Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:242e6b48563091af59d44cb94bdc8612a85936595e389dc9ffde811ee4c7805f
+oid sha256:e4448e201e452705d1fbabc240201fd82065d02d8aae8ec41177be9cb398a05c
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1536a74ca4489eb937b3ad7adca5c2d6216c23d952ac8ac1fa64693db343f00d
+oid sha256:f843f6a3f71bacf46dc98ceb23f0e02ac7cbcbfd51d09d0cd44288a4480dd9af
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a991012fbb3e0053bc41a0b782b67db27509c27d2801c8bf4a64c3687e55e582
+oid sha256:02d97e2af7e51ba89efcffc7f2a661ca0885e61db7f78987db5df30514ab62df
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0044526901669758815,
+  "epoch": 0.005936920222634508,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -74,6 +74,21 @@
       "eval_samples_per_second": 13.381,
       "eval_steps_per_second": 1.674,
       "step": 15
+    },
+    {
+      "epoch": 0.005343228200371058,
+      "grad_norm": NaN,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.005936920222634508,
+      "eval_loss": NaN,
+      "eval_runtime": 423.9902,
+      "eval_samples_per_second": 13.382,
+      "eval_steps_per_second": 1.675,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -93,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.1288138546610176e+16,
+  "total_flos": 2.8605936172007424e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null