Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a1d84ea17937cd9f06c3759118d86dadb9729b48209f514e1917c5b35389542
+oid sha256:940616eaf780402523bf46b8c5fec3c9efe84d7b329a832ead7075e99453a734
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3eb068e2af2a6540fbfac7600c671d5fe22e12e261ec5c267a382f7bc7662b2c
+oid sha256:9e1b16115b9908eab00f4676b7080cd99f632689e4ec4a021e5ab6402f96b5a6
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c61993168353c8d250f3af4b44e28b5ee9094b106e3aa05b160282ff8ed2ef0
+oid sha256:afb545f8e58697058fbefb3de9020d83f15fa2aa26ad3230bc2a6d11766abf95
 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": 0.08411214953271028,
+  "epoch": 0.09345794392523364,
   "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": 4.554,
       "eval_steps_per_second": 2.328,
       "step": 9
+    },
+    {
+      "epoch": 0.09345794392523364,
+      "grad_norm": 1.7849133014678955,
+      "learning_rate": 0.0002,
+      "loss": 0.1533,
+      "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": 1.1762247634255872e+16,
+  "total_flos": 1.306916403806208e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null