Training in progress, step 35, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6507eba1614933a24c2ad24894a842b52b623e2d470742817d195929814e661
+oid sha256:371cd4d0cfd0d580634cfbc06adbcd65948cc45b1a785bedaa9ef3c3bdd5e2a1
 size 150486964

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5140c4e7690dfd5c2a867cfa97142c17be010090a2de97d92131e03d7c9fa73f
+oid sha256:390cfa0e48621cb6efdad1de5fca72660b371d8ad0395431856a239156fe719f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d37b0dad6b9c48822da5c83a071d50252502799ad22c4c4907147ad4e4f8e2f4
+oid sha256:88f387d8c434535a84694e469cebc18f2e722ba31b0dc0372632798b59011377
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.16759776536312848,
+  "epoch": 0.19553072625698323,
   "eval_steps": 5,
-  "global_step": 30,
+  "global_step": 35,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -133,6 +133,21 @@
       "eval_samples_per_second": 36.728,
       "eval_steps_per_second": 4.621,
       "step": 30
+    },
+    {
+      "epoch": 0.18435754189944134,
+      "grad_norm": NaN,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.19553072625698323,
+      "eval_loss": NaN,
+      "eval_runtime": 8.2053,
+      "eval_samples_per_second": 36.806,
+      "eval_steps_per_second": 4.631,
+      "step": 35
     }
   ],
   "logging_steps": 3,
@@ -152,7 +167,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8164341920563200.0,
+  "total_flos": 9525065573990400.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null