Training in progress, epoch 19, checkpoint

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:229b67cee0d153dbbec3afa0cd55b16c35a65448be81d69271e468f452c12c37
+oid sha256:590ca6cf7a51bd34cebcce091bf7b19ed8c4800b52fae63fdebbcb234b0e6d1d
 size 14244

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "dq158/morbius/checkpoint-144",
-  "epoch": 18.993949870354363,
+  "epoch": 19.913569576490925,
   "eval_steps": 500,
-  "global_step": 2747,
+  "global_step": 2880,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -398,13 +398,32 @@
       "eval_steps_per_second": 1.053,
       "eval_translation_length": 18771,
       "step": 2747
+    },
+    {
+      "epoch": 19.91,
+      "eval_bleu": 1.0,
+      "eval_brevity_penalty": 1.0,
+      "eval_length_ratio": 1.0,
+      "eval_loss": NaN,
+      "eval_precisions": [
+        1.0,
+        1.0,
+        1.0,
+        1.0
+      ],
+      "eval_reference_length": 18771,
+      "eval_runtime": 122.5437,
+      "eval_samples_per_second": 8.389,
+      "eval_steps_per_second": 1.053,
+      "eval_translation_length": 18771,
+      "step": 2880
     }
   ],
   "logging_steps": 500,
   "max_steps": 2880,
   "num_train_epochs": 20,
   "save_steps": 500,
-  "total_flos": 1.2037212547212902e+17,
+  "total_flos": 1.2616243364442931e+17,
   "trial_name": null,
   "trial_params": null
 }