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:bd2ff0a1ea77107bc0ff9abc718f43b5c390a3d7d86146e4696c6ee13a26b003
+oid sha256:196af8a5f1139372265e26aecd19260e85348cb4034dd1755e691ecfad31ad04
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dfae8c5a8aded5989063a707e862dea252008ac0590ef0b0adad0388eba483d
+oid sha256:e0d765879b365997eaa4dd457b87e80b6607ff2c296705b5b299d6827895d446
 size 25986148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17180c52a3bd518e0ef3a6c2b2af2da2fdbe09eb8ac3c2cdeb7acff9012e0f39
+oid sha256:ddbad4ca227ed67773de15874f13a3fcf104c58206903b9c73e3f573cd9797d9
 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": 0.0009240483585307631,
+  "epoch": 0.0010267203983675146,
   "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": 6.415,
       "eval_steps_per_second": 3.209,
       "step": 9
+    },
+    {
+      "epoch": 0.0010267203983675146,
+      "grad_norm": 0.2965444028377533,
+      "learning_rate": 0.0002,
+      "loss": 1.9257,
+      "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": 1852863789662208.0,
+  "total_flos": 2058737544069120.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null