End of training

all_results.json

@@ -1,17 +1,17 @@
 {
     "epoch": 2.13,
-    "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_accuracy": 0.909112825458052,
+    "eval_f1": 0.8837125963089052,
+    "eval_loss": 0.6461763978004456,
+    "eval_precision": 0.879144385026738,
+    "eval_recall": 0.888328530259366,
+    "eval_runtime": 15.0345,
     "eval_samples": 189,
-    "eval_samples_per_second": 13.657,
-    "eval_steps_per_second": 0.867,
-    "train_loss": 1.3181494140625,
-    "train_runtime": 166.3023,
+    "eval_samples_per_second": 12.571,
+    "eval_steps_per_second": 0.798,
+    "train_loss": 1.3162074279785156,
+    "train_runtime": 179.095,
     "train_samples": 752,
-    "train_samples_per_second": 9.621,
-    "train_steps_per_second": 0.601
+    "train_samples_per_second": 8.934,
+    "train_steps_per_second": 0.558
 }

eval_results.json

@@ -1,12 +1,12 @@
 {
     "epoch": 2.13,
-    "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_accuracy": 0.909112825458052,
+    "eval_f1": 0.8837125963089052,
+    "eval_loss": 0.6461763978004456,
+    "eval_precision": 0.879144385026738,
+    "eval_recall": 0.888328530259366,
+    "eval_runtime": 15.0345,
     "eval_samples": 189,
-    "eval_samples_per_second": 13.657,
-    "eval_steps_per_second": 0.867
+    "eval_samples_per_second": 12.571,
+    "eval_steps_per_second": 0.798
 }

runs/Dec20_17-08-06_pod-pasha/events.out.tfevents.1671556396.pod-pasha.540307.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5731a67d73ca95e9a0ab41cd46cc39dd399ddccbc861be676d55fe31616f005
+size 503

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 2.13,
-    "train_loss": 1.3181494140625,
-    "train_runtime": 166.3023,
+    "train_loss": 1.3162074279785156,
+    "train_runtime": 179.095,
     "train_samples": 752,
-    "train_samples_per_second": 9.621,
-    "train_steps_per_second": 0.601
+    "train_samples_per_second": 8.934,
+    "train_steps_per_second": 0.558
 }

trainer_state.json

@@ -9,24 +9,24 @@
   "log_history": [
     {
       "epoch": 2.13,
-      "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,
+      "eval_accuracy": 0.909112825458052,
+      "eval_f1": 0.8837125963089052,
+      "eval_loss": 0.6461763978004456,
+      "eval_precision": 0.879144385026738,
+      "eval_recall": 0.888328530259366,
+      "eval_runtime": 15.0755,
+      "eval_samples_per_second": 12.537,
+      "eval_steps_per_second": 0.796,
       "step": 100
     },
     {
       "epoch": 2.13,
       "step": 100,
       "total_flos": 424705445068800.0,
-      "train_loss": 1.3181494140625,
-      "train_runtime": 166.3023,
-      "train_samples_per_second": 9.621,
-      "train_steps_per_second": 0.601
+      "train_loss": 1.3162074279785156,
+      "train_runtime": 179.095,
+      "train_samples_per_second": 8.934,
+      "train_steps_per_second": 0.558
     }
   ],
   "max_steps": 100,