Training in progress, step 10, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8c9c750dc3f88bb3640705e7f35ef7c14563a8cf585855709ba483e025a3c7b
+oid sha256:e07f600fb597088a902196bf21c0d0d7fba2f5afa28d2b50b63125f1fa85e4de
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83e1d42fa3a43f0b49fecc1fb9869481eef60e0607192a6ff7e39173952f7302
+oid sha256:71e9af821c38bae7b342c85301f6dc4d8d96eaade7716ea8e604522769dc1743
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0034334763948497852,
+  "epoch": 0.005722460658082976,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,42 @@
       "eval_samples_per_second": 30.109,
       "eval_steps_per_second": 15.054,
       "step": 6
+    },
+    {
+      "epoch": 0.004005722460658083,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014,
+      "loss": 0.0,
+      "step": 7
+    },
+    {
+      "epoch": 0.004577968526466381,
+      "grad_norm": NaN,
+      "learning_rate": 0.00016,
+      "loss": 0.0,
+      "step": 8
+    },
+    {
+      "epoch": 0.005150214592274678,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018,
+      "loss": 0.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.005150214592274678,
+      "eval_loss": NaN,
+      "eval_runtime": 24.3782,
+      "eval_samples_per_second": 30.191,
+      "eval_steps_per_second": 15.095,
+      "step": 9
+    },
+    {
+      "epoch": 0.005722460658082976,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -87,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1155977655091200.0,
+  "total_flos": 1895803354349568.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null