Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ff2100fea2dfc380bdef3549f175e5585edea544dbd79c05a31f698a1fd29a5
+oid sha256:b104399b415f3be3818472308d39e1040a3bf3842bc3ac29687d4fa5e3520aba
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9687ff02b1fd9730a6e431e8faab9f7d7287192cc4a19f8bfe6420b6aa5feddb
+oid sha256:836b58d36189e137c74b2066dcb7428f1813f90dd91b4d530a5da4f4207abe59
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:200897803867d9476163ce84baa477ea4bfc2d20fbca1d606afa2d969206fa8c
+oid sha256:a3efe221c4a0adf497082884c488f9d91c42d1d873e72d47409fbf104eb83048
 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": 0.0008416130917592051,
+  "epoch": 0.000935125657510228,
   "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": 29.384,
       "eval_steps_per_second": 14.695,
       "step": 9
+    },
+    {
+      "epoch": 0.000935125657510228,
+      "grad_norm": 15.700958251953125,
+      "learning_rate": 0.0002,
+      "loss": 12.4007,
+      "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": 1465859822321664.0,
+  "total_flos": 1628733135912960.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null