End of training

all_results.json

@@ -1,14 +1,14 @@
 {
     "epoch": 1.0,
-    "eval_loss": 2.260770559310913,
-    "eval_runtime": 79.7553,
+    "eval_loss": 2.260770082473755,
+    "eval_runtime": 80.1136,
     "eval_samples": 1000,
-    "eval_samples_per_second": 12.538,
-    "eval_steps_per_second": 1.567,
-    "perplexity": 9.590476351115461,
-    "train_loss": 2.2107459688026094,
-    "train_runtime": 5291.3805,
+    "eval_samples_per_second": 12.482,
+    "eval_steps_per_second": 1.56,
+    "perplexity": 9.590471778021062,
+    "train_loss": 2.2107484348695285,
+    "train_runtime": 5306.8515,
     "train_samples": 19004,
-    "train_samples_per_second": 3.592,
+    "train_samples_per_second": 3.581,
     "train_steps_per_second": 0.056
 }

eval_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 1.0,
-    "eval_loss": 2.260770559310913,
-    "eval_runtime": 79.7553,
+    "eval_loss": 2.260770082473755,
+    "eval_runtime": 80.1136,
     "eval_samples": 1000,
-    "eval_samples_per_second": 12.538,
-    "eval_steps_per_second": 1.567,
-    "perplexity": 9.590476351115461
+    "eval_samples_per_second": 12.482,
+    "eval_steps_per_second": 1.56,
+    "perplexity": 9.590471778021062
 }

runs/Nov16_16-30-36_3efc2dca9104/events.out.tfevents.1637080427.3efc2dca9104.2457.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c466d02756a539af062305d6d877e7a74f2661440f711d2d944b9513b322fff
-size 3413
+oid sha256:5a558e07e896e6697111e5078c051e189f6aca4d971185a850e7443b3a6b35dd
+size 3767

runs/Nov16_16-30-36_3efc2dca9104/events.out.tfevents.1637085821.3efc2dca9104.2457.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5eef34ffef17c474b5412740b791f597683ce43c59ae1ad10a472f2f3ee77562
+size 311

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
-    "train_loss": 2.2107459688026094,
-    "train_runtime": 5291.3805,
+    "train_loss": 2.2107484348695285,
+    "train_runtime": 5306.8515,
     "train_samples": 19004,
-    "train_samples_per_second": 3.592,
+    "train_samples_per_second": 3.581,
     "train_steps_per_second": 0.056
 }

trainer_state.json

@@ -9,19 +9,19 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 2.241901397705078,
-      "eval_runtime": 80.2863,
-      "eval_samples_per_second": 12.455,
-      "eval_steps_per_second": 1.557,
+      "eval_loss": 2.2418715953826904,
+      "eval_runtime": 79.9164,
+      "eval_samples_per_second": 12.513,
+      "eval_steps_per_second": 1.564,
       "step": 297
     },
     {
       "epoch": 1.0,
       "step": 297,
       "total_flos": 5001918049701888.0,
-      "train_loss": 2.2107459688026094,
-      "train_runtime": 5291.3805,
-      "train_samples_per_second": 3.592,
+      "train_loss": 2.2107484348695285,
+      "train_runtime": 5306.8515,
+      "train_samples_per_second": 3.581,
       "train_steps_per_second": 0.056
     }
   ],