Training in progress, step 200, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88897aae948a7f1aa08a2b65863577cd1c611b91bf994f2be1f2746d1654a8f3
+oid sha256:7d1a5e15bd05defd2f2b4eb1ce0347cafcf9d08a600a35d4c4c302d893e2fe51
 size 61297812

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8aaa29f442def983c1291d91388d8c8fdd7bfd52d12d6fef8e31698ba0d71810
+oid sha256:b0ced129acba1e1a34c766a17b2fd6ac29b6ad5a6d4b025744663ee483dade79
 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": 0.027091093802912292,
+  "epoch": 0.036121458403883054,
   "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": 39.341,
       "eval_steps_per_second": 19.675,
       "step": 150
+    },
+    {
+      "epoch": 0.028897166723106445,
+      "grad_norm": NaN,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.036121458403883054,
+      "grad_norm": NaN,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.036121458403883054,
+      "eval_loss": NaN,
+      "eval_runtime": 120.8447,
+      "eval_samples_per_second": 38.587,
+      "eval_steps_per_second": 19.298,
+      "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": 9657410125824000.0,
+  "total_flos": 1.2876546834432e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null