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:bc707b5cbd8d250673b0dd8105294bbcd47e886dc8a20bec20f93a686d3aebf8
+oid sha256:5139457f5949ce7ed0752eafb91613ad8eb463db73f650d1d3e1407cf70dc4d6
 size 39256456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2813f172bec345395f230978c8b9b9bc47589e033f88edb8bc5ac7979d815f7d
+oid sha256:9c39e80603847d9f7bd023144d417448f9ba684f3883b84e403bdd52eb42a47f
 size 20632826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c99a5c11c0b82fc5bdf98c308da31be04d7e528dc72c280e687a63346b44e2fc
+oid sha256:3095faa2ae47044a7174cbb3d856c22bc490144a31307187c067df8d5e627e16
 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": 9.646845079707057e-05,
+  "epoch": 0.00010718716755230064,
   "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": 54.706,
       "eval_steps_per_second": 27.354,
       "step": 9
+    },
+    {
+      "epoch": 0.00010718716755230064,
+      "grad_norm": 14.61885929107666,
+      "learning_rate": 0.0002,
+      "loss": 2.3176,
+      "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": 440530014044160.0,
+  "total_flos": 489477793382400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null