End of training

all_results.json

@@ -3,21 +3,21 @@
     "eval_bleu": 0.0,
     "eval_gen_len": 9.0,
     "eval_loss": 0.8440382480621338,
-    "eval_runtime": 13.5992,
+    "eval_runtime": 14.8283,
     "eval_samples": 793,
-    "eval_samples_per_second": 58.312,
-    "eval_steps_per_second": 3.677,
+    "eval_samples_per_second": 53.479,
+    "eval_steps_per_second": 3.372,
     "predict_bleu": 0.0,
     "predict_gen_len": 9.0,
     "predict_loss": 0.8730815052986145,
-    "predict_runtime": 13.4765,
+    "predict_runtime": 14.4411,
     "predict_samples": 793,
-    "predict_samples_per_second": 58.843,
-    "predict_steps_per_second": 3.71,
+    "predict_samples_per_second": 54.913,
+    "predict_steps_per_second": 3.462,
     "total_flos": 2211059618611200.0,
     "train_loss": 1.1873271798006533,
-    "train_runtime": 486.4883,
+    "train_runtime": 515.885,
     "train_samples": 6342,
-    "train_samples_per_second": 130.363,
-    "train_steps_per_second": 8.161
+    "train_samples_per_second": 122.934,
+    "train_steps_per_second": 7.696
 }

eval_results.json

@@ -3,8 +3,8 @@
     "eval_bleu": 0.0,
     "eval_gen_len": 9.0,
     "eval_loss": 0.8440382480621338,
-    "eval_runtime": 13.5992,
+    "eval_runtime": 14.8283,
     "eval_samples": 793,
-    "eval_samples_per_second": 58.312,
-    "eval_steps_per_second": 3.677
+    "eval_samples_per_second": 53.479,
+    "eval_steps_per_second": 3.372
 }

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": 0.8730815052986145,
-    "predict_runtime": 13.4765,
+    "predict_runtime": 14.4411,
     "predict_samples": 793,
-    "predict_samples_per_second": 58.843,
-    "predict_steps_per_second": 3.71
+    "predict_samples_per_second": 54.913,
+    "predict_steps_per_second": 3.462
 }

runs/Apr12_23-59-52_ea8d7db94b39/events.out.tfevents.1681345048.ea8d7db94b39.1070.20

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1eaa1798ac9b93b7b17d682c6729cd44e33faff4c10e52394e4c50a3ae6daa42
+size 458

train_results.json

@@ -2,8 +2,8 @@
     "epoch": 10.0,
     "total_flos": 2211059618611200.0,
     "train_loss": 1.1873271798006533,
-    "train_runtime": 486.4883,
+    "train_runtime": 515.885,
     "train_samples": 6342,
-    "train_samples_per_second": 130.363,
-    "train_steps_per_second": 8.161
+    "train_samples_per_second": 122.934,
+    "train_steps_per_second": 7.696
 }

trainer_state.json

@@ -54,9 +54,9 @@
       "step": 3970,
       "total_flos": 2211059618611200.0,
       "train_loss": 1.1873271798006533,
-      "train_runtime": 486.4883,
-      "train_samples_per_second": 130.363,
-      "train_steps_per_second": 8.161
+      "train_runtime": 515.885,
+      "train_samples_per_second": 122.934,
+      "train_steps_per_second": 7.696
     }
   ],
   "max_steps": 3970,