Training in progress, step 400, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d194837bfa168aa3eda84e48aaee114c991e8d206f6c7f7e4df24ccb8cb89b7
+oid sha256:7ce82a4c5826666916dca5fced06b2ed9a31f38b84c0f05a77b63fc8b2faafbe
 size 2066752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8d815c461c61fd30ed0dc73cc86c2b1aa1fa376dce1c1a113c3fd96c48c8fdf
+oid sha256:f12dbd0e046c0dd5b8cf15bd086b00347583042f40900c1fced314071c1fb807
 size 2162798

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8f261f6dfb4eb05280385874f96d4bbb80c17684a3d0ee60f31105f1343260a
+oid sha256:aa20c10368c9b6560fc415cff6934039731a02984b5d43451c95162cb063b4de
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b73ca3a50ea8f8955b531fe7086eac3562d0d0cd978970f2ba2615091a0e6b8
+oid sha256:92b7afd2237234322bfb3424f202a630e518f7e447f4fb99f19d2471d4ee793c
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b73473ec1a5a599a5ea9ab4e72021cbbeb65e0e85e988871ca89e952f6adc26
+oid sha256:0e4c78e85c4ba926d25150d4aaddeaf5728dcb066f4afc01202e3e56f29a5487
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 29.23076923076923,
+  "epoch": 30.76923076923077,
   "eval_steps": 40,
-  "global_step": 380,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -353,6 +353,28 @@
       "learning_rate": 6.493624448072457e-05,
       "loss": 9.1822,
       "step": 380
+    },
+    {
+      "epoch": 30.0,
+      "grad_norm": 0.4140625,
+      "learning_rate": 5.983045753470308e-05,
+      "loss": 9.1806,
+      "step": 390
+    },
+    {
+      "epoch": 30.76923076923077,
+      "grad_norm": 0.419921875,
+      "learning_rate": 5.484666416891109e-05,
+      "loss": 9.18,
+      "step": 400
+    },
+    {
+      "epoch": 30.76923076923077,
+      "eval_loss": 9.19638442993164,
+      "eval_runtime": 5.3201,
+      "eval_samples_per_second": 282.139,
+      "eval_steps_per_second": 4.511,
+      "step": 400
     }
   ],
   "logging_steps": 10,
@@ -372,7 +394,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 155480248811520.0,
+  "total_flos": 163663419801600.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null