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:edb36a27b2062f93c785692ec11020c06ebe274b4d89a622dfd0dd24a69f2181
+oid sha256:b445539a3a4799a0f3651a6afbbaa925d7864837bf26e6b1b5cccbb5beb7cff4
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33d2d31314868ee2dd032357cbb81d9282b3615a543b8c22d17c1f72533ed41b
+oid sha256:47f498dfb937cb43b04b16111c14f91c9ac1c0bb11a4662cf789f4568869717c
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c13d44d958df7e38818d974f43d567abf0a05df1a33d9128a1027ae012e00a84
+oid sha256:8409d680589fc470d347d9080c7a3f75b66b2ec8534a65e71a29740892ab42cd
 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": 0.0002894495634135752,
+  "epoch": 0.0003216106260150835,
   "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": 30.697,
       "eval_steps_per_second": 15.349,
       "step": 9
+    },
+    {
+      "epoch": 0.0003216106260150835,
+      "grad_norm": 0.4322715103626251,
+      "learning_rate": 0.0002,
+      "loss": 1.1018,
+      "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": 799547448360960.0,
+  "total_flos": 902053531484160.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null