Training in progress, step 80, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72e6882e247bc4734c68b129eb6d7e994f21838dd115878589741be0fbeaf3a5
+oid sha256:c437504bed28726a172523f0e4cb0f9a2b955208e9299525aae2855806d659cc
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f09ddbe9ea103a2a896291410b960f6442a0954e33e4bc8eada1c4d0c1481931
+oid sha256:bf77dc40f56e270cb7941ae0fa57a679007e39602d1df0abe7ad10bff2bc743a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:721a82cc54baa1d744828761304c3f1e991f36bc90b1b9f92fe61ed53569abd0
+oid sha256:774252ad2ca59a173251c393bb9775b6ad50592c78a9adb425c0845b0166a283
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.006169150392319408,
+  "epoch": 0.012338300784638816,
   "eval_steps": 40,
-  "global_step": 40,
+  "global_step": 80,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -30,6 +30,21 @@
       "eval_samples_per_second": 17.172,
       "eval_steps_per_second": 8.587,
       "step": 40
+    },
+    {
+      "epoch": 0.012338300784638816,
+      "grad_norm": NaN,
+      "learning_rate": 2e-05,
+      "loss": 0.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.012338300784638816,
+      "eval_loss": NaN,
+      "eval_runtime": 635.916,
+      "eval_samples_per_second": 17.174,
+      "eval_steps_per_second": 8.588,
+      "step": 80
     }
   ],
   "logging_steps": 40,
@@ -49,7 +64,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.788217673744384e+16,
+  "total_flos": 5.576435347488768e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null