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:ca7b708749625940367dc254cd82674c71f639fb62335b0ecaadfed15c57437f
+oid sha256:75e56d91a41830ecb01d11d0884c687265f2df76df88a60394785a9c6dd28ea5
 size 65309632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2f20fcaab207b7d9fa118758fc479300f07a763d5b37b297991d4164167a035
+oid sha256:152ac830ca3a64edb9295dfc6c0707cdfd5b180601fce1f159e3bca43e496157
 size 33424212

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:487921a1acd258b82e58b9ec98a7bf8fbb6715ade97fa26c5f93634426742553
+oid sha256:e7a3cb48a6d6dd27fc13994f6dc6775c95e0795a042b71c5eef13e3e74c00be7
 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": 0.0005868257616509365,
+  "epoch": 0.0006520286240565961,
   "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": 36.11,
       "eval_steps_per_second": 18.055,
       "step": 9
+    },
+    {
+      "epoch": 0.0006520286240565961,
+      "grad_norm": 9.884368896484375,
+      "learning_rate": 0.0002,
+      "loss": 11.8573,
+      "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": 1469230227652608.0,
+  "total_flos": 1632478030725120.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null