Training in progress, step 250, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9368230205e73d969946114670003269720fc83e6f5c6922c61544f33df26a55
+oid sha256:385cc2ab74390ddab6efd944244469de19aff07a1c042e1fc40655d6baff73e6
 size 78207176

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:575c2732ab169bd0ec5543fbb777f0ed97e3dfe15d8e7497a4ad06b35e17fb38
+oid sha256:f4547581331d26e8963b36a6531732ce1838ddb7e953cdb167674de10f2cae6c
 size 40177764

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aeda9cb70e42fbbb35a1dc0f39125a6383bf6bc683e5b322ad921bdaddae30c0
+oid sha256:98e7257ad47309fc7e2680519ade99aef9be3ec7bb3a4a1d24ea1cd74e5a95ee
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28e5d71a0aeb47061932e6cbb43a24f283fa1f06d78538ebaf9b09e4db2b7bc3
+oid sha256:e1694f1a3446acd7c60128fa27d7f8561ecc8247edb048b51ca23e45e76cd306
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0759819746017456,
-  "best_model_checkpoint": "miner_id_24/checkpoint-200",
-  "epoch": 2.191256830601093,
+  "best_metric": 1.0732088088989258,
+  "best_model_checkpoint": "miner_id_24/checkpoint-250",
+  "epoch": 2.737704918032787,
   "eval_steps": 50,
-  "global_step": 200,
+  "global_step": 250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -75,6 +75,21 @@
       "eval_samples_per_second": 131.815,
       "eval_steps_per_second": 4.287,
       "step": 200
+    },
+    {
+      "epoch": 2.737704918032787,
+      "grad_norm": 0.12843619287014008,
+      "learning_rate": 0.000212,
+      "loss": 1.0462,
+      "step": 250
+    },
+    {
+      "epoch": 2.737704918032787,
+      "eval_loss": 1.0732088088989258,
+      "eval_runtime": 4.5325,
+      "eval_samples_per_second": 135.688,
+      "eval_steps_per_second": 4.413,
+      "step": 250
     }
   ],
   "logging_steps": 50,
@@ -103,7 +118,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.155742301159424e+16,
+  "total_flos": 1.4449868984549376e+16,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null