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:ad1c1f8dad9193636b580b44b8eccda0073988e822421614a941cc4c753aa03b
+oid sha256:cba6df109600eddf5058c99cf629a75308923ea3443214a1c55f3879ae8dff40
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1f596c42641cddf38f4ed961cc31b9326ef36699b5ec07f10b0cdb50f684756
+oid sha256:85d0ce7d9973c62f51982e47e0252973f74528b621eed8231022758fec39b7ac
 size 170920084

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f168a48809971cd222155ba1abbde2d913fe1426d9c9c66d023c27e955c2808
+oid sha256:240be3e06fbeb9708e3934ba8b11cb3604176df5ec1e1630cb26ff9f3df30d9b
 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": 0.1439453661441803,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.051035597329137074,
+  "epoch": 0.0680474631055161,
   "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": 11.376,
       "eval_steps_per_second": 5.69,
       "step": 150
+    },
+    {
+      "epoch": 0.05443797048441288,
+      "grad_norm": 6.40620756149292,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.2657,
+      "step": 160
+    },
+    {
+      "epoch": 0.0680474631055161,
+      "grad_norm": 36.11760330200195,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 1.2847,
+      "step": 200
+    },
+    {
+      "epoch": 0.0680474631055161,
+      "eval_loss": 0.1601235717535019,
+      "eval_runtime": 217.8253,
+      "eval_samples_per_second": 11.362,
+      "eval_steps_per_second": 5.683,
+      "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": 7.602974830362624e+16,
+  "total_flos": 1.0157928000100762e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null