Training in progress, epoch 1

all_results.json

@@ -6,23 +6,23 @@
     "eval_rouge2": 3.1211,
     "eval_rougeL": 10.9379,
     "eval_rougeLsum": 15.8203,
-    "eval_runtime": 321.129,
+    "eval_runtime": 317.8178,
     "eval_samples": 286,
-    "eval_samples_per_second": 0.891,
-    "eval_steps_per_second": 0.891,
+    "eval_samples_per_second": 0.9,
+    "eval_steps_per_second": 0.9,
     "predict_gen_len": 86.58898305084746,
     "predict_loss": 3.0853381156921387,
     "predict_rouge1": 18.1172,
     "predict_rouge2": 3.4127,
     "predict_rougeL": 11.2062,
     "predict_rougeLsum": 12.5441,
-    "predict_runtime": 225.8529,
+    "predict_runtime": 262.8252,
     "predict_samples": 236,
-    "predict_samples_per_second": 1.045,
-    "predict_steps_per_second": 1.045,
+    "predict_samples_per_second": 0.898,
+    "predict_steps_per_second": 0.898,
     "train_loss": 0.4568321267587167,
-    "train_runtime": 2567.7496,
+    "train_runtime": 2611.1815,
     "train_samples": 2025,
-    "train_samples_per_second": 3.943,
-    "train_steps_per_second": 3.943
+    "train_samples_per_second": 3.878,
+    "train_steps_per_second": 3.878
 }

eval_results.json

@@ -6,8 +6,8 @@
     "eval_rouge2": 3.1211,
     "eval_rougeL": 10.9379,
     "eval_rougeLsum": 15.8203,
-    "eval_runtime": 321.129,
+    "eval_runtime": 317.8178,
     "eval_samples": 286,
-    "eval_samples_per_second": 0.891,
-    "eval_steps_per_second": 0.891
+    "eval_samples_per_second": 0.9,
+    "eval_steps_per_second": 0.9
 }

predict_results.json

@@ -5,8 +5,8 @@
     "predict_rouge2": 3.4127,
     "predict_rougeL": 11.2062,
     "predict_rougeLsum": 12.5441,
-    "predict_runtime": 225.8529,
+    "predict_runtime": 262.8252,
     "predict_samples": 236,
-    "predict_samples_per_second": 1.045,
-    "predict_steps_per_second": 1.045
+    "predict_samples_per_second": 0.898,
+    "predict_steps_per_second": 0.898
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6902d1896ca8ad19f375b35d44d9e224ebd29fbc4199844044daccae0714ecc4
+oid sha256:479a16662531508b9f6eeda30775691b89ca046731b6cce103ef89e37dd889c1
 size 501807853

runs/Mar26_15-40-21_kogecha/events.out.tfevents.1711438179.kogecha

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d059a5c52765c4c18d2bacb1ca15570de6e765fa72cb103d2da1a5aed2ecd957
+size 565

runs/Mar26_17-48-18_kogecha/events.out.tfevents.1711442909.kogecha

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:897d6d9ae1ab575031ec746d70a6311affa2d4a23606fc7b83434961c2b803fe
+size 6326

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 5.0,
     "train_loss": 0.4568321267587167,
-    "train_runtime": 2567.7496,
+    "train_runtime": 2611.1815,
     "train_samples": 2025,
-    "train_samples_per_second": 3.943,
-    "train_steps_per_second": 3.943
+    "train_samples_per_second": 3.878,
+    "train_steps_per_second": 3.878
 }

trainer_state.json

@@ -39,9 +39,9 @@
       "eval_rouge2": 1.2888,
       "eval_rougeL": 11.0128,
       "eval_rougeLsum": 15.2802,
-      "eval_runtime": 269.5917,
-      "eval_samples_per_second": 1.061,
-      "eval_steps_per_second": 1.061,
+      "eval_runtime": 267.3657,
+      "eval_samples_per_second": 1.07,
+      "eval_steps_per_second": 1.07,
       "step": 2025
     },
     {
@@ -76,9 +76,9 @@
       "eval_rouge2": 2.8091,
       "eval_rougeL": 10.9133,
       "eval_rougeLsum": 15.4068,
-      "eval_runtime": 324.1284,
-      "eval_samples_per_second": 0.882,
-      "eval_steps_per_second": 0.882,
+      "eval_runtime": 356.3388,
+      "eval_samples_per_second": 0.803,
+      "eval_steps_per_second": 0.803,
       "step": 4050
     },
     {
@@ -113,9 +113,9 @@
       "eval_rouge2": 3.0026,
       "eval_rougeL": 10.272,
       "eval_rougeLsum": 14.0716,
-      "eval_runtime": 281.1095,
-      "eval_samples_per_second": 1.017,
-      "eval_steps_per_second": 1.017,
+      "eval_runtime": 279.7235,
+      "eval_samples_per_second": 1.022,
+      "eval_steps_per_second": 1.022,
       "step": 6075
     },
     {
@@ -150,9 +150,9 @@
       "eval_rouge2": 2.9937,
       "eval_rougeL": 10.8765,
       "eval_rougeLsum": 15.6203,
-      "eval_runtime": 326.4072,
-      "eval_samples_per_second": 0.876,
-      "eval_steps_per_second": 0.876,
+      "eval_runtime": 323.891,
+      "eval_samples_per_second": 0.883,
+      "eval_steps_per_second": 0.883,
       "step": 8100
     },
     {
@@ -187,9 +187,9 @@
       "eval_rouge2": 3.1211,
       "eval_rougeL": 10.9379,
       "eval_rougeLsum": 15.8203,
-      "eval_runtime": 320.7013,
-      "eval_samples_per_second": 0.892,
-      "eval_steps_per_second": 0.892,
+      "eval_runtime": 317.0639,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.902,
       "step": 10125
     },
     {
@@ -197,9 +197,9 @@
       "step": 10125,
       "total_flos": 1931007009669120.0,
       "train_loss": 0.4568321267587167,
-      "train_runtime": 2567.7496,
-      "train_samples_per_second": 3.943,
-      "train_steps_per_second": 3.943
+      "train_runtime": 2611.1815,
+      "train_samples_per_second": 3.878,
+      "train_steps_per_second": 3.878
     }
   ],
   "max_steps": 10125,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1f06036d74c60635455d9d063b586bccc9945de86b85390e3d282dc4ada8f2c
+oid sha256:fe408de49090e9d0c183138d8685c145d59b62f9884c078cb6fbadb736db474a
 size 4475