End of training

all_results.json

@@ -1,11 +1,11 @@
 {
     "epoch": 1.0,
-    "eval_exact_match": 79.33774834437087,
-    "eval_f1": 87.12191251890178,
+    "eval_exact_match": 79.04446546830653,
+    "eval_f1": 87.02201254070765,
     "eval_samples": 12097,
-    "train_loss": 1.2300268692036653,
-    "train_runtime": 4576.3813,
+    "train_loss": 1.240907019917191,
+    "train_runtime": 2500.1104,
     "train_samples": 97408,
-    "train_samples_per_second": 21.285,
-    "train_steps_per_second": 1.33
+    "train_samples_per_second": 38.961,
+    "train_steps_per_second": 2.435
 }

eval_nbest_predictions.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0ff4aa82b05987f5fc97da148f6608891d99f0e6f3032d5196f81408c2b9329
-size 49409449
+oid sha256:36b56de06419dff4a209a3e24455c3f4d4855ebfd160228bdc37d34a295af6c9
+size 49604590

eval_results.json

@@ -1,6 +1,6 @@
 {
     "epoch": 1.0,
-    "eval_exact_match": 79.33774834437087,
-    "eval_f1": 87.12191251890178,
+    "eval_exact_match": 79.04446546830653,
+    "eval_f1": 87.02201254070765,
     "eval_samples": 12097
 }

runs/Aug10_08-46-16_f311d5ee993e/events.out.tfevents.1660124544.f311d5ee993e.366.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c5566311ef3044797ddbeb7fcec09747700c46219dcf5fff0278f51153f9ea1
+size 191

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
-    "train_loss": 1.2300268692036653,
-    "train_runtime": 4576.3813,
+    "train_loss": 1.240907019917191,
+    "train_runtime": 2500.1104,
     "train_samples": 97408,
-    "train_samples_per_second": 21.285,
-    "train_steps_per_second": 1.33
+    "train_samples_per_second": 38.961,
+    "train_steps_per_second": 2.435
 }

trainer_state.json

@@ -10,83 +10,83 @@
     {
       "epoch": 0.08,
       "learning_rate": 2.7536136662286466e-05,
-      "loss": 2.3317,
+      "loss": 2.3225,
       "step": 500
     },
     {
       "epoch": 0.16,
       "learning_rate": 2.5072273324572932e-05,
-      "loss": 1.4294,
+      "loss": 1.4439,
       "step": 1000
     },
     {
       "epoch": 0.25,
       "learning_rate": 2.2608409986859398e-05,
-      "loss": 1.3087,
+      "loss": 1.3325,
       "step": 1500
     },
     {
       "epoch": 0.33,
       "learning_rate": 2.014454664914586e-05,
-      "loss": 1.2303,
+      "loss": 1.236,
       "step": 2000
     },
     {
       "epoch": 0.41,
       "learning_rate": 1.7680683311432326e-05,
-      "loss": 1.1531,
+      "loss": 1.1708,
       "step": 2500
     },
     {
       "epoch": 0.49,
       "learning_rate": 1.5216819973718791e-05,
-      "loss": 1.1192,
+      "loss": 1.1273,
       "step": 3000
     },
     {
       "epoch": 0.57,
       "learning_rate": 1.2752956636005257e-05,
-      "loss": 1.0921,
+      "loss": 1.097,
       "step": 3500
     },
     {
       "epoch": 0.66,
       "learning_rate": 1.0289093298291721e-05,
-      "loss": 1.078,
+      "loss": 1.0855,
       "step": 4000
     },
     {
       "epoch": 0.74,
       "learning_rate": 7.825229960578187e-06,
-      "loss": 1.043,
+      "loss": 1.0549,
       "step": 4500
     },
     {
       "epoch": 0.82,
       "learning_rate": 5.361366622864652e-06,
-      "loss": 0.9911,
+      "loss": 1.0084,
       "step": 5000
     },
     {
       "epoch": 0.9,
       "learning_rate": 2.8975032851511168e-06,
-      "loss": 1.006,
+      "loss": 1.0201,
       "step": 5500
     },
     {
       "epoch": 0.99,
       "learning_rate": 4.336399474375821e-07,
-      "loss": 1.02,
+      "loss": 1.0301,
       "step": 6000
     },
     {
       "epoch": 1.0,
       "step": 6088,
       "total_flos": 1.2726197240070144e+16,
-      "train_loss": 1.2300268692036653,
-      "train_runtime": 4576.3813,
-      "train_samples_per_second": 21.285,
-      "train_steps_per_second": 1.33
+      "train_loss": 1.240907019917191,
+      "train_runtime": 2500.1104,
+      "train_samples_per_second": 38.961,
+      "train_steps_per_second": 2.435
     }
   ],
   "max_steps": 6088,