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:a6f0111be9a8c907ca40016bd9b78bc69fb711439764cfe20eae85a248504b48
+oid sha256:1f75a5ba5ebc8995b9be0efaca3e52ec80bd85d9d4f82d5fed8798d1560840cd
 size 81576

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28ae19fa8b99403bbeb4ef3f55d75c5bd05ddda6bc56edaa66dc94375286e20b
+oid sha256:ebaf43a4af9510f13d600a6e98ea789d748510f8e3ef3ea02db11070eb739b01
 size 173094

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56e4c605570ee3c73fe8ff5167e52a53ea3100415d1bfd842431b5b9a62a411e
+oid sha256:c12066a9c624fe38430ff3feea2dc6451e9f1a920255c11680c737a33d2c53a0
 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": 0.023809523809523808,
+  "epoch": 0.026455026455026454,
   "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": 342.601,
       "eval_steps_per_second": 171.301,
       "step": 9
+    },
+    {
+      "epoch": 0.026455026455026454,
+      "grad_norm": 0.20795820653438568,
+      "learning_rate": 0.0002,
+      "loss": 10.8276,
+      "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": 1168921460736.0,
+  "total_flos": 1291965825024.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null