Training in progress, step 420, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ce82a4c5826666916dca5fced06b2ed9a31f38b84c0f05a77b63fc8b2faafbe
+oid sha256:58d07caf9aa80839281c79f13b683b604a675fd4afe87e9190eac4d154b49532
 size 2066752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f12dbd0e046c0dd5b8cf15bd086b00347583042f40900c1fced314071c1fb807
+oid sha256:68d759b0f923c2bf9fc620f063306846faf916fa0435a3b7512e71b59b8cde72
 size 2162798

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa20c10368c9b6560fc415cff6934039731a02984b5d43451c95162cb063b4de
+oid sha256:de8a7d3ae35e0cfde7019bc76a87a4f5d2f57ea272cb1b432abf0d4078169331
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92b7afd2237234322bfb3424f202a630e518f7e447f4fb99f19d2471d4ee793c
+oid sha256:846e47b3f08eae7caf9f57a22e4f7db968751c20e77f131354e1ce6ef8905e6d
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e4c78e85c4ba926d25150d4aaddeaf5728dcb066f4afc01202e3e56f29a5487
+oid sha256:f859ddc3da44307ab9a20989e57c7a9e48c43cb14e7243a363c14a732e7b6863
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 30.76923076923077,
+  "epoch": 32.30769230769231,
   "eval_steps": 40,
-  "global_step": 400,
+  "global_step": 420,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -375,6 +375,20 @@
       "eval_samples_per_second": 282.139,
       "eval_steps_per_second": 4.511,
       "step": 400
+    },
+    {
+      "epoch": 31.53846153846154,
+      "grad_norm": 0.4140625,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 9.1787,
+      "step": 410
+    },
+    {
+      "epoch": 32.30769230769231,
+      "grad_norm": 0.419921875,
+      "learning_rate": 4.530518418775733e-05,
+      "loss": 9.1782,
+      "step": 420
     }
   ],
   "logging_steps": 10,
@@ -394,7 +408,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 163663419801600.0,
+  "total_flos": 171846590791680.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null