Training in progress, step 9, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c809cbd26e6e1134a0374f4d3818e3d0012028d43b20c86c2a3a689b843f56b
+oid sha256:6504cfbd1dd963b655dd975f320308f8e764b37597448e504e8ea559cc339936
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c9d7047b5ecedfc11ee031ca60ced77c4f080ba57be142f62761b013a312681
+oid sha256:756f5354e70cf8ea389a55b973a7a83a0698ead411ced9a550dad53863f8e805
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92b4cf85d7ba7a497f88ff799bf4dec5af7dd95be6e00f78bf46ba5deb56bbf8
+oid sha256:1eca0ddb3ec890c90e8e6e7325bec40cdb8b59e4bebf5c0da8473b02809de875
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00046848693360661736,
+  "epoch": 0.0007027304004099261,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 30.931,
       "eval_steps_per_second": 15.466,
       "step": 6
+    },
+    {
+      "epoch": 0.0005465680892077203,
+      "grad_norm": NaN,
+      "learning_rate": 7e-05,
+      "loss": 0.0,
+      "step": 7
+    },
+    {
+      "epoch": 0.0006246492448088232,
+      "grad_norm": NaN,
+      "learning_rate": 8e-05,
+      "loss": 253.8839,
+      "step": 8
+    },
+    {
+      "epoch": 0.0007027304004099261,
+      "grad_norm": NaN,
+      "learning_rate": 9e-05,
+      "loss": 0.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.0007027304004099261,
+      "eval_loss": NaN,
+      "eval_runtime": 697.6516,
+      "eval_samples_per_second": 30.918,
+      "eval_steps_per_second": 15.459,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6134351297249280.0,
+  "total_flos": 9552061305716736.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null