Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51e8be5e06c2a06f02c41ecb622e9c47147abe64e3952034156af7ed24cb7ce5
+oid sha256:1cdee7e117608b4ca0ef686843146e610438fc8f1ce9085fae120b66afc9849a
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40bd2bc252edc6b00dc39cfef5f9958a6e9490cf444cd94e33e1341079d530df
+oid sha256:5c5347dc9128fd7f997e562b5dfedd9e932a46854358b7e335a08114b44aced4
 size 11710970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9827b398fc968e0b0684f99c11a527546e70ab824cd0ae8d6535c172e2f92b44
+oid sha256:589a495a456a288a3d3bfaca9b82c2e657ed19ad3f77e257b88f82fb5a6e2660
 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": 0.042105263157894736,
+  "epoch": 0.04678362573099415,
   "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": 56.995,
       "eval_steps_per_second": 28.497,
       "step": 9
+    },
+    {
+      "epoch": 0.04678362573099415,
+      "grad_norm": 1.449363112449646,
+      "learning_rate": 0.0002,
+      "loss": 2.181,
+      "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": 408927376244736.0,
+  "total_flos": 451022841446400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null