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:bef99946eb34ec0647a1edf8c74e325e1969090ed523973584d5e6445ffddd8d
+oid sha256:1c6f6023d86ffb44292bc64bc0e222dda8a2dd96bd1c9672dc19ae59b93c65bd
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77b222df6957bd8bf47db6e9023ce10dc419ac115cfd2ade5f03038356158514
+oid sha256:ceec45b723897661f6507c012c464479ffefc07de76f2213f781253586bf2d77
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cc9eef375a6a2362cd53802648651c4607bf45707a26cee3305c65b0a8ec483
+oid sha256:c1cedbd64d66a98a09ab33ab3be3b6fffe16e85ded7d149812e44a764a47ee43
 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": 17.715,
       "eval_steps_per_second": 8.857,
       "step": 9
+    },
+    {
+      "epoch": 0.0051013901288101005,
+      "grad_norm": 0.8415577411651611,
+      "learning_rate": 0.0002,
+      "loss": 1.2254,
+      "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