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:d13fbc13144a990f465ef91f4e90defc1709ade1466caac0a6e90948ee83c458
+oid sha256:74c3c5c569754ce7ade4d1c7f6eff09afd4282456544c1bf1c461c015a765fdf
 size 390888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2613027427580dae177656a8f4ac1ed333d6847300284c7c34a5de0382dfe7ec
+oid sha256:0374371c4a7904574e83efb7282d8e6f8a854e539bcf08b4a4a9794467e7cb84
 size 819770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3c4140fd6dce9e65319f7d658a1b225649f7fb6d3492d10c3e3d2622515091c
+oid sha256:b286680e3925bc31baee6d7023f8d43842b88db19834690bb82e4de8877e4601
 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": 0.03769633507853403,
+  "epoch": 0.041884816753926704,
   "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": 85.653,
       "eval_steps_per_second": 43.25,
       "step": 9
+    },
+    {
+      "epoch": 0.041884816753926704,
+      "grad_norm": 8.484256744384766,
+      "learning_rate": 0.0002,
+      "loss": 8.708,
+      "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": 590026899456.0,
+  "total_flos": 655585443840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null