Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:387d1a7cc4f21d45ff7fff4288fe3641aa55cd2c7499ec011af26a619104d28f
+oid sha256:835885e660c8b8b41a4561c6ed2cc504b828b55061953e2b5fad565de2d570e4
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43a5e22cad56e83c59060824ee92d09fb6c86f2266fb21d04a017dab0a3998d1
+oid sha256:cc5afef187849047eb914f378922521e9a0f0145b5c5382a54723384df11ae5c
 size 82461044

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a1430a78651f9f94509881864fe6f6c669b7cdf4b562fbaef9d4c52f6df7d2f
+oid sha256:477876f44f281a61a86d1447349c724569d2765aa4ae6a070d95c9d4ad91b99e
 size 14180

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b154362c7157b852d512cab3c071eefcea4136cc17eaccb50f7f0c044a60554
+oid sha256:f2cdbfc7c53ac5e07e0f51cc8792da823a3a052a350539d74ad1412a24fbf346
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.00016280841373372823,
   "best_model_checkpoint": "miner_id_24/checkpoint-250",
-  "epoch": 0.07423904974016332,
+  "epoch": 0.08484462827447237,
   "eval_steps": 50,
-  "global_step": 350,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -316,6 +316,49 @@
       "eval_samples_per_second": 11.453,
       "eval_steps_per_second": 2.868,
       "step": 350
+    },
+    {
+      "epoch": 0.07636016544702513,
+      "grad_norm": 0.0014348330441862345,
+      "learning_rate": 4.760716642515936e-05,
+      "loss": 0.0001,
+      "step": 360
+    },
+    {
+      "epoch": 0.07848128115388694,
+      "grad_norm": 0.0005178822902962565,
+      "learning_rate": 4.1508560664828905e-05,
+      "loss": 0.0003,
+      "step": 370
+    },
+    {
+      "epoch": 0.08060239686074876,
+      "grad_norm": 0.0005457755760289729,
+      "learning_rate": 3.573389451324334e-05,
+      "loss": 0.0,
+      "step": 380
+    },
+    {
+      "epoch": 0.08272351256761057,
+      "grad_norm": 0.0008481218828819692,
+      "learning_rate": 3.0311301563425695e-05,
+      "loss": 0.0,
+      "step": 390
+    },
+    {
+      "epoch": 0.08484462827447237,
+      "grad_norm": 0.017539557069540024,
+      "learning_rate": 2.5267200143150385e-05,
+      "loss": 0.0001,
+      "step": 400
+    },
+    {
+      "epoch": 0.08484462827447237,
+      "eval_loss": 0.00030467374017462134,
+      "eval_runtime": 173.0,
+      "eval_samples_per_second": 11.474,
+      "eval_steps_per_second": 2.873,
+      "step": 400
     }
   ],
   "logging_steps": 10,
@@ -330,7 +373,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 2
+        "early_stopping_patience_counter": 3
       }
     },
     "TrainerControl": {
@@ -339,12 +382,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 9.716637837243187e+16,
+  "total_flos": 1.1114715223896883e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null