End of training

all_results.json

@@ -3,21 +3,21 @@
     "eval_bleu": 0.0,
     "eval_gen_len": 9.0,
     "eval_loss": 0.8365611433982849,
-    "eval_runtime": 13.4964,
+    "eval_runtime": 14.0746,
     "eval_samples": 795,
-    "eval_samples_per_second": 58.904,
-    "eval_steps_per_second": 3.705,
+    "eval_samples_per_second": 56.485,
+    "eval_steps_per_second": 3.552,
     "predict_bleu": 0.0,
     "predict_gen_len": 9.0,
     "predict_loss": 0.8690455555915833,
-    "predict_runtime": 13.503,
+    "predict_runtime": 14.2101,
     "predict_samples": 796,
-    "predict_samples_per_second": 58.95,
-    "predict_steps_per_second": 3.703,
+    "predict_samples_per_second": 56.017,
+    "predict_steps_per_second": 3.519,
     "total_flos": 2218381008076800.0,
     "train_loss": 1.172858095408684,
-    "train_runtime": 488.7684,
+    "train_runtime": 512.5959,
     "train_samples": 6363,
-    "train_samples_per_second": 130.184,
-    "train_steps_per_second": 8.143
+    "train_samples_per_second": 124.133,
+    "train_steps_per_second": 7.764
 }

eval_results.json

@@ -3,8 +3,8 @@
     "eval_bleu": 0.0,
     "eval_gen_len": 9.0,
     "eval_loss": 0.8365611433982849,
-    "eval_runtime": 13.4964,
+    "eval_runtime": 14.0746,
     "eval_samples": 795,
-    "eval_samples_per_second": 58.904,
-    "eval_steps_per_second": 3.705
+    "eval_samples_per_second": 56.485,
+    "eval_steps_per_second": 3.552
 }

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": 0.8690455555915833,
-    "predict_runtime": 13.503,
+    "predict_runtime": 14.2101,
     "predict_samples": 796,
-    "predict_samples_per_second": 58.95,
-    "predict_steps_per_second": 3.703
+    "predict_samples_per_second": 56.017,
+    "predict_steps_per_second": 3.519
 }

runs/Apr12_22-28-09_ea8d7db94b39/events.out.tfevents.1681339537.ea8d7db94b39.1070.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdab8f32dae55ebe2aab6b1c2bc8cd679389a9165c10502df0c80811e9ba4d82
+size 458

train_results.json

@@ -2,8 +2,8 @@
     "epoch": 10.0,
     "total_flos": 2218381008076800.0,
     "train_loss": 1.172858095408684,
-    "train_runtime": 488.7684,
+    "train_runtime": 512.5959,
     "train_samples": 6363,
-    "train_samples_per_second": 130.184,
-    "train_steps_per_second": 8.143
+    "train_samples_per_second": 124.133,
+    "train_steps_per_second": 7.764
 }

trainer_state.json

@@ -54,9 +54,9 @@
       "step": 3980,
       "total_flos": 2218381008076800.0,
       "train_loss": 1.172858095408684,
-      "train_runtime": 488.7684,
-      "train_samples_per_second": 130.184,
-      "train_steps_per_second": 8.143
+      "train_runtime": 512.5959,
+      "train_samples_per_second": 124.133,
+      "train_steps_per_second": 7.764
     }
   ],
   "max_steps": 3980,