Training in progress, step 250, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff9db6e23c92fdcbf6127ff35c7f1fd6ef4cf0f8084ba798e623b35b94f01bd4
+oid sha256:cef398831b79f1092f987f6b6603e568cfafaf1fb9f8837c2eceed0cadcdeee3
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7215daaf4083333c881aec3f934a4eca6017b8e9b07ea9f78670a882171a4b4
+oid sha256:229cf4c106072fb969132bf4ab3473201870c2d8f6d222dfad2adfc866afb050
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e31a0db1fe901aae8d342a723e96edfbdf00ec59df64e785ff59a6a197f3a04
+oid sha256:95226b9443ed4e38c27bbb8187789d508a89cfc90744595951e5068e3128acf8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:126a95bf1277ff34f610ecef71ab3da4221c5fdf57145767d775e04c91223794
+oid sha256:180579b18c9e708a5cf9b411c96230bb3cb8d2c4c87c23004deaa70e5c990f72
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.35316547751426697,
   "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 0.175054704595186,
+  "epoch": 0.2188183807439825,
   "eval_steps": 50,
-  "global_step": 200,
+  "global_step": 250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,49 @@
       "eval_samples_per_second": 10.049,
       "eval_steps_per_second": 2.528,
       "step": 200
+    },
+    {
+      "epoch": 0.1838074398249453,
+      "grad_norm": 0.5865310430526733,
+      "learning_rate": 0.00015174815598624768,
+      "loss": 0.7926,
+      "step": 210
+    },
+    {
+      "epoch": 0.1925601750547046,
+      "grad_norm": 0.6336154341697693,
+      "learning_rate": 0.00014502099560537873,
+      "loss": 0.7418,
+      "step": 220
+    },
+    {
+      "epoch": 0.2013129102844639,
+      "grad_norm": 0.0030132222454994917,
+      "learning_rate": 0.00013810129290655696,
+      "loss": 0.1631,
+      "step": 230
+    },
+    {
+      "epoch": 0.2100656455142232,
+      "grad_norm": 0.004187281243503094,
+      "learning_rate": 0.00013102275998576495,
+      "loss": 0.001,
+      "step": 240
+    },
+    {
+      "epoch": 0.2188183807439825,
+      "grad_norm": 0.03684316575527191,
+      "learning_rate": 0.00012381988274386116,
+      "loss": 0.0009,
+      "step": 250
+    },
+    {
+      "epoch": 0.2188183807439825,
+      "eval_loss": 0.3651936948299408,
+      "eval_runtime": 48.1017,
+      "eval_samples_per_second": 10.0,
+      "eval_steps_per_second": 2.516,
+      "step": 250
     }
   ],
   "logging_steps": 10,
@@ -201,7 +244,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 2
+        "early_stopping_patience_counter": 3
       }
     },
     "TrainerControl": {
@@ -210,12 +253,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6.540687952576512e+16,
+  "total_flos": 8.17585994072064e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null