Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e893e1eb229b5d8bfdc440b8003b12d0dae5396c16e22b31c76cb22951170a8
+oid sha256:4744a2216ba605d2c6cb27c5eee20ddf0d5b77eb4f4c6c79607fe480b132d0fe
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e0f7b13c23ee94f1981489a9bc60395a11173f035ec681a8dc9b2f59e241f69
+oid sha256:a0ed36c6d8650c6eaffc0658628510262dd716f102634cbead199919195cd94c
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0b20db3596a2edec9e10a5bcdb00be79cffac991bb5d006b2a6127e36af7471
+oid sha256:cf31bb6ac85ba138e86eb732286ff40f519ea5ca978d8d3b947c1db40708e52b
 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": 0.0059210526315789476,
+  "epoch": 0.006578947368421052,
   "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": 20.721,
       "eval_steps_per_second": 10.361,
       "step": 9
+    },
+    {
+      "epoch": 0.006578947368421052,
+      "grad_norm": 0.4082265794277191,
+      "learning_rate": 0.0002,
+      "loss": 2.2388,
+      "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": 2512929958133760.0,
+  "total_flos": 2801298969722880.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null