Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66908bd04f898d6f40651f6c1f3e5598c4e514e2f1f7ff1591dae3ef4a535325
+oid sha256:b076e79bd4388209ac63fba0620eb3c9a733efa6c36778f7be669c0061f701be
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f127f9a7e9502553768a061fb8d92376f776644f343bf3b14fcc8711d2bf0e4
+oid sha256:e69a1c16718e444f903d9c34841282ee04cbda64ecb4a966084c6247ba5f0ed7
 size 11710970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d67462133f0869238598f8229a8919771cd31c8c5b7561e7da6d0c8eaf56ea93
+oid sha256:9fd4f38597ec495deae669629e0018ab1cdbeaaeb39f597cc401fd9b5fa188ec
 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": 0.0010967584694126249,
+  "epoch": 0.0012186205215695832,
   "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": 73.673,
       "eval_steps_per_second": 36.836,
       "step": 9
+    },
+    {
+      "epoch": 0.0012186205215695832,
+      "grad_norm": 0.7863947153091431,
+      "learning_rate": 0.0002,
+      "loss": 1.2169,
+      "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": 252572791209984.0,
+  "total_flos": 276627342753792.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null