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:f55f6aeb20d5bc9b93803e4ddc77dcfeb2e521a782b687b1415db23d5b86c49c
+oid sha256:4b02890f72a11a488b20b7cda6dc04b3578c0744a324cba6ac533f33f62ce35b
 size 12609416

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a709eab9469fea2f8251a09432314ce20a6feb9f8a376cf192234b85bfc1e77a
+oid sha256:7dc0737a81e2631fe5c330d83efd71e872fe45445cbeb48c645bfb60b91694c2
 size 6615034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c1070b4b71b3aa6b0d173c2b7428c5d6455ce4abe75e6156073cc3fd4d802d3
+oid sha256:3af208be928351f886eeb10757a39eb1944b63462f6c3ea957ea6dfb0f8eb3c1
 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": 0.010462074978204011,
+  "epoch": 0.011624527753560012,
   "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": 64.704,
       "eval_steps_per_second": 32.441,
       "step": 9
+    },
+    {
+      "epoch": 0.011624527753560012,
+      "grad_norm": 2.4245104789733887,
+      "learning_rate": 0.0002,
+      "loss": 6.607,
+      "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": 95713807564800.0,
+  "total_flos": 105097514188800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null