Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d00312a11bb85421e2b02c24d0b846b7c746125e741249f110d00d86914aa3d
+oid sha256:80893a4b2991e2ff605b62e37323f3197cce25f5b315de8910abec6ea24b3c20
 size 40036040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f03a18828d8803b2be25e50bbb760d08950077963848306d35cb18c19af618e5
+oid sha256:9d8f05503bfa6fecd05300b839dd5f7bde8dcb32179d3554e6e40c1efe6b333a
 size 20814996

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b26abbf1b59934080d069888ddc280966a21772b32c06587e6b149de3c91db2
+oid sha256:561a55685a3cc1c3c67f8d1b76dcf29e73d0ebb9abc059e3b698558c2be1d65e
 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": 0.006674701029016409,
+  "epoch": 0.007416334476684898,
   "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": 7.99,
       "eval_steps_per_second": 7.99,
       "step": 9
+    },
+    {
+      "epoch": 0.007416334476684898,
+      "grad_norm": 27.757686614990234,
+      "learning_rate": 0.0002,
+      "loss": 11.5992,
+      "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": 731831875928064.0,
+  "total_flos": 813146528808960.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null