Training in progress, step 35, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f849cc0f7f9bb97ece17104260ae77980107537ecccebdced4f1cd6ecece641b
+oid sha256:99f77011c2753a3764b3dcb336ff0b12ddc119e028e891a447e623435172b859
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67ed692faf639600dadb63e47f782862b02e2b4f1c7bed5e0ed7d786d641b235
+oid sha256:2f6cda69bfbe0de119defc83e5da3ac5af16a274455608c670b1651222f7fc96
 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": 0.12371134020618557,
+  "epoch": 0.14432989690721648,
   "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": 14.56,
       "eval_steps_per_second": 1.851,
       "step": 30
+    },
+    {
+      "epoch": 0.1360824742268041,
+      "grad_norm": NaN,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.14432989690721648,
+      "eval_loss": NaN,
+      "eval_runtime": 28.0691,
+      "eval_samples_per_second": 14.571,
+      "eval_steps_per_second": 1.853,
+      "step": 35
     }
   ],
   "logging_steps": 3,
@@ -152,7 +167,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.026121939058688e+16,
+  "total_flos": 4.697142262235136e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null