Training in progress, step 120, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2049ad971725c8ba7e50b65f20a592ebe35fac985d820a3608bc79eeb50ecfbe
+oid sha256:9609f4b966903c1d1f1a328439486f5617f052e946ef1bb6f248d37466f6f3d6
 size 74291604

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71cc480c37231e0fedeb4fe141efde60188aefce8cf6de1a66297a3e2ae06090
+oid sha256:f897f47a5a189148c5723ae6d5e03dd35a40403877646007518e71bba38617d3
 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": 0.18189569418786414,
+  "epoch": 0.2728435412817962,
   "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": 8.388,
       "eval_steps_per_second": 4.2,
       "step": 80
+    },
+    {
+      "epoch": 0.2728435412817962,
+      "grad_norm": NaN,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.2728435412817962,
+      "eval_loss": NaN,
+      "eval_runtime": 88.487,
+      "eval_samples_per_second": 8.374,
+      "eval_steps_per_second": 4.193,
+      "step": 120
     }
   ],
   "logging_steps": 40,
@@ -64,7 +79,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.14813690018005e+17,
+  "total_flos": 1.72058597523456e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null