Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a203c5312b2f898e3e5b9f824d61a23668deeb9cd3c9fa4f6cc0323d06abb61
+oid sha256:4e90710e23f0a1403969c689ed7629e23d59aa913dc6eb06b370c0ecc955b45c
 size 28350504

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d5b17f33e8c8d947db47fa9d75dbcdef35fc27c9b7dbd1fe823bb5680861112
+oid sha256:57943be52858a156a3af2905a1cf55fd97e72a36986d7677c2c769921bb70de9
 size 14714068

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1af8d7dca6c9565d1b6e676b22355e3e8ad95ec63bcc7c1df5799573dcf447f2
+oid sha256:ba29f511ffb9f0e66c1c861ed69f0cb9c0989ba9903c8abe6d6a72ca40d4ebf5
 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": 0.07484407484407485,
+  "epoch": 0.08316008316008316,
   "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": 46.507,
       "eval_steps_per_second": 23.709,
       "step": 9
+    },
+    {
+      "epoch": 0.08316008316008316,
+      "grad_norm": 1.7604037523269653,
+      "learning_rate": 0.0002,
+      "loss": 3.4752,
+      "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": 321134109130752.0,
+  "total_flos": 358475284611072.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null