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: 0.6215
-- Exact Match Accuracy: 0.3435
-- Macro Precision: 0.4155
-- Macro Recall: 0.3041
-- Macro F1: 0.3445
-- Micro Precision: 0.7256
-- Micro Recall: 0.4923
-- Micro F1: 0.5866
-- Hamming Loss: 0.0611
+- Loss: 0.5985
+- Exact Match Accuracy: 0.4183
+- Macro Precision: 0.4538
+- Macro Recall: 0.3430
+- Macro F1: 0.3834
+- Micro Precision: 0.7414
+- Micro Recall: 0.5599
+- Micro F1: 0.6380
+- Hamming Loss: 0.0546
 
 ## Model description
 

all_results.json

@@ -1,5 +1,17 @@
 {
     "epoch": 27.273764258555133,
+    "eval_exact_match_accuracy": 0.41825095057034223,
+    "eval_hamming_loss": 0.05457392082308209,
+    "eval_loss": 0.5984852313995361,
+    "eval_macro_f1": 0.38341302923814835,
+    "eval_macro_precision": 0.45383243040806065,
+    "eval_macro_recall": 0.3429726955977066,
+    "eval_micro_f1": 0.6379821958456974,
+    "eval_micro_precision": 0.7413793103448276,
+    "eval_micro_recall": 0.5598958333333334,
+    "eval_runtime": 1.3136,
+    "eval_samples_per_second": 200.212,
+    "eval_steps_per_second": 25.122,
     "total_flos": 0.0,
     "train_loss": 0.6497067387898763,
     "train_runtime": 976.094,

runs/Jun21_18-48-59_458a99d4b970/events.out.tfevents.1750532748.458a99d4b970.3723.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a3131b385c14756807d4abb98cd09e57a57d1fc2f5d600252fd914bb170349f
+size 34077

test_results.json

@@ -1,15 +1,15 @@
 {
-    "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
+    "epoch": 27.273764258555133,
+    "eval_exact_match_accuracy": 0.41825095057034223,
+    "eval_hamming_loss": 0.05457392082308209,
+    "eval_loss": 0.5984852313995361,
+    "eval_macro_f1": 0.38341302923814835,
+    "eval_macro_precision": 0.45383243040806065,
+    "eval_macro_recall": 0.3429726955977066,
+    "eval_micro_f1": 0.6379821958456974,
+    "eval_micro_precision": 0.7413793103448276,
+    "eval_micro_recall": 0.5598958333333334,
+    "eval_runtime": 1.3136,
+    "eval_samples_per_second": 200.212,
+    "eval_steps_per_second": 25.122
 }