End of training

README.md

@@ -20,9 +20,9 @@ It achieves the following results on the evaluation set:
 - eval_precision: 0.8899
 - eval_recall: 0.9510
 - eval_f1: 0.9194
-- eval_runtime: 4.9925
-- eval_samples_per_second: 40.06
-- eval_steps_per_second: 2.604
+- eval_runtime: 5.3671
+- eval_samples_per_second: 37.264
+- eval_steps_per_second: 2.422
 - step: 0
 
 ## Model description

all_results.json

@@ -5,11 +5,11 @@
     "eval_loss": 0.19574587047100067,
     "eval_precision": 0.8899082568807339,
     "eval_recall": 0.9509803921568627,
-    "eval_runtime": 4.9925,
-    "eval_samples_per_second": 40.06,
-    "eval_steps_per_second": 2.604,
+    "eval_runtime": 5.3671,
+    "eval_samples_per_second": 37.264,
+    "eval_steps_per_second": 2.422,
     "train_loss": 0.3774217462539673,
-    "train_runtime": 95.667,
-    "train_samples_per_second": 33.449,
-    "train_steps_per_second": 0.523
+    "train_runtime": 132.5639,
+    "train_samples_per_second": 24.139,
+    "train_steps_per_second": 0.377
 }

eval_results.json

@@ -4,7 +4,7 @@
     "eval_loss": 0.19574587047100067,
     "eval_precision": 0.8899082568807339,
     "eval_recall": 0.9509803921568627,
-    "eval_runtime": 4.9925,
-    "eval_samples_per_second": 40.06,
-    "eval_steps_per_second": 2.604
+    "eval_runtime": 5.3671,
+    "eval_samples_per_second": 37.264,
+    "eval_steps_per_second": 2.422
 }

train_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 2.0,
     "train_loss": 0.3774217462539673,
-    "train_runtime": 95.667,
-    "train_samples_per_second": 33.449,
-    "train_steps_per_second": 0.523
+    "train_runtime": 132.5639,
+    "train_samples_per_second": 24.139,
+    "train_steps_per_second": 0.377
 }

trainer_state.json

@@ -27,9 +27,9 @@
       "eval_loss": 0.25200986862182617,
       "eval_precision": 0.8512396694214877,
       "eval_recall": 0.9626168224299065,
-      "eval_runtime": 5.3079,
-      "eval_samples_per_second": 37.679,
-      "eval_steps_per_second": 2.449,
+      "eval_runtime": 5.2866,
+      "eval_samples_per_second": 37.832,
+      "eval_steps_per_second": 2.459,
       "step": 25
     },
     {
@@ -57,9 +57,9 @@
       "eval_loss": 0.17430706322193146,
       "eval_precision": 0.9196428571428571,
       "eval_recall": 0.9626168224299065,
-      "eval_runtime": 4.9249,
-      "eval_samples_per_second": 40.61,
-      "eval_steps_per_second": 2.64,
+      "eval_runtime": 5.9099,
+      "eval_samples_per_second": 33.842,
+      "eval_steps_per_second": 2.2,
       "step": 50
     },
     {
@@ -67,9 +67,9 @@
       "step": 50,
       "total_flos": 2.479743667666944e+17,
       "train_loss": 0.3774217462539673,
-      "train_runtime": 95.667,
-      "train_samples_per_second": 33.449,
-      "train_steps_per_second": 0.523
+      "train_runtime": 132.5639,
+      "train_samples_per_second": 24.139,
+      "train_steps_per_second": 0.377
     }
   ],
   "logging_steps": 10,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5688ca45b8db9d4154397e485cb2e8d1a859e515f4eee193e31f43e3c2846c1d
+oid sha256:7e1f24e0337705b54dc65eb40ee1fbf4ff27663a1b3b191582dc4689106de7cb
 size 4536