End of training

all_results.json

@@ -1,19 +1,19 @@
 {
     "epoch": 2.0,
-    "eval_bleu": 0.11424056852356153,
+    "eval_bleu": 0.11424038411303619,
     "eval_loss": 3.128293514251709,
     "eval_rouge1": 0.3297614987151056,
     "eval_rouge2": 0.08429294540985294,
     "eval_rougeL": 0.2561476738686219,
-    "eval_runtime": 26.9033,
+    "eval_runtime": 28.613,
     "eval_samples": 847,
-    "eval_samples_per_second": 31.483,
-    "eval_steps_per_second": 3.94,
+    "eval_samples_per_second": 29.602,
+    "eval_steps_per_second": 3.705,
     "perplexity": 22.834978708992665,
     "total_flos": 2000451796992000.0,
-    "train_loss": 4.0498331004175645,
-    "train_runtime": 264.5821,
+    "train_loss": 4.049833148250759,
+    "train_runtime": 274.3289,
     "train_samples": 2552,
-    "train_samples_per_second": 19.291,
-    "train_steps_per_second": 2.411
+    "train_samples_per_second": 18.605,
+    "train_steps_per_second": 2.326
 }

eval_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 2.0,
-    "eval_bleu": 0.11424056852356153,
+    "eval_bleu": 0.11424038411303619,
     "eval_loss": 3.128293514251709,
     "eval_rouge1": 0.3297614987151056,
     "eval_rouge2": 0.08429294540985294,
     "eval_rougeL": 0.2561476738686219,
-    "eval_runtime": 26.9033,
+    "eval_runtime": 28.613,
     "eval_samples": 847,
-    "eval_samples_per_second": 31.483,
-    "eval_steps_per_second": 3.94,
+    "eval_samples_per_second": 29.602,
+    "eval_steps_per_second": 3.705,
     "perplexity": 22.834978708992665
 }

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 2.0,
     "total_flos": 2000451796992000.0,
-    "train_loss": 4.0498331004175645,
-    "train_runtime": 264.5821,
+    "train_loss": 4.049833148250759,
+    "train_runtime": 274.3289,
     "train_samples": 2552,
-    "train_samples_per_second": 19.291,
-    "train_steps_per_second": 2.411
+    "train_samples_per_second": 18.605,
+    "train_steps_per_second": 2.326
 }

trainer_state.json

@@ -10,31 +10,31 @@
   "log_history": [
     {
       "epoch": 1.567398119122257,
-      "grad_norm": 1.3536421060562134,
+      "grad_norm": 1.3536407947540283,
       "learning_rate": 5e-05,
       "loss": 4.3013,
       "step": 500
     },
     {
       "epoch": 1.567398119122257,
-      "eval_bleu": 0.11424056852356153,
+      "eval_bleu": 0.11424038411303619,
       "eval_loss": 3.128293514251709,
       "eval_rouge1": 0.3297614987151056,
       "eval_rouge2": 0.08429294540985294,
       "eval_rougeL": 0.2561476738686219,
-      "eval_runtime": 27.454,
-      "eval_samples_per_second": 30.852,
-      "eval_steps_per_second": 3.861,
+      "eval_runtime": 29.502,
+      "eval_samples_per_second": 28.71,
+      "eval_steps_per_second": 3.593,
       "step": 500
     },
     {
       "epoch": 2.0,
       "step": 638,
       "total_flos": 2000451796992000.0,
-      "train_loss": 4.0498331004175645,
-      "train_runtime": 264.5821,
-      "train_samples_per_second": 19.291,
-      "train_steps_per_second": 2.411
+      "train_loss": 4.049833148250759,
+      "train_runtime": 274.3289,
+      "train_samples_per_second": 18.605,
+      "train_steps_per_second": 2.326
     }
   ],
   "logging_steps": 500,