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:a0aa5a1072b4fb9a0db9dfe651b7606e0624431412965c22f983f249688fc93f
+oid sha256:2aeb6178e7f933e5c55105f9d59917c6944001c61626e5c8f7fdaaa0b03276ac
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e1f51a56700b4282e5db10ebb0a066be278916e97a2273f8fe7588b5d3997e2
+oid sha256:642568bea9a9b850940ac48132657db94a1d175cc01c62dc491b47c82d388b46
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f797822d7f90ddd36d01752f52a725432b47768e1274ee0905f5c20838530138
+oid sha256:d4f6d989512e2981e87cb20d029e07eea26ab441189565dac2161e311c57b89f
 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": 0.0004147083218136577,
+  "epoch": 0.00046078702423739745,
   "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": 13.243,
       "eval_steps_per_second": 6.621,
       "step": 9
+    },
+    {
+      "epoch": 0.00046078702423739745,
+      "grad_norm": 0.7399348020553589,
+      "learning_rate": 0.0002,
+      "loss": 4.753,
+      "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": 4591025242767360.0,
+  "total_flos": 5065958888570880.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null