Training in progress, step 30, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c6669e743dba98df7c56600c538e3002b7c4220c38e083ce33cf86167c47839
+oid sha256:4c6e0a255824653706628b9c668bd617f0387d3fbb3db134b83af615c372526a
 size 456603682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4db16b66d924db35ca922619ae5315c9bf623173b1f35fa14ec5ea6c1ca8bb24
+oid sha256:27dda49e3c662d8ae35bbed5c7910e852710db95858fa8dba4b98a5d1c00f698
 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": 0.08417508417508418,
+  "epoch": 0.10101010101010101,
   "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": 5.84,
       "eval_steps_per_second": 2.943,
       "step": 24
+    },
+    {
+      "epoch": 0.09090909090909091,
+      "grad_norm": NaN,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.10101010101010101,
+      "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": 1.4295502946304e+16,
+  "total_flos": 1.71546035355648e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null