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:d0ecffff45e15a667d10411a578d6e242f9d0bf70c720f9d04ab7c57ea00c673
+oid sha256:6aea73e7f604e6d907b1a9b0bb11eef1689b58ab44c3c6536e5f1cf9fcc7eb3d
 size 25192496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b86442c7ba6f23d5e6064607dc03ab522a20a78966b395871aae53d17d6d4379
+oid sha256:60caff49339380205564a6519c327768c728fd0137961c54796570512faeef99
 size 13005178

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ab9d398487ecf9d29f7084b6ced43e6cdd3361942d700ae0f8d1ad11344c230
+oid sha256:c642a6558982c29e8656658320286763e9e161353e493770215a765b27f4f7c7
 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": 0.0010160307067058026,
+  "epoch": 0.001128923007450892,
   "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": 64.065,
       "eval_steps_per_second": 32.033,
       "step": 9
+    },
+    {
+      "epoch": 0.001128923007450892,
+      "grad_norm": 15.317606925964355,
+      "learning_rate": 0.0002,
+      "loss": 13.9904,
+      "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": 276179441418240.0,
+  "total_flos": 306036678328320.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null