Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fccfcf3c4ad4e40b043c9655487e6c0cae280dbca24ea98eadb4e3d5072f173
+oid sha256:cbe499749ca3ea28726427f2d49d804b436d52f7bba547e0d3632564c5d2d88e
 size 111454040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10144e93b13a53e80e17dfee20bfa435e2ba9cd0043797ed5632746c26f61a64
+oid sha256:cf65cad90129fd687064aa41cc68ceab0e5e21d97c2fa098c1827c9c27ff42e1
 size 56950676

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5588aff3cee8219990dfadcaebed17215cc4ab404606e462a877fa96227e0f0
+oid sha256:a4aa0c83534d08045be7938ed99f8f17fd82997a6299060f9ec900e6d68ee8a4
 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": 0.0057161003493172435,
+  "epoch": 0.006351222610352493,
   "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": 15.234,
       "eval_steps_per_second": 7.629,
       "step": 9
+    },
+    {
+      "epoch": 0.006351222610352493,
+      "grad_norm": 1.0911132097244263,
+      "learning_rate": 0.0002,
+      "loss": 0.9827,
+      "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": 3312433181491200.0,
+  "total_flos": 3737104102195200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null