 ### Framework versions

config.json

@@ -10,16 +10,14 @@
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
   "id2label": {
-    "0": "\u7528\u6237\u767b\u5f55",
-    "1": "\u6ce8\u518c",
-    "2": "\u540e\u53f0\u767b\u5f55"
+    "0": "\u767b\u5f55",
+    "1": "\u6ce8\u518c"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "label2id": {
-    "\u540e\u53f0\u767b\u5f55": 2,
     "\u6ce8\u518c": 1,
-    "\u7528\u6237\u767b\u5f55": 0
+    "\u767b\u5f55": 0
   },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:692986ba35ac437cc2f86e7edab092de58885a11f761e2060547657f848cec25
-size 438226204
+oid sha256:d8a7792d000abcbb9f062db08dbfe4f5ede0b4090eda928a1185f4094ab60fd7
+size 438223128