Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:355c026c970ef6209a047f854a987f4b2f2bbb3e6b9208b6e9a5ad0c12c512c4
+oid sha256:2d33057caf117f6db8b4dcbe6c8af2a3375cc192accf469eaab6c8436ff95649
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2df2148812936d9bde0394501f5a610f846caf523535cd7c0cd81ed9838193e
+oid sha256:f8f36817fe08713f71303e1fe01b811ec8ecbdea008286f4d094ec4e982b4e31
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d350fb63629b5bbbb1b6067754fd294bad8dde900daee7588c8d726fa5fb4835
+oid sha256:a43ddc14c7ec51649c402ce4d44c026af80252540e3350ce764c94187f06272c
 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": 0.0007658759706414211,
+  "epoch": 0.0008509733007126901,
   "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": 20.319,
       "eval_steps_per_second": 10.159,
       "step": 9
+    },
+    {
+      "epoch": 0.0008509733007126901,
+      "grad_norm": 1.642189383506775,
+      "learning_rate": 0.0002,
+      "loss": 2.0084,
+      "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": 2849584887889920.0,
+  "total_flos": 3166205430988800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null