Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e685f9de10ae8e0042d030f3ef5d1d4e12cf5a4bcdcba2b413625675f94305e
+oid sha256:4154661babda0e24bc2ff0e2e12264eaec2b8490216fc87e59aafa5e33c841fe
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2f786fd3f840ceea0e074566724939613c3aa157fa9eab561d6aae45dc993c2
+oid sha256:49daec3d14cc3900f861c0d99878d1ce7d49e32fa404ad5a23c78b75252b88ee
 size 160172858

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54088f61daf67ba3987886527d2520040d63916cf72a674a3a58d1cc4e57624a
+oid sha256:cf31bb6ac85ba138e86eb732286ff40f519ea5ca978d8d3b947c1db40708e52b
 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": 0.0009637006103437199,
+  "epoch": 0.0010707784559374665,
   "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": 10.633,
       "eval_steps_per_second": 10.633,
       "step": 9
+    },
+    {
+      "epoch": 0.0010707784559374665,
+      "grad_norm": 0.6000295877456665,
+      "learning_rate": 0.0002,
+      "loss": 0.7515,
+      "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": 2524536360665088.0,
+  "total_flos": 2768846331052032.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null