Training in progress, step 9, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bddfa18d558da2a95549fd5c5c3106e83eb75f2273fb542749812555fcea5e1f
+oid sha256:9422c181e80beaba0508e43a70fb2f21e087ccc636502200eb59d351b326eb15
 size 64683604

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78331973c5d8c34051d821833d1fcb868cb0851e27fd9dbdecbe2d9e9d501114
+oid sha256:44232a8f039b0babf38a6cbf02183bf27c1c449e114887567619f44838603534
 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": 0.021739130434782608,
+  "epoch": 0.03260869565217391,
   "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": 16.262,
       "eval_steps_per_second": 8.201,
       "step": 6
+    },
+    {
+      "epoch": 0.025362318840579712,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014,
+      "loss": 0.0,
+      "step": 7
+    },
+    {
+      "epoch": 0.028985507246376812,
+      "grad_norm": NaN,
+      "learning_rate": 0.00016,
+      "loss": 0.0,
+      "step": 8
+    },
+    {
+      "epoch": 0.03260869565217391,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018,
+      "loss": 0.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.03260869565217391,
+      "eval_loss": NaN,
+      "eval_runtime": 7.166,
+      "eval_samples_per_second": 16.327,
+      "eval_steps_per_second": 8.233,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2482253145833472.0,
+  "total_flos": 3723379718750208.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null