Training in progress, step 18, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19ec97644119cc7d00b044cd01307d742f1fe80c28d03fbaad3db1a861ae24fc
+oid sha256:004d1836c5e2987b1409a93fbd9adab3af148849184f3bf9ce4ffcd34ddeceb9
 size 1342555602

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bd7b17b48ee3e82b4b209a130f1bdce363a75b3463b23bb15ba34a533916425
+oid sha256:c4ac4d29fdcd503d958f287ad107413cee2283f5bb25be9e5ac2fac1d8f3afa9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c1fa12db6e65a79cc008f6035c457ab68bb8c45c7fe7a2790ea24e528e6b743
+oid sha256:a4b679dfcad285902b67d18379c2cc1ca0aebfc7646cb33fa82a3fb8ed15c820
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.004789144605560729,
+  "epoch": 0.009578289211121457,
   "eval_steps": 9,
-  "global_step": 9,
+  "global_step": 18,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -30,6 +30,28 @@
       "eval_samples_per_second": 10.202,
       "eval_steps_per_second": 1.276,
       "step": 9
+    },
+    {
+      "epoch": 0.005321271783956366,
+      "grad_norm": NaN,
+      "learning_rate": 7.5e-05,
+      "loss": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.007981907675934548,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001125,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.009578289211121457,
+      "eval_loss": NaN,
+      "eval_runtime": 654.9211,
+      "eval_samples_per_second": 10.203,
+      "eval_steps_per_second": 1.276,
+      "step": 18
     }
   ],
   "logging_steps": 5,
@@ -49,7 +71,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.4136217259933696e+16,
+  "total_flos": 4.940381970392678e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null