Training in progress, step 30, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b612858315c44145bffd1c98ff3a3c5bb38c9a7bf38c41190c9f0e21ca48f05d
+oid sha256:9c2d6c7530a868a4c368dfa792f8950b20bcbe5ea6bca988b21eab7503948d49
 size 503884594

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37a7b1eefc0898a8d01ccd457dcb62891acd5769ebfaef6b5416f953f1df19c1
+oid sha256:5650086ba9cea3a2f21eb35e293f4f9495d4314840a20e19a7232bc4ba101bc4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e2686563472cd649084082a2c329fd627ce86023a87d1ac3f5dd126e100dfda
+oid sha256:0ec942292267bb06cc495f28f765abdfdf101d23971c1de481c4ea2a744d43b7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.037968675842429994,
+  "epoch": 0.05695301376364499,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 4.093,
       "eval_steps_per_second": 2.046,
       "step": 20
+    },
+    {
+      "epoch": 0.03986710963455149,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014067366430758004,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.045562411010915994,
+      "grad_norm": NaN,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.04746084480303749,
+      "eval_loss": NaN,
+      "eval_runtime": 54.2597,
+      "eval_samples_per_second": 4.091,
+      "eval_steps_per_second": 2.046,
+      "step": 25
+    },
+    {
+      "epoch": 0.051257712387280496,
+      "grad_norm": NaN,
+      "learning_rate": 7.920883091822408e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.05695301376364499,
+      "grad_norm": NaN,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.05695301376364499,
+      "eval_loss": NaN,
+      "eval_runtime": 54.2539,
+      "eval_samples_per_second": 4.092,
+      "eval_steps_per_second": 2.046,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -108,7 +152,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.048251595751424e+16,
+  "total_flos": 1.572377393627136e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null