Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd8bcef2fc4ffca527e08ee7176b76c319452c37b0f0e0cb73fdf610c8c9f54f
+oid sha256:71a230936ecb06cdaa130432ec53a661294fe76eb88f1308683fe52cf1526290
 size 69732794

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46701aacbf54025d1d0ab0c4ac8a896380e50265c94b575814dba5115273f574
+oid sha256:4a427adcb42a5e21efe60aeff1fc331ce48c7ff904cf00d837fab2409ae1ed3f
 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": 0.00011539415759380103,
+  "epoch": 0.00023078831518760207,
   "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": 0.00013847298911256122,
+      "grad_norm": NaN,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.00017309123639070153,
+      "grad_norm": NaN,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.00018463065215008163,
+      "eval_loss": NaN,
+      "eval_runtime": 1328.9321,
+      "eval_samples_per_second": 27.457,
+      "eval_steps_per_second": 13.729,
+      "step": 16
+    },
+    {
+      "epoch": 0.00020770948366884183,
+      "grad_norm": NaN,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.0,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 158917617254400.0,
+  "total_flos": 317835234508800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null