Training in progress, step 30, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75dd6ce2f8b5aa43a8054a9dc6e512014b44ad2d5a071e79783610c18d7d0794
+oid sha256:9bbeb9c95b050c35725bc26058030f4a4f57cfa5339bb28b102ea2fe0af01b29
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca8b220aee854998a07252e0f1e9e424befdb7e44ea8ae74c18bf94d995cf5b3
+oid sha256:597811f14c0f972055f8c8ac4b383e771c0b41facab9f6319fbf87abce02e43f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c689d11d790b42a822d1d0bd898c629c33707959b02e1b0262fbbd901e5c2939
+oid sha256:49e1bfd52a490099e464b8d13923eb3d78b1f031b80eae5c9499339bb7ea905b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5298013245033113,
+  "epoch": 0.7947019867549668,
   "eval_steps": 8,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -59,6 +59,28 @@
       "learning_rate": 7.169418695587791e-05,
       "loss": 0.0,
       "step": 20
+    },
+    {
+      "epoch": 0.6357615894039735,
+      "eval_loss": NaN,
+      "eval_runtime": 0.712,
+      "eval_samples_per_second": 22.473,
+      "eval_steps_per_second": 11.236,
+      "step": 24
+    },
+    {
+      "epoch": 0.6622516556291391,
+      "grad_norm": NaN,
+      "learning_rate": 4.4401776194834613e-05,
+      "loss": 0.0,
+      "step": 25
+    },
+    {
+      "epoch": 0.7947019867549668,
+      "grad_norm": NaN,
+      "learning_rate": 1.8825509907063327e-05,
+      "loss": 0.0,
+      "step": 30
     }
   ],
   "logging_steps": 5,
@@ -78,7 +100,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 705348712267776.0,
+  "total_flos": 1078291709558784.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null