Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1baace793f9b0cb3c5ea6aa45b33e0226c36720b7e7e853ae9af7b6abce60956
+oid sha256:be21e1f343e3a3b967648ff8122fc80a318ba532f3751df29ee95974e1b3a4d0
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a1da7c2d677d2a1fdaa1b44383e65652bf486256a14bb76d54dbd5c96572de6
+oid sha256:2e7e609cb5f8ac648e8ac3b9f7c651014909babe0c3e982192042e2b16f2cf17
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31ed13482514d5fe173f7e6479c4bc15074205edaaf4395f93b9d96e2a449025
+oid sha256:25eaac48015267721be7b08f50889e85b9139c3125945f35790d7b9dba5e96d1
 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": 0.0013573125212080082,
+  "epoch": 0.0015081250235644535,
   "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": 23.846,
       "eval_steps_per_second": 11.923,
       "step": 9
+    },
+    {
+      "epoch": 0.0015081250235644535,
+      "grad_norm": 0.443646639585495,
+      "learning_rate": 0.0002,
+      "loss": 1.1217,
+      "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": 2142169800376320.0,
+  "total_flos": 2389343238881280.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null