Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98af3491ea730a4350238c6641beccb1957a6a655c1919847c8ecb869d277bc1
+oid sha256:b1dc4b26e0a4ffa66f478c9b25ab1f7a2edc280ed97f0f83572d9686c26e2ffe
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5079f41c1b792f7f44161652fabedefebee91d98e659a1fd4af474894f625768
+oid sha256:dcaa7de5a654d2ec383548348dded61b3b23b3996fad461935ea0a9f71f49d3b
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92fcfdecbe8e06023b8f1d0c13f16c778064bbbcf1e94aaddd84cfee35dc98bd
+oid sha256:bb2cc5b66146e2ad348c59ee418ab730ba1f58e730c588c98d1478dc3471953b
 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": 0.010452961672473868,
+  "epoch": 0.011614401858304297,
   "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": 10.51,
       "eval_steps_per_second": 5.269,
       "step": 9
+    },
+    {
+      "epoch": 0.011614401858304297,
+      "grad_norm": 0.1530240923166275,
+      "learning_rate": 0.0002,
+      "loss": 1.0511,
+      "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": 2962481278353408.0,
+  "total_flos": 3223876685266944.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null