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:f2dff01153873da707395bca6bf96a30ca92ec32043387ec4568ad55128a0bdb
+oid sha256:1f164cfcfafb72bf0b62fa07a8036a015df84c53b73bb2c724ce3d7381cc1575
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efe1ca1a057dbb9f049a0cd15b912f8f1b7f38ee99c6c7dfc30e1e5fe7b185d6
+oid sha256:ba2a4932916a02c6cb772b74d4d6046e4a3affb1b35a5b0b41b7071994629d92
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:915103fe450d953b29e1d31a1d1e65678aaa8be9d58fd089a14a19ed1a7723ea
+oid sha256:413ae6e59b7750ae76a5bca4ac2c7fe394a53f18547a89c6d1c6a7aa1a7a7812
 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": 0.00033707549554779447,
+  "epoch": 0.0003745283283864383,
   "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": 54.607,
       "eval_steps_per_second": 27.306,
       "step": 9
+    },
+    {
+      "epoch": 0.0003745283283864383,
+      "grad_norm": 0.13710124790668488,
+      "learning_rate": 0.0002,
+      "loss": 0.973,
+      "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": 402872365744128.0,
+  "total_flos": 441241162481664.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null