Training in progress, step 161088, checkpoint

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3fd70c2ee9103dacc2e8460e11a544a0da08573c15a524763aa473249698e80
+oid sha256:4caa78e2064d47e2ccbf882089e5403067cd8ee5d79157d96a300242fc6a5b1b
 size 14244

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.972983710766786,
+  "epoch": 4.0,
   "eval_steps": 5000,
-  "global_step": 160000,
+  "global_step": 161088,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2504,6 +2504,20 @@
       "eval_samples_per_second": 440.496,
       "eval_steps_per_second": 13.766,
       "step": 160000
+    },
+    {
+      "epoch": 3.985399284862932,
+      "grad_norm": NaN,
+      "learning_rate": 0.0004900742091849483,
+      "loss": 0.0,
+      "step": 160500
+    },
+    {
+      "epoch": 3.997814858959078,
+      "grad_norm": NaN,
+      "learning_rate": 0.0004900742091849483,
+      "loss": 0.0,
+      "step": 161000
     }
   ],
   "logging_steps": 500,
@@ -2518,12 +2532,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.3978863868862464e+17,
+  "total_flos": 3.4209723453526426e+17,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null