Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31158f9abf77439f82d2f7f17e2265e93937badb8b6eefcdd7d7e91880441d35
+oid sha256:18da5021fbb79e2b51d3ac244d506f0aa36afe9bba044c52274349d2474d9a51
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74cfbbb4fcfaa10c6458b62a72672df65879d2388477430964f0b59b454245a8
+oid sha256:3977da0bac2dd5aa96668d92a2b1754701fa65c985b16926a30c711c66e42606
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93122c6b6abacfb0c5c82bfe87cf21b6d9a18158b01b69b22b7fc137d1a9643b
+oid sha256:977e92a36c80d71d543381e40de4d1b0534573a2c48521b7b09a24d3931db4e9
 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": 0.00021259131092069754,
+  "epoch": 0.00023621256768966393,
   "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": 19.247,
       "eval_steps_per_second": 9.623,
       "step": 9
+    },
+    {
+      "epoch": 0.00023621256768966393,
+      "grad_norm": 1.6501195430755615,
+      "learning_rate": 0.0002,
+      "loss": 2.39,
+      "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": 1373581513850880.0,
+  "total_flos": 1517090030223360.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null