Training in progress, step 9, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14bd0c06c80d61f1927477e9f0617d8d72e5acff9a5971f02a2e4348d4603c84
+oid sha256:ed9554f0ff7779dbd1d8f5225fceea91b22e45b87d8e31e96d00d48192148136
 size 4027642

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76dcee882f4dc2e4d687c8630a2c8cc6fd9f77ee85547cd089ac94eda9a85c52
+oid sha256:bf21db4092fb4bef27530bc72ef43233c1caae691096cf7b30a52327c291d854
 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": 0.0011319152950054238,
+  "epoch": 0.0016978729425081356,
   "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": 63.554,
       "eval_steps_per_second": 31.777,
       "step": 6
+    },
+    {
+      "epoch": 0.0013205678441729944,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014,
+      "loss": 0.0,
+      "step": 7
+    },
+    {
+      "epoch": 0.0015092203933405651,
+      "grad_norm": NaN,
+      "learning_rate": 0.00016,
+      "loss": 0.0,
+      "step": 8
+    },
+    {
+      "epoch": 0.0016978729425081356,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018,
+      "loss": 0.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.0016978729425081356,
+      "eval_loss": NaN,
+      "eval_runtime": 35.174,
+      "eval_samples_per_second": 63.456,
+      "eval_steps_per_second": 31.728,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 50449944674304.0,
+  "total_flos": 77002547134464.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null