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:f43cf85787a5b0ec1d3bd415a163827ee1456ed2cb5324958a31e5e65c37ecee
+oid sha256:1b7c61370bc727dd054d1d81ddf05ea73e51bc7c62ddced051e41d94e672854d
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f7adfcbcdead734a76726f6cc961749f2faaeeed41fe3d03a5573b4a9b5b7c5
+oid sha256:e56cccf5f88706508ea1b90c9c5551faa5013269947188612c6afd176498547b
 size 49846260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:435f128f828c406f26123ce127372a7c2d56c5195044db2df1ad8a9fa02e39c6
+oid sha256:05e22fba92b29c1f5f0cd59a19fdf634f506ef846ae85ca8af68d60096387010
 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": 0.0032307278111819077,
+  "epoch": 0.0035896975679798977,
   "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": 3.313,
       "eval_steps_per_second": 1.658,
       "step": 9
+    },
+    {
+      "epoch": 0.0035896975679798977,
+      "grad_norm": 2.710617780685425,
+      "learning_rate": 0.0002,
+      "loss": 0.5559,
+      "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": 5030717272621056.0,
+  "total_flos": 5589685858467840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null