Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ddc160207ee1af6ca45186728d88636abfa8efb51d4a42ac4708b05c22bd608
+oid sha256:e20c023db1b0d5cbb1a09cdbad4d246451dd8b4f199e8cf71f24075560049d92
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a20ffcb8145697491800552415bfdd00122d234e2338bd0c402a760fe92e72a
+oid sha256:401a5264f22861ae17ef243c6e4336125932a11d7e97738cf61c42ad0fe53ef0
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccb04223ba875e51fcbb6b90adb429f8425ccc26eacd70e231de69e7656d74fd
+oid sha256:61bba220b883d6a4dabf08b1becb9e342c58b851309448f618be065a85d3d7b3
 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": 0.0018837318821621056,
+  "epoch": 0.0020930354246245617,
   "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": 26.852,
       "eval_steps_per_second": 13.426,
       "step": 9
+    },
+    {
+      "epoch": 0.0020930354246245617,
+      "grad_norm": 1.0946333408355713,
+      "learning_rate": 0.0002,
+      "loss": 2.2845,
+      "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": 787653295865856.0,
+  "total_flos": 887672762007552.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null