Training in progress, step 36, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7f5c4411056bd5ff8a600ddff63f6d8e4ccb5c4682dfe35e06e619408d44083
+oid sha256:bbc492c7dcb1b68709844dd81cd0ef68d1d212e82d927e6d9ab39297fcb9ad98
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4eded5bf1a4d979d559b4882889b39abc6f555952054dfa7b40c3cf2a7bd8b8e
+oid sha256:4efd675893ea3bfea429ac29294f5d4c67e6e2b92517beb0ae876715d73929f2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd4a07944f7914b974e23583756a2e0907223f4627a9b1ba247bd8f732140689
+oid sha256:b09cef78339a08679f2a6cf4a4b56eca3094fb6b859867afd839be3db1415460
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.39705882352941174,
+  "epoch": 0.5294117647058824,
   "eval_steps": 9,
-  "global_step": 27,
+  "global_step": 36,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,6 +102,35 @@
       "eval_samples_per_second": 6.857,
       "eval_steps_per_second": 0.894,
       "step": 27
+    },
+    {
+      "epoch": 0.4411764705882353,
+      "grad_norm": NaN,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 3.1853,
+      "step": 30
+    },
+    {
+      "epoch": 0.4852941176470588,
+      "grad_norm": NaN,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 8.3073,
+      "step": 33
+    },
+    {
+      "epoch": 0.5294117647058824,
+      "grad_norm": NaN,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 1.5029,
+      "step": 36
+    },
+    {
+      "epoch": 0.5294117647058824,
+      "eval_loss": NaN,
+      "eval_runtime": 16.7719,
+      "eval_samples_per_second": 6.857,
+      "eval_steps_per_second": 0.894,
+      "step": 36
     }
   ],
   "logging_steps": 3,
@@ -121,7 +150,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.678198900850688e+16,
+  "total_flos": 1.0237598534467584e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null