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:ba42abdb7b54dee2fe1f11ea435dbc97baa5e68c91e2876a6087c9943c673556
+oid sha256:e58eb08d41e0f95cb296ac7e747b5d003ab01579c6f41574888737b288b60630
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b893363dcd2f44361beef88b5294a2276e92ca09851be591e778ddd42ba7529
+oid sha256:ef605cfb6fa171d29b933ebe9933c0be094bfae659c128a881e42073609e78bf
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:629575ee7c6b92853a352888f0843a4c6538c991a998ec627f12a96885306e87
+oid sha256:ef85f51d139fa88c501e9c10d2687be0cda0b477cc0a0033709ee647d8e59c50
 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": 0.0004190383070852394,
+  "epoch": 0.0004655981189835993,
   "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": 23.853,
       "eval_steps_per_second": 11.926,
       "step": 9
+    },
+    {
+      "epoch": 0.0004655981189835993,
+      "grad_norm": 1.5686155557632446,
+      "learning_rate": 0.0002,
+      "loss": 0.6175,
+      "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": 2311955310182400.0,
+  "total_flos": 2589389947404288.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null