Training in progress, step 30, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60d9dd7a962f874818ebfbca1e6c651b43dbb13b53ec20c040106a4020698db5
+oid sha256:1f35714587ac1df395e60d7cc5e7528459c0bd0a9fb3b87890bf58aecac04c99
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb7c67821feeaa234c6c478af37337bb11cb486a1c28ab9734deba949ae773e5
+oid sha256:14644b86c32e9a50267a521abd11f75aae99201cf6e084821f2934b401e4ca7b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95758e6aadaa863940ee26d7d4bc2716664c72b77251097ec968b5c9819c88ad
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03926701570680628,
+  "epoch": 0.04712041884816754,
   "eval_steps": 8,
-  "global_step": 25,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -95,6 +95,20 @@
       "eval_samples_per_second": 7.991,
       "eval_steps_per_second": 4.005,
       "step": 24
+    },
+    {
+      "epoch": 0.042408376963350786,
+      "grad_norm": NaN,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.04712041884816754,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -109,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.3857361584128e+16,
+  "total_flos": 2.86288339009536e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null