Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6df3835ebb8a410086e40775839dcd215ef004799cfb91fcd99f06ed300090ac
+oid sha256:9f6eebfa927dd597f5b2467576d1b4e5a74f50d01f39872c16db123c54f82a8c
 size 148047722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa4e7f8e1a356dfd91af4f6dc97d320355e9398087d782439c72ed46d0880789
+oid sha256:24494dcec7b740a1ea000f51e050a81a7bb6c3b4ff898bada8de0f3588a1a971
 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": 0.00016848844801078326,
+  "epoch": 0.0003369768960215665,
   "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": 0.0002021861376129399,
+      "grad_norm": NaN,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.0002527326720161749,
+      "grad_norm": NaN,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.00026958151681725324,
+      "eval_loss": NaN,
+      "eval_runtime": 1069.7599,
+      "eval_samples_per_second": 23.36,
+      "eval_steps_per_second": 11.68,
+      "step": 16
+    },
+    {
+      "epoch": 0.0003032792064194099,
+      "grad_norm": NaN,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.0,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 653134418411520.0,
+  "total_flos": 1306268836823040.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null