End of training

all_results.json

@@ -3,21 +3,21 @@
     "eval_bleu": 0.0,
     "eval_gen_len": 9.0,
     "eval_loss": 0.734420120716095,
-    "eval_runtime": 13.5697,
+    "eval_runtime": 14.2391,
     "eval_samples": 793,
-    "eval_samples_per_second": 58.439,
-    "eval_steps_per_second": 3.685,
+    "eval_samples_per_second": 55.692,
+    "eval_steps_per_second": 3.511,
     "predict_bleu": 0.0,
     "predict_gen_len": 9.0,
     "predict_loss": 0.7520648837089539,
-    "predict_runtime": 13.5032,
+    "predict_runtime": 14.2551,
     "predict_samples": 794,
-    "predict_samples_per_second": 58.801,
-    "predict_steps_per_second": 3.703,
+    "predict_samples_per_second": 55.699,
+    "predict_steps_per_second": 3.508,
     "total_flos": 2212105531392000.0,
     "train_loss": 1.0583241114388184,
-    "train_runtime": 487.1376,
+    "train_runtime": 517.4021,
     "train_samples": 6345,
-    "train_samples_per_second": 130.251,
-    "train_steps_per_second": 8.15
+    "train_samples_per_second": 122.632,
+    "train_steps_per_second": 7.673
 }

eval_results.json

@@ -3,8 +3,8 @@
     "eval_bleu": 0.0,
     "eval_gen_len": 9.0,
     "eval_loss": 0.734420120716095,
-    "eval_runtime": 13.5697,
+    "eval_runtime": 14.2391,
     "eval_samples": 793,
-    "eval_samples_per_second": 58.439,
-    "eval_steps_per_second": 3.685
+    "eval_samples_per_second": 55.692,
+    "eval_steps_per_second": 3.511
 }

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": 0.7520648837089539,
-    "predict_runtime": 13.5032,
+    "predict_runtime": 14.2551,
     "predict_samples": 794,
-    "predict_samples_per_second": 58.801,
-    "predict_steps_per_second": 3.703
+    "predict_samples_per_second": 55.699,
+    "predict_steps_per_second": 3.508
 }

runs/Apr12_23-41-18_ea8d7db94b39/events.out.tfevents.1681343939.ea8d7db94b39.1070.17

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d69f7ef0b101b6cf3e5b7dcc9b40f13edf5f39fe8a7a5b99e1a16384118ee4d0
+size 458

train_results.json

@@ -2,8 +2,8 @@
     "epoch": 10.0,
     "total_flos": 2212105531392000.0,
     "train_loss": 1.0583241114388184,
-    "train_runtime": 487.1376,
+    "train_runtime": 517.4021,
     "train_samples": 6345,
-    "train_samples_per_second": 130.251,
-    "train_steps_per_second": 8.15
+    "train_samples_per_second": 122.632,
+    "train_steps_per_second": 7.673
 }

trainer_state.json

@@ -54,9 +54,9 @@
       "step": 3970,
       "total_flos": 2212105531392000.0,
       "train_loss": 1.0583241114388184,
-      "train_runtime": 487.1376,
-      "train_samples_per_second": 130.251,
-      "train_steps_per_second": 8.15
+      "train_runtime": 517.4021,
+      "train_samples_per_second": 122.632,
+      "train_steps_per_second": 7.673
     }
   ],
   "max_steps": 3970,