Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94690690830017e6347789af52568e34b82b8fa55377598cf00e6910abab2f73
+oid sha256:4221118b129436730eabbb8d75b8543b4c45aeafdd2eae440e895241f15f4e08
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de66b946fc67277e38a0bc81e2676cb095389122bd04a89fbf00f589e1d0fdaf
+oid sha256:140d193ff5c962ff1892ae37b2a5970f055a57d7d058a20a0ef33914c4a3104b
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e8dadec0ac13fe08ed6f0b2ce6c0759a1bb8b461f8fb9a3d8c9d1ecba1a4dbe
+oid sha256:6f99c225b1e62527726e1c00f73b1b826f66dd6799fae34c3a65f86d6338b320
 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": 0.0014354066985645933,
+  "epoch": 0.001594896331738437,
   "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": 17.633,
       "eval_steps_per_second": 8.816,
       "step": 9
+    },
+    {
+      "epoch": 0.001594896331738437,
+      "grad_norm": 1.6461585760116577,
+      "learning_rate": 0.0002,
+      "loss": 4.1039,
+      "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": 3087049068380160.0,
+  "total_flos": 3403669485649920.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null