Training in progress, step 9, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87fe88de4833fabc6ccb9c3dfdbd970c638bdfca11344dd77472ca8d985c95a3
+oid sha256:0ccbd87296fe7edfb62b00c7c2773bb390eed1a2e39b5709993405542a238de7
 size 58562260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9097bc16a0c76788ee7a5f684c31f0d7c36e318e22db7989c97c5d118999d57e
+oid sha256:17989e4b174913a94301e4261e049da6093277462fff73f01ba67f3ddd0055ec
 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": 0.02203856749311295,
+  "epoch": 0.03305785123966942,
   "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": 19.417,
       "eval_steps_per_second": 9.793,
       "step": 6
+    },
+    {
+      "epoch": 0.025711662075298437,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014,
+      "loss": 0.0,
+      "step": 7
+    },
+    {
+      "epoch": 0.02938475665748393,
+      "grad_norm": NaN,
+      "learning_rate": 0.00016,
+      "loss": 0.0,
+      "step": 8
+    },
+    {
+      "epoch": 0.03305785123966942,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018,
+      "loss": 0.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.03305785123966942,
+      "eval_loss": NaN,
+      "eval_runtime": 5.9337,
+      "eval_samples_per_second": 19.381,
+      "eval_steps_per_second": 9.775,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1853861375508480.0,
+  "total_flos": 2923396784455680.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null