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 [albert-base-v2](https://huggingface.co/albert-base-v2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.2495
-- Validation Loss: 0.2841
-- Train Accuracy: 0.9304
-- Epoch: 2
+- Train Loss: 2.3070
+- Validation Loss: 0.9137
+- Train Accuracy: 0.8732
+- Epoch: 0
 
 ## Model description
 
@@ -44,9 +44,7 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Train Accuracy | Epoch |
 |:----------:|:---------------:|:--------------:|:-----:|
-| 2.2473     | 0.8915          | 0.8667         | 0     |
-| 0.5458     | 0.3423          | 0.9440         | 1     |
-| 0.2495     | 0.2841          | 0.9304         | 2     |
+| 2.3070     | 0.9137          | 0.8732         | 0     |
 
 
 ### Framework versions

config.json

@@ -54,8 +54,8 @@
     "37": "Return on Involvement",
     "38": "Recruitment Process Outsourcing",
     "39": "Request for Purchase Order",
-    "41": "Small and Medium-sized Enterprises",
-    "42": "Subject Matter Expert"
+    "40": "Small and Medium-sized Enterprises",
+    "41": "Subject Matter Expert"
   },
   "initializer_range": 0.02,
   "inner_group_num": 1,
@@ -101,8 +101,8 @@
     "Return on Investment": 36,
     "Return on Involvement": 37,
     "Risk Assessment": 35,
-    "Small and Medium-sized Enterprises": 41,
-    "Subject Matter Expert": 42
+    "Small and Medium-sized Enterprises": 40,
+    "Subject Matter Expert": 41
   },
   "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:e57cc55df3446ada98fbf088d8b38a505108a901be0f346f9156d0debd4436e3
+oid sha256:6f6b8f44e087c8f5ed259d817af0dee6d3d9e105ab76156c53744967dcf83445
 size 46904728