Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83318db624ebbb95c8e11b373531ba5ff5efae08c89d782a184e81c1cbf372a2
+oid sha256:053d9c880da6e612c2f0cd30c59cdb08fa1773ff88c574d0f3c85b943a458c29
 size 47724600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:438e3afa80ecf913444c4bcadbb933ff8362931fe744446e3339381c8054f0dd
+oid sha256:1f1f009430cbea8b9faa473c6fe3106abb13dd29ccd1ebea2cbd5d1c75133efc
 size 25331516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcc2f7ba78d087fd6edcc04083dc4f5c91a3a841219d045c11e8138cee12979e
+oid sha256:c653939ace2063e2fa832e99466f2a24ed3a82ae3058c8bbdd96b612af82cb67
 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": 0.010380622837370242,
+  "epoch": 0.011534025374855825,
   "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": 40.947,
       "eval_steps_per_second": 20.53,
       "step": 9
+    },
+    {
+      "epoch": 0.011534025374855825,
+      "grad_norm": 14.663287162780762,
+      "learning_rate": 0.0002,
+      "loss": 11.2106,
+      "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": 799385447301120.0,
+  "total_flos": 888206052556800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null