Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26de5d28274b6f93d1a55f54864367c7afb50c28446986ab0d78842241e1b702
+oid sha256:a1323af51047d8fbbbd3b528f85ed404654e354c2606d6463f1e68796ebcfbf9
 size 247944

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:856375b6b55002239d6172b1067d918dda285a65a29b73bb424cde5d5291ac1d
+oid sha256:6f5167e0bb6eba45f98823fb30f732bd56f4c942b45e862a2f07f8486adb3bd3
 size 505518

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df85fba7d34da3f3558395d4111261185109b47d56a4c11be57f0d4f275c4c42
+oid sha256:514659fe6587e5a360c1da77a9bf3d5a140023fc4c9c6193d1463a71ec2ba65e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 11.076057434082031,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.06172839506172839,
+  "best_metric": 11.031575202941895,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.12345679012345678,
   "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": 198.139,
       "eval_steps_per_second": 100.505,
       "step": 10
+    },
+    {
+      "epoch": 0.07407407407407407,
+      "grad_norm": 1.4536323547363281,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 44.2973,
+      "step": 12
+    },
+    {
+      "epoch": 0.09259259259259259,
+      "grad_norm": 1.4778214693069458,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 44.2606,
+      "step": 15
+    },
+    {
+      "epoch": 0.09259259259259259,
+      "eval_loss": 11.052154541015625,
+      "eval_runtime": 0.3719,
+      "eval_samples_per_second": 185.525,
+      "eval_steps_per_second": 94.107,
+      "step": 15
+    },
+    {
+      "epoch": 0.1111111111111111,
+      "grad_norm": 1.3547159433364868,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 44.1819,
+      "step": 18
+    },
+    {
+      "epoch": 0.12345679012345678,
+      "eval_loss": 11.031575202941895,
+      "eval_runtime": 0.3552,
+      "eval_samples_per_second": 194.253,
+      "eval_steps_per_second": 98.534,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 207995535360.0,
+  "total_flos": 415991070720.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null