Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0c6c3755b837f70a356681e31f15206b86b04b5664fd69d7d10bee3b8c9213a
+oid sha256:038eb1284fa3987668b1523e1bc545fa6b15fd974b056d838ffd12c7b8ea56dd
 size 194840426

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 sha256:6b28ee0addfe1fdb5c9554035d0aace280dc61b8aded9640b8ddc91a063558e8
+oid sha256:22e67cb47ff12ababb2db5752a0059510ef75c13ebd9ed242d32d1eb2ba8aa08
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01914486279514997,
+  "epoch": 0.03828972559029994,
   "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": 0.00027,
       "loss": 0.0,
       "step": 9
+    },
+    {
+      "epoch": 0.02297383535417996,
+      "grad_norm": NaN,
+      "learning_rate": 0.00029265847744427303,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.02871729419272495,
+      "grad_norm": NaN,
+      "learning_rate": 0.00025606601717798207,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.03063178047223995,
+      "eval_loss": NaN,
+      "eval_runtime": 7.5649,
+      "eval_samples_per_second": 21.811,
+      "eval_steps_per_second": 10.972,
+      "step": 16
+    },
+    {
+      "epoch": 0.03446075303126994,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001963525491562421,
+      "loss": 0.0,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1048066098462720.0,
+  "total_flos": 2096132196925440.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null