Training in progress, step 30, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96fa0888a3f915bd35c1624e77def14d8bce53ec92c183ea7221d458da25733d
+oid sha256:2648ff728f90c3482885079d09e8740207b49cb18e38688b145bf1d4cbe39ed4
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:614b08dade8621d9a2a5ded66ad541e2769dda8b85330edc4037dd6b262d70ef
+oid sha256:ca0e5b4e8e8e6bd017f58f31ef81629fea322ef8b284f70dccd9bb86610608a6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6676fe28230ae15b45fb334c871c6fdf1a7984a935952b9f8650896c37a8c106
+oid sha256:d37b0dad6b9c48822da5c83a071d50252502799ad22c4c4907147ad4e4f8e2f4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0711743772241993,
+  "epoch": 0.08540925266903915,
   "eval_steps": 5,
-  "global_step": 25,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -111,6 +111,28 @@
       "eval_samples_per_second": 12.315,
       "eval_steps_per_second": 1.539,
       "step": 25
+    },
+    {
+      "epoch": 0.07686832740213523,
+      "grad_norm": NaN,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.08540925266903915,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.08540925266903915,
+      "eval_loss": NaN,
+      "eval_runtime": 48.0844,
+      "eval_samples_per_second": 12.312,
+      "eval_steps_per_second": 1.539,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -130,7 +152,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.443402141696e+16,
+  "total_flos": 5.260988135768064e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null