End of training

all_results.json

@@ -1,28 +1,28 @@
 {
-    "epoch": 3.0,
-    "eval_gen_len": 236.2392,
-    "eval_loss": 1.5022238492965698,
-    "eval_rouge1": 50.8664,
-    "eval_rouge2": 26.5857,
-    "eval_rougeL": 31.1338,
-    "eval_rougeLsum": 48.4801,
-    "eval_runtime": 1527.8305,
+    "epoch": 10.0,
+    "eval_gen_len": 248.1199,
+    "eval_loss": 1.275891661643982,
+    "eval_rouge1": 52.3608,
+    "eval_rouge2": 27.6526,
+    "eval_rougeL": 31.8509,
+    "eval_rougeLsum": 49.9086,
+    "eval_runtime": 1504.8405,
     "eval_samples": 1568,
-    "eval_samples_per_second": 1.026,
-    "eval_steps_per_second": 0.043,
-    "predict_gen_len": 236.2392,
-    "predict_loss": 1.5022238492965698,
-    "predict_rouge1": 50.8664,
-    "predict_rouge2": 26.5857,
-    "predict_rougeL": 31.1338,
-    "predict_rougeLsum": 48.4801,
-    "predict_runtime": 1525.7443,
+    "eval_samples_per_second": 1.042,
+    "eval_steps_per_second": 0.029,
+    "predict_gen_len": 248.1199,
+    "predict_loss": 1.275891661643982,
+    "predict_rouge1": 52.3608,
+    "predict_rouge2": 27.6526,
+    "predict_rougeL": 31.8509,
+    "predict_rougeLsum": 49.9086,
+    "predict_runtime": 1513.1914,
     "predict_samples": 1568,
-    "predict_samples_per_second": 1.028,
-    "predict_steps_per_second": 0.043,
-    "train_loss": 1.6923205314095087,
-    "train_runtime": 822.2959,
+    "predict_samples_per_second": 1.036,
+    "predict_steps_per_second": 0.029,
+    "train_loss": 1.389875247819083,
+    "train_runtime": 2378.4813,
     "train_samples": 6271,
-    "train_samples_per_second": 22.879,
-    "train_steps_per_second": 0.956
+    "train_samples_per_second": 26.366,
+    "train_steps_per_second": 0.736
 }

eval_results.json

@@ -1,13 +1,13 @@
 {
-    "epoch": 3.0,
-    "eval_gen_len": 236.2392,
-    "eval_loss": 1.5022238492965698,
-    "eval_rouge1": 50.8664,
-    "eval_rouge2": 26.5857,
-    "eval_rougeL": 31.1338,
-    "eval_rougeLsum": 48.4801,
-    "eval_runtime": 1527.8305,
+    "epoch": 10.0,
+    "eval_gen_len": 248.1199,
+    "eval_loss": 1.275891661643982,
+    "eval_rouge1": 52.3608,
+    "eval_rouge2": 27.6526,
+    "eval_rougeL": 31.8509,
+    "eval_rougeLsum": 49.9086,
+    "eval_runtime": 1504.8405,
     "eval_samples": 1568,
-    "eval_samples_per_second": 1.026,
-    "eval_steps_per_second": 0.043
+    "eval_samples_per_second": 1.042,
+    "eval_steps_per_second": 0.029
 }

predict_results.json

@@ -1,12 +1,12 @@
 {
-    "predict_gen_len": 236.2392,
-    "predict_loss": 1.5022238492965698,
-    "predict_rouge1": 50.8664,
-    "predict_rouge2": 26.5857,
-    "predict_rougeL": 31.1338,
-    "predict_rougeLsum": 48.4801,
-    "predict_runtime": 1525.7443,
+    "predict_gen_len": 248.1199,
+    "predict_loss": 1.275891661643982,
+    "predict_rouge1": 52.3608,
+    "predict_rouge2": 27.6526,
+    "predict_rougeL": 31.8509,
+    "predict_rougeLsum": 49.9086,
+    "predict_runtime": 1513.1914,
     "predict_samples": 1568,
-    "predict_samples_per_second": 1.028,
-    "predict_steps_per_second": 0.043
+    "predict_samples_per_second": 1.036,
+    "predict_steps_per_second": 0.029
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 3.0,
-    "train_loss": 1.6923205314095087,
-    "train_runtime": 822.2959,
+    "epoch": 10.0,
+    "train_loss": 1.389875247819083,
+    "train_runtime": 2378.4813,
     "train_samples": 6271,
-    "train_samples_per_second": 22.879,
-    "train_steps_per_second": 0.956
+    "train_samples_per_second": 26.366,
+    "train_steps_per_second": 0.736
 }