Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d65631f63710eef60db1df6ea21802b0102a05a0a33208fc3c04cf498ab7f6e
+oid sha256:f1d1064cc3f551305b35512e277e11f23c9dbcf55b0e4fd39edd39597c57485c
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b739b7988211135826a1933575db03c251b4611b0de38bbee2e19ebe7f43c95b
+oid sha256:d48a05988060453571b1cb878d594e161dd5f7293dcf119e8474cfc7ebc4ad61
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40f97bfccd229445f360530dbc1fbaff299ee1ca72d89b2724959b4b2d971e0d
+oid sha256:ca1b3696f6862fa46dcee829a2b9bcd052353b7f179825893b5dce308f7619d7
 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": 0.003511167463181508,
+  "epoch": 0.0039012971813127866,
   "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": 18.765,
       "eval_steps_per_second": 9.383,
       "step": 9
+    },
+    {
+      "epoch": 0.0039012971813127866,
+      "grad_norm": 3.0988426208496094,
+      "learning_rate": 0.0002,
+      "loss": 3.2137,
+      "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": 3110988870057984.0,
+  "total_flos": 3461522827247616.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null