Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e7881d7b2b61ce0bea41bb5cdcf47d89f1ad7cfee1826ead3d2543c4b6ddd8f
+oid sha256:83804ffd05c95af3acf33f1319f353c8aa0f533e312b874026bba3aa6906e715
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fdc4134f6c5b306b5f271edf1ffd3a800f44175fb61cfcaf68b21ecd6369e99
+oid sha256:c3b30eb6238349ae5982c6486ca925d56ffc6b0012d89fa6a737c0c9fc7432d9
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7170a2d9b24ecc77552af509fa5ca848d0a66f21c29b073517cc02fd19368fe3
+oid sha256:d8b308b5e594ea75d70a9db0c7e4c8ae8b3c774396b79358868a60b3a58dba9e
 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

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0003478529741429289,
+  "epoch": 0.00038650330460325436,
   "eval_steps": 3,
-  "global_step": 9,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -103,6 +103,13 @@
       "eval_samples_per_second": 15.169,
       "eval_steps_per_second": 7.585,
       "step": 9
+    },
+    {
+      "epoch": 0.00038650330460325436,
+      "grad_norm": 0.7762258052825928,
+      "learning_rate": 0.00018,
+      "loss": 1.705,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -117,12 +124,12 @@
         "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