Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7614719d265c44c6749a3d5fa26a737be0bcdf1a81fa39c53b56e7cd0182c81e
+oid sha256:668d2e31857cbbda343ca592a4cc900f177a1b55572036175c05c43e45087ea3
 size 47235968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77e4588b8e0c0d099709eec0c9e9473d6e162ddf92f62f85757db76054e2930f
+oid sha256:a2ad5eae2802c5ba17e9dd2e4e2b2cc5525567d3edf794bdf9e922be748c29e1
 size 24410836

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:117713f911e3bbde232fed1f9c982d52569051843b0469e2720e7db50b1598ed
+oid sha256:cbfac41ab1a2c1afa0b2165fdcca0acf1b2f190ac4920762e3790de5b534d96f
 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": 0.005120910384068279,
+  "epoch": 0.005689900426742532,
   "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": 42.093,
       "eval_steps_per_second": 21.047,
       "step": 9
+    },
+    {
+      "epoch": 0.005689900426742532,
+      "grad_norm": 19.17963981628418,
+      "learning_rate": 0.0002,
+      "loss": 4.1686,
+      "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": 604785302568960.0,
+  "total_flos": 670167497441280.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null