Training in progress, step 15, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed52651882f3ad60fa16b5550b578219df457978330e3d83cb4c02f027cb591a
+oid sha256:01c2c2126eb66446831668f44cab95658b5612fd6e057584e33f7565803d2c71
 size 335810490

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8256a51c921e3764623587232574eeea4ef70bf2e730f79b7a5b429639bc4f0
+oid sha256:18c91c570b07019a1068294715f275674400f8131145c713b4a085e0034f5c76
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:55cc6a3635d19619caf820a77458fa3cfe7756f7bb9d10678c62733cb46f36c0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.024198427102238355,
+  "epoch": 0.036297640653357534,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 15,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 8.997,
       "eval_steps_per_second": 4.498,
       "step": 10
+    },
+    {
+      "epoch": 0.02661826981246219,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.0,
+      "step": 11
+    },
+    {
+      "epoch": 0.029038112522686024,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.03145795523290986,
+      "grad_norm": NaN,
+      "learning_rate": 0.00015877852522924732,
+      "loss": 0.0,
+      "step": 13
+    },
+    {
+      "epoch": 0.0338777979431337,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.0,
+      "step": 14
+    },
+    {
+      "epoch": 0.036297640653357534,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.036297640653357534,
+      "eval_loss": NaN,
+      "eval_runtime": 19.3315,
+      "eval_samples_per_second": 9.001,
+      "eval_steps_per_second": 4.5,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7418872835604480.0,
+  "total_flos": 1.112830925340672e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null