Training in progress, step 18, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe6761db302d71b032c9f7d45329ea3f0288ae940e638bcaaf42d7ee0af58561
+oid sha256:73eb267d16bbbf5c8481e31e433eccf43fa4c0d767d0aacdd64de2f65cb7adc0
 size 150486964

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b0bb62c383dd93bb7277f2f4f3ecc51f45d7c7b1a6c0012d26a10c5589360f2
+oid sha256:6122816c42780a868d77d7c48cf66d125e516c03075f49e683bda8693a41f3d6
 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": 0.07964601769911504,
+  "epoch": 0.1592920353982301,
   "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": 36.244,
       "eval_steps_per_second": 4.578,
       "step": 9
+    },
+    {
+      "epoch": 0.10619469026548672,
+      "grad_norm": NaN,
+      "learning_rate": 9.987820251299122e-05,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.13274336283185842,
+      "grad_norm": NaN,
+      "learning_rate": 9.924038765061042e-05,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.1592920353982301,
+      "grad_norm": NaN,
+      "learning_rate": 9.806308479691595e-05,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.1592920353982301,
+      "eval_loss": NaN,
+      "eval_runtime": 5.2369,
+      "eval_samples_per_second": 36.281,
+      "eval_steps_per_second": 4.583,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2449302576168960.0,
+  "total_flos": 4898605152337920.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null