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:bcba65f37b6eb563d0469ce8acb542ae2a53610e3042bc1f2c1f379e4a274c5a
+oid sha256:263dd5678ae8e5387edc43d87e00924bc080690fa56be6dfdb8bae1d96b5f828
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06a7ffb7dd8a31893a77d9476c1d28f5383371fd8104f21e75afef1e442e2e92
+oid sha256:fb311355f69145c2d5c5b62eb6e830ae8fb690753ad47660b3c10281ef060e6a
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:094837089fa2ed1c4f9dc6c25bac04422ed41c22630725ca5cdf86ffa65f03cf
+oid sha256:787ef78ee12881294c4aa83ed64603709fff88fc133de1a040e06eba2a245935
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cda2d7da3ce8a95be6df505b84eace6ccd5aa18ffc6d1bcc9a79572045c8d78f
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00016930341052314753,
+  "epoch": 0.00018811490058127505,
   "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": 5.092,
       "eval_steps_per_second": 5.092,
       "step": 9
+    },
+    {
+      "epoch": 0.00018811490058127505,
+      "grad_norm": 92.64408111572266,
+      "learning_rate": 0.00012,
+      "loss": 11.9718,
+      "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": 6328165488132096.0,
+  "total_flos": 7031294986813440.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null