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:e4c7ba34927c891215cdd3cb1900a2644b78fd2869ccbf2b815458c1714c544c
+oid sha256:ac5a9f39740c2b0a35adaf72a0edf2bd7407272fba1fe0130ba5eceaa838a017
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e975bcab1668a4eca9b88d80ef7d7b6a8a30e7808f78348814dbed50607b6c38
+oid sha256:8128c2cd2dff56837734207d014a6a9e379db9fca58914443017dd83a62f8b8f
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f25fd11b6c56f79f3f87a7138e96ebdc8fa6ba4ac58a0040c86d5934744edf26
+oid sha256:d1b4980633edee10d462dc3e0c1eb5d9e179a124b68daca4cf031e164eff8298
 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": 0.010657193605683837,
+  "epoch": 0.011841326228537596,
   "eval_steps": 3,
-  "global_step": 9,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -94,6 +94,13 @@
       "eval_samples_per_second": 14.18,
       "eval_steps_per_second": 7.09,
       "step": 9
+    },
+    {
+      "epoch": 0.011841326228537596,
+      "grad_norm": 1.0583250522613525,
+      "learning_rate": 0.0002,
+      "loss": 2.0317,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -108,12 +115,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 120201521135616.0,
+  "total_flos": 133557245706240.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null