End of training

README.md

@@ -16,15 +16,15 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [maximuspowers/bert-philosophy-adapted](https://huggingface.co/maximuspowers/bert-philosophy-adapted) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6556
-- Exact Match Accuracy: 0.4258
-- Macro Precision: 0.5340
-- Macro Recall: 0.4231
-- Macro F1: 0.4521
-- Micro Precision: 0.7162
-- Micro Recall: 0.5372
-- Micro F1: 0.6139
-- Hamming Loss: 0.0563
+- Loss: 0.5990
+- Exact Match Accuracy: 0.3971
+- Macro Precision: 0.5269
+- Macro Recall: 0.3761
+- Macro F1: 0.4169
+- Micro Precision: 0.7149
+- Micro Recall: 0.5734
+- Micro F1: 0.6364
+- Hamming Loss: 0.0540
 
 ## Model description
 

all_results.json

@@ -1,5 +1,17 @@
 {
     "epoch": 32.38277511961722,
+    "eval_exact_match_accuracy": 0.39712918660287083,
+    "eval_hamming_loss": 0.0540388404165494,
+    "eval_loss": 0.5990312099456787,
+    "eval_macro_f1": 0.41694037088029773,
+    "eval_macro_precision": 0.5269255701663154,
+    "eval_macro_recall": 0.37612722642612434,
+    "eval_micro_f1": 0.6363636363636364,
+    "eval_micro_precision": 0.7148936170212766,
+    "eval_micro_recall": 0.5733788395904437,
+    "eval_runtime": 1.0584,
+    "eval_samples_per_second": 197.466,
+    "eval_steps_per_second": 25.51,
     "total_flos": 0.0,
     "train_loss": 0.6106048311906702,
     "train_runtime": 911.6953,

runs/Jun18_00-43-06_7248b5eeee0d/events.out.tfevents.1750208328.7248b5eeee0d.3526.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94cbc7171308d728a55b6285c3940c0fad8b020fd1292bc1b60fe40603fac440
+size 28029

test_results.json

@@ -1,15 +1,15 @@
 {
-    "epoch": 34.248275862068965,
-    "eval_exact_match_accuracy": 0.41379310344827586,
-    "eval_hamming_loss": 0.04989858012170385,
-    "eval_loss": 0.5930218696594238,
-    "eval_macro_f1": 0.32054514113337645,
-    "eval_macro_precision": 0.3909600203717851,
-    "eval_macro_recall": 0.2934883988593418,
-    "eval_micro_f1": 0.6283987915407855,
-    "eval_micro_precision": 0.8062015503875969,
-    "eval_micro_recall": 0.5148514851485149,
-    "eval_runtime": 0.7302,
-    "eval_samples_per_second": 198.571,
-    "eval_steps_per_second": 26.02
+    "epoch": 32.38277511961722,
+    "eval_exact_match_accuracy": 0.39712918660287083,
+    "eval_hamming_loss": 0.0540388404165494,
+    "eval_loss": 0.5990312099456787,
+    "eval_macro_f1": 0.41694037088029773,
+    "eval_macro_precision": 0.5269255701663154,
+    "eval_macro_recall": 0.37612722642612434,
+    "eval_micro_f1": 0.6363636363636364,
+    "eval_micro_precision": 0.7148936170212766,
+    "eval_micro_recall": 0.5733788395904437,
+    "eval_runtime": 1.0584,
+    "eval_samples_per_second": 197.466,
+    "eval_steps_per_second": 25.51
 }