Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01eddb5a242deb24cc183ff90767e8ba94f8904d2fec2abf3ae0c84f64338f13
+oid sha256:6e71b46f3d7d7f212aac0c93657ba09a9048a5177d71d62eb4a3ae998cb19b0b
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e87f920ce396dea4e2284d80aa988b37ab7919dce57ca5831636344521f7b676
+oid sha256:0777f6c442390ab2f8b191b7ef9d5d113f665b43b010f93751197428e8f67d4e
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d350fb63629b5bbbb1b6067754fd294bad8dde900daee7588c8d726fa5fb4835
+oid sha256:a43ddc14c7ec51649c402ce4d44c026af80252540e3350ce764c94187f06272c
 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": 0.008993255058705971,
+  "epoch": 0.009992505620784412,
   "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": 18.673,
       "eval_steps_per_second": 9.337,
       "step": 9
+    },
+    {
+      "epoch": 0.009992505620784412,
+      "grad_norm": 3.947751760482788,
+      "learning_rate": 0.0002,
+      "loss": 10.0674,
+      "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": 2849601874821120.0,
+  "total_flos": 3166224305356800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null