Training in progress, step 15, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e302cb9d181a612d7cf18e36c3480699649aeb15d7695ed2d8b072942fd25923
+oid sha256:bebec76956f7aaf741e594dc53a0b27608dea69de2c22e0d3b457654df9f17d2
 size 148047722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81dd3c316299ef2e40bd3ba7fb6631b0d1a0c4b5fd887535e17137b2a79683cc
+oid sha256:dac7bede21f3322345b0b38171a42d331c8328d417c4f3993654026282712c53
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:8bb840dbc65c27ef8840855786e35bfea033749e5d7571cf601f6645aa29cc1e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.09142857142857143,
+  "epoch": 0.13714285714285715,
   "eval_steps": 3,
-  "global_step": 10,
+  "global_step": 15,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -109,6 +109,57 @@
       "learning_rate": 0.0002,
       "loss": 0.0,
       "step": 10
+    },
+    {
+      "epoch": 0.10057142857142858,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 0.0,
+      "step": 11
+    },
+    {
+      "epoch": 0.10971428571428571,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.10971428571428571,
+      "eval_loss": NaN,
+      "eval_runtime": 4.0214,
+      "eval_samples_per_second": 23.126,
+      "eval_steps_per_second": 11.687,
+      "step": 12
+    },
+    {
+      "epoch": 0.11885714285714286,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.0,
+      "step": 13
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": NaN,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 0.0,
+      "step": 14
+    },
+    {
+      "epoch": 0.13714285714285715,
+      "grad_norm": NaN,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.13714285714285715,
+      "eval_loss": NaN,
+      "eval_runtime": 4.004,
+      "eval_samples_per_second": 23.227,
+      "eval_steps_per_second": 11.738,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -128,7 +179,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2612537673646080.0,
+  "total_flos": 3918806510469120.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null