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:eb38865a848bcf10e4c85d3d77140b7f897c0dea6d378f8609c3f93b6c1b450e
+oid sha256:3ff3d762e7343f44740d89ac32ce2bb16628f033ae04a113b1b8b8e2d220e425
 size 111454040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa4957691ae5964395931e6c78102b3853b8c5c74a881424d709d2d7e537d7cf
+oid sha256:2b8549fa277b4f68e54600ab0228d44994c5f9ac9801c2ec57ee64854851639a
 size 56950676

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8af3ed17966012a6cf5d2f9ea17272133e21c46574744b4f4eb540eee9f302a4
+oid sha256:f1f98c4607cef82ccb26ea4455d64bbd81e63c2e791ee6965cfda9823d50355b
 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": 0.0006374163391054924,
+  "epoch": 0.0007082403767838804,
   "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": 13.142,
       "eval_steps_per_second": 6.571,
       "step": 9
+    },
+    {
+      "epoch": 0.0007082403767838804,
+      "grad_norm": 1.6583317518234253,
+      "learning_rate": 0.0002,
+      "loss": 3.9243,
+      "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": 4161775022899200.0,
+  "total_flos": 4586445943603200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null