Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:063b6e7b123cd0b0d531bdcc9a5a582f479116b38763244730344118cd444d37
+oid sha256:550de90b560431c724dc75dad75a607370d91d9226e5705d24852aebf0b97730
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfc04eccaefdae34d8c191c216f5f0c28718ffaa3677c8029cd1deb8b359cd38
+oid sha256:2bc9ef688b393511d31b5f7bb8d9eab5e0319c8c0a6e1977df675c1a1a684047
 size 11710970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e430790c418395df8ca73708b8c4c3a500f2ad56804e8db2527f4c5b2ee2f2c1
+oid sha256:d6715e79f938c3772d484e1af1debd21a7398c7ee517a31af38185495f5c63d7
 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": 0.001405591129158207,
+  "epoch": 0.0015617679212868967,
   "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": 47.645,
       "eval_steps_per_second": 23.831,
       "step": 9
+    },
+    {
+      "epoch": 0.0015617679212868967,
+      "grad_norm": 5.907142162322998,
+      "learning_rate": 0.0002,
+      "loss": 4.4764,
+      "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": 216490963894272.0,
+  "total_flos": 240545515438080.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null