Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2614777148c89e2c5ad8bd675787ce4d58cac7df9d6f815e1e09ad4b11ce671f
+oid sha256:2832095f87aa654884749b52a2b5d69932f6e819e0034d4905c055b064267ecd
 size 5752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05df3bfc4f5a78ad7423cd5ba0c7165cfe19a15546e85169163d795e5db2cba3
+oid sha256:d80e6ba593c7d50487258d4881b8d88f6ea293427e40ad1e8a27f4db3f1fd207
 size 15814

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb04243bb25bf686a4dbec102fd9ca7613ad5c31a6a03dfc0541d4df84930100
+oid sha256:9c4e103f057cbf52631a0f74dec69e271b2b990ec70bac9b6694c66ba4e1959d
 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": 0.0379746835443038,
+  "epoch": 0.04219409282700422,
   "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": 172.965,
       "eval_steps_per_second": 86.482,
       "step": 9
+    },
+    {
+      "epoch": 0.04219409282700422,
+      "grad_norm": 1.965663795999717e-05,
+      "learning_rate": 0.0002,
+      "loss": 46.0,
+      "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": 179305906176.0,
+  "total_flos": 199228784640.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null