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:bc88e77eaf52868617491a1aa575c7d4b77cd353728dc93a5d2b3e242d4c3025
+oid sha256:0c876fc94e10d618b56d16f0b465fafaace1b772d3f424bb2dc03240fefa3b6c
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5f6ea4185af4f7f508f20d964fe708f6b7efe43da67be528bce31edeb717f51
+oid sha256:13ee9705d097f7a6b79480cfcd0324c8acf69083c8f32cd4900135c5c21430a3
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b90a19943f8ef28f7f3c1abafd8de7b24ff68c3eda11dffdc748b1a1d989fcb2
+oid sha256:574c700717b33f47ad8a70b47083271e5db120d9e87ae1c83258d7702c5eeb81
 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": 0.02706766917293233,
+  "epoch": 0.03007518796992481,
   "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": 32.103,
       "eval_steps_per_second": 16.052,
       "step": 9
+    },
+    {
+      "epoch": 0.03007518796992481,
+      "grad_norm": 4.671468257904053,
+      "learning_rate": 0.0002,
+      "loss": 4.0647,
+      "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": 1664607823331328.0,
+  "total_flos": 1849564248145920.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null