Training in progress, step 99, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b0923ce01a88cf1eb985e1342b5bbaf01782f816914e15f7fb1427307a618d3
+oid sha256:efbf714eb80d6180f98e62c56e81773a6c049aadff9b9898ac60269a30605c67
 size 1001863522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43c89c5409cd0a3da2f5bd67d1cc7a881477591d7daaeacb55ad17c38bf4d43f
+oid sha256:54cec50ef05a433f2c0a5f842fc7bb4ac1eae14355c597349c7f84cc22b0410c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4967fab956f007beafd6b8bc5c5dee4d86950ea055e4ab46c9a7cdc66a69112d
+oid sha256:7041fa0be7432c15ac468c1425bc3b5d595e4b5b769cfa7728743ab80ef12291
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.02357327997817289,
+  "epoch": 0.028811786639989085,
   "eval_steps": 9,
-  "global_step": 81,
+  "global_step": 99,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -276,6 +276,64 @@
       "eval_samples_per_second": 2.623,
       "eval_steps_per_second": 1.311,
       "step": 81
+    },
+    {
+      "epoch": 0.024446364421808923,
+      "grad_norm": NaN,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.0,
+      "step": 84
+    },
+    {
+      "epoch": 0.025319448865444953,
+      "grad_norm": NaN,
+      "learning_rate": 1.2750399292720283e-05,
+      "loss": 0.0,
+      "step": 87
+    },
+    {
+      "epoch": 0.026192533309080987,
+      "grad_norm": NaN,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.026192533309080987,
+      "eval_loss": NaN,
+      "eval_runtime": 4409.9116,
+      "eval_samples_per_second": 2.625,
+      "eval_steps_per_second": 1.312,
+      "step": 90
+    },
+    {
+      "epoch": 0.02706561775271702,
+      "grad_norm": NaN,
+      "learning_rate": 3.7544763546352834e-06,
+      "loss": 0.0,
+      "step": 93
+    },
+    {
+      "epoch": 0.027938702196353055,
+      "grad_norm": NaN,
+      "learning_rate": 1.231165940486234e-06,
+      "loss": 0.0,
+      "step": 96
+    },
+    {
+      "epoch": 0.028811786639989085,
+      "grad_norm": NaN,
+      "learning_rate": 7.709637592770991e-08,
+      "loss": 0.0,
+      "step": 99
+    },
+    {
+      "epoch": 0.028811786639989085,
+      "eval_loss": NaN,
+      "eval_runtime": 4413.4607,
+      "eval_samples_per_second": 2.623,
+      "eval_steps_per_second": 1.311,
+      "step": 99
     }
   ],
   "logging_steps": 3,
@@ -295,7 +353,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.284972626896486e+17,
+  "total_flos": 1.0126077655095706e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null