Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7be5facbc44796fc72b37c1ec608b126b5d8314c4a0db318bb887365899a5f9a
+oid sha256:3ca30485db3f386b1eeab7b0a62d61c220314425dc9c426272aa5942e71cea23
 size 94412008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efcb5f01b3d828364544cf06e0ffd698cfb6dc5d3dc888636a76e635b4013161
+oid sha256:f99af3f9a6bf1b1ba898713c544c1d178cb01fc65466bab872b145763e12e909
 size 48260756

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e40e5299fd01e8b6d766680bf3e901a3191a7ff234b09bf485cb92c3fed6364e
+oid sha256:a7b07705cdd965f3a6be3f96556df5291ffbacca044c445cd4e4aab2e1bcb8ff
 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": 0.025139664804469275,
+  "epoch": 0.027932960893854747,
   "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": 13.619,
       "eval_steps_per_second": 6.855,
       "step": 9
+    },
+    {
+      "epoch": 0.027932960893854747,
+      "grad_norm": 4.46405029296875,
+      "learning_rate": 0.0002,
+      "loss": 7.6561,
+      "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": 2567524822548480.0,
+  "total_flos": 2852805358387200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null