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:ee06a3205306d36a2019a9f0315ddada445dc9a0f1920f720f8a9e3b7703c389
+oid sha256:12c21046a6dc0a3d4b1e6ed3331b377b4e3a7f71fe1b51d1c06240f252dd436d
 size 200068512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95b4836971a8071eb1d56a6e0a6a5286747f79dab3d887647e559f849ad46fbe
+oid sha256:2e03b3da552c938507cabdb1ad4ce57c81593e20a81ad6abbfd7e3bd276710f1
 size 102030196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3167b45e8191cbbe1e15b6e4e3e671c26ef8fc1eff2010be5aceabaa71c7c16a
+oid sha256:eceafea254f171991eb2372221c5b96dfb1a6aa3abf95c819282b5b3825bae54
 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": 0.005082592121982211,
+  "epoch": 0.005647324579980234,
   "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": 3.525,
       "eval_steps_per_second": 1.762,
       "step": 9
+    },
+    {
+      "epoch": 0.005647324579980234,
+      "grad_norm": 4.247814655303955,
+      "learning_rate": 0.0002,
+      "loss": 1.8169,
+      "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": 1.3804098507767808e+16,
+  "total_flos": 1.533788723085312e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null