Training in progress, step 39, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b54a48a97aae933e2faf1a3c1e75742dc4a9529c75e875ccfda78efc9a4a11f
+oid sha256:c9f9ed3984bb015a1f07bbff5d61875af822f0306e75b4f3a8d45f7765a65bde
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe811a66d30687e509246a270e8c6f37d3a7b430b53a76fe7519c6dca6d5e76e
+oid sha256:56a7f2192f9943370041dc8061e7f36329e4e9e09cb55d87866fb96eee2ca4e3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e65bdb10468d12c8b6afa89fe8730e38a94a4f704431de04b0c1bf27440afce
+oid sha256:75c3c8ae7ddabeca3cb69703f6b35f00b9125a4c27b56ccba4ed0e4669bb5433
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.17056170561705616,
+  "epoch": 0.25584255842558423,
   "eval_steps": 10,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -45,6 +45,21 @@
       "eval_samples_per_second": 46.644,
       "eval_steps_per_second": 5.859,
       "step": 20
+    },
+    {
+      "epoch": 0.1968019680196802,
+      "grad_norm": NaN,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.1968019680196802,
+      "eval_loss": NaN,
+      "eval_runtime": 22.0626,
+      "eval_samples_per_second": 46.549,
+      "eval_steps_per_second": 5.847,
+      "step": 30
     }
   ],
   "logging_steps": 10,
@@ -64,7 +79,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7407975228506112.0,
+  "total_flos": 1.1111962842759168e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null