Training in progress, step 27, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e4548c53b2ab0c18851f77ff5febece20c4081a7d379ed8c6fe3b0ccc1734d2
+oid sha256:f7f5c4411056bd5ff8a600ddff63f6d8e4ccb5c4682dfe35e06e619408d44083
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:962d3889ea97c326954bb3e3aa3a35cc8e051c5d22c3d153cce779e37d6183e4
+oid sha256:4eded5bf1a4d979d559b4882889b39abc6f555952054dfa7b40c3cf2a7bd8b8e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ed723721bc2dad2381ab5522e40123ba4aa738fa3e449c48809fa9c2697eb95
+oid sha256:bd4a07944f7914b974e23583756a2e0907223f4627a9b1ba247bd8f732140689
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2647058823529412,
+  "epoch": 0.39705882352941174,
   "eval_steps": 9,
-  "global_step": 18,
+  "global_step": 27,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 6.864,
       "eval_steps_per_second": 0.895,
       "step": 18
+    },
+    {
+      "epoch": 0.3088235294117647,
+      "grad_norm": NaN,
+      "learning_rate": 9.635919272833938e-05,
+      "loss": 22.9854,
+      "step": 21
+    },
+    {
+      "epoch": 0.35294117647058826,
+      "grad_norm": NaN,
+      "learning_rate": 9.414737964294636e-05,
+      "loss": 0.8414,
+      "step": 24
+    },
+    {
+      "epoch": 0.39705882352941174,
+      "grad_norm": NaN,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 15.9645,
+      "step": 27
+    },
+    {
+      "epoch": 0.39705882352941174,
+      "eval_loss": NaN,
+      "eval_runtime": 16.7723,
+      "eval_samples_per_second": 6.857,
+      "eval_steps_per_second": 0.894,
+      "step": 27
     }
   ],
   "logging_steps": 3,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.118799267233792e+16,
+  "total_flos": 7.678198900850688e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null