End of training

all_results.json

@@ -3,21 +3,21 @@
     "eval_bleu": 0.0,
     "eval_gen_len": 9.0,
     "eval_loss": 0.5292456746101379,
-    "eval_runtime": 13.5701,
+    "eval_runtime": 14.1609,
     "eval_samples": 795,
-    "eval_samples_per_second": 58.585,
-    "eval_steps_per_second": 3.685,
+    "eval_samples_per_second": 56.141,
+    "eval_steps_per_second": 3.531,
     "predict_bleu": 0.0,
     "predict_gen_len": 9.0,
     "predict_loss": 0.5050508975982666,
-    "predict_runtime": 13.4766,
+    "predict_runtime": 14.148,
     "predict_samples": 795,
-    "predict_samples_per_second": 58.991,
-    "predict_steps_per_second": 3.71,
+    "predict_samples_per_second": 56.192,
+    "predict_steps_per_second": 3.534,
     "total_flos": 2215940544921600.0,
     "train_loss": 0.7078812297265135,
-    "train_runtime": 490.0153,
+    "train_runtime": 511.9716,
     "train_samples": 6356,
-    "train_samples_per_second": 129.71,
-    "train_steps_per_second": 8.122
+    "train_samples_per_second": 124.148,
+    "train_steps_per_second": 7.774
 }

eval_results.json

@@ -3,8 +3,8 @@
     "eval_bleu": 0.0,
     "eval_gen_len": 9.0,
     "eval_loss": 0.5292456746101379,
-    "eval_runtime": 13.5701,
+    "eval_runtime": 14.1609,
     "eval_samples": 795,
-    "eval_samples_per_second": 58.585,
-    "eval_steps_per_second": 3.685
+    "eval_samples_per_second": 56.141,
+    "eval_steps_per_second": 3.531
 }

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": 0.5050508975982666,
-    "predict_runtime": 13.4766,
+    "predict_runtime": 14.148,
     "predict_samples": 795,
-    "predict_samples_per_second": 58.991,
-    "predict_steps_per_second": 3.71
+    "predict_samples_per_second": 56.192,
+    "predict_steps_per_second": 3.534
 }

runs/Apr12_23-23-09_ea8d7db94b39/events.out.tfevents.1681342825.ea8d7db94b39.1070.14

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:374510bd4766844d3d6d56e09beadb2b288b7c803953ada0d37b4685ce89d069
+size 458

train_results.json

@@ -2,8 +2,8 @@
     "epoch": 10.0,
     "total_flos": 2215940544921600.0,
     "train_loss": 0.7078812297265135,
-    "train_runtime": 490.0153,
+    "train_runtime": 511.9716,
     "train_samples": 6356,
-    "train_samples_per_second": 129.71,
-    "train_steps_per_second": 8.122
+    "train_samples_per_second": 124.148,
+    "train_steps_per_second": 7.774
 }

trainer_state.json

@@ -54,9 +54,9 @@
       "step": 3980,
       "total_flos": 2215940544921600.0,
       "train_loss": 0.7078812297265135,
-      "train_runtime": 490.0153,
-      "train_samples_per_second": 129.71,
-      "train_steps_per_second": 8.122
+      "train_runtime": 511.9716,
+      "train_samples_per_second": 124.148,
+      "train_steps_per_second": 7.774
     }
   ],
   "max_steps": 3980,