Training in progress, step 200, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8229a03173fdecd5b62082f72d500e9f9b4d252d351f4a390d9802733fdbc81
+oid sha256:99258ce78b5e71be96b85c446200bd05184fbf5f0538ad03ea9d51c205d4ce7a
 size 162933396

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4df3ec58412b1e338e1e7ad0b0bf2398ac8bf4e5610bc882335ce0260383db5a
+oid sha256:a8e66a0dd5515894c569f10320ca57410d726a3b361cea0adfe114c0f1ac5aa5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:321052ad5e93c8a107bd6c10f372f50285d863120fc0088befc39ec2733238fb
+oid sha256:530505d607699f384741067a5f9139d72f043713adb680898a3f1b5714170c97
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.012089949222213266,
+  "epoch": 0.016119932296284355,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -60,6 +60,28 @@
       "eval_samples_per_second": 16.093,
       "eval_steps_per_second": 8.047,
       "step": 150
+    },
+    {
+      "epoch": 0.012895945837027484,
+      "grad_norm": NaN,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.016119932296284355,
+      "grad_norm": NaN,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.016119932296284355,
+      "eval_loss": NaN,
+      "eval_runtime": 643.6392,
+      "eval_samples_per_second": 16.234,
+      "eval_steps_per_second": 8.118,
+      "step": 200
     }
   ],
   "logging_steps": 40,
@@ -74,7 +96,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 2
+        "early_stopping_patience_counter": 3
       }
     },
     "TrainerControl": {
@@ -83,12 +105,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.946893909209907e+16,
+  "total_flos": 6.594488973656064e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null