Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d797abb3e7ab929d9e601ed29678d787334034d9611944bbba645b5f8a9f0d5
+oid sha256:4ccb83c1f2c7e363efa2b95ccc96915047630319ac749b727f86ece48d66d2e2
 size 111454040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f639fee65ac7081846d14f4a6d7ffff7469dafad77c185821c0ad5c4d66b9d07
+oid sha256:b69892613c1368a6023262aa7e0d111d8bf0dfa6e87f34653298e8bc8122f857
 size 56950676

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:836bdf6622005bd1eae48ddbb8f060c7755138b25b822e798006703ec4217354
+oid sha256:f1e339279e44c5c15da33d41816eb20d1d43d6744958966d073b2d253a0420c7
 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": 0.0016758216180988734,
+  "epoch": 0.0018620240201098594,
   "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": 18.383,
       "eval_steps_per_second": 9.192,
       "step": 9
+    },
+    {
+      "epoch": 0.0018620240201098594,
+      "grad_norm": 14.976569175720215,
+      "learning_rate": 0.0002,
+      "loss": 23.6391,
+      "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": 3057630629068800.0,
+  "total_flos": 3397367365632000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null