Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fb905e53ff021b1d82226c7935e07a629c536872e76787934fd881600c2231d
+oid sha256:48fda28e7c85c1bb0eb0906255d500943689db85e3abb6aefbdfdddc58066166
 size 9864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46d243a03a8f4a0ca819b5b50cac3bd343c55d2dc007efcc37a1dea97b4729a7
+oid sha256:230cc7f167440f0df27c061e7f91524c7394f1f700131551bb8ba6d38efe5462
 size 24006

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60423c71c5b8e73600bff527b52de9581f2d28b792427fd4885a3b17bce0902d
+oid sha256:64d45ea449e8097764aa8707a9b9226eaf553015b9a7605dce73a54836985e52
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1b1f2714a85aa9c62c59c149ed93d359ad92fd51fac9fa652c3e63d5b612e43
+oid sha256:dede1fa048a18dfec7c909d545c1f9f24ebdbe5d9b70332aebc26e0cb3e8a94f
 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": 151.526,
       "eval_steps_per_second": 37.881,
       "step": 150
+    },
+    {
+      "epoch": 0.00156787425648463,
+      "grad_norm": 2.330802453798242e-05,
+      "learning_rate": 0.00017967100913538904,
+      "loss": 23.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.0016658663975149192,
+      "grad_norm": 6.599299376830459e-05,
+      "learning_rate": 0.0001744241483645007,
+      "loss": 23.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.0017638585385452087,
+      "grad_norm": 6.412757647922263e-05,
+      "learning_rate": 0.00016883662417153128,
+      "loss": 23.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.001861850679575498,
+      "grad_norm": 6.308197043836117e-05,
+      "learning_rate": 0.00016293565841269306,
+      "loss": 23.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.0019598428206057876,
+      "grad_norm": 0.0002540747227612883,
+      "learning_rate": 0.00015675000000000002,
+      "loss": 23.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.0019598428206057876,
+      "eval_loss": 11.5,
+      "eval_runtime": 283.3935,
+      "eval_samples_per_second": 151.62,
+      "eval_steps_per_second": 37.905,
+      "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": 4009556901888.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null