Training in progress, step 250, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90e5772404c246f879a51f9fbc160d928bbd3292efdde08e067e3557a32f2cff
+oid sha256:a3ab4b5d668a646f26d96f6dbb21c13dfeec990cb143f4c6e69304b25b56b93a
 size 1001465824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55562a4bb595b9c937a47e2b592ca9b4209134c55e5b2eb1dc1166e4c4932136
+oid sha256:7081c32460c2b00a7f9aae5ea2f0fd32b9164d298343236f71c51b7735457c18
 size 509176980

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:978adf3ea0400b68da2de3bc98072490751633d1be6e1827474e23d2c7f34414
+oid sha256:497a369390e6a383eac0de681b4a7d0ac9b6457e419072bfbbdb16ca18ffbad6
 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": 0.1364036649465561,
-  "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.1088139281828074,
+  "best_metric": 0.13536955416202545,
+  "best_model_checkpoint": "miner_id_24/checkpoint-250",
+  "epoch": 0.13601741022850924,
   "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": 5.852,
       "eval_steps_per_second": 1.467,
       "step": 200
+    },
+    {
+      "epoch": 0.11425462459194777,
+      "grad_norm": 0.17673972249031067,
+      "learning_rate": 0.00015174815598624768,
+      "loss": 0.1101,
+      "step": 210
+    },
+    {
+      "epoch": 0.11969532100108814,
+      "grad_norm": 0.18985572457313538,
+      "learning_rate": 0.00014502099560537873,
+      "loss": 0.1234,
+      "step": 220
+    },
+    {
+      "epoch": 0.1251360174102285,
+      "grad_norm": 0.1908355951309204,
+      "learning_rate": 0.00013810129290655696,
+      "loss": 0.13,
+      "step": 230
+    },
+    {
+      "epoch": 0.1305767138193689,
+      "grad_norm": 0.2177634984254837,
+      "learning_rate": 0.00013102275998576495,
+      "loss": 0.1802,
+      "step": 240
+    },
+    {
+      "epoch": 0.13601741022850924,
+      "grad_norm": 0.18758904933929443,
+      "learning_rate": 0.00012381988274386116,
+      "loss": 0.1612,
+      "step": 250
+    },
+    {
+      "epoch": 0.13601741022850924,
+      "eval_loss": 0.13536955416202545,
+      "eval_runtime": 66.6366,
+      "eval_samples_per_second": 5.808,
+      "eval_steps_per_second": 1.456,
+      "step": 250
     }
   ],
   "logging_steps": 10,
@@ -201,7 +244,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 0
       }
     },
     "TrainerControl": {
@@ -215,7 +258,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.216495638413312e+16,
+  "total_flos": 6.826525156442112e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null