Training in progress, step 36, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f20830c6caf4c7dca95f08a3c501b829938736d1cacc80dd700af419bb1e9ac7
+oid sha256:b411d8f3e7add8b3d93adcf458ccd53cd6ff52a54095368d2ebd43894569e445
 size 240145026

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f76e123acfda2786d4800d79a98e4806fa0178234cf8d24804c284042464c169
+oid sha256:e40dca7108cb0726f72ab1eed645c75414cec0897da6df467a42096be439a048
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:014898519bf1f31fef4a7ab39caf2eaa1ff4fbc5662e969211f7676259067ad2
+oid sha256:f1fbe8f3807fcf2c9b342444bf912c2b4a5837aba74951c80e3f443bde6ab488
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0024259100672460025,
+  "epoch": 0.0032345467563280033,
   "eval_steps": 9,
-  "global_step": 27,
+  "global_step": 36,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,6 +102,35 @@
       "eval_samples_per_second": 26.825,
       "eval_steps_per_second": 13.412,
       "step": 27
+    },
+    {
+      "epoch": 0.002695455630273336,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001923879532511287,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.00296500119330067,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018724960070727972,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.0032345467563280033,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.0032345467563280033,
+      "eval_loss": NaN,
+      "eval_runtime": 1397.6922,
+      "eval_samples_per_second": 26.823,
+      "eval_steps_per_second": 13.411,
+      "step": 36
     }
   ],
   "logging_steps": 3,
@@ -121,7 +150,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.819963756740608e+16,
+  "total_flos": 3.756732538945536e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null