Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cf989f3b5dcefc1ae93edb02857e247bf1ca7c7ec7070b2645197126ece3227
+oid sha256:9ed0b90cd7b0a461a75dc122c5ee4bba79b70c61f7d84458286612093c66b05d
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db7db3de8a5fdb96c16f2bd7182b2e80c7b485c214152943ec00f1ce41d33669
+oid sha256:155802a4abb9e673a057b3feaf79675bb377de6daf86110dcfc690ab8e5e6ce3
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af580fd975d21313d4a2bcc3b613a6e995ba2fded0279253051f99a1fa6a2d88
+oid sha256:4fe2d93083d442b1cc689b68c0cf096441aebfd2677037101b902692f6601bbf
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c188a6a4749e6ca627bb6d536eb7443f499d5b1b88d98a78f9c713443e010d9c
+oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.9574483633041382,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.01564945226917058,
+  "best_metric": 1.7805674076080322,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.03129890453834116,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 15.572,
       "eval_steps_per_second": 3.9,
       "step": 10
+    },
+    {
+      "epoch": 0.018779342723004695,
+      "grad_norm": 9.912591934204102,
+      "learning_rate": 0.000163742398974869,
+      "loss": 7.5866,
+      "step": 12
+    },
+    {
+      "epoch": 0.023474178403755867,
+      "grad_norm": 8.794225692749023,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 7.4394,
+      "step": 15
+    },
+    {
+      "epoch": 0.023474178403755867,
+      "eval_loss": 1.855014443397522,
+      "eval_runtime": 34.607,
+      "eval_samples_per_second": 15.575,
+      "eval_steps_per_second": 3.901,
+      "step": 15
+    },
+    {
+      "epoch": 0.028169014084507043,
+      "grad_norm": 8.808883666992188,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 7.1421,
+      "step": 18
+    },
+    {
+      "epoch": 0.03129890453834116,
+      "eval_loss": 1.7805674076080322,
+      "eval_runtime": 34.6067,
+      "eval_samples_per_second": 15.575,
+      "eval_steps_per_second": 3.901,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7031294986813440.0,
+  "total_flos": 1.406258997362688e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null