Training in progress, step 9, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8663c5a1b351b7e358ac35fd06d575dd41d4bb2e8ae839c297516acb56ea026
+oid sha256:56c801d2e696b669864092361361536b78bc93719af5bf612a532b0b573ada50
 size 10251668

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cb741a1b6c12fea007d9d6a85137f098d7e74d9ca251e354a6aa242a9cce0ef
+oid sha256:a2ee2f82fa9877270da0bc343a9bd0e3c4839a305e76fea1a709dd5632527e43
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00039009801212554657,
+  "epoch": 0.0005851470181883198,
   "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": 33.222,
       "eval_steps_per_second": 16.614,
       "step": 6
+    },
+    {
+      "epoch": 0.0004551143474798043,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014,
+      "loss": 0.0,
+      "step": 7
+    },
+    {
+      "epoch": 0.000520130682834062,
+      "grad_norm": NaN,
+      "learning_rate": 0.00016,
+      "loss": 0.0,
+      "step": 8
+    },
+    {
+      "epoch": 0.0005851470181883198,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018,
+      "loss": 0.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.0005851470181883198,
+      "eval_loss": NaN,
+      "eval_runtime": 176.1141,
+      "eval_samples_per_second": 36.777,
+      "eval_steps_per_second": 18.391,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 94070133227520.0,
+  "total_flos": 139145405399040.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null