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:a49d83e389ad887b1763b72c12b0a12fe41aedaaeb82546e9d6f19f7904a34a4
+oid sha256:d99aae0b8f742262aafb799cdb4d820c10f93df7f1b79a395855906c2125d4af
 size 228140600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85b03db9aeb0407d75951040b44bdc4c6bf88d7d878842433160a87cde91024e
+oid sha256:78a37e7e7ccd62bab415145f3af28bcf4ef389cc870b310527adceb4207dfbc1
 size 116472340

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:940d78ce95bb8f7eb48adc329f7531c0db71f4ebde5ffbc17217d635e541d518
+oid sha256:ba93f8db423cb3b679c79a7db27151bfbed53e821114d602901acf9157000a85
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:917587e2c0a52fd7c3d6680e02e388879c84c249a215f319208d6a9951b36ba9
+oid sha256:cda2d7da3ce8a95be6df505b84eace6ccd5aa18ffc6d1bcc9a79572045c8d78f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00046463603510583376,
+  "epoch": 0.0005162622612287042,
   "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": 3.53,
       "eval_steps_per_second": 3.53,
       "step": 9
+    },
+    {
+      "epoch": 0.0005162622612287042,
+      "grad_norm": 98.54031372070312,
+      "learning_rate": 0.0001,
+      "loss": 11.2608,
+      "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": 1.029276212133888e+16,
+  "total_flos": 1.14364023570432e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null