Training in progress, step 30, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:038eb1284fa3987668b1523e1bc545fa6b15fd974b056d838ffd12c7b8ea56dd
+oid sha256:7439a38915696521058ab6fe1b0e63d89af65d071540a1be8e5afe0a81b55ad6
 size 194840426

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24494dcec7b740a1ea000f51e050a81a7bb6c3b4ff898bada8de0f3588a1a971
+oid sha256:cdf0878306dfabad22df73aa5835c9e34d3f3302f1c21c247c88f8c2ea4fd50f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22e67cb47ff12ababb2db5752a0059510ef75c13ebd9ed242d32d1eb2ba8aa08
+oid sha256:204b783eee4578e262211ed4342a25463d72b9f2b43a34a1fb0c83abcbfcca96
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03828972559029994,
+  "epoch": 0.0574345883854499,
   "eval_steps": 8,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,42 @@
       "learning_rate": 0.0001963525491562421,
       "loss": 0.0,
       "step": 18
+    },
+    {
+      "epoch": 0.04020421186981493,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012653483024396533,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.04594767070835992,
+      "grad_norm": NaN,
+      "learning_rate": 6.183221215612904e-05,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.04594767070835992,
+      "eval_loss": NaN,
+      "eval_runtime": 7.5799,
+      "eval_samples_per_second": 21.768,
+      "eval_steps_per_second": 10.95,
+      "step": 24
+    },
+    {
+      "epoch": 0.05169112954690491,
+      "grad_norm": NaN,
+      "learning_rate": 1.634902137174483e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.0574345883854499,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -87,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2096132196925440.0,
+  "total_flos": 3144198295388160.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null