Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44610b30bd68c1d3c6a26cc04eb6963cc9f20f36a4e4dd4fc95a610f487c8280
+oid sha256:4eb4da9168d63e564e2740ffad442afbc1fc49d4160445aaf317b2a86dedfe02
 size 50365768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97c3c0eb23addf69dd277ec2a66265b806316a8f35a8789240b83d750c3f518d
+oid sha256:eda5adbd90570683aea419e3d2e0a3cb623e99e41df30e47f77181b119744469
 size 25859156

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:926b0216261745d538fa9693c7e914f79ff3ad174c16127c670efa4c3175eb4b
+oid sha256:bc509bfffe368a3b507e1a6745d2334b99c44dd4a0142a255d84e4b16deb8d3e
 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": 0.00020765676643805196,
+  "epoch": 0.0002307297404867244,
   "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": 31.52,
       "eval_steps_per_second": 15.761,
       "step": 9
+    },
+    {
+      "epoch": 0.0002307297404867244,
+      "grad_norm": 6.4836835861206055,
+      "learning_rate": 0.0002,
+      "loss": 11.5023,
+      "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": 849106874400768.0,
+  "total_flos": 940902212173824.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null