Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60c3ae985e8152f156025e87a1da3185c1147d80c463d4badce733cec41a306d
+oid sha256:18cbc1cd0f2b72e3108af9f63ed39f30057206d7a322a6996eaebdb72b5556c0
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21b421ba0526913142097c4a32033a6cd4b9eb761a162de2923b30393266f779
+oid sha256:08445d75b7308b5c36fbf52cb6738b0cfccc95f4dc935232308068c8f8224c41
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81feec53929608a3d2b539f66e29270211cb35072ffa9c1bcebaa955f7bdc514
+oid sha256:71e9af821c38bae7b342c85301f6dc4d8d96eaade7716ea8e604522769dc1743
 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": 0.005565002318750966,
+  "epoch": 0.006183335909723296,
   "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": 33.144,
       "eval_steps_per_second": 16.596,
       "step": 9
+    },
+    {
+      "epoch": 0.006183335909723296,
+      "grad_norm": 1.6402016878128052,
+      "learning_rate": 0.0002,
+      "loss": 1.5694,
+      "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": 1710846929534976.0,
+  "total_flos": 1895803354349568.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null