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:bae18a0f0fffb00b11efcbd6d2d4d0e0e5d1d243dac833c135a1f7360a49bcbc
+oid sha256:74634be227472357df5cc5eda3d8468aca4c26aba99709381460f95422ad4149
 size 12609416

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:999da798058886131135c0b4e37c4db89559788fdf90630195278dc0de334930
+oid sha256:9476ae947a66d1c782acc1f925c9c562a81c8620148f912eba2031f17472aa68
 size 6615034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:399171def2779bd0a4edea00ec815fe9bfd7f86cec979b7ea47ed048203a9783
+oid sha256:d67462133f0869238598f8229a8919771cd31c8c5b7561e7da6d0c8eaf56ea93
 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": 0.0006902502157031924,
+  "epoch": 0.0007669446841146582,
   "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": 23.058,
       "eval_steps_per_second": 11.529,
       "step": 9
+    },
+    {
+      "epoch": 0.0007669446841146582,
+      "grad_norm": 4.063102722167969,
+      "learning_rate": 0.0002,
+      "loss": 10.0235,
+      "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": 135125375385600.0,
+  "total_flos": 150139305984000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null