Training in progress, step 450, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f1d057cabb86e83fd443a7fcbf0e0941deb5ed1df348cef2b8ebdba660fcfc3
+oid sha256:75bbe67a5221554012d1a0abe98cfef9cb3d2ce84930edd8f0bdca7f359834da
 size 1001465824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c1c95901f908d5b7210acaba7431c31fbac716fce225a13d2af72874f847431
+oid sha256:69f6ff799ae141dfebffb5e5543de928351bdc53209182d29ccd523c130600b9
 size 509177556

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d1a80655827a7dbaebded152cf843bd9c4136038249aa248956f2e8c8b725f2
+oid sha256:9e6a76e3bf01ce0abfb46b08e0e12448701dac9fdc00f5bcf08f1da2695ab7f9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfb04ef1a2aa7d59f8fd57263f8ca35825fbc8b8f3364e09a103cc34539bef25
+oid sha256:07ec5d18fbee4ceb79650729eac8dcbe812062dc71c315bc7032dd15edeeaee3
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.0008633602410554886,
-  "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.8639308855291576,
+  "best_metric": 0.0007766146445646882,
+  "best_model_checkpoint": "miner_id_24/checkpoint-450",
+  "epoch": 0.9719222462203023,
   "eval_steps": 50,
-  "global_step": 400,
+  "global_step": 450,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -359,6 +359,49 @@
       "eval_samples_per_second": 6.89,
       "eval_steps_per_second": 1.731,
       "step": 400
+    },
+    {
+      "epoch": 0.8855291576673866,
+      "grad_norm": 0.04856608808040619,
+      "learning_rate": 8.177699930169379e-06,
+      "loss": 0.0023,
+      "step": 410
+    },
+    {
+      "epoch": 0.9071274298056156,
+      "grad_norm": 0.004636272322386503,
+      "learning_rate": 5.4079321382439e-06,
+      "loss": 0.0015,
+      "step": 420
+    },
+    {
+      "epoch": 0.9287257019438445,
+      "grad_norm": 0.12631860375404358,
+      "learning_rate": 3.1968039012795417e-06,
+      "loss": 0.0005,
+      "step": 430
+    },
+    {
+      "epoch": 0.9503239740820735,
+      "grad_norm": 0.0010080524953082204,
+      "learning_rate": 1.5571032641086151e-06,
+      "loss": 0.0015,
+      "step": 440
+    },
+    {
+      "epoch": 0.9719222462203023,
+      "grad_norm": 0.02956795133650303,
+      "learning_rate": 4.983134240007501e-07,
+      "loss": 0.0003,
+      "step": 450
+    },
+    {
+      "epoch": 0.9719222462203023,
+      "eval_loss": 0.0007766146445646882,
+      "eval_runtime": 28.3411,
+      "eval_samples_per_second": 6.88,
+      "eval_steps_per_second": 1.729,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -387,7 +430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.0640449370783744e+17,
+  "total_flos": 2.3232580688019456e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null