Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8eb7a43ce83555125330fee7c7c6c8b4bdbdc915a7b1c211aed8de41d7231ad0
+oid sha256:28a6652be9ed7bedb6de8a425307955b7c97992dc821b5309ef5212b06ffcab2
 size 9864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9736aa9be2e0d07ed54b511309fedbbc395b3203b08aa46ef6011cab32482d3
+oid sha256:fdd1237c647b52a298dcdd382e81f3b1a9a158fc47b711f2f3a1a0256fe54c42
 size 24006

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88a7979cf0154c645c28860441e6fd310e68f11fd8f5398f7137050e72f417a3
+oid sha256:162da4923a6f25f89d8b8ac25a1fa840b0f11b456ba4cc70887918f1fdbaa585
 size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96aa36799c943a9bfefa20f32f650908880b1404c454cf725bf5d9ee2c75343e
+oid sha256:126a95bf1277ff34f610ecef71ab3da4221c5fdf57145767d775e04c91223794
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 11.5,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.006002761270184284,
+  "epoch": 0.008003681693579047,
   "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": 150.215,
       "eval_steps_per_second": 37.561,
       "step": 150
+    },
+    {
+      "epoch": 0.006402945354863237,
+      "grad_norm": 1.4135210221866146e-05,
+      "learning_rate": 0.0001813903489357277,
+      "loss": 23.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.00680312943954219,
+      "grad_norm": 5.2519440941978246e-05,
+      "learning_rate": 0.00017609327897085954,
+      "loss": 23.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.007203313524221142,
+      "grad_norm": 9.449065692024305e-05,
+      "learning_rate": 0.00017045228564685694,
+      "loss": 23.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.007603497608900094,
+      "grad_norm": 0.0001462511863792315,
+      "learning_rate": 0.0001644948513161638,
+      "loss": 23.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.008003681693579047,
+      "grad_norm": 0.00014933152124285698,
+      "learning_rate": 0.00015825,
+      "loss": 23.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.008003681693579047,
+      "eval_loss": 11.5,
+      "eval_runtime": 69.7076,
+      "eval_samples_per_second": 150.945,
+      "eval_steps_per_second": 37.743,
+      "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": 3032102731776.0,
+  "total_flos": 4039478968320.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null