Training in progress epoch 0

README.md

@@ -14,10 +14,10 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.1919
-- Validation Loss: 0.5331
-- Train Matthews Correlation: 0.5285
-- Epoch: 2
+- Train Loss: 0.5162
+- Validation Loss: 0.4568
+- Train Matthews Correlation: 0.4417
+- Epoch: 0
 
 ## Model description
 
@@ -43,9 +43,7 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Train Matthews Correlation | Epoch |
 |:----------:|:---------------:|:--------------------------:|:-----:|
-| 0.5182     | 0.4571          | 0.4509                     | 0     |
-| 0.3156     | 0.4675          | 0.5132                     | 1     |
-| 0.1919     | 0.5331          | 0.5285                     | 2     |
+| 0.5162     | 0.4568          | 0.4417                     | 0     |
 
 
 ### Framework versions

config.json

@@ -8,7 +8,15 @@
   "dim": 768,
   "dropout": 0.1,
   "hidden_dim": 3072,
+  "id2label": {
+    "0": "Invalid",
+    "1": "Valid"
+  },
   "initializer_range": 0.02,
+  "label2id": {
+    "Invalid": 0,
+    "Valid": 1
+  },
   "max_position_embeddings": 512,
   "model_type": "distilbert",
   "n_heads": 12,

logs/train/events.out.tfevents.1658245469.matt-TRX40-AORUS-PRO-WIFI.113477.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3f92b8d74e7c6570c2f7744ba18347191c841468a9571d1bc61e6d524f294f4
+size 1590973

logs/validation/events.out.tfevents.1658245488.matt-TRX40-AORUS-PRO-WIFI.113477.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4f944afec165f86b6aa659de4df6a8a518ad996a207d5eede7ec4c53c966f90
+size 194

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb2ed9b96c1d721d967830d1c4e339b2f4189c937502423b3ba6067666e8aa2e
+oid sha256:2bed8ab7371bd21e6ed7e3a6cc1cd6d2bed357e2990e194c6a53c60726ba8bbb
 size 267951896