End of training

README.md

@@ -20,9 +20,9 @@ It achieves the following results on the evaluation set:
 - eval_precision: 0.9434
 - eval_recall: 0.9392
 - eval_f1: 0.9398
-- eval_runtime: 5.3705
-- eval_samples_per_second: 37.24
-- eval_steps_per_second: 2.421
+- eval_runtime: 5.4111
+- eval_samples_per_second: 36.961
+- eval_steps_per_second: 2.402
 - step: 0
 
 ## Model description

all_results.json

@@ -5,11 +5,11 @@
     "eval_loss": 0.1684570461511612,
     "eval_precision": 0.9434343434343434,
     "eval_recall": 0.9391756702681072,
-    "eval_runtime": 5.3705,
-    "eval_samples_per_second": 37.24,
-    "eval_steps_per_second": 2.421,
+    "eval_runtime": 5.4111,
+    "eval_samples_per_second": 36.961,
+    "eval_steps_per_second": 2.402,
     "train_loss": 0.2957918119430542,
-    "train_runtime": 132.8245,
-    "train_samples_per_second": 24.092,
-    "train_steps_per_second": 0.376
+    "train_runtime": 128.4347,
+    "train_samples_per_second": 24.915,
+    "train_steps_per_second": 0.389
 }

eval_results.json

@@ -4,7 +4,7 @@
     "eval_loss": 0.1684570461511612,
     "eval_precision": 0.9434343434343434,
     "eval_recall": 0.9391756702681072,
-    "eval_runtime": 5.3705,
-    "eval_samples_per_second": 37.24,
-    "eval_steps_per_second": 2.421
+    "eval_runtime": 5.4111,
+    "eval_samples_per_second": 36.961,
+    "eval_steps_per_second": 2.402
 }

train_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 2.0,
     "train_loss": 0.2957918119430542,
-    "train_runtime": 132.8245,
-    "train_samples_per_second": 24.092,
-    "train_steps_per_second": 0.376
+    "train_runtime": 128.4347,
+    "train_samples_per_second": 24.915,
+    "train_steps_per_second": 0.389
 }

trainer_state.json

@@ -27,9 +27,9 @@
       "eval_loss": 0.2042059749364853,
       "eval_precision": 0.9145833333333333,
       "eval_recall": 0.8999598030348709,
-      "eval_runtime": 5.1322,
-      "eval_samples_per_second": 38.97,
-      "eval_steps_per_second": 2.533,
+      "eval_runtime": 5.1312,
+      "eval_samples_per_second": 38.977,
+      "eval_steps_per_second": 2.534,
       "step": 25
     },
     {
@@ -57,9 +57,9 @@
       "eval_loss": 0.1735258251428604,
       "eval_precision": 0.9345268542199489,
       "eval_recall": 0.9268415234649784,
-      "eval_runtime": 5.1121,
-      "eval_samples_per_second": 39.123,
-      "eval_steps_per_second": 2.543,
+      "eval_runtime": 5.1664,
+      "eval_samples_per_second": 38.712,
+      "eval_steps_per_second": 2.516,
       "step": 50
     },
     {
@@ -67,9 +67,9 @@
       "step": 50,
       "total_flos": 2.479743667666944e+17,
       "train_loss": 0.2957918119430542,
-      "train_runtime": 132.8245,
-      "train_samples_per_second": 24.092,
-      "train_steps_per_second": 0.376
+      "train_runtime": 128.4347,
+      "train_samples_per_second": 24.915,
+      "train_steps_per_second": 0.389
     }
   ],
   "logging_steps": 10,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:524a6a0092ec2f6db2e6446623161d74af6a8fc76718cfc8b2f0c65d66ca36e8
+oid sha256:37e71a7ec659fa3cabca816b7a7316bf4c07498b267c34a0a37dbd48a9b0c707
 size 4536