End of training

README.md

@@ -19,12 +19,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5283
-- Accuracy: 0.6607
-- F1: 0.6345
-- Precision: 0.7254
-- Recall: 0.6607
-- Roc Auc: 0.8393
+- Loss: 0.6343
+- Accuracy: 0.6875
+- F1: 0.6537
+- Precision: 0.8077
+- Recall: 0.6875
+- Roc Auc: 0.7296
 
 ## Model description
 

all_results.json

@@ -1,5 +1,14 @@
 {
     "epoch": 22.011111111111113,
+    "eval_accuracy": 0.6875,
+    "eval_f1": 0.6536796536796536,
+    "eval_loss": 0.6343340277671814,
+    "eval_precision": 0.8076923076923077,
+    "eval_recall": 0.6875,
+    "eval_roc_auc": 0.729591836734694,
+    "eval_runtime": 84.2734,
+    "eval_samples_per_second": 1.329,
+    "eval_steps_per_second": 0.024,
     "total_flos": 0.0,
     "train_loss": 0.4831820335653093,
     "train_runtime": 4324.1379,

runs/Nov04_11-08-11_484667db42d4/events.out.tfevents.1730722906.484667db42d4.54441.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36881b5087f27a87463e53ad2166fe35ecc957f46eaf72ff455b712791e16e42
+size 601

test_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 22.011111111111113,
+    "eval_accuracy": 0.6875,
+    "eval_f1": 0.6536796536796536,
+    "eval_loss": 0.6343340277671814,
+    "eval_precision": 0.8076923076923077,
+    "eval_recall": 0.6875,
+    "eval_roc_auc": 0.729591836734694,
+    "eval_runtime": 84.2734,
+    "eval_samples_per_second": 1.329,
+    "eval_steps_per_second": 0.024
+}