Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73774fe393a3853cd56fea5b547c17ec8c14b2a8ee65b41b52166c5d5d9f229f
+oid sha256:b52e505fd63c70056c40f6bf2967cda35b91c0fea1ed12f5504e9039bada7696
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5516f57bbe2e9aef508500fcba56342789be439bb63c5620fb9c7210b188b3a
+oid sha256:a19de93feef781c0299b2a1b51ee17bff90607cd4504bb5c0e1c5cc9d9d3fdef
 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 sha256:8bdda546a1390be3b85a90dd4ef31050dfb7b691765ffc12ed691b6786ed6e3d
+oid sha256:26a93b2a1f4b5368650119fe6e0d6eec6d19cda6badeba4d21943ab48964fa00
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00024032524015834764,
+  "epoch": 0.00026702804462038626,
   "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": 4.777,
       "eval_steps_per_second": 4.777,
       "step": 9
+    },
+    {
+      "epoch": 0.00026702804462038626,
+      "grad_norm": 7.225358009338379,
+      "learning_rate": 0.00016,
+      "loss": 1.7405,
+      "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": 6676985552044032.0,
+  "total_flos": 7418872835604480.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null