Training in progress, step 160, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64bad22b1e162183d0e22dbb06ccbe8f8faff82bb04185b8b4de7532b3760364
+oid sha256:9d99eb48b3aec557bb54461866cd724a4b2bb84d15b355e46bd05839c445f35b
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ef180f41ff4843fa63d754462f404b8fc12d165280a5d3c202084e1a89097c8
+oid sha256:a9d5f5a43b0310502543e267b2712058435176ce355ad98673eee30c66eb3e32
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:080e787c96fa8b09f9b8bcf88f51a3766bad6b6691637c9fc0b084cb355db333
+oid sha256:500b1c78c9d3af1c55fbf9cc6e380394ac567579f265e54ad9607c3dc9f74108
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.17320703653585928,
+  "epoch": 0.2309427153811457,
   "eval_steps": 40,
-  "global_step": 120,
+  "global_step": 160,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -60,6 +60,21 @@
       "eval_samples_per_second": 16.32,
       "eval_steps_per_second": 8.167,
       "step": 120
+    },
+    {
+      "epoch": 0.2309427153811457,
+      "grad_norm": NaN,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 0.071,
+      "step": 160
+    },
+    {
+      "epoch": 0.2309427153811457,
+      "eval_loss": NaN,
+      "eval_runtime": 71.4346,
+      "eval_samples_per_second": 16.337,
+      "eval_steps_per_second": 8.175,
+      "step": 160
     }
   ],
   "logging_steps": 40,
@@ -79,7 +94,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.704467050220749e+16,
+  "total_flos": 1.1632095607652352e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null