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:e4dd0c06ba521dbdbf66273735f31a05a83a68f5203011563a005a529f7a7828
+oid sha256:6358f71d3ff34049141e67bc0748bba990ef7957d99b629eab73bf15dfd4ee8e
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8f0d77ba169cb2026d74795fb5635b1f9a228f123c8c1b35bbd0a2e18905ee5
+oid sha256:57a94b1cda1cc9e51b17e20f5c3b1cd6ffcdbe25acf7780efa434b7472f94836
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cacc62993b5d9a421d8750cf4083ab6c687913fd4ddc5fbb5de659e873600b2a
+oid sha256:05c3e7b275db272d3e9eec25bc72b90084e3b45909bf238a46021bcb8ee62b47
 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": 0.3025210084033613,
+  "epoch": 0.33613445378151263,
   "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": 20.25,
       "eval_steps_per_second": 10.904,
       "step": 9
+    },
+    {
+      "epoch": 0.33613445378151263,
+      "grad_norm": 7.979007244110107,
+      "learning_rate": 0.0002,
+      "loss": 0.0344,
+      "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": 1577402807353344.0,
+  "total_flos": 1752669785948160.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null