Training in progress, step 9, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f74e32c80a27b88d895bdb1f4578e05687337736870720b59fe44dba58c489ce
+oid sha256:ae9c2ce877ad9d5a7b87776d946ef0c29b3faa8267742a48760b5cc3fe014694
 size 5962860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e272e9d7e493c9b11d52af458cc392aea6cce8c014e1d7b5cb2cc292f76675e
+oid sha256:f6ad45e1fcda13f7d40bfde1e0812869861c06b7394fd68058f388e6817a020f
 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": 0.005823829167677748,
+  "epoch": 0.008735743751516622,
   "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": 44.676,
       "eval_steps_per_second": 22.338,
       "step": 6
+    },
+    {
+      "epoch": 0.006794467362290706,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014,
+      "loss": 0.0,
+      "step": 7
+    },
+    {
+      "epoch": 0.007765105556903664,
+      "grad_norm": NaN,
+      "learning_rate": 0.00016,
+      "loss": 0.0,
+      "step": 8
+    },
+    {
+      "epoch": 0.008735743751516622,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018,
+      "loss": 0.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.008735743751516622,
+      "eval_loss": NaN,
+      "eval_runtime": 9.6903,
+      "eval_samples_per_second": 44.787,
+      "eval_steps_per_second": 22.394,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 23363170467840.0,
+  "total_flos": 35378515279872.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null