Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb3a3980ed311df8752e49b3ddbad2f5c6a0a4b88b4704c37848069930aa75e8
+oid sha256:31ab8e9d1624b311b4534671a5170e47c756e3059c3df1aefc1149f7871ea07f
 size 93608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cbbaea17ae763eab25139b495c50bd6bb491983b7982ca5c08737ae671bc91f
+oid sha256:4be4c916eb470ce7dffb698952b4b96f679ae233cffd0b6a440d56c091d41e91
 size 197158

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a88858842f7927b26ec5ef01058fccadc87ac4a2b2ae7fae17ff35802a115c5
+oid sha256:ed29aef78b0ba54864d12f6d67490208e9f8a3cbe246fde432154e1667424086
 size 14180

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de68da4a411755dd89261d95dc85b46978ce68b71b6b640a5e732fce38d3ca1d
+oid sha256:673699a33c258fc5668f5919a0c3d2b61b77874f7dbb4fb806a02e77a15f3cef
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 11.879236221313477,
   "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.35474970437524633,
+  "epoch": 0.3941663381947182,
   "eval_steps": 50,
-  "global_step": 450,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -402,6 +402,49 @@
       "eval_samples_per_second": 75.39,
       "eval_steps_per_second": 18.883,
       "step": 450
+    },
+    {
+      "epoch": 0.3626330311391407,
+      "grad_norm": 0.10696567595005035,
+      "learning_rate": 3.893199558198952e-06,
+      "loss": 11.8918,
+      "step": 460
+    },
+    {
+      "epoch": 0.37051635790303505,
+      "grad_norm": 0.20454297959804535,
+      "learning_rate": 2.1961661262525285e-06,
+      "loss": 11.8865,
+      "step": 470
+    },
+    {
+      "epoch": 0.37839968466692947,
+      "grad_norm": 0.21538551151752472,
+      "learning_rate": 9.780590914721787e-07,
+      "loss": 11.8861,
+      "step": 480
+    },
+    {
+      "epoch": 0.38628301143082383,
+      "grad_norm": 0.281142920255661,
+      "learning_rate": 2.4481294888766817e-07,
+      "loss": 11.8759,
+      "step": 490
+    },
+    {
+      "epoch": 0.3941663381947182,
+      "grad_norm": 0.4691304564476013,
+      "learning_rate": 0.0,
+      "loss": 11.8598,
+      "step": 500
+    },
+    {
+      "epoch": 0.3941663381947182,
+      "eval_loss": 11.87945556640625,
+      "eval_runtime": 7.1342,
+      "eval_samples_per_second": 74.991,
+      "eval_steps_per_second": 18.783,
+      "step": 500
     }
   ],
   "logging_steps": 10,
@@ -416,7 +459,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 2
       }
     },
     "TrainerControl": {
@@ -425,12 +468,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 308231700480.0,
+  "total_flos": 342278799360.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null