Upload trained sentiment classifier

README.md

@@ -19,14 +19,14 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model was trained from scratch on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1175
-- Accuracy: 0.9717
-- F1: 0.6478
-- Precision: 0.6478
-- Recall: 0.6478
-- F1 Negative: 0.9717
-- F1 Neutral: 0.0
-- F1 Positive: 0.9718
+- Loss: 0.0820
+- Accuracy: 0.9736
+- F1: 0.9736
+- Precision: 0.9736
+- Recall: 0.9736
+- F1 Negative: 0.9736
+- F1 Neutral: 0.9736
+- F1 Positive: 0.0
 
 ## Model description
 

all_results.json

@@ -1,19 +1,19 @@
 {
-    "epoch": 3.0,
-    "eval_accuracy": 0.9736134168050083,
-    "eval_f1": 0.9736134056553343,
-    "eval_f1_negative": 0.9735962533398713,
-    "eval_f1_neutral": 0.9736305579707972,
+    "epoch": 10.0,
+    "eval_accuracy": 0.9736184171050263,
+    "eval_f1": 0.9736184057853046,
+    "eval_f1_negative": 0.973601124804235,
+    "eval_f1_neutral": 0.973635686766374,
     "eval_f1_positive": 0.0,
-    "eval_loss": 0.08203645795583725,
-    "eval_precision": 0.9736141800660696,
-    "eval_recall": 0.9736134041929403,
-    "eval_runtime": 157.4778,
-    "eval_samples_per_second": 2539.888,
-    "eval_steps_per_second": 9.925,
-    "total_flos": 1.3775350726676972e+18,
-    "train_loss": 0.08639436010468234,
-    "train_runtime": 30946.7727,
-    "train_samples_per_second": 348.966,
-    "train_steps_per_second": 1.363
+    "eval_loss": 0.0820448026061058,
+    "eval_precision": 0.9736191924477628,
+    "eval_recall": 0.9736184043929482,
+    "eval_runtime": 156.7418,
+    "eval_samples_per_second": 2551.815,
+    "eval_steps_per_second": 4.989,
+    "total_flos": 4.5910293334888284e+18,
+    "train_loss": 0.03279527726586759,
+    "train_runtime": 72417.8071,
+    "train_samples_per_second": 497.087,
+    "train_steps_per_second": 1.942
 }

eval_results.json

@@ -1,14 +1,14 @@
 {
-    "epoch": 3.0,
-    "eval_accuracy": 0.9736134168050083,
-    "eval_f1": 0.9736134056553343,
-    "eval_f1_negative": 0.9735962533398713,
-    "eval_f1_neutral": 0.9736305579707972,
+    "epoch": 10.0,
+    "eval_accuracy": 0.9736184171050263,
+    "eval_f1": 0.9736184057853046,
+    "eval_f1_negative": 0.973601124804235,
+    "eval_f1_neutral": 0.973635686766374,
     "eval_f1_positive": 0.0,
-    "eval_loss": 0.08203645795583725,
-    "eval_precision": 0.9736141800660696,
-    "eval_recall": 0.9736134041929403,
-    "eval_runtime": 157.4778,
-    "eval_samples_per_second": 2539.888,
-    "eval_steps_per_second": 9.925
+    "eval_loss": 0.0820448026061058,
+    "eval_precision": 0.9736191924477628,
+    "eval_recall": 0.9736184043929482,
+    "eval_runtime": 156.7418,
+    "eval_samples_per_second": 2551.815,
+    "eval_steps_per_second": 4.989
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 3.0,
-    "total_flos": 1.3775350726676972e+18,
-    "train_loss": 0.08639436010468234,
-    "train_runtime": 30946.7727,
-    "train_samples_per_second": 348.966,
-    "train_steps_per_second": 1.363
+    "epoch": 10.0,
+    "total_flos": 4.5910293334888284e+18,
+    "train_loss": 0.03279527726586759,
+    "train_runtime": 72417.8071,
+    "train_samples_per_second": 497.087,
+    "train_steps_per_second": 1.942
 }