End of training

all_results.json

@@ -3,21 +3,21 @@
     "eval_bleu": 0.0,
     "eval_gen_len": 9.0,
     "eval_loss": 0.6404397487640381,
-    "eval_runtime": 13.5331,
+    "eval_runtime": 14.6467,
     "eval_samples": 795,
-    "eval_samples_per_second": 58.745,
-    "eval_steps_per_second": 3.695,
+    "eval_samples_per_second": 54.279,
+    "eval_steps_per_second": 3.414,
     "predict_bleu": 0.0,
     "predict_gen_len": 9.0,
     "predict_loss": 0.6172239780426025,
-    "predict_runtime": 13.5277,
+    "predict_runtime": 13.9864,
     "predict_samples": 796,
-    "predict_samples_per_second": 58.842,
-    "predict_steps_per_second": 3.696,
+    "predict_samples_per_second": 56.912,
+    "predict_steps_per_second": 3.575,
     "total_flos": 2217335095296000.0,
     "train_loss": 0.9207983505785765,
-    "train_runtime": 489.2905,
+    "train_runtime": 513.5357,
     "train_samples": 6360,
-    "train_samples_per_second": 129.984,
-    "train_steps_per_second": 8.134
+    "train_samples_per_second": 123.847,
+    "train_steps_per_second": 7.75
 }

eval_results.json

@@ -3,8 +3,8 @@
     "eval_bleu": 0.0,
     "eval_gen_len": 9.0,
     "eval_loss": 0.6404397487640381,
-    "eval_runtime": 13.5331,
+    "eval_runtime": 14.6467,
     "eval_samples": 795,
-    "eval_samples_per_second": 58.745,
-    "eval_steps_per_second": 3.695
+    "eval_samples_per_second": 54.279,
+    "eval_steps_per_second": 3.414
 }

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": 0.6172239780426025,
-    "predict_runtime": 13.5277,
+    "predict_runtime": 13.9864,
     "predict_samples": 796,
-    "predict_samples_per_second": 58.842,
-    "predict_steps_per_second": 3.696
+    "predict_samples_per_second": 56.912,
+    "predict_steps_per_second": 3.575
 }

runs/Apr12_23-04-50_ea8d7db94b39/events.out.tfevents.1681341738.ea8d7db94b39.1070.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5dc2e9f77bc52443df34591dfe9cdcb03474ae097da64c66b8fa5ee6fd7e4c0
+size 458

train_results.json

@@ -2,8 +2,8 @@
     "epoch": 10.0,
     "total_flos": 2217335095296000.0,
     "train_loss": 0.9207983505785765,
-    "train_runtime": 489.2905,
+    "train_runtime": 513.5357,
     "train_samples": 6360,
-    "train_samples_per_second": 129.984,
-    "train_steps_per_second": 8.134
+    "train_samples_per_second": 123.847,
+    "train_steps_per_second": 7.75
 }

trainer_state.json

@@ -54,9 +54,9 @@
       "step": 3980,
       "total_flos": 2217335095296000.0,
       "train_loss": 0.9207983505785765,
-      "train_runtime": 489.2905,
-      "train_samples_per_second": 129.984,
-      "train_steps_per_second": 8.134
+      "train_runtime": 513.5357,
+      "train_samples_per_second": 123.847,
+      "train_steps_per_second": 7.75
     }
   ],
   "max_steps": 3980,