End of training

all_results.json

@@ -2,13 +2,13 @@
     "epoch": 3.0,
     "eval_loss": 0.624345064163208,
     "eval_matthews_correlation": 0.0,
-    "eval_runtime": 22.759,
+    "eval_runtime": 22.7153,
     "eval_samples": 1043,
-    "eval_samples_per_second": 45.828,
-    "eval_steps_per_second": 5.756,
+    "eval_samples_per_second": 45.916,
+    "eval_steps_per_second": 5.767,
     "train_loss": 0.6174308222552717,
-    "train_runtime": 2056.4994,
+    "train_runtime": 2128.6729,
     "train_samples": 8551,
-    "train_samples_per_second": 12.474,
-    "train_steps_per_second": 3.119
+    "train_samples_per_second": 12.051,
+    "train_steps_per_second": 3.013
 }

eval_results.json

@@ -2,8 +2,8 @@
     "epoch": 3.0,
     "eval_loss": 0.624345064163208,
     "eval_matthews_correlation": 0.0,
-    "eval_runtime": 22.759,
+    "eval_runtime": 22.7153,
     "eval_samples": 1043,
-    "eval_samples_per_second": 45.828,
-    "eval_steps_per_second": 5.756
+    "eval_samples_per_second": 45.916,
+    "eval_steps_per_second": 5.767
 }

runs/Oct09_09-15-18_patrick-general-gpu/events.out.tfevents.1633771761.patrick-general-gpu.40257.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a1c55e3805cf532df97873439b80d8b95b3cf5ba6054ded52d241a7f8f3b445
-size 4730
+oid sha256:2c79b3d2229e3d03a39848c4880589b318982bc94503b5d564187889ac0dd174
+size 5084

runs/Oct09_09-15-18_patrick-general-gpu/events.out.tfevents.1633773921.patrick-general-gpu.40257.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49e4134e023573d5076badfdd6b2f63837cff1de4feb259b3e10f3ea9e7a0a9d
+size 375

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
     "train_loss": 0.6174308222552717,
-    "train_runtime": 2056.4994,
+    "train_runtime": 2128.6729,
     "train_samples": 8551,
-    "train_samples_per_second": 12.474,
-    "train_steps_per_second": 3.119
+    "train_samples_per_second": 12.051,
+    "train_steps_per_second": 3.013
 }

trainer_state.json

@@ -17,9 +17,9 @@
       "epoch": 1.0,
       "eval_loss": 0.6526795029640198,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 22.9563,
-      "eval_samples_per_second": 45.434,
-      "eval_steps_per_second": 5.706,
+      "eval_runtime": 22.9461,
+      "eval_samples_per_second": 45.454,
+      "eval_steps_per_second": 5.709,
       "step": 2138
     },
     {
@@ -32,9 +32,9 @@
       "epoch": 2.0,
       "eval_loss": 0.6258916258811951,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 22.8508,
-      "eval_samples_per_second": 45.644,
-      "eval_steps_per_second": 5.733,
+      "eval_runtime": 22.6853,
+      "eval_samples_per_second": 45.977,
+      "eval_steps_per_second": 5.775,
       "step": 4276
     },
     {
@@ -47,9 +47,9 @@
       "epoch": 3.0,
       "eval_loss": 0.624345064163208,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 22.8559,
-      "eval_samples_per_second": 45.634,
-      "eval_steps_per_second": 5.732,
+      "eval_runtime": 22.6868,
+      "eval_samples_per_second": 45.974,
+      "eval_steps_per_second": 5.774,
       "step": 6414
     },
     {
@@ -57,9 +57,9 @@
       "step": 6414,
       "total_flos": 1.6048929796061184e+16,
       "train_loss": 0.6174308222552717,
-      "train_runtime": 2056.4994,
-      "train_samples_per_second": 12.474,
-      "train_steps_per_second": 3.119
+      "train_runtime": 2128.6729,
+      "train_samples_per_second": 12.051,
+      "train_steps_per_second": 3.013
     }
   ],
   "max_steps": 6414,