Training in progress, step 99, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58b6862caf6ead58311a3810175e0702b332df373b20b0327302a9bf902ca58c
+oid sha256:075f7693f79bc421c2556517c3acd5fd5e9d00c5f65d803e8a7b02dd73ce3c1f
 size 40177764

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:361b31f47cacf980fa5dee9699485958c7673fa2b5614795ec67434d52c36a9c
+oid sha256:27e0c39fd304bfb39141f0e074f03b801127bca16c6a3cdccf8df73fd567ffc9
 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": 0.10230179028132992,
+  "epoch": 0.11253196930946291,
   "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": 78.544,
       "eval_steps_per_second": 19.715,
       "step": 90
+    },
+    {
+      "epoch": 0.10571184995737426,
+      "grad_norm": NaN,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.0,
+      "step": 93
+    },
+    {
+      "epoch": 0.10912190963341858,
+      "grad_norm": NaN,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.0,
+      "step": 96
+    },
+    {
+      "epoch": 0.11253196930946291,
+      "grad_norm": NaN,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.0,
+      "step": 99
+    },
+    {
+      "epoch": 0.11253196930946291,
+      "eval_loss": NaN,
+      "eval_runtime": 9.1912,
+      "eval_samples_per_second": 80.621,
+      "eval_steps_per_second": 20.237,
+      "step": 99
     }
   ],
   "logging_steps": 3,
@@ -324,7 +353,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1195915161894912.0,
+  "total_flos": 1310253303988224.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null