Training in progress, step 36, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d79035a77b8af93ed625dddbdf69f7b138f37f11242f6e892460a33847f7fc32
+oid sha256:54bc834b0b102b5738c6f329b2c9726532c034ff47b44d3f4004945a23f50cee
 size 49846260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68726575bc3953efd1f0f03d12422c84092fd0f66b74c5722849bdea24401053
+oid sha256:5ea44352ddfa8203e0768cb21a45faa7a448031317064d98fe10d093bef34c2d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06c69db2db6de56f38ba12b474a491d20087e27dc2893a95d6ac7716476ca645
+oid sha256:0aa0f75a1f3e346be25756b578158b09a68943f0b9f1cfe29f97939687f864ef
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03470715835140998,
+  "epoch": 0.039045553145336226,
   "eval_steps": 4,
-  "global_step": 32,
+  "global_step": 36,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -303,6 +303,42 @@
       "eval_samples_per_second": 7.644,
       "eval_steps_per_second": 3.832,
       "step": 32
+    },
+    {
+      "epoch": 0.03579175704989154,
+      "grad_norm": NaN,
+      "learning_rate": 7.66554636144095e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.0368763557483731,
+      "grad_norm": NaN,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.03796095444685466,
+      "grad_norm": NaN,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.039045553145336226,
+      "grad_norm": NaN,
+      "learning_rate": 5.4600950026045326e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.039045553145336226,
+      "eval_loss": NaN,
+      "eval_runtime": 50.8731,
+      "eval_samples_per_second": 7.646,
+      "eval_steps_per_second": 3.833,
+      "step": 36
     }
   ],
   "logging_steps": 1,
@@ -322,7 +358,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8943497373548544.0,
+  "total_flos": 1.0061434545242112e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null