Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e6bd90112056d7e13e4968611dad457d290c004bf507a5a6a5c0e016dad95f4
+oid sha256:bb7fae141c50fec6109eccb02250d064ba0e919afbb00943513190b67752ec6a
 size 39428606

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3abfd5193fedbfce48db3c4617b73cf1dac15d9205c9e7cc9df3cb65366af372
+oid sha256:b6ac1651ae8cf71243f5f0bbf70998708eb3e053b590724c9133801836ac2fe6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00011747430249632892,
+  "epoch": 0.00023494860499265785,
   "eval_steps": 8,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "learning_rate": 9e-05,
       "loss": 0.0,
       "step": 9
+    },
+    {
+      "epoch": 0.0001409691629955947,
+      "grad_norm": NaN,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.0001762114537444934,
+      "grad_norm": NaN,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.00018795888399412628,
+      "eval_loss": NaN,
+      "eval_runtime": 679.5473,
+      "eval_samples_per_second": 52.745,
+      "eval_steps_per_second": 26.373,
+      "step": 16
+    },
+    {
+      "epoch": 0.00021145374449339208,
+      "grad_norm": NaN,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.0,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 68252427878400.0,
+  "total_flos": 128314564411392.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null