Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:181729fbae5b914f3c68e212801830b48ea63af37af65b6ab55903dedcbacffa
+oid sha256:1901901ea1bd9d853b37c863ea02c9653d2cf6945698347e2d63d7b67f4b4ec0
 size 33572288

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:861ad631dcac34793b2cc17adb6b177ce25ac3ca92d62af75a2da6ebeb1c36e6
+oid sha256:f2d5e4ff847c86a38f29f3089f3919e7ff4c5dc8ce40a3a5036332c35544000c
 size 17190970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1ae6309517a2108e6bd10ea1fd8da0edc71a65cb14916086f3915020657220a
+oid sha256:c9781fdc3586903f2d905fffde1a3cbb7386ef33d492e867874b683c64816158
 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": 0.01955458989679522,
+  "epoch": 0.021727322107550243,
   "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": 5.817,
       "eval_steps_per_second": 2.909,
       "step": 9
+    },
+    {
+      "epoch": 0.021727322107550243,
+      "grad_norm": 35.36907958984375,
+      "learning_rate": 0.0002,
+      "loss": 16.0779,
+      "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": 1622867083001856.0,
+  "total_flos": 1803185647779840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null