Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50a4abc575c8a093274cf3d4d97c2e92a6578043c22dc337a9af0cc31294f16b
+oid sha256:7b931c0e7d8570e4fd602945df59d100e77693d4bb9f96a7a286475bd7b9e0d6
 size 58680

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5daf2ff34ac0bbb5914dec959b779732814786112c3667a7d1bc64bc8fc438bc
+oid sha256:effda1732306bcacc70601b66f3b7af17577ce2b88a00134790446e21af01500
 size 127270

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2773538eab8478e525d9e2c8badc22aef2d0788ebba6aec2bae14ee506c3b74
+oid sha256:af3f7f45a31d2cb8942d285dd1bdffc878d955a79d6c06428c889eb796e4f8a8
 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": 0.0014602685271569384,
+  "epoch": 0.0016225205857299315,
   "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": 98.293,
       "eval_steps_per_second": 49.146,
       "step": 9
+    },
+    {
+      "epoch": 0.0016225205857299315,
+      "grad_norm": 0.3687320053577423,
+      "learning_rate": 0.0002,
+      "loss": 41.4688,
+      "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": 1860068966400.0,
+  "total_flos": 2066743296000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null