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:be236612c87ffc774179beb2e22e39e31ddb7e54225de97e371a344518f5c80c
+oid sha256:d9d4f8cdfb849dfab5cb5c75da21844b1efd9020c04ab8cbd386e9a3a46cda1f
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fe54e7752434839ac1ae1239a785a9402bc3703320f5a77cbf76bfe4d1bafa0
+oid sha256:787b29b7f7e2f1df81e6a68a9f2e72f3c9983e679ae9a133163817bddc9e2b3e
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84ee884b5433a97b1054465aa099ee0c0f65679ae0844ac1b66a5f9c3a44c74b
+oid sha256:8a71c51c80146f18ea09d5ceac8e3b8ba50fb50c8a5d8b268ca719837f3ec6a1
 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": 1.749941349029541,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.07207207207207207,
+  "best_metric": 0.5944854617118835,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.14414414414414414,
   "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": 4.566,
       "eval_steps_per_second": 1.171,
       "step": 10
+    },
+    {
+      "epoch": 0.08648648648648649,
+      "grad_norm": 3.3332393169403076,
+      "learning_rate": 0.000163742398974869,
+      "loss": 7.0536,
+      "step": 12
+    },
+    {
+      "epoch": 0.10810810810810811,
+      "grad_norm": 4.653995037078857,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 4.5987,
+      "step": 15
+    },
+    {
+      "epoch": 0.10810810810810811,
+      "eval_loss": 0.8163535594940186,
+      "eval_runtime": 25.7616,
+      "eval_samples_per_second": 4.542,
+      "eval_steps_per_second": 1.165,
+      "step": 15
+    },
+    {
+      "epoch": 0.12972972972972974,
+      "grad_norm": 2.8169493675231934,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 2.9801,
+      "step": 18
+    },
+    {
+      "epoch": 0.14414414414414414,
+      "eval_loss": 0.5944854617118835,
+      "eval_runtime": 25.5671,
+      "eval_samples_per_second": 4.576,
+      "eval_steps_per_second": 1.173,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.26648972214272e+16,
+  "total_flos": 2.53297944428544e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null