Training in progress, step 5478, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af33858c5c886a868e427a6a837ff04fb423bca594c03aabb38293223f09a777
+oid sha256:925071aab6b3ced4c3e8d306f1f5fcb2186c832a0400e4c06dbd24440d0f1ea5
 size 4785762744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00184d8d018217b8c5c28eb0dbe786eac72e9d32d132ef69b0bfab9f29bee0c3
+oid sha256:78eca8f0f5d19928e0971e07141c0b10408b08a68152764a7dfb9145e8a511e5
 size 3497859804

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5bb9a16abc726ae10edbd1c8badac548eb870d1e2b85f486141fc47114a01df
+oid sha256:d1685f9443568ffbbe43dd49b7eea4f6c1439744464b77233039354594fb3fe6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.738225629791895,
+  "epoch": 3.0,
   "eval_steps": 500,
-  "global_step": 5000,
+  "global_step": 5478,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -357,6 +357,34 @@
       "learning_rate": 2.301660326042443e-06,
       "loss": 0.4596,
       "step": 5000
+    },
+    {
+      "epoch": 2.792990142387733,
+      "grad_norm": 1.5731868743896484,
+      "learning_rate": 1.4435393538625497e-06,
+      "loss": 0.4652,
+      "step": 5100
+    },
+    {
+      "epoch": 2.8477546549835706,
+      "grad_norm": 1.4046640396118164,
+      "learning_rate": 7.825271578155602e-07,
+      "loss": 0.4419,
+      "step": 5200
+    },
+    {
+      "epoch": 2.9025191675794084,
+      "grad_norm": 2.1482276916503906,
+      "learning_rate": 3.2130703283768106e-07,
+      "loss": 0.4663,
+      "step": 5300
+    },
+    {
+      "epoch": 2.9572836801752462,
+      "grad_norm": 1.5635905265808105,
+      "learning_rate": 6.175124336402217e-08,
+      "loss": 0.4757,
+      "step": 5400
     }
   ],
   "logging_steps": 100,
@@ -371,12 +399,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.406826165707178e+18,
+  "total_flos": 2.633057747449823e+18,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null