Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2aead67378eb080b6439e73f92b79b22ba3fff6719672a9daece2960f68cbfb9
+oid sha256:be0ce45c4bb7556c7887e8bba639a476b63c6c45d6eb3897765e4481c59abb3a
 size 390888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28dc4ef51aaf7b90827fc66fd26b60dfedb06701a7589abb0499ddf65ebb125c
+oid sha256:95d5cce4f64aa655231adb3b76da9449beae45664123ff07bb0a1b5d940d47bc
 size 819770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffe0152387846c1162de177cdc53167a9183696b149d3eb20d4cf5fbd6b53e78
+oid sha256:557fadda68f81af2c774a79a4c369bd061cd88e6452778324e57a9edcd611ffb
 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": 0.035285469247733396,
+  "epoch": 0.039206076941926,
   "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": 343.979,
       "eval_steps_per_second": 171.989,
       "step": 9
+    },
+    {
+      "epoch": 0.039206076941926,
+      "grad_norm": 1.9871147871017456,
+      "learning_rate": 0.0001,
+      "loss": 6.8283,
+      "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": 2360107597824.0,
+  "total_flos": 2622341775360.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null