Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:910e404b2b59e72b3e6c90c18109f69406737c8b4e44e2f45f3c92cb62fe5467
+oid sha256:93610978150fd9b7b375c86704e55b8b782d90047cd1e5a1c5dbf0aab49fd3d4
 size 9864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0691d17739861fe60b765afda50168dfe945c5771c3fc627b17e0cd63afd960
+oid sha256:720af88f10e1769cae6e434df2c496f6d03b8ecdc98a3ec3604f154d6d9cc9e1
 size 24006

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:921b6dffccb83ff8d23238ad9633bfabc41949cd706bc19f44b8f1ef432e4850
+oid sha256:f4487a6652a1f955709b23a104d311f38248f20d654f5072fa3c004ed21a09d0
 size 14180

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36d662a32df821fd1f61229044a1b057cdbb06bb6df8ba0be9914f76ab89a8c3
+oid sha256:4d4f6cbb9698c5703beaed4a561bedcaa249201096cc6cbb6aac194285ef07b2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 11.5,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.0014698821154543406,
+  "epoch": 0.0019598428206057876,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 151.563,
       "eval_steps_per_second": 37.891,
       "step": 150
+    },
+    {
+      "epoch": 0.00156787425648463,
+      "grad_norm": 4.204720244160853e-05,
+      "learning_rate": 0.0001856886984365743,
+      "loss": 23.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.0016658663975149192,
+      "grad_norm": 8.322260691784322e-05,
+      "learning_rate": 0.00018026610548675667,
+      "loss": 23.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.0017638585385452087,
+      "grad_norm": 8.221106691053137e-05,
+      "learning_rate": 0.0001744914393351711,
+      "loss": 23.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.001861850679575498,
+      "grad_norm": 4.8690235416870564e-05,
+      "learning_rate": 0.00016839283357484065,
+      "loss": 23.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.0019598428206057876,
+      "grad_norm": 0.00044765390339307487,
+      "learning_rate": 0.00016199999999999998,
+      "loss": 23.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.0019598428206057876,
+      "eval_loss": 11.5,
+      "eval_runtime": 283.4302,
+      "eval_samples_per_second": 151.6,
+      "eval_steps_per_second": 37.9,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -158,7 +201,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 2
+        "early_stopping_patience_counter": 3
       }
     },
     "TrainerControl": {
@@ -167,12 +210,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3022128709632.0,
+  "total_flos": 4019530924032.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null