Training in progress epoch 0

README.md

@@ -15,11 +15,11 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [ProsusAI/finbert](https://huggingface.co/ProsusAI/finbert) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.0039
-- Validation Loss: 0.7602
-- Train Accuracy: 0.8679
-- Train F1 Macro: 0.8537
-- Epoch: 4
+- Train Loss: 0.4675
+- Validation Loss: 0.2828
+- Train Accuracy: 0.9012
+- Train F1 Macro: 0.8926
+- Epoch: 0
 
 ## Model description
 
@@ -45,11 +45,7 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Train Accuracy | Train F1 Macro | Epoch |
 |:----------:|:---------------:|:--------------:|:--------------:|:-----:|
-| 0.0085     | 0.7174          | 0.8762         | 0.8642         | 0     |
-| 0.0050     | 0.7373          | 0.8726         | 0.8563         | 1     |
-| 0.0023     | 0.7720          | 0.8738         | 0.8586         | 2     |
-| 0.0054     | 0.8142          | 0.8690         | 0.8569         | 3     |
-| 0.0039     | 0.7602          | 0.8679         | 0.8537         | 4     |
+| 0.4675     | 0.2828          | 0.9012         | 0.8926         | 0     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ed58b87e8ec340eb55af90328ed24add1f484b6e97a3f940c43df2abd6ff4b1
+oid sha256:62b6224e9bf8accadfb512ce183e1b30c0ab956d401210d79f92dcf98ffb9ea5
 size 438226204

tokenizer.json

@@ -1,7 +1,21 @@
 {
   "version": "1.0",
-  "truncation": null,
-  "padding": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 128,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
+  "padding": {
+    "strategy": {
+      "Fixed": 128
+    },
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 0,
+    "pad_type_id": 0,
+    "pad_token": "[PAD]"
+  },
   "added_tokens": [
     {
       "id": 0,