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: 0.3680
-- Exact Match Accuracy: 0.4274
-- Macro Precision: 0.2731
-- Macro Recall: 0.1999
-- Macro F1: 0.2261
-- Micro Precision: 0.8
-- Micro Recall: 0.45
-- Micro F1: 0.576
-- Hamming Loss: 0.0533
+- Loss: 0.5794
+- Exact Match Accuracy: 0.3644
+- Macro Precision: 0.3426
+- Macro Recall: 0.2254
+- Macro F1: 0.2522
+- Micro Precision: 0.7475
+- Micro Recall: 0.4654
+- Micro F1: 0.5736
+- Hamming Loss: 0.0548
 
 ## Model description
 

all_results.json

@@ -1,17 +1,17 @@
 {
     "epoch": 25.423728813559322,
     "eval_exact_match_accuracy": 0.3644067796610169,
-    "eval_hamming_loss": 0.05284147557328016,
-    "eval_loss": 0.5806254744529724,
-    "eval_macro_f1": 0.36363379388909356,
-    "eval_macro_precision": 0.4744231050359171,
-    "eval_macro_recall": 0.3219569646040234,
-    "eval_micro_f1": 0.6102941176470589,
-    "eval_micro_precision": 0.7345132743362832,
-    "eval_micro_recall": 0.5220125786163522,
-    "eval_runtime": 0.5971,
-    "eval_samples_per_second": 197.608,
-    "eval_steps_per_second": 25.12,
+    "eval_hamming_loss": 0.054835493519441676,
+    "eval_loss": 0.5794392228126526,
+    "eval_macro_f1": 0.25224180581323435,
+    "eval_macro_precision": 0.3426470588235294,
+    "eval_macro_recall": 0.2253973559120618,
+    "eval_micro_f1": 0.5736434108527132,
+    "eval_micro_precision": 0.7474747474747475,
+    "eval_micro_recall": 0.46540880503144655,
+    "eval_runtime": 0.5885,
+    "eval_samples_per_second": 200.516,
+    "eval_steps_per_second": 25.489,
     "total_flos": 0.0,
     "train_loss": 0.8584918467203776,
     "train_runtime": 398.2207,

runs/Jun15_23-08-10_bb491f89c3e4/events.out.tfevents.1750029319.bb491f89c3e4.1541.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e887197d0c77f055b1613f23d387a863b504819909eeedda7cfac1f963d13fb
+size 15933

test_results.json

@@ -1,15 +1,15 @@
 {
-    "epoch": 32.20338983050848,
+    "epoch": 25.423728813559322,
     "eval_exact_match_accuracy": 0.3644067796610169,
-    "eval_hamming_loss": 0.05284147557328016,
-    "eval_loss": 0.5806254744529724,
-    "eval_macro_f1": 0.36363379388909356,
-    "eval_macro_precision": 0.4744231050359171,
-    "eval_macro_recall": 0.3219569646040234,
-    "eval_micro_f1": 0.6102941176470589,
-    "eval_micro_precision": 0.7345132743362832,
-    "eval_micro_recall": 0.5220125786163522,
-    "eval_runtime": 0.5971,
-    "eval_samples_per_second": 197.608,
-    "eval_steps_per_second": 25.12
+    "eval_hamming_loss": 0.054835493519441676,
+    "eval_loss": 0.5794392228126526,
+    "eval_macro_f1": 0.25224180581323435,
+    "eval_macro_precision": 0.3426470588235294,
+    "eval_macro_recall": 0.2253973559120618,
+    "eval_micro_f1": 0.5736434108527132,
+    "eval_micro_precision": 0.7474747474747475,
+    "eval_micro_recall": 0.46540880503144655,
+    "eval_runtime": 0.5885,
+    "eval_samples_per_second": 200.516,
+    "eval_steps_per_second": 25.489
 }