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: 0.3962
-- Exact Match Accuracy: 0.4017
-- Macro Precision: 0.4165
-- Macro Recall: 0.2684
-- Macro F1: 0.3116
-- Micro Precision: 0.7917
-- Micro Recall: 0.475
-- Micro F1: 0.5938
-- Hamming Loss: 0.0523
+- Loss: 0.5806
+- Exact Match Accuracy: 0.3644
+- Macro Precision: 0.4744
+- Macro Recall: 0.3220
+- Macro F1: 0.3636
+- Micro Precision: 0.7345
+- Micro Recall: 0.5220
+- Micro F1: 0.6103
+- Hamming Loss: 0.0528
 
 ## Model description
 

all_results.json

@@ -1,5 +1,17 @@
 {
     "epoch": 32.20338983050848,
+    "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,
     "total_flos": 0.0,
     "train_loss": 0.74248863370795,
     "train_runtime": 501.6916,

runs/Jun15_22-46-52_bb491f89c3e4/events.out.tfevents.1750028144.bb491f89c3e4.1541.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2db985f43d5c979c1e86e20fb7d860653fde81576f72e43cb704a445483bd3c2
+size 15933

test_results.json

@@ -1,15 +1,15 @@
 {
-    "epoch": 110.0,
-    "eval_exact_match_accuracy": 0.45,
-    "eval_hamming_loss": 0.051470588235294115,
-    "eval_loss": 0.5014987587928772,
-    "eval_macro_f1": 0.3625902992776057,
-    "eval_macro_precision": 0.3892156862745098,
-    "eval_macro_recall": 0.3911764705882353,
-    "eval_micro_f1": 0.6391752577319587,
-    "eval_micro_precision": 0.775,
-    "eval_micro_recall": 0.543859649122807,
-    "eval_runtime": 0.2083,
-    "eval_samples_per_second": 192.015,
-    "eval_steps_per_second": 24.002
+    "epoch": 32.20338983050848,
+    "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
 }