Training in progress, step 72, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bfc38de157b483a196afcac9a46c29141384848365c412e307d791d2a5f2008
+oid sha256:0d3ddcb24bb843733a9b2da4df67da4ca5cc70cad9e3668614243fefd97bbd2b
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f249013890690838eaacac0577330eb1ce20bd7f29839b9b80b34a4939f21da
+oid sha256:9c61097b74f07da4d84f1931679522624f41c17c7d57fd72f73912b3ea5f868c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d85eac2daddfe8e3f78a5d6ef1e9ba13c04651694635a9ed76369a20726389db
+oid sha256:8d43bd90ad476e419738deb9472ad85fd5991005a147e1627aa99867bdfc5655
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.07062532842879664,
+  "epoch": 0.08071466106148187,
   "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": 8.27,
       "eval_steps_per_second": 4.136,
       "step": 63
+    },
+    {
+      "epoch": 0.07398843930635839,
+      "grad_norm": NaN,
+      "learning_rate": 5.7491597710807114e-05,
+      "loss": 0.0,
+      "step": 66
+    },
+    {
+      "epoch": 0.07735155018392012,
+      "grad_norm": NaN,
+      "learning_rate": 4.904122071918801e-05,
+      "loss": 0.0,
+      "step": 69
+    },
+    {
+      "epoch": 0.08071466106148187,
+      "grad_norm": NaN,
+      "learning_rate": 4.095071251953399e-05,
+      "loss": 0.0,
+      "step": 72
+    },
+    {
+      "epoch": 0.08071466106148187,
+      "eval_loss": NaN,
+      "eval_runtime": 363.4291,
+      "eval_samples_per_second": 8.268,
+      "eval_steps_per_second": 4.136,
+      "step": 72
     }
   ],
   "logging_steps": 3,
@@ -237,7 +266,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.082542199470817e+17,
+  "total_flos": 4.684945639593738e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null