Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b3a6581ae97b021c5280e77b51d4bef4fd7d12057b347470336799cd93dfb36
+oid sha256:1c722142997d6783369ac097bc76dedf8ee96d81320cd70bcdddaa924a5ab4eb
 size 6804608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:580627a591ab2e9562738dbf84f494f731c8564e463c36e050b81bed833bf321
+oid sha256:7ebdb38ec328479165845841d9c4a00d2aa66fd11a87dca8a07cbcce6ee1726a
 size 3633530

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d648a1322336ba65450c8c6b38551a9c8a4b8d3ca0a43997d4dca4e78ff923ae
+oid sha256:df2eff7fc04c424d03efebb207948c12df40c4005d61c167cc0982b8e6c469d5
 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": 0.0001264422317053896,
+  "epoch": 0.000140491368561544,
   "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": 73.447,
       "eval_steps_per_second": 36.723,
       "step": 9
+    },
+    {
+      "epoch": 0.000140491368561544,
+      "grad_norm": 6.2739386558532715,
+      "learning_rate": 0.0002,
+      "loss": 11.6255,
+      "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": 30863385427968.0,
+  "total_flos": 34292650475520.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null