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:c77c836d16a4615a05b0f4f10e84e7fed1c5a2cc38d7bbbdad0b3bcd44da71b6
+oid sha256:4cb1808116fcf8122fcd185c0411effad8dead4b000cae5e2ebd0a3852a4510d
 size 556856304

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f9477da2f772e6008a21d93101c1713cd80e6bafe77a21aeeb866df5b32777f
+oid sha256:c3ce2b25c5a97eec31dc1511498b173c4909f315cd056fdf8ec42b886280c339
 size 21599060

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a35eeaee2fc6ff5eb7293ee55ff68f802ce990682daebb0cbe7616b4bd61689f
+oid sha256:850db83aee9b6f55f1bc6893d9d4b2c92fa73d26405aa258a01e55e7a8c10d49
 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": 0.03015075376884422,
+  "epoch": 0.03350083752093802,
   "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": 51.869,
       "eval_steps_per_second": 25.934,
       "step": 9
+    },
+    {
+      "epoch": 0.03350083752093802,
+      "grad_norm": 8.440423011779785,
+      "learning_rate": 0.0002,
+      "loss": 6.299,
+      "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": 620301857587200.0,
+  "total_flos": 685596789964800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null