End of training

all_results.json

@@ -3,21 +3,21 @@
     "eval_bleu": 0.0,
     "eval_gen_len": 9.0,
     "eval_loss": 0.7622068524360657,
-    "eval_runtime": 13.2087,
+    "eval_runtime": 14.0376,
     "eval_samples": 771,
-    "eval_samples_per_second": 58.371,
-    "eval_steps_per_second": 3.71,
+    "eval_samples_per_second": 54.924,
+    "eval_steps_per_second": 3.491,
     "predict_bleu": 0.0,
     "predict_gen_len": 9.0,
     "predict_loss": 0.729883074760437,
-    "predict_runtime": 13.1751,
+    "predict_runtime": 13.9098,
     "predict_samples": 771,
-    "predict_samples_per_second": 58.52,
-    "predict_steps_per_second": 3.719,
+    "predict_samples_per_second": 55.429,
+    "predict_steps_per_second": 3.523,
     "total_flos": 2149699402137600.0,
     "train_loss": 1.0592799369535297,
-    "train_runtime": 473.9997,
+    "train_runtime": 503.7989,
     "train_samples": 6166,
-    "train_samples_per_second": 130.084,
-    "train_steps_per_second": 8.143
+    "train_samples_per_second": 122.39,
+    "train_steps_per_second": 7.662
 }

eval_results.json

@@ -3,8 +3,8 @@
     "eval_bleu": 0.0,
     "eval_gen_len": 9.0,
     "eval_loss": 0.7622068524360657,
-    "eval_runtime": 13.2087,
+    "eval_runtime": 14.0376,
     "eval_samples": 771,
-    "eval_samples_per_second": 58.371,
-    "eval_steps_per_second": 3.71
+    "eval_samples_per_second": 54.924,
+    "eval_steps_per_second": 3.491
 }

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": 0.729883074760437,
-    "predict_runtime": 13.1751,
+    "predict_runtime": 13.9098,
     "predict_samples": 771,
-    "predict_samples_per_second": 58.52,
-    "predict_steps_per_second": 3.719
+    "predict_samples_per_second": 55.429,
+    "predict_steps_per_second": 3.523
 }

runs/Apr13_00-18-22_ea8d7db94b39/events.out.tfevents.1681346143.ea8d7db94b39.1070.23

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ec02f493c8357812b1f30029c313a8edf7d3c375a63b4fbb2417119c34f5dd8
+size 458

train_results.json

@@ -2,8 +2,8 @@
     "epoch": 10.0,
     "total_flos": 2149699402137600.0,
     "train_loss": 1.0592799369535297,
-    "train_runtime": 473.9997,
+    "train_runtime": 503.7989,
     "train_samples": 6166,
-    "train_samples_per_second": 130.084,
-    "train_steps_per_second": 8.143
+    "train_samples_per_second": 122.39,
+    "train_steps_per_second": 7.662
 }

trainer_state.json

@@ -54,9 +54,9 @@
       "step": 3860,
       "total_flos": 2149699402137600.0,
       "train_loss": 1.0592799369535297,
-      "train_runtime": 473.9997,
-      "train_samples_per_second": 130.084,
-      "train_steps_per_second": 8.143
+      "train_runtime": 503.7989,
+      "train_samples_per_second": 122.39,
+      "train_steps_per_second": 7.662
     }
   ],
   "max_steps": 3860,