Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32ee2b53f6805b3f8752ddef61c4d23ff6fccd115c7712b2d7809faeb13dbed8
+oid sha256:c0844fdacb0eb7deb5c797929911512d167ecff929d2af3d92bb407838e27256
 size 767856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22576e885298578cdbfafdbc8d579766a1c6d6ec748fa0999ac4cf2e0b4ed7e5
+oid sha256:6b0b33a46c62108e3f0e4ea80ebb859649036a0987cac42ba772603051bb14a2
 size 1003002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03b6cde79fbc4b5b26bf00e97c36fd2d90b042fd30be528f298072427e071121
+oid sha256:494b33d421b03d1cd28f79b8a14e3ee58ac7b56ac617857ec95c88d4246e6c4f
 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": 0.0013644633110976349,
+  "epoch": 0.0015160703456640388,
   "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": 30.482,
       "eval_steps_per_second": 15.241,
       "step": 9
+    },
+    {
+      "epoch": 0.0015160703456640388,
+      "grad_norm": 13.891613960266113,
+      "learning_rate": 0.0002,
+      "loss": 10.5964,
+      "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": 4886913613824.0,
+  "total_flos": 5429904015360.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null