Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c142876c6213b1cd007d2c596234069c634bd9889d0f7f14d64f222a25db6d0c
+oid sha256:9d41f4a21bdbeb71ccbfdfbd3c1e51e850c6b98638681a203e1acf9bd628d6a1
 size 524761122

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:139902d6f1c5ecb87ebd67e8bc0b0f5c60f709abf28f12ffe9c8398dabb0497f
+oid sha256:92b26122dca29c86eac41c5225db68a7b75a12c7d3af23baa075907184dcb057
 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": 0.03469210754553339,
+  "epoch": 0.06938421509106678,
   "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": 0.04163052905464007,
+      "grad_norm": NaN,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.05203816131830009,
+      "grad_norm": NaN,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.055507372072853424,
+      "eval_loss": NaN,
+      "eval_runtime": 23.3703,
+      "eval_samples_per_second": 5.22,
+      "eval_steps_per_second": 2.61,
+      "step": 16
+    },
+    {
+      "epoch": 0.062445793581960105,
+      "grad_norm": NaN,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.0,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6813256777728000.0,
+  "total_flos": 1.3626513555456e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null