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:aeeea8c5a8ece9a78a187e6cf569908fe3b5ca13c97bb6316871244899872ab2
+oid sha256:ffb4648b25f3917e3115a77bc74879bc21fcf631513836d6dd75d2bf67c8180e
 size 4731640

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90d4623a22399abedc37828ad000da739a23e7f25ae7debd71ca7b5ee6d980a4
+oid sha256:152916cc2bb71d350a510beba0b7b1944e633bafc262e6f86c09436b0f07b764
 size 2505722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03b6cde79fbc4b5b26bf00e97c36fd2d90b042fd30be528f298072427e071121
+oid sha256:494b33d421b03d1cd28f79b8a14e3ee58ac7b56ac617857ec95c88d4246e6c4f
 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": 0.0033182781823209513,
+  "epoch": 0.0036869757581343902,
   "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": 150.876,
       "eval_steps_per_second": 75.438,
       "step": 9
+    },
+    {
+      "epoch": 0.0036869757581343902,
+      "grad_norm": 1386.0103759765625,
+      "learning_rate": 0.0002,
+      "loss": 11.0184,
+      "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": 27619051438080.0,
+  "total_flos": 30687834931200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null