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 sha256:24291d0aa47fc1cf29ad8a1a3f799e2b038515b459a034ba33fe6c34f5fd21ff
+oid sha256:fd6ce35db78642b81a936d63e81073fe945f996b3d85633986eb9a2d8c6d6f07
 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": 0.014805675508945095,
+  "epoch": 0.022208513263417645,
   "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": 19.652,
       "eval_steps_per_second": 9.884,
       "step": 6
+    },
+    {
+      "epoch": 0.01727328809376928,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014,
+      "loss": 0.0,
+      "step": 7
+    },
+    {
+      "epoch": 0.01974090067859346,
+      "grad_norm": NaN,
+      "learning_rate": 0.00016,
+      "loss": 0.0,
+      "step": 8
+    },
+    {
+      "epoch": 0.022208513263417645,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018,
+      "loss": 0.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.022208513263417645,
+      "eval_loss": NaN,
+      "eval_runtime": 8.6701,
+      "eval_samples_per_second": 19.723,
+      "eval_steps_per_second": 9.919,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2067768457297920.0,
+  "total_flos": 3137303866245120.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null