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 [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.3247
-- Validation Loss: 0.7499
-- Train Accuracy: 0.7222
-- Epoch: 29
+- Train Loss: 0.9441
+- Validation Loss: 0.4817
+- Train Accuracy: 0.8652
+- Epoch: 0
 
 ## Model description
 
@@ -36,43 +36,14 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'name': 'Adam', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 120, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
+- optimizer: {'name': 'Adam', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 330, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
 - training_precision: float32
 
 ### Training results
 
 | Train Loss | Validation Loss | Train Accuracy | Epoch |
 |:----------:|:---------------:|:--------------:|:-----:|
-| 1.0644     | 0.9892          | 0.7222         | 0     |
-| 0.9866     | 0.8384          | 0.7222         | 1     |
-| 0.9341     | 0.7685          | 0.7222         | 2     |
-| 0.8946     | 0.7523          | 0.7222         | 3     |
-| 0.8589     | 0.7458          | 0.7222         | 4     |
-| 0.7856     | 0.6541          | 0.7222         | 5     |
-| 0.7570     | 0.5996          | 0.7222         | 6     |
-| 0.7728     | 0.5791          | 0.7222         | 7     |
-| 0.6380     | 0.5488          | 0.6944         | 8     |
-| 0.6683     | 0.5332          | 0.75           | 9     |
-| 0.6156     | 0.5306          | 0.7778         | 10    |
-| 0.5433     | 0.5667          | 0.7778         | 11    |
-| 0.6143     | 0.5682          | 0.7222         | 12    |
-| 0.5455     | 0.5490          | 0.6944         | 13    |
-| 0.5045     | 0.5527          | 0.6944         | 14    |
-| 0.5107     | 0.5777          | 0.6944         | 15    |
-| 0.5066     | 0.5969          | 0.7222         | 16    |
-| 0.4521     | 0.6230          | 0.6944         | 17    |
-| 0.4614     | 0.6640          | 0.7222         | 18    |
-| 0.4343     | 0.6704          | 0.7222         | 19    |
-| 0.3759     | 0.7125          | 0.7222         | 20    |
-| 0.3583     | 0.7524          | 0.7222         | 21    |
-| 0.3758     | 0.7736          | 0.6944         | 22    |
-| 0.3575     | 0.7750          | 0.6944         | 23    |
-| 0.3519     | 0.7519          | 0.6944         | 24    |
-| 0.3421     | 0.7191          | 0.7222         | 25    |
-| 0.3579     | 0.7339          | 0.7222         | 26    |
-| 0.3342     | 0.7453          | 0.7222         | 27    |
-| 0.3070     | 0.7495          | 0.7222         | 28    |
-| 0.3247     | 0.7499          | 0.7222         | 29    |
+| 0.9441     | 0.4817          | 0.8652         | 0     |
 
 
 ### Framework versions

logs/train/events.out.tfevents.1704352166.104-171-203-254.2434976.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed507c9e23abfe3e4a279eca38b3b5deff5022ba3d96c03cc9490e52cfe02686
+size 2876978

logs/validation/events.out.tfevents.1704352185.104-171-203-254.2434976.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8193c987eacc24b158a58c159ca8137f64a3cc77ee3c81096cfe18c3540a3d55
+size 193

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c63e9983dfadd28369c511765025819ce2f4dc75d769e087927b063c69facd7f
-size 498865280
+oid sha256:4fc599f821333f80662f5c863ae7d927208abbddfb8bc289f1d937393565a21b
+size 498865680