Training in progress, step 81, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64b2e9a8cd38c5d36cb5bfc550da0cfecc84915a63ea7d8e3df324b6727169d3
+oid sha256:29046213a991b5eadc248f90be681087b37e001bc4afc585a83f12d47f0233d7
 size 15156512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7df5de490fe94c336968e5e61fa603f19aa594ce85fc4f61af0840a4251f16de
+oid sha256:c8b4f78d3c9e9f9d78df5489b3d6ab7f6417c6c47d6429bfeebc25047975ba6f
 size 7825914

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ec828114a9f823c079e9a002c62811de494f0b068f4847b658d0732d7ab7f53
+oid sha256:84ba9cb58552d57919ace8ff4e50292be4084136c7d5c3eed2aa84b64d8ad528
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d899e046e5eb8fee9b81979db8db7b88d6dc92f30a13d049b906f3a3be1dfc0f
+oid sha256:bec84b33191b76a1f66109f05ca2863b65ba9c0ae66be6a4921ad95ad9f1a38e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.07239819004524888,
+  "epoch": 0.08144796380090498,
   "eval_steps": 9,
-  "global_step": 72,
+  "global_step": 81,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -247,6 +247,35 @@
       "eval_samples_per_second": 151.282,
       "eval_steps_per_second": 18.967,
       "step": 72
+    },
+    {
+      "epoch": 0.07541478129713423,
+      "grad_norm": 2.6221296787261963,
+      "learning_rate": 8.930309757836517e-06,
+      "loss": 4.3823,
+      "step": 75
+    },
+    {
+      "epoch": 0.0784313725490196,
+      "grad_norm": 2.882395029067993,
+      "learning_rate": 7.016504991533726e-06,
+      "loss": 4.5094,
+      "step": 78
+    },
+    {
+      "epoch": 0.08144796380090498,
+      "grad_norm": 2.5901410579681396,
+      "learning_rate": 5.299731159831953e-06,
+      "loss": 4.2592,
+      "step": 81
+    },
+    {
+      "epoch": 0.08144796380090498,
+      "eval_loss": 4.210515022277832,
+      "eval_runtime": 11.0579,
+      "eval_samples_per_second": 151.475,
+      "eval_steps_per_second": 18.991,
+      "step": 81
     }
   ],
   "logging_steps": 3,
@@ -266,7 +295,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6171298652749824.0,
+  "total_flos": 6942710984343552.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null