End of training

all_results.json

@@ -1,17 +1,17 @@
 {
     "epoch": 2.13,
-    "eval_accuracy": 0.9093539054966249,
-    "eval_f1": 0.8845947396672033,
-    "eval_loss": 0.6478922367095947,
-    "eval_precision": 0.8787771062922147,
-    "eval_recall": 0.8904899135446686,
-    "eval_runtime": 14.0235,
+    "eval_accuracy": 0.9095949855351977,
+    "eval_f1": 0.8849525854356771,
+    "eval_loss": 0.647879958152771,
+    "eval_precision": 0.8791325986491291,
+    "eval_recall": 0.890850144092219,
+    "eval_runtime": 13.8388,
     "eval_samples": 189,
-    "eval_samples_per_second": 13.477,
-    "eval_steps_per_second": 0.856,
-    "train_loss": 1.3186872863769532,
-    "train_runtime": 168.7443,
+    "eval_samples_per_second": 13.657,
+    "eval_steps_per_second": 0.867,
+    "train_loss": 1.3181494140625,
+    "train_runtime": 166.3023,
     "train_samples": 752,
-    "train_samples_per_second": 9.482,
-    "train_steps_per_second": 0.593
+    "train_samples_per_second": 9.621,
+    "train_steps_per_second": 0.601
 }

eval_results.json

@@ -1,12 +1,12 @@
 {
     "epoch": 2.13,
-    "eval_accuracy": 0.9093539054966249,
-    "eval_f1": 0.8845947396672033,
-    "eval_loss": 0.6478922367095947,
-    "eval_precision": 0.8787771062922147,
-    "eval_recall": 0.8904899135446686,
-    "eval_runtime": 14.0235,
+    "eval_accuracy": 0.9095949855351977,
+    "eval_f1": 0.8849525854356771,
+    "eval_loss": 0.647879958152771,
+    "eval_precision": 0.8791325986491291,
+    "eval_recall": 0.890850144092219,
+    "eval_runtime": 13.8388,
     "eval_samples": 189,
-    "eval_samples_per_second": 13.477,
-    "eval_steps_per_second": 0.856
+    "eval_samples_per_second": 13.657,
+    "eval_steps_per_second": 0.867
 }

runs/Dec20_17-01-04_pod-pasha/events.out.tfevents.1671555964.pod-pasha.539018.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a608112d2c5b3b1632ffa219ff4dd79e354a3077894b4616b271c3095cf1b86
+size 503

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 2.13,
-    "train_loss": 1.3186872863769532,
-    "train_runtime": 168.7443,
+    "train_loss": 1.3181494140625,
+    "train_runtime": 166.3023,
     "train_samples": 752,
-    "train_samples_per_second": 9.482,
-    "train_steps_per_second": 0.593
+    "train_samples_per_second": 9.621,
+    "train_steps_per_second": 0.601
 }

trainer_state.json

@@ -9,24 +9,24 @@
   "log_history": [
     {
       "epoch": 2.13,
-      "eval_accuracy": 0.9093539054966249,
-      "eval_f1": 0.8845947396672033,
-      "eval_loss": 0.6478922367095947,
-      "eval_precision": 0.8787771062922147,
-      "eval_recall": 0.8904899135446686,
-      "eval_runtime": 13.9513,
-      "eval_samples_per_second": 13.547,
-      "eval_steps_per_second": 0.86,
+      "eval_accuracy": 0.9095949855351977,
+      "eval_f1": 0.8849525854356771,
+      "eval_loss": 0.647879958152771,
+      "eval_precision": 0.8791325986491291,
+      "eval_recall": 0.890850144092219,
+      "eval_runtime": 13.776,
+      "eval_samples_per_second": 13.72,
+      "eval_steps_per_second": 0.871,
       "step": 100
     },
     {
       "epoch": 2.13,
       "step": 100,
       "total_flos": 424705445068800.0,
-      "train_loss": 1.3186872863769532,
-      "train_runtime": 168.7443,
-      "train_samples_per_second": 9.482,
-      "train_steps_per_second": 0.593
+      "train_loss": 1.3181494140625,
+      "train_runtime": 166.3023,
+      "train_samples_per_second": 9.621,
+      "train_steps_per_second": 0.601
     }
   ],
   "max_steps": 100,