Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f889b2884853eda4f55c9ec0fdfa641df4ee527f0bbdf528bf08000499da2ab
+oid sha256:cf5a9ffdaaf15b14e3209095b313d41083b14a7cd09b7c83dd26acde29e9b8b8
 size 200068512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc11dc4d7e4459b78a251da66c76cffac9e2b162b84fb7dca23a9c2405e64db3
+oid sha256:af44f60fd1097c697189144848171e3f88485d2802d8cea306fd17ab6a88eded
 size 102030196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd4269677e3d335673fbcee71e5b78f83433b7173960adf0a51d212c7727af18
+oid sha256:0115a51802b9fbbc4b35b5253182300acdb5f38e83f59ae76d850f9880396752
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26a93b2a1f4b5368650119fe6e0d6eec6d19cda6badeba4d21943ab48964fa00
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0019303984127835272,
+  "epoch": 0.0021448871253150303,
   "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": 4.264,
       "eval_steps_per_second": 4.264,
       "step": 9
+    },
+    {
+      "epoch": 0.0021448871253150303,
+      "grad_norm": 33.359867095947266,
+      "learning_rate": 0.00018,
+      "loss": 2.2976,
+      "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": 6902049253883904.0,
+  "total_flos": 7668943615426560.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null