Training in progress, step 90, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49cff359b46d1190978725cd5fb8178b74707aaa56df5bbc5985530a072a2771
+oid sha256:03be4978e0b498e2e7caee9f057aa76ef8e3bceebed2cc6981fcdbe64b19023f
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:709dc371c4a0dceb80cd18c183bb01780a051802db9b606fb1402eab32de104f
+oid sha256:5bf5969a0aae65742d515a959c2c593b8e0b14be862d05c119d875b5572fb9d8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09ab64d5ace66796aa9c2fa2fc4e0206d69a1eb4ef03f574f85ee8eb16a64b71
+oid sha256:429c9f0a4ff1909f8cc1cafc3bf6eb6ff29e4592139b5344f1aee9b75eae7379
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0908039936941671,
+  "epoch": 0.10089332632685234,
   "eval_steps": 9,
-  "global_step": 81,
+  "global_step": 90,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -276,6 +276,35 @@
       "eval_samples_per_second": 8.268,
       "eval_steps_per_second": 4.135,
       "step": 81
+    },
+    {
+      "epoch": 0.09416710457172885,
+      "grad_norm": NaN,
+      "learning_rate": 1.4323725421878949e-05,
+      "loss": 0.0,
+      "step": 84
+    },
+    {
+      "epoch": 0.0975302154492906,
+      "grad_norm": NaN,
+      "learning_rate": 9.56279946954021e-06,
+      "loss": 0.0,
+      "step": 87
+    },
+    {
+      "epoch": 0.10089332632685234,
+      "grad_norm": NaN,
+      "learning_rate": 5.709035061653494e-06,
+      "loss": 0.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.10089332632685234,
+      "eval_loss": NaN,
+      "eval_runtime": 363.4698,
+      "eval_samples_per_second": 8.268,
+      "eval_steps_per_second": 4.135,
+      "step": 90
     }
   ],
   "logging_steps": 3,
@@ -295,7 +324,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.283619027455836e+17,
+  "total_flos": 5.869237232405053e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null