Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:384df8e64544c483bf640971572f4ecbc1628cffdf1bcf1c1b3b1981318cca24
+oid sha256:5a4b9340b44e7d78d641a5b7fe6d880111d04b0caa495971d57735ea0bcae919
 size 9864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcaf547e9ca2bc317075ffd7993c1f11117616da4f2aef5c8e878860ca623821
+oid sha256:5d86c53d23a56f025ce2177a311535e0fd10b8b7a3909b4d5834ac3b2296ebcf
 size 24006

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b878e9fc2d256cba4a64372e379e6136cb65d164862216d964dedbf7b340f41d
+oid sha256:ab03c070f34e6e767282a899da280a1f1827a4082bb3fb009c3916de684f53a4
 size 14180

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:317ba05605195c1d4e2040522f74e7ab98f17d7a309d9ff3aaeabe58a301e214
+oid sha256:c9abf3b00130ebbc35657fb7788755e92886d9a53e2a5677dea2a31074b05473
 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": 151.56,
       "eval_steps_per_second": 37.89,
       "step": 150
+    },
+    {
+      "epoch": 0.00156787425648463,
+      "grad_norm": 3.542968988767825e-05,
+      "learning_rate": 0.00018053067903555837,
+      "loss": 23.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.0016658663975149192,
+      "grad_norm": 2.9423687010421418e-05,
+      "learning_rate": 0.00017525871366768012,
+      "loss": 23.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.0017638585385452087,
+      "grad_norm": 3.727466537384316e-05,
+      "learning_rate": 0.00016964445490919413,
+      "loss": 23.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.001861850679575498,
+      "grad_norm": 6.14957680227235e-05,
+      "learning_rate": 0.00016371525486442843,
+      "loss": 23.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.0019598428206057876,
+      "grad_norm": 0.0003162079374305904,
+      "learning_rate": 0.0001575,
+      "loss": 23.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.0019598428206057876,
+      "eval_loss": 11.5,
+      "eval_runtime": 283.5247,
+      "eval_samples_per_second": 151.549,
+      "eval_steps_per_second": 37.887,
+      "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": 3002180665344.0,
+  "total_flos": 3999582879744.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null