Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c5c44d0975dc4b72b69461be3bb048f6d2107b4559b124ac826b4d1ffe2548f
+oid sha256:07c94fa0c4635f85bb48d48493bb17c7a13de9264636d9fb8b7d54ebb16a7126
 size 104902272

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bcecdb9e36c2dd86afe520fde2cb722824fea586c3d31379053777cb01ebb01
+oid sha256:2cad2ad52c3221d64bcd1bf6a43da1887fb2626626ac5caf15db0aea6546e6db
 size 53622996

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed34390a764668e92ff7e77eaebad3d1854e0f9a41fb8aba2b2390c65bcd0fcb
+oid sha256:43500146af380d1ac3d4156cc3442adb022f46615b8c7bd120d1e988a1d0347c
 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": 0.00021259131092069754,
+  "epoch": 0.00023621256768966393,
   "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": 13.327,
       "eval_steps_per_second": 6.663,
       "step": 9
+    },
+    {
+      "epoch": 0.00023621256768966393,
+      "grad_norm": 1.4865165948867798,
+      "learning_rate": 0.0002,
+      "loss": 6.1353,
+      "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": 5568752108175360.0,
+  "total_flos": 6196217134448640.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null