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:c7558fc34b13b9d6f89453dfbfbbc18c9f3c897f6ec4cef0c825218db7034eae
+oid sha256:745bc9fc5883547250beac08b931d983343a2356de4396a3f7f087fc2c49a228
 size 12609312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5120947287d4080b5f45371daae5396d4946b0298bf86e156b636b54c9cd7f5
+oid sha256:fdb6adb514323bcad116d03f8300bb44bebafe8521633db35402e9aa870dc7aa
 size 6615034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fea276383daa6be11cb41bcf079e20917a66b8a1df06264809ff50445c989c9
+oid sha256:3af208be928351f886eeb10757a39eb1944b63462f6c3ea957ea6dfb0f8eb3c1
 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": 0.0015948256766933947,
+  "epoch": 0.0017720285296593276,
   "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": 73.231,
       "eval_steps_per_second": 36.631,
       "step": 9
+    },
+    {
+      "epoch": 0.0017720285296593276,
+      "grad_norm": 64.37794494628906,
+      "learning_rate": 0.0002,
+      "loss": 18.2627,
+      "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": 109660707225600.0,
+  "total_flos": 122819992092672.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null