Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c0c826e8c426217592a6ed521887632322765459be0a6dec5a9a2d9eab024b5
+oid sha256:1074e5294fd89ce499f1fe00ede0d18c3eec9b53d402258b846bccfc050f41d1
 size 101184122

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4fe6edaed203836109846c9373c72af92af579005375d18dfc07a6ffc24fda9
+oid sha256:ccd1574947e49e066e75130f0763899ec12b864a5ed89b94808408d4da676a13
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.001732051615138131,
+  "epoch": 0.003464103230276262,
   "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": 0.00018,
       "loss": 0.0,
       "step": 9
+    },
+    {
+      "epoch": 0.0020784619381657575,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.002598077422707197,
+      "grad_norm": NaN,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.0027712825842210096,
+      "eval_loss": NaN,
+      "eval_runtime": 56.1127,
+      "eval_samples_per_second": 43.324,
+      "eval_steps_per_second": 21.671,
+      "step": 16
+    },
+    {
+      "epoch": 0.003117692907248636,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.0,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 514684386017280.0,
+  "total_flos": 1029368772034560.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null