Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57f7d15e87a1345f460979fe7b195964be7ccf8f5bfbb4614d0c5eda491b99f0
+oid sha256:f5f7d93410dbd36b756feafc1c872a7b1f314893b30613b368971d23eb3eb81c
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a97e5679abdd3c88169da7348fc41838f93ac996f88be2709b5bf432ee98f1e
+oid sha256:394919cbfa2382f759d13b6e2ab56bcdfaa9843350e784488c4bc06088190641
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64a4194de54d6d7d6f878f2d2a5d9788db19c7edbf35d3e4277e1855d2306354
+oid sha256:4ae13db9a08f67f94954df1508ef4b85f07ce87b424f467e1bfc8d5110842656
 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": 0.005650604300737718,
+  "epoch": 0.006278449223041909,
   "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": 18.732,
       "eval_steps_per_second": 9.38,
       "step": 9
+    },
+    {
+      "epoch": 0.006278449223041909,
+      "grad_norm": 3.829953670501709,
+      "learning_rate": 0.0002,
+      "loss": 5.4463,
+      "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": 2849601874821120.0,
+  "total_flos": 3166224305356800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null