Training in progress, step 9, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee28496989d105945f7c6121bf5a20aa7aae99d28fa7fb5573512c7f71c18f12
+oid sha256:3eea4fa638baaf8d472a3a354c065c1e117bae3812cab21611a3e83f5012d229
 size 25152500

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80b0a5a6c037b9f4df9580eca1f830194a5774c8376183b2a3644a26bb0057fa
+oid sha256:1afaf5931a77d79e8a92b2add18ddb87ec49d3811af688bc81ad1bf47a330da9
 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": 0.001131648434552999,
+  "epoch": 0.0016974726518294984,
   "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": 42.668,
       "eval_steps_per_second": 21.344,
       "step": 6
+    },
+    {
+      "epoch": 0.0013202565069784986,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014,
+      "loss": 0.0,
+      "step": 7
+    },
+    {
+      "epoch": 0.0015088645794039985,
+      "grad_norm": NaN,
+      "learning_rate": 0.00016,
+      "loss": 0.0,
+      "step": 8
+    },
+    {
+      "epoch": 0.0016974726518294984,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018,
+      "loss": 0.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.0016974726518294984,
+      "eval_loss": NaN,
+      "eval_runtime": 51.4787,
+      "eval_samples_per_second": 43.377,
+      "eval_steps_per_second": 21.698,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 417433827409920.0,
+  "total_flos": 643543817256960.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null