Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0198fa1043672a2e5457fc6548a981d909af66372adb4df08d0fcc423e52b2c9
+oid sha256:6b640982a420e66f352e1069677175c0fa46e85e22d258b955ab69333b4e1668
 size 140815952

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:621725840c98d2ba67d8d9e7f838132a841a3899f80f9cf7b063f06f0656291c
+oid sha256:e93684ac216ed2da887a26ee531cd26a596fe5dcad9ccb3d3e513a0d8de20d09
 size 71878996

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fab2e60c6d5285ba5a17c09d5fb7a360771cd406be3140995e7c1d763fd29b8
+oid sha256:9ab1880f49a1207b7d9cfe11db3df5e2d765eb537c63a10f7c3dd07940f7f2f7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30565d7b1986ad1c3966f0f9b850f0ae7d4cfe76be60a78deb1442c25c9c950e
+oid sha256:693af3889e4633c932ce337b10348752049de987b4153b6619512b489850fe7b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 2.0274436473846436,
   "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.08817478201234447,
+  "epoch": 0.09797198001371608,
   "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": 47.675,
       "eval_steps_per_second": 11.935,
       "step": 450
+    },
+    {
+      "epoch": 0.09013422161261879,
+      "grad_norm": 1.8561580181121826,
+      "learning_rate": 4.028783622414835e-06,
+      "loss": 1.7263,
+      "step": 460
+    },
+    {
+      "epoch": 0.09209366121289311,
+      "grad_norm": 2.299384117126465,
+      "learning_rate": 2.272649523684208e-06,
+      "loss": 1.9996,
+      "step": 470
+    },
+    {
+      "epoch": 0.09405310081316744,
+      "grad_norm": 2.3790676593780518,
+      "learning_rate": 1.0121208508766823e-06,
+      "loss": 1.8968,
+      "step": 480
+    },
+    {
+      "epoch": 0.09601254041344176,
+      "grad_norm": 2.971630096435547,
+      "learning_rate": 2.533387729782834e-07,
+      "loss": 2.2472,
+      "step": 490
+    },
+    {
+      "epoch": 0.09797198001371608,
+      "grad_norm": 7.310604572296143,
+      "learning_rate": 0.0,
+      "loss": 2.3115,
+      "step": 500
+    },
+    {
+      "epoch": 0.09797198001371608,
+      "eval_loss": 2.027695417404175,
+      "eval_runtime": 44.2229,
+      "eval_samples_per_second": 48.595,
+      "eval_steps_per_second": 12.166,
+      "step": 500
     }
   ],
   "logging_steps": 10,
@@ -416,7 +459,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "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": 4554974333239296.0,
+  "total_flos": 5062155992825856.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null