Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91127052598edb38ea03505603f9c4c6c7a6f63f938c7c4a68caaa0737730ae0
+oid sha256:66faea43d75eeef558cd079b739ab766a7d3b57db4d5c02747471a4e040e6dbe
 size 327040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd611169bd8808c28bf91c36c72363796d4839f76f23f28860c806cb33f51830
+oid sha256:0793ff7c22f8aa86a84395328524b071d524369dd5b1fc5565d7cb51b718a357
 size 739258

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce48dec86ac6000671bbcda61602ac669c6643b660b3c79e45fe5bfda138dc71
+oid sha256:731356647582c8ef90f666e46f0dafaa099438d483cb22a0268abc589e0178cb
 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": 0.0008531210009953079,
+  "epoch": 0.0009479122233281199,
   "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": 76.819,
       "eval_steps_per_second": 38.409,
       "step": 9
+    },
+    {
+      "epoch": 0.0009479122233281199,
+      "grad_norm": 0.18024900555610657,
+      "learning_rate": 0.0002,
+      "loss": 11.9185,
+      "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": 1470582226944.0,
+  "total_flos": 1658316128256.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null