Training in progress, step 18, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f386a9310fd318404114566bc2724a402a7a1dcf8857bf713248bd6303ce30b
+oid sha256:fd5ba4b98176cb6f867ce577ee3ce841f53e16fca2f79ce8c5ac66ab23f80e60
 size 463916180

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:441ae27bf550aa6cb16faac3ab4bddeaaf91f0b7062a66779ba838b33537e2b4
+oid sha256:c6348a493fcfdbf7bdbd4d898957add20d5f39f4a3ba3bc86aa50523a2dfb1f4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1eca0ddb3ec890c90e8e6e7325bec40cdb8b59e4bebf5c0da8473b02809de875
+oid sha256:5ed723721bc2dad2381ab5522e40123ba4aa738fa3e449c48809fa9c2697eb95
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.05187319884726225,
+  "epoch": 0.1037463976945245,
   "eval_steps": 9,
-  "global_step": 9,
+  "global_step": 18,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 9.532,
       "eval_steps_per_second": 1.204,
       "step": 9
+    },
+    {
+      "epoch": 0.069164265129683,
+      "grad_norm": NaN,
+      "learning_rate": 9.987820251299122e-05,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.08645533141210375,
+      "grad_norm": NaN,
+      "learning_rate": 9.924038765061042e-05,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.1037463976945245,
+      "grad_norm": NaN,
+      "learning_rate": 9.806308479691595e-05,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.1037463976945245,
+      "eval_loss": NaN,
+      "eval_runtime": 30.8365,
+      "eval_samples_per_second": 9.502,
+      "eval_steps_per_second": 1.2,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.088819058802688e+16,
+  "total_flos": 4.235660869238784e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null