Training in progress, step 99, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29e252c04e857beed56ba9c05643777defe5c72e28af079800128dfb1ded5021
+oid sha256:108af482cdb75b573129cbaebd8f88bb31a1fbccb8b40989e9dbb4d554a44130
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd7d8149dd47248022abe05611857b243aff6821b2b6b4c415311ca15e0764f8
+oid sha256:fa726cbc95e031cba4e22bf38e01e0eb453775c5efed064b9f16a7fd6eac04c3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f7d03f1dba06dbe949e0b7294b5a80e81e1c97413b12e930c7d1d62b4e569ba
+oid sha256:43444b0a2aaeda40531bf13a694e8a3eeeb489f81435e9521c012609a5be4dc4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1147227533460803,
+  "epoch": 0.12619502868068833,
   "eval_steps": 9,
-  "global_step": 90,
+  "global_step": 99,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -305,6 +305,35 @@
       "eval_samples_per_second": 14.467,
       "eval_steps_per_second": 1.818,
       "step": 90
+    },
+    {
+      "epoch": 0.11854684512428298,
+      "grad_norm": NaN,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.0,
+      "step": 93
+    },
+    {
+      "epoch": 0.12237093690248566,
+      "grad_norm": NaN,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.0,
+      "step": 96
+    },
+    {
+      "epoch": 0.12619502868068833,
+      "grad_norm": NaN,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.0,
+      "step": 99
+    },
+    {
+      "epoch": 0.12619502868068833,
+      "eval_loss": NaN,
+      "eval_runtime": 91.2841,
+      "eval_samples_per_second": 14.471,
+      "eval_steps_per_second": 1.818,
+      "step": 99
     }
   ],
   "logging_steps": 3,
@@ -324,7 +353,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2145467849493709e+17,
+  "total_flos": 1.3353304431211315e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null