Training in progress, step 120, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c437504bed28726a172523f0e4cb0f9a2b955208e9299525aae2855806d659cc
+oid sha256:64bad22b1e162183d0e22dbb06ccbe8f8faff82bb04185b8b4de7532b3760364
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf77dc40f56e270cb7941ae0fa57a679007e39602d1df0abe7ad10bff2bc743a
+oid sha256:0606005585f8ace8dbfd2324cec83feb0fab36941b3818ba4f6991c22bac1941
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:774252ad2ca59a173251c393bb9775b6ad50592c78a9adb425c0845b0166a283
+oid sha256:080e787c96fa8b09f9b8bcf88f51a3766bad6b6691637c9fc0b084cb355db333
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.012338300784638816,
+  "epoch": 0.018507451176958224,
   "eval_steps": 40,
-  "global_step": 80,
+  "global_step": 120,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -45,6 +45,21 @@
       "eval_samples_per_second": 17.174,
       "eval_steps_per_second": 8.588,
       "step": 80
+    },
+    {
+      "epoch": 0.018507451176958224,
+      "grad_norm": NaN,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.018507451176958224,
+      "eval_loss": NaN,
+      "eval_runtime": 636.2214,
+      "eval_samples_per_second": 17.165,
+      "eval_steps_per_second": 8.583,
+      "step": 120
     }
   ],
   "logging_steps": 40,
@@ -64,7 +79,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.576435347488768e+16,
+  "total_flos": 8.364653021233152e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null