Training in progress, step 16, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7655c7b685c399d19d65a82d649ccd3cbe037a52d8866bc9d1421efefb1513a6
+oid sha256:a49a55118c235785ce61ce68518afe096c42c1da0e15ec7b432baddb3bd19fca
 size 335922386

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea12441da8aa5cf6a4fba0da8d5eeb66363e9327da1fdd4b5c2c7b1f575bddda
+oid sha256:79b86ff0a5072134cac7bc6d03fa050eb39fd904cc925d808c31e906cc8e2aad
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fd42fc88546c9b34bc2fbf63a1b59a7f4813abff981c3e9be6ae79921af6f2a
+oid sha256:4d55a315fe2b1bf0fbdcce0639e6180d7cc5db0fe45b7a48f9754981c7dc610e
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c1f81faa4b8d80993a6133b2de45d1509d0e26c7e0b7f8ce631a8c84e5145c4
+oid sha256:de6a090a8d55e4fd5919a1b3bec8508dee55a83b95323dc92338cba6bfb71872
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9dfb88b67d8d33eccaa87f24678bef9c55b93fbb8ffa16b9919e8d6782593f15
+oid sha256:30b4357440ab6d2b2572106bac312d01b38dfabe56ce03386f7019dcd63b7cce
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68888158764ed5e658b457a541f86335ea31432325308674d2962aa98e037fa4
+oid sha256:5b52924c88c1c80163d374a6650253dd74b8b46052a3da6fc5e4076e57b5effa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.08540925266903915,
+  "epoch": 0.11387900355871886,
   "eval_steps": 4,
-  "global_step": 12,
+  "global_step": 16,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -123,6 +123,42 @@
       "eval_samples_per_second": 32.935,
       "eval_steps_per_second": 4.169,
       "step": 12
+    },
+    {
+      "epoch": 0.09252669039145907,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019723699203976766,
+      "loss": 0.0,
+      "step": 13
+    },
+    {
+      "epoch": 0.099644128113879,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.0,
+      "step": 14
+    },
+    {
+      "epoch": 0.10676156583629894,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001923879532511287,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.11387900355871886,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001891006524188368,
+      "loss": 0.0,
+      "step": 16
+    },
+    {
+      "epoch": 0.11387900355871886,
+      "eval_loss": NaN,
+      "eval_runtime": 7.1925,
+      "eval_samples_per_second": 32.951,
+      "eval_steps_per_second": 4.171,
+      "step": 16
     }
   ],
   "logging_steps": 1,
@@ -142,7 +178,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.5610589610901504e+16,
+  "total_flos": 4.748078614786867e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null