Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7c02aba99973b10a7dfafa7bcd9a75fe12d13ea34fabb70f1aabb457960381e
+oid sha256:ba41cef85f8f2c6cc9de7d5dd267b638bb55100b5f215a78047376bb05c80ba6
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac73fcef0178e0b5e417bbb81dec02e8a57efdaf13660a9a79d9a51c0695b055
+oid sha256:69d587ac6cfd182b620fbc20066085dba6fd3ac9c3baad092f03fefb1afb1264
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a6d0ee99bdd0319882c2fbace1fb60e096d6f8574b0dc2a723a28b6700bceec
+oid sha256:ad74980069f629013c957125408eb0cf4f93b437748595d273037605a559708a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
+oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.024623803009575923,
+  "epoch": 0.027359781121751026,
   "eval_steps": 3,
-  "global_step": 9,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,6 +102,13 @@
       "eval_samples_per_second": 24.249,
       "eval_steps_per_second": 12.124,
       "step": 9
+    },
+    {
+      "epoch": 0.027359781121751026,
+      "grad_norm": 2.2644660472869873,
+      "learning_rate": 0.0002,
+      "loss": 7.5187,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -116,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1628733135912960.0,
+  "total_flos": 1873043106299904.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null