Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bcd6cc9741f1879ca8446e3cfbfe92ad60cdc61df9faeecfc8f50a1ca222abd
+oid sha256:4b0955cb83c2bf76846433055f93d433b873cfd004f527a353b2d93c463fbbac
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01386634e67b5a03d7405d25f58a44dc2d7cb1d80b583dfca2d86383a042c9ad
+oid sha256:faf5486e8e62ea93264404940a35fb97bfc1cfc76f88088c45764d5790fef23e
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed95e3385ea48e1762d9eb678fb30b365bc474f1a9d94017d202102f6e7ebac7
+oid sha256:7f040856032b46a149bdfca7621e3b1d33fd69f4f54f37cf5dcd89ea5b102b00
 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": 0.00459125111592909,
+  "epoch": 0.0051013901288101005,
   "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": 17.632,
       "eval_steps_per_second": 8.816,
       "step": 9
+    },
+    {
+      "epoch": 0.0051013901288101005,
+      "grad_norm": 0.8385860323905945,
+      "learning_rate": 0.0002,
+      "loss": 1.2186,
+      "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": 3153300836843520.0,
+  "total_flos": 3535519120097280.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null