Training in progress epoch 3

README.md

@@ -14,10 +14,10 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.2478
-- Validation Loss: 0.4089
-- Train Accuracy: 0.8603
-- Epoch: 2
+- Train Loss: 0.1821
+- Validation Loss: 0.4577
+- Train Accuracy: 0.8575
+- Epoch: 3
 
 ## Model description
 
@@ -46,6 +46,7 @@ The following hyperparameters were used during training:
 | 0.4543     | 0.3920          | 0.8526         | 0     |
 | 0.3298     | 0.3979          | 0.8546         | 1     |
 | 0.2478     | 0.4089          | 0.8603         | 2     |
+| 0.1821     | 0.4577          | 0.8575         | 3     |
 
 
 ### Framework versions

logs/train/events.out.tfevents.1705433427.104-171-203-254.1949139.0.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5858d49a952c56671be7b52a30bf8a1030e9d50105c8e18df914b57f6f823b0c
-size 2838049
+oid sha256:04970822923b9f1bd6bc64ba6c9e8d39b8f44d70738c04d4097612250b40f201
+size 2838266

logs/validation/events.out.tfevents.1705435659.104-171-203-254.1949139.1.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69a8c6148ba184d866b3a706e750c357279c5a6582c4537f94555dbb77e4298b
-size 509
+oid sha256:d8a6c40ceed1fc276b423dd90ba7cdc383e726f6bf99bda52e758cb0b84a6faa
+size 666

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:421f7a0848706a56e00b577e9e63c81488e8da205360ecf7f76c1b1c866a1c98
+oid sha256:3e68f2f39498fda69630723edbffa0de6b24bcf80e0b84c041dd42498e67ce9a
 size 498865280