Training in progress, step 30, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46f1c4b3f3e865acb10f07ea3213d8b2d2b7afbf288f443165a2b62a5fb00d46
+oid sha256:d6507eba1614933a24c2ad24894a842b52b623e2d470742817d195929814e661
 size 150486964

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67124e1bb49f0d1ecfd196b6845c01ded38adeb7a043cc29e559851d658d090a
+oid sha256:5140c4e7690dfd5c2a867cfa97142c17be010090a2de97d92131e03d7c9fa73f
 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": 0.13966480446927373,
+  "epoch": 0.16759776536312848,
   "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": 36.747,
       "eval_steps_per_second": 4.624,
       "step": 25
+    },
+    {
+      "epoch": 0.15083798882681565,
+      "grad_norm": NaN,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.16759776536312848,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.16759776536312848,
+      "eval_loss": NaN,
+      "eval_runtime": 8.2227,
+      "eval_samples_per_second": 36.728,
+      "eval_steps_per_second": 4.621,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -130,7 +152,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6803618267136000.0,
+  "total_flos": 8164341920563200.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null