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:b006e075b5558ef7c6adb23fb7f16e51402785594c26bf57efeb3dcc5e24da62
+oid sha256:db3fc933a1d62f73bf86e4f49002638289e7b4340e6bad5aa403b74c8bcb09a5
 size 767856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b61c14112728d2ade6ec3f8a437bfb9cb458bc83a5ed74623b83549c39b13c0
+oid sha256:fa90e5eff6ab093af970c65466fcad868dfeca672cc006dd6420fd94c9ff3936
 size 1003002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7ecc63df12c57baa58797cbad45fd25f5504b307a5ad4ad822f1c6c0804d66f
+oid sha256:77eb7a8efcda755f6cf5f1bf7541c682197083c64109e1175011208308cb49e9
 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": 0.0015558820987120754,
+  "epoch": 0.0017287578874578616,
   "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": 22.82,
       "eval_steps_per_second": 11.41,
       "step": 9
+    },
+    {
+      "epoch": 0.0017287578874578616,
+      "grad_norm": 3.962679147720337,
+      "learning_rate": 0.0002,
+      "loss": 9.874,
+      "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