End of training

all_results.json

@@ -6,13 +6,13 @@
     "eval_rouge2": 29.8987,
     "eval_rougeL": 37.7495,
     "eval_rougeLsum": 49.1744,
-    "eval_runtime": 22.3667,
+    "eval_runtime": 22.347,
     "eval_samples": 86,
-    "eval_samples_per_second": 3.845,
+    "eval_samples_per_second": 3.848,
     "eval_steps_per_second": 0.984,
     "train_loss": 1.6933694292408552,
-    "train_runtime": 106.8575,
+    "train_runtime": 107.1989,
     "train_samples": 342,
-    "train_samples_per_second": 9.602,
-    "train_steps_per_second": 2.414
+    "train_samples_per_second": 9.571,
+    "train_steps_per_second": 2.407
 }

eval_results.json

@@ -6,8 +6,8 @@
     "eval_rouge2": 29.8987,
     "eval_rougeL": 37.7495,
     "eval_rougeLsum": 49.1744,
-    "eval_runtime": 22.3667,
+    "eval_runtime": 22.347,
     "eval_samples": 86,
-    "eval_samples_per_second": 3.845,
+    "eval_samples_per_second": 3.848,
     "eval_steps_per_second": 0.984
 }

runs/Nov15_16-51-10_node0385.palmetto.clemson.edu/events.out.tfevents.1700085220.node0385.palmetto.clemson.edu.552718.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae217253f1216df661e831552bff41b9156fe8278f88e0ceddaaff9377ab05d8
+size 613

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
     "train_loss": 1.6933694292408552,
-    "train_runtime": 106.8575,
+    "train_runtime": 107.1989,
     "train_samples": 342,
-    "train_samples_per_second": 9.602,
-    "train_steps_per_second": 2.414
+    "train_samples_per_second": 9.571,
+    "train_steps_per_second": 2.407
 }

trainer_state.json

@@ -16,9 +16,9 @@
       "eval_rouge2": 27.7443,
       "eval_rougeL": 35.7708,
       "eval_rougeLsum": 47.0373,
-      "eval_runtime": 22.6647,
-      "eval_samples_per_second": 3.794,
-      "eval_steps_per_second": 0.971,
+      "eval_runtime": 22.9482,
+      "eval_samples_per_second": 3.748,
+      "eval_steps_per_second": 0.959,
       "step": 86
     },
     {
@@ -29,9 +29,9 @@
       "eval_rouge2": 29.9039,
       "eval_rougeL": 37.6105,
       "eval_rougeLsum": 49.6511,
-      "eval_runtime": 22.5195,
-      "eval_samples_per_second": 3.819,
-      "eval_steps_per_second": 0.977,
+      "eval_runtime": 22.5751,
+      "eval_samples_per_second": 3.81,
+      "eval_steps_per_second": 0.975,
       "step": 172
     },
     {
@@ -42,7 +42,7 @@
       "eval_rouge2": 29.8987,
       "eval_rougeL": 37.7495,
       "eval_rougeLsum": 49.1744,
-      "eval_runtime": 22.4754,
+      "eval_runtime": 22.4771,
       "eval_samples_per_second": 3.826,
       "eval_steps_per_second": 0.979,
       "step": 258
@@ -52,9 +52,9 @@
       "step": 258,
       "total_flos": 583436809912320.0,
       "train_loss": 1.6933694292408552,
-      "train_runtime": 106.8575,
-      "train_samples_per_second": 9.602,
-      "train_steps_per_second": 2.414
+      "train_runtime": 107.1989,
+      "train_samples_per_second": 9.571,
+      "train_steps_per_second": 2.407
     }
   ],
   "logging_steps": 500,