Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aabdf806b6dc8aa08fcc47aa653cd3948303217ffc47cd4409799423b279d04f
+oid sha256:53590e2d62b9c7c6849c90cf431d1bc80555b8303247bbb4b042a3994b74d366
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94eb3af0be59b8022e591483a56634de67b6ec709d4a7976205940027b927a1a
+oid sha256:a8d0ca5f94c74be21f7e258f478e4f1bcf339ab697a95d852a0fd9b800d39d6b
 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": 0.0007591285204585136,
+  "epoch": 0.0015182570409170272,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 13.192,
       "eval_steps_per_second": 6.597,
       "step": 10
+    },
+    {
+      "epoch": 0.0009109542245502164,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.0011386927806877705,
+      "grad_norm": NaN,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.0011386927806877705,
+      "eval_loss": NaN,
+      "eval_runtime": 420.5451,
+      "eval_samples_per_second": 13.19,
+      "eval_steps_per_second": 6.596,
+      "step": 15
+    },
+    {
+      "epoch": 0.0013664313368253246,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.0015182570409170272,
+      "eval_loss": NaN,
+      "eval_runtime": 707.8603,
+      "eval_samples_per_second": 7.836,
+      "eval_steps_per_second": 3.919,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -71,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3515647493406720.0,
+  "total_flos": 7031294986813440.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null