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:e76965ac0ed8d753e46487dec7fe3f2dcfde7f5bb884805e3e7df52ad9311462
+oid sha256:1d0c8125c314323debf3e2e9a2170bb2a6238f81452669fee40ab2bf49abbbeb
 size 216151256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f32b3cf40d967b7dc913518771c235a2fd118d58ddc7849fc094850325186fa
+oid sha256:3be1499db4c8507302ac2ad766810032221fbba7e5b4ba42c39bf0572fdb3210
 size 110412612

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be62651cc0fa25670490cc8653cf4e8dab49630a7a93d6af055ca1aab8fabfeb
+oid sha256:05b82f71131c7cd64698f261810dbddc4ef9086716ea2bf6bdf9d8a6f040e915
 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": 0.02547320007075889,
+  "epoch": 0.028303555634176542,
   "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": 5.283,
       "eval_steps_per_second": 2.646,
       "step": 9
+    },
+    {
+      "epoch": 0.028303555634176542,
+      "grad_norm": 0.39359647035598755,
+      "learning_rate": 0.0001,
+      "loss": 0.6108,
+      "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": 5.930010302585242e+16,
+  "total_flos": 6.588900336205824e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null