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:d3e406c0bfe59e75ab8df0dd22aedff5f4cfb16c17f8072d570143ca4ebb28e9
+oid sha256:10eca25b9c26d910656b0b51673d68243399d4226581d7d50fa973c9510e11bc
 size 9864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f645147b374e11844486d65a4e6bbf6a5c401ea06cedce78c8c04db893d090b
+oid sha256:f50da6c3b269afc8d9fb56c97d4ee741c032c62ac1fb52c3416fcee133644627
 size 24006

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e34e3c64adab84fa97b529f96717304601b7faa9caa2676f7d55a34900bf567
+oid sha256:494d32cfe0982cc4670431f398b7bac04d6f568ac220e275ca821c692f1a6259
 size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f2e88614aff46cd1ada70fbc3b2ec41b24cceb0ef1b4801de4a83c39b9b26bc
+oid sha256:1782a34e31686f496476697aa213a8a4eb0ce51a76589caf9070e07b3ee2de6a
 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": 151.388,
       "eval_steps_per_second": 37.847,
       "step": 150
+    },
+    {
+      "epoch": 0.00156787425648463,
+      "grad_norm": 2.6445213734405115e-05,
+      "learning_rate": 0.000184829028536405,
+      "loss": 23.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.0016658663975149192,
+      "grad_norm": 7.023169746389613e-05,
+      "learning_rate": 0.00017943154018357726,
+      "loss": 23.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.0017638585385452087,
+      "grad_norm": 7.002270285738632e-05,
+      "learning_rate": 0.00017368360859750824,
+      "loss": 23.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.001861850679575498,
+      "grad_norm": 0.0001267843908863142,
+      "learning_rate": 0.00016761323712310527,
+      "loss": 23.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.0019598428206057876,
+      "grad_norm": 0.0002765184617601335,
+      "learning_rate": 0.00016125,
+      "loss": 23.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.0019598428206057876,
+      "eval_loss": 11.5,
+      "eval_runtime": 283.5571,
+      "eval_samples_per_second": 151.532,
+      "eval_steps_per_second": 37.883,
+      "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": 3012154687488.0,
+  "total_flos": 4019530924032.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null