Training in progress, step 30, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0192d3d1f511e10707718291e81a91e89f1efd65737e8e97008136acdd4e3c89
+oid sha256:fe22956dee81b8720146e97823d967b2360f02a1270423821fc3f0566b163bca
 size 162933396

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdc28c2c72b1f6e1a5a24e5542d571bb53cb9adf873c1c5c878ea6f1cfafe922
+oid sha256:46e3bcfae0fd51237888949718f53823fabe426b5744b1d49ee211c8a86c17e6
 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": 0.2247191011235955,
+  "epoch": 0.2696629213483146,
   "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": 7.156,
       "eval_steps_per_second": 1.827,
       "step": 25
+    },
+    {
+      "epoch": 0.24269662921348314,
+      "grad_norm": NaN,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.2696629213483146,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.2696629213483146,
+      "eval_loss": NaN,
+      "eval_runtime": 13.1502,
+      "eval_samples_per_second": 7.148,
+      "eval_steps_per_second": 1.825,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -130,7 +152,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.1719286527492096e+16,
+  "total_flos": 3.81288832869335e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null