Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03c7d180a19b44794ca000d2ac9a044f1208efd45d788b186b2cb4aa92a38f39
+oid sha256:80582003423f5863c748f0d66f54e0b7ebbd76de4b3ff95701cd268623bdd0a4
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:557ea13c11ce98813552511fa97e10d4f01136341ec47a731712dc2928949737
+oid sha256:27f5195650433ac57f36235e3fbb4e9973c3cda4beb3a176b460154246ec1ac4
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b70f29a81cab5749b7acb47c2046572b3022dd01b41109c8e1baa88cfd573b4b
+oid sha256:eaaae57ea544793f8498ea930cc6022c0875d69417c53b70b22c86f3547c7459
 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": 0.0005692419594573227,
+  "epoch": 0.0006324910660636918,
   "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": 29.392,
       "eval_steps_per_second": 14.696,
       "step": 9
+    },
+    {
+      "epoch": 0.0006324910660636918,
+      "grad_norm": 15.345791816711426,
+      "learning_rate": 0.0002,
+      "loss": 5.3196,
+      "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": 1719982274641920.0,
+  "total_flos": 1911091416268800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null