Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9083026baf394fb415584f9450a9815f04c4f920e1a3d7e0792f399cb0c8f14
+oid sha256:90f76a8de4a111f94e4874506056d5e56c27cb584b307fff785cefe3e47d1d2d
 size 323290986

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0327c646fbcebdbfe58bb39ffa0aa64a521ffb921c8df37b9e57436d246f1866
+oid sha256:d55774272b40167ace32d2a1dfefb695dfdce3c9404341ab2e7fb49b3fc7bfda
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00046108447067502766,
+  "epoch": 0.0009221689413500553,
   "eval_steps": 8,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "learning_rate": 0.00018,
       "loss": 0.0,
       "step": 9
+    },
+    {
+      "epoch": 0.0005533013648100332,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.0006916267060125415,
+      "grad_norm": NaN,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.0007377351530800443,
+      "eval_loss": NaN,
+      "eval_runtime": 652.574,
+      "eval_samples_per_second": 13.994,
+      "eval_steps_per_second": 6.997,
+      "step": 16
+    },
+    {
+      "epoch": 0.0008299520472150498,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.0,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3495193466634240.0,
+  "total_flos": 7077766769934336.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null