End of training

all_results.json

@@ -1,18 +1,18 @@
 {
     "epoch": 10.0,
-    "eval_gen_len": 53.91466666666667,
-    "eval_loss": 2.068262815475464,
-    "eval_rouge1": 27.7929,
-    "eval_rouge2": 9.0297,
-    "eval_rougeL": 19.2124,
-    "eval_rougeLsum": 24.0555,
-    "eval_runtime": 260.222,
+    "eval_gen_len": 53.36933333333333,
+    "eval_loss": 2.040886878967285,
+    "eval_rouge1": 28.129,
+    "eval_rouge2": 8.967,
+    "eval_rougeL": 19.4801,
+    "eval_rougeLsum": 24.2979,
+    "eval_runtime": 253.0867,
     "eval_samples": 1500,
-    "eval_samples_per_second": 5.764,
-    "eval_steps_per_second": 0.722,
-    "train_loss": 1.9408494245256696,
-    "train_runtime": 6269.9469,
+    "eval_samples_per_second": 5.927,
+    "eval_steps_per_second": 0.743,
+    "train_loss": 1.9174187186104912,
+    "train_runtime": 6255.5929,
     "train_samples": 7000,
-    "train_samples_per_second": 11.164,
-    "train_steps_per_second": 1.396
+    "train_samples_per_second": 11.19,
+    "train_steps_per_second": 1.399
 }

eval_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 10.0,
-    "eval_gen_len": 53.91466666666667,
-    "eval_loss": 2.068262815475464,
-    "eval_rouge1": 27.7929,
-    "eval_rouge2": 9.0297,
-    "eval_rougeL": 19.2124,
-    "eval_rougeLsum": 24.0555,
-    "eval_runtime": 260.222,
+    "eval_gen_len": 53.36933333333333,
+    "eval_loss": 2.040886878967285,
+    "eval_rouge1": 28.129,
+    "eval_rouge2": 8.967,
+    "eval_rougeL": 19.4801,
+    "eval_rougeLsum": 24.2979,
+    "eval_runtime": 253.0867,
     "eval_samples": 1500,
-    "eval_samples_per_second": 5.764,
-    "eval_steps_per_second": 0.722
+    "eval_samples_per_second": 5.927,
+    "eval_steps_per_second": 0.743
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 10.0,
-    "train_loss": 1.9408494245256696,
-    "train_runtime": 6269.9469,
+    "train_loss": 1.9174187186104912,
+    "train_runtime": 6255.5929,
     "train_samples": 7000,
-    "train_samples_per_second": 11.164,
-    "train_steps_per_second": 1.396
+    "train_samples_per_second": 11.19,
+    "train_steps_per_second": 1.399
 }

trainer_state.json

@@ -10,118 +10,118 @@
     {
       "epoch": 0.57,
       "learning_rate": 4.714285714285714e-05,
-      "loss": 2.2116,
+      "loss": 2.2023,
       "step": 500
     },
     {
       "epoch": 1.14,
       "learning_rate": 4.428571428571428e-05,
-      "loss": 2.1923,
+      "loss": 2.1613,
       "step": 1000
     },
     {
       "epoch": 1.71,
       "learning_rate": 4.1428571428571437e-05,
-      "loss": 2.1166,
+      "loss": 2.0903,
       "step": 1500
     },
     {
       "epoch": 2.29,
       "learning_rate": 3.857142857142858e-05,
-      "loss": 2.0608,
+      "loss": 2.0519,
       "step": 2000
     },
     {
       "epoch": 2.86,
       "learning_rate": 3.571428571428572e-05,
-      "loss": 2.0436,
+      "loss": 2.0146,
       "step": 2500
     },
     {
       "epoch": 3.43,
       "learning_rate": 3.285714285714286e-05,
-      "loss": 1.9908,
+      "loss": 1.9635,
       "step": 3000
     },
     {
       "epoch": 4.0,
       "learning_rate": 3e-05,
-      "loss": 1.9829,
+      "loss": 1.9629,
       "step": 3500
     },
     {
       "epoch": 4.57,
       "learning_rate": 2.714285714285714e-05,
-      "loss": 1.926,
+      "loss": 1.8956,
       "step": 4000
     },
     {
       "epoch": 5.14,
       "learning_rate": 2.4285714285714288e-05,
-      "loss": 1.9079,
+      "loss": 1.8874,
       "step": 4500
     },
     {
       "epoch": 5.71,
       "learning_rate": 2.1428571428571428e-05,
-      "loss": 1.8819,
+      "loss": 1.8671,
       "step": 5000
     },
     {
       "epoch": 6.29,
       "learning_rate": 1.8571428571428572e-05,
-      "loss": 1.8635,
+      "loss": 1.833,
       "step": 5500
     },
     {
       "epoch": 6.86,
       "learning_rate": 1.5714285714285715e-05,
-      "loss": 1.8477,
+      "loss": 1.8309,
       "step": 6000
     },
     {
       "epoch": 7.43,
       "learning_rate": 1.2857142857142857e-05,
-      "loss": 1.822,
+      "loss": 1.8051,
       "step": 6500
     },
     {
       "epoch": 8.0,
       "learning_rate": 1e-05,
-      "loss": 1.8319,
+      "loss": 1.7947,
       "step": 7000
     },
     {
       "epoch": 8.57,
       "learning_rate": 7.142857142857143e-06,
-      "loss": 1.7958,
+      "loss": 1.7707,
       "step": 7500
     },
     {
       "epoch": 9.14,
       "learning_rate": 4.285714285714286e-06,
-      "loss": 1.8055,
+      "loss": 1.7849,
       "step": 8000
     },
     {
       "epoch": 9.71,
       "learning_rate": 1.4285714285714286e-06,
-      "loss": 1.7855,
+      "loss": 1.7576,
       "step": 8500
     },
     {
       "epoch": 10.0,
       "step": 8750,
-      "total_flos": 4.261218996068352e+16,
-      "train_loss": 1.9408494245256696,
-      "train_runtime": 6269.9469,
-      "train_samples_per_second": 11.164,
-      "train_steps_per_second": 1.396
+      "total_flos": 4.26168713244672e+16,
+      "train_loss": 1.9174187186104912,
+      "train_runtime": 6255.5929,
+      "train_samples_per_second": 11.19,
+      "train_steps_per_second": 1.399
     }
   ],
   "max_steps": 8750,
   "num_train_epochs": 10,
-  "total_flos": 4.261218996068352e+16,
+  "total_flos": 4.26168713244672e+16,
   "trial_name": null,
   "trial_params": null
 }