Training in progress epoch 3

README.md

@@ -13,10 +13,10 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [allenai/scibert_scivocab_uncased](https://huggingface.co/allenai/scibert_scivocab_uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 4.9365
-- Validation Loss: 5.8427
-- Train Accuracy: 0.1206
-- Epoch: 2
+- Train Loss: 4.3345
+- Validation Loss: 5.5243
+- Train Accuracy: 0.1562
+- Epoch: 3
 
 ## Model description
 
@@ -45,6 +45,7 @@ The following hyperparameters were used during training:
 | 6.8503     | 6.9170          | 0.0323         | 0     |
 | 5.7494     | 6.3086          | 0.0738         | 1     |
 | 4.9365     | 5.8427          | 0.1206         | 2     |
+| 4.3345     | 5.5243          | 0.1562         | 3     |
 
 
 ### Framework versions

logs/train/events.out.tfevents.1680559352.e6764e395944.388.0.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:194b5655221b846b49148da450ea5dcd308d0013a3001762b8f9355c38566c69
-size 3556083
+oid sha256:3e5504551416899c72b2ffd625c34ce76b9118ad792b87b964e225634d2971c9
+size 3556300

logs/validation/events.out.tfevents.1680559718.e6764e395944.388.1.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:580d03436a378fb6163a3ba97b70d33c1901f1893635e328db3a31fc059ea1e7
-size 544
+oid sha256:39a8bb7254d0b7cf4c3c8fe459b8a5726ef22458fc792c403dd67934c63c3762
+size 700

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b651df2dc1c237ca8b2d14022397ef8e09bc7d9f0e3f27cf0e0dcdd0f37cbc51
+oid sha256:06b44de3efc098250cb21792f5a3cd298e6c0a29717e5c6c135faa531ef6f2ed
 size 444606632