End of training

all_results.json

@@ -3,21 +3,21 @@
     "eval_bleu": 0.0,
     "eval_gen_len": 9.0,
     "eval_loss": 0.7010424137115479,
-    "eval_runtime": 13.4998,
+    "eval_runtime": 14.47,
     "eval_samples": 794,
-    "eval_samples_per_second": 58.816,
-    "eval_steps_per_second": 3.704,
+    "eval_samples_per_second": 54.872,
+    "eval_steps_per_second": 3.455,
     "predict_bleu": 0.0,
     "predict_gen_len": 9.0,
     "predict_loss": 0.6438102126121521,
-    "predict_runtime": 13.74,
+    "predict_runtime": 14.3407,
     "predict_samples": 795,
-    "predict_samples_per_second": 57.86,
-    "predict_steps_per_second": 3.639,
+    "predict_samples_per_second": 55.437,
+    "predict_steps_per_second": 3.487,
     "total_flos": 2215243269734400.0,
     "train_loss": 0.9812813993674426,
-    "train_runtime": 488.8488,
+    "train_runtime": 514.4973,
     "train_samples": 6354,
-    "train_samples_per_second": 129.979,
-    "train_steps_per_second": 8.142
+    "train_samples_per_second": 123.499,
+    "train_steps_per_second": 7.736
 }

eval_results.json

@@ -3,8 +3,8 @@
     "eval_bleu": 0.0,
     "eval_gen_len": 9.0,
     "eval_loss": 0.7010424137115479,
-    "eval_runtime": 13.4998,
+    "eval_runtime": 14.47,
     "eval_samples": 794,
-    "eval_samples_per_second": 58.816,
-    "eval_steps_per_second": 3.704
+    "eval_samples_per_second": 54.872,
+    "eval_steps_per_second": 3.455
 }

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": 0.6438102126121521,
-    "predict_runtime": 13.74,
+    "predict_runtime": 14.3407,
     "predict_samples": 795,
-    "predict_samples_per_second": 57.86,
-    "predict_steps_per_second": 3.639
+    "predict_samples_per_second": 55.437,
+    "predict_steps_per_second": 3.487
 }

runs/Apr12_22-46-28_ea8d7db94b39/events.out.tfevents.1681340638.ea8d7db94b39.1070.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab2470311a90f4df22831dbf5ce32d86077ea8b72856934d6474ab401aeacdac
+size 458

train_results.json

@@ -2,8 +2,8 @@
     "epoch": 10.0,
     "total_flos": 2215243269734400.0,
     "train_loss": 0.9812813993674426,
-    "train_runtime": 488.8488,
+    "train_runtime": 514.4973,
     "train_samples": 6354,
-    "train_samples_per_second": 129.979,
-    "train_steps_per_second": 8.142
+    "train_samples_per_second": 123.499,
+    "train_steps_per_second": 7.736
 }

trainer_state.json

@@ -54,9 +54,9 @@
       "step": 3980,
       "total_flos": 2215243269734400.0,
       "train_loss": 0.9812813993674426,
-      "train_runtime": 488.8488,
-      "train_samples_per_second": 129.979,
-      "train_steps_per_second": 8.142
+      "train_runtime": 514.4973,
+      "train_samples_per_second": 123.499,
+      "train_steps_per_second": 7.736
     }
   ],
   "max_steps": 3980,