End of training

all_results.json

@@ -3,21 +3,21 @@
     "eval_bleu": 0.0,
     "eval_gen_len": 9.0,
     "eval_loss": 0.7730677127838135,
-    "eval_runtime": 13.4765,
+    "eval_runtime": 14.1749,
     "eval_samples": 785,
-    "eval_samples_per_second": 58.249,
-    "eval_steps_per_second": 3.71,
+    "eval_samples_per_second": 55.38,
+    "eval_steps_per_second": 3.527,
     "predict_bleu": 0.0,
     "predict_gen_len": 9.0,
     "predict_loss": 0.8163799047470093,
-    "predict_runtime": 13.459,
+    "predict_runtime": 14.3114,
     "predict_samples": 785,
-    "predict_samples_per_second": 58.325,
-    "predict_steps_per_second": 3.715,
+    "predict_samples_per_second": 54.851,
+    "predict_steps_per_second": 3.494,
     "total_flos": 2189095450214400.0,
     "train_loss": 1.140592199427481,
-    "train_runtime": 483.719,
+    "train_runtime": 504.5513,
     "train_samples": 6279,
-    "train_samples_per_second": 129.807,
-    "train_steps_per_second": 8.125
+    "train_samples_per_second": 124.447,
+    "train_steps_per_second": 7.789
 }

eval_results.json

@@ -3,8 +3,8 @@
     "eval_bleu": 0.0,
     "eval_gen_len": 9.0,
     "eval_loss": 0.7730677127838135,
-    "eval_runtime": 13.4765,
+    "eval_runtime": 14.1749,
     "eval_samples": 785,
-    "eval_samples_per_second": 58.249,
-    "eval_steps_per_second": 3.71
+    "eval_samples_per_second": 55.38,
+    "eval_steps_per_second": 3.527
 }

generation_config.json

@@ -1,5 +1,4 @@
 {
-  "_from_model_config": true,
   "decoder_start_token_id": 0,
   "eos_token_id": 1,
   "pad_token_id": 0,

predict_results.json

@@ -2,8 +2,8 @@
     "predict_bleu": 0.0,
     "predict_gen_len": 9.0,
     "predict_loss": 0.8163799047470093,
-    "predict_runtime": 13.459,
+    "predict_runtime": 14.3114,
     "predict_samples": 785,
-    "predict_samples_per_second": 58.325,
-    "predict_steps_per_second": 3.715
+    "predict_samples_per_second": 54.851,
+    "predict_steps_per_second": 3.494
 }

runs/Apr12_22-09-43_ea8d7db94b39/events.out.tfevents.1681338442.ea8d7db94b39.1070.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce5c951bdd787c4e7a642e59d5b3e5a9761ce461ea112ac1b16dee2ae262808c
+size 458

train_results.json

@@ -2,8 +2,8 @@
     "epoch": 10.0,
     "total_flos": 2189095450214400.0,
     "train_loss": 1.140592199427481,
-    "train_runtime": 483.719,
+    "train_runtime": 504.5513,
     "train_samples": 6279,
-    "train_samples_per_second": 129.807,
-    "train_steps_per_second": 8.125
+    "train_samples_per_second": 124.447,
+    "train_steps_per_second": 7.789
 }

trainer_state.json

@@ -54,9 +54,9 @@
       "step": 3930,
       "total_flos": 2189095450214400.0,
       "train_loss": 1.140592199427481,
-      "train_runtime": 483.719,
-      "train_samples_per_second": 129.807,
-      "train_steps_per_second": 8.125
+      "train_runtime": 504.5513,
+      "train_samples_per_second": 124.447,
+      "train_steps_per_second": 7.789
     }
   ],
   "max_steps": 3930,