Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0de374e99949bbb7b77f1e08bb579d169a79f7fa4b39a59e81e7c0c8824392e6
+oid sha256:99947e144b7f825097f58b83ba5cbafcda17740b60d8314cc6dbe5196fc02587
 size 14696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3cf075bef0a4623f4350eab20d9bfe51e28768b87129bb894ee121bc53b3c72
+oid sha256:76f090600cd46bb71b770a2e3f18e65365f190e73a94cb26e2ead8129623e502
 size 39398

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:756f5354e70cf8ea389a55b973a7a83a0698ead411ced9a550dad53863f8e805
+oid sha256:85d7dcb82cc9c8edaa0c5feb250680d2ea54a2f1b97d0e9fe9ea7b25c22b72c1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1eca0ddb3ec890c90e8e6e7325bec40cdb8b59e4bebf5c0da8473b02809de875
+oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.020199186421658015,
+  "epoch": 0.022443540468508907,
   "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": 582.476,
       "eval_steps_per_second": 291.626,
       "step": 9
+    },
+    {
+      "epoch": 0.022443540468508907,
+      "grad_norm": 0.005243333987891674,
+      "learning_rate": 0.0001,
+      "loss": 11.9326,
+      "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": 5140021248.0,
+  "total_flos": 5671747584.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null