Training in progress, step 39, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59d717237662ebe0e3eb1443064fadff6463b9604761d84bf438962c3ddf5958
+oid sha256:681a3ce1d9d9dd847912717c1b276b28039b14da8644a778a1c80a13b6c8b8f9
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b8655a5a9160ec43d953c1802967f30ec2e3cb247ed234027cc1d2b343c4362
+oid sha256:ea267ef336f545ee13129e04c6900d8f57a1651580fec8eaa3ab7b4252dbc4b4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e65bdb10468d12c8b6afa89fe8730e38a94a4f704431de04b0c1bf27440afce
+oid sha256:75c3c8ae7ddabeca3cb69703f6b35f00b9125a4c27b56ccba4ed0e4669bb5433
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.35738831615120276,
+  "epoch": 0.5360824742268041,
   "eval_steps": 10,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -45,6 +45,21 @@
       "eval_samples_per_second": 29.957,
       "eval_steps_per_second": 3.79,
       "step": 20
+    },
+    {
+      "epoch": 0.41237113402061853,
+      "grad_norm": NaN,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.41237113402061853,
+      "eval_loss": NaN,
+      "eval_runtime": 16.4258,
+      "eval_samples_per_second": 29.831,
+      "eval_steps_per_second": 3.775,
+      "step": 30
     }
   ],
   "logging_steps": 10,
@@ -64,7 +79,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.347919391640781e+16,
+  "total_flos": 3.4797203138543616e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null