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:fba57323b5ba508f5a70c463eca9b0f2440e817c56f270fdc08651301202bb25
+oid sha256:c0583bce63289fe87cc0ec005ed94587d5ce1fa91e3401abf13d408192740286
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2553f2d63025481e908dd4e101addeda960d57bd8e85dfa5d8bfec3c8525450f
+oid sha256:3389835c8ca5e2fd81a7bf13ed59cd1a1da6b4c6b485ed8dcab655aa1b3a42d1
 size 23159290

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": 0.002811182258316414,
+  "epoch": 0.0031235358425737935,
   "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": 16.51,
       "eval_steps_per_second": 16.51,
       "step": 9
+    },
+    {
+      "epoch": 0.0031235358425737935,
+      "grad_norm": 2.347788095474243,
+      "learning_rate": 0.0002,
+      "loss": 2.3914,
+      "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": 870950312607744.0,
+  "total_flos": 967722569564160.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null