Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e5229c3cc57104124dd1ae12623069ea6521b6f6376419ce7074e80aa9f9052
+oid sha256:35d7cb0f61ba769d2e70fcacf9029eca99784bd8f0e6bf664955c8f8013f249c
 size 619632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d2b3d92c242925d070889bb3f2bbc98bacf2924f1bbb3affaa63d80a4118437
+oid sha256:55fcfb8e664e0415edebc291e7cea302e23abdf3b07a4f131e2def53c3723c1e
 size 1324282

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83e163b54d47b0db0faf5592b2f2bcaeba7873c7b214847bd82234440ed1c678
+oid sha256:d70a1bbe58500c05dccfbf055b539c7e69f53b75ce18a695bfa41672417e6b60
 size 14180

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ae0a5f636e3b7efad4ad765d67a451cd40f8f2e24e01c5d42929e454a337257
+oid sha256:4f23fa0ef01cbb776456cad40209cd1c0c6a02d9fdf8c0632982552f2f542168
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 11.815816879272461,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.014500459181207405,
+  "best_metric": 11.815800666809082,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.01611162131245267,
   "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": 52.437,
       "eval_steps_per_second": 13.11,
       "step": 450
+    },
+    {
+      "epoch": 0.014822691607456459,
+      "grad_norm": 0.03025321289896965,
+      "learning_rate": 4.067521926476516e-06,
+      "loss": 11.8193,
+      "step": 460
+    },
+    {
+      "epoch": 0.015144924033705511,
+      "grad_norm": 0.043944135308265686,
+      "learning_rate": 2.294501922950403e-06,
+      "loss": 11.8187,
+      "step": 470
+    },
+    {
+      "epoch": 0.015467156459954565,
+      "grad_norm": 0.048449497669935226,
+      "learning_rate": 1.021852782135112e-06,
+      "loss": 11.8171,
+      "step": 480
+    },
+    {
+      "epoch": 0.01578938888620362,
+      "grad_norm": 0.05778438597917557,
+      "learning_rate": 2.5577472271845927e-07,
+      "loss": 11.817,
+      "step": 490
+    },
+    {
+      "epoch": 0.01611162131245267,
+      "grad_norm": 0.0808941200375557,
+      "learning_rate": 0.0,
+      "loss": 11.8119,
+      "step": 500
+    },
+    {
+      "epoch": 0.01611162131245267,
+      "eval_loss": 11.815800666809082,
+      "eval_runtime": 249.0861,
+      "eval_samples_per_second": 52.46,
+      "eval_steps_per_second": 13.116,
+      "step": 500
     }
   ],
   "logging_steps": 10,
@@ -425,12 +468,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 78265512493056.0,
+  "total_flos": 86898204868608.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null