Training in progress, step 72, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:588031339b5de9b3ea98d51426343071d246ece3f8daf16cf691744c0fd09f02
+oid sha256:6e1101ae4a140d8c48d78c060b5b1a82992299967e2d9bafce48d694ba81133f
 size 240145026

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca3c1de581a0daca6b2e6f170eac9e4d1a25aac1c30727383c2fe2ead7db79c4
+oid sha256:ee9627d324fa9d9eaa4cfb33dcf81f82b5bc2076fb94fc413cc20a4173caed78
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03b2d2818ab3151c9ed744a4cb682fe1730b800005846a54cc3da941ac8ce20d
+oid sha256:3f9245597e5014ecf432f2646dbac4f88c26cbc6ab1676ee7be71281b45d826d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.005660456823574005,
+  "epoch": 0.006469093512656007,
   "eval_steps": 9,
-  "global_step": 63,
+  "global_step": 72,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -218,6 +218,35 @@
       "eval_samples_per_second": 26.823,
       "eval_steps_per_second": 13.411,
       "step": 63
+    },
+    {
+      "epoch": 0.00593000238660134,
+      "grad_norm": NaN,
+      "learning_rate": 7.66554636144095e-05,
+      "loss": 0.0,
+      "step": 66
+    },
+    {
+      "epoch": 0.006199547949628673,
+      "grad_norm": NaN,
+      "learning_rate": 6.538829429225069e-05,
+      "loss": 0.0,
+      "step": 69
+    },
+    {
+      "epoch": 0.006469093512656007,
+      "grad_norm": NaN,
+      "learning_rate": 5.4600950026045326e-05,
+      "loss": 0.0,
+      "step": 72
+    },
+    {
+      "epoch": 0.006469093512656007,
+      "eval_loss": NaN,
+      "eval_runtime": 1397.7111,
+      "eval_samples_per_second": 26.822,
+      "eval_steps_per_second": 13.411,
+      "step": 72
     }
   ],
   "logging_steps": 3,
@@ -237,7 +266,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.573477158977536e+16,
+  "total_flos": 7.510245941182464e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null