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:fc326d449d8a35aaeaf5b7208f9b446eaadcf3576f75852bdeaf386a38b24415
+oid sha256:f30cf2215b42e61c2b8fb45994e5b96ee692c57f74627d6b9c994a8cd22215ad
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ada468f216d8de05afdb5cff38a0cd13d2fcb8e9331269dea8b84d009cdec4a3
+oid sha256:7e0e8b3e4fc8e87ce7ac5a8fe93bf1f8c87e1fc1588c1eb7f8f5ad3c7e15eb9e
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f33169c41abfc2782696aae4031cb159043e279d849b89a0c624dc050b972ef1
+oid sha256:e512fd1b23889ea705683aabed6066a8ef2089ddef5c8810bef20005556fa356
 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": 0.013910355486862442,
+  "epoch": 0.015455950540958269,
   "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": 56.666,
       "eval_steps_per_second": 28.437,
       "step": 9
+    },
+    {
+      "epoch": 0.015455950540958269,
+      "grad_norm": 0.37601980566978455,
+      "learning_rate": 0.0002,
+      "loss": 1.0025,
+      "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": 255791978250240.0,
+  "total_flos": 287765975531520.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null