Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d59b9e1a92f7305939d2f0c45593d4fc76b32fb9de6ec1dcb7077fadb1b75aa
+oid sha256:1cbddcf1c3580c6f2fb59b773dbcff23078926feb494170972f1bf775609c568
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:171cf63a1306630d3e2d026d59e582e605a24b135907a360761e948dadc54eaa
+oid sha256:f202746f4560bcca07b371c595d8c0df11868760211b92a6182973f9a697b2bb
 size 111142

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4d5a61f54fc87372e46a202a94df31ed2db3cd5d6d0426b43d1ce44b91621bb
+oid sha256:1c32cc2e7fed49bbe1a22bbae17013f45779209354422f104bc00c3e8ae9497e
 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": 0.0008771929824561404,
+  "epoch": 0.0009746588693957114,
   "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": 317.645,
       "eval_steps_per_second": 158.822,
       "step": 9
+    },
+    {
+      "epoch": 0.0009746588693957114,
+      "grad_norm": 0.16271695494651794,
+      "learning_rate": 0.0001,
+      "loss": 11.7674,
+      "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": 687487647744.0,
+  "total_flos": 763875164160.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null