Training in progress, step 4421, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e143a1e5a73e096a140f0bd1452c8b7543b3430a8d5240f9d74ca6450f58dcb9
+oid sha256:fbc68c162e53d2aac26456683814d8d51e7523de276c1e5d970882f334de98f1
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3705a8f886e273cba119ed04ba0ce1aae786e2313cf7876f6762c478ad00ed53
+oid sha256:046e0344f94182f69dc2f01192aa3c2dbd83a21e77945252a81adee8593c8aa8
 size 168155346

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8821bf43a6000473419bec4575048dedc76938d427b244cdf9370912feaace5
+oid sha256:8e9cbf36cc778790142eadfdac22fd02d67467e63a64edf810a72e967757bb21
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9950998869204674,
+  "epoch": 0.9998492272898606,
   "eval_steps": 500,
-  "global_step": 4400,
+  "global_step": 4421,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6167,6 +6167,34 @@
       "learning_rate": 2.913878093990796e-09,
       "loss": 0.6676,
       "step": 4400
+    },
+    {
+      "epoch": 0.9962306822465133,
+      "grad_norm": 0.3391641080379486,
+      "learning_rate": 1.6915167145525878e-09,
+      "loss": 0.6981,
+      "step": 4405
+    },
+    {
+      "epoch": 0.9973614775725593,
+      "grad_norm": 0.41276663541793823,
+      "learning_rate": 7.995107016406378e-10,
+      "loss": 0.6594,
+      "step": 4410
+    },
+    {
+      "epoch": 0.9984922728986053,
+      "grad_norm": 0.4570743143558502,
+      "learning_rate": 2.3787184321444335e-10,
+      "loss": 0.7059,
+      "step": 4415
+    },
+    {
+      "epoch": 0.9996230682246513,
+      "grad_norm": 0.3156117796897888,
+      "learning_rate": 6.607561386928751e-12,
+      "loss": 0.6465,
+      "step": 4420
     }
   ],
   "logging_steps": 5,
@@ -6181,12 +6209,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.724528719081767e+18,
+  "total_flos": 4.746119130111803e+18,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null