Training in progress, step 63, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:167982673263fefed59672346edc9f1210361bb99721b1c2d1a3bd53cefcce5d
+oid sha256:560328ad1ead82256b7dd494b6819dd6ffa7f9002401cfebbad9117059fb87d8
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3faf2db23915d2ffb11d5aa51406a3f749dda121e2e62e1166baa68c864f325f
+oid sha256:1ea8b6d28d0d1b59e5b3c8956211f04c51f1289465720c6ed12b7be9cf41af89
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f449418676ee143dc49fe68c0605204371c150076b291ef62a6b7b955efd8f73
+oid sha256:03b2d2818ab3151c9ed744a4cb682fe1730b800005846a54cc3da941ac8ce20d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.3730283911671926,
+  "epoch": 1.6001577287066246,
   "eval_steps": 9,
-  "global_step": 54,
+  "global_step": 63,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -189,6 +189,35 @@
       "eval_samples_per_second": 8.708,
       "eval_steps_per_second": 4.354,
       "step": 54
+    },
+    {
+      "epoch": 1.4487381703470033,
+      "grad_norm": NaN,
+      "learning_rate": 0.00011175373974578378,
+      "loss": 0.0,
+      "step": 57
+    },
+    {
+      "epoch": 1.524447949526814,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 60
+    },
+    {
+      "epoch": 1.6001577287066246,
+      "grad_norm": NaN,
+      "learning_rate": 8.824626025421626e-05,
+      "loss": 0.0,
+      "step": 63
+    },
+    {
+      "epoch": 1.6001577287066246,
+      "eval_loss": NaN,
+      "eval_runtime": 15.3973,
+      "eval_samples_per_second": 8.703,
+      "eval_steps_per_second": 4.351,
+      "step": 63
     }
   ],
   "logging_steps": 3,
@@ -208,7 +237,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.9861872595789414e+17,
+  "total_flos": 3.477585163053957e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null