Training in progress, step 45, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b390765ddd6d2367e2df9d01b65d75cabeee049367f967a6b89e59b61d4c28f
+oid sha256:ede24956eeef046345f67ac667a3442af77e2f5cc8313d231ea9bf142fb355b3
 size 463916180

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd9b8b454a3a12de31f0095de92dbcd209883ef391cb6254e0cdac318f6f69dd
+oid sha256:0a64d59455c25e54ebdfd555df5ffaa4710f3501d9e958743fb96a41e493b3ec
 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": 0.207492795389049,
+  "epoch": 0.25936599423631124,
   "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": 9.514,
       "eval_steps_per_second": 1.201,
       "step": 36
+    },
+    {
+      "epoch": 0.22478386167146974,
+      "grad_norm": NaN,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.2420749279538905,
+      "grad_norm": NaN,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.25936599423631124,
+      "grad_norm": NaN,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.25936599423631124,
+      "eval_loss": NaN,
+      "eval_runtime": 30.846,
+      "eval_samples_per_second": 9.499,
+      "eval_steps_per_second": 1.2,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -150,7 +179,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.471321738477568e+16,
+  "total_flos": 1.0560140797280256e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null