Training in progress, step 45, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e1e79f5c8f2683015511e3d0b65d6258a92eaa553cbb5272cdab0ff9214d3ac
+oid sha256:b6422b36d4172a9861478d9b7cd296a64984caae03646b3b89ef637782f4ad0b
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10350b5619e7d96fb7f3bffab3732b8b921da553987e25ecf13af945b954a09e
+oid sha256:49324b9e90e4a3300216fe09ec318d103f16e5de8c543c825c0b873b9acee835
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b09cef78339a08679f2a6cf4a4b56eca3094fb6b859867afd839be3db1415460
+oid sha256:0896677f34f08366c4c71a3f69133212afc490296ec7ee225b8aefde1f38f24c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.045889101338432124,
+  "epoch": 0.05736137667304015,
   "eval_steps": 9,
-  "global_step": 36,
+  "global_step": 45,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -131,6 +131,35 @@
       "eval_samples_per_second": 14.473,
       "eval_steps_per_second": 1.819,
       "step": 36
+    },
+    {
+      "epoch": 0.0497131931166348,
+      "grad_norm": NaN,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.05353728489483748,
+      "grad_norm": NaN,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.05736137667304015,
+      "grad_norm": NaN,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.05736137667304015,
+      "eval_loss": NaN,
+      "eval_runtime": 91.2609,
+      "eval_samples_per_second": 14.475,
+      "eval_steps_per_second": 1.819,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -150,7 +179,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.831346326870426e+16,
+  "total_flos": 6.039182908588032e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null