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:f8f2430a5bd0193c6117e1aa1f90830bc82689511ce8e91673081050d763cd40
+oid sha256:15d12968aa61dc710a572c086fc41277a9cac5bd94b271368875c5f4094d712f
 size 94412008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a6f7b8fa866303f614fb2f5a1a39d8340f315b88a1f879b4621c3fbe12822b5
+oid sha256:4397c96829386e73abb206dd26d803f6541b97888e0ee0478ab070457b5d8e8a
 size 48260756

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c739500c9202a78fb09c2104fffee8e4a73ac00a1794c6d7e3e16ca201049b72
+oid sha256:68bc48585e08a6b1f56d74546f0b156cdbd7fd42aeed08f8646571909f5064e2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0760761499404907,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0017617264919621229,
+  "best_metric": 0.5938207507133484,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0035234529839242457,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,92 @@
       "eval_samples_per_second": 4.552,
       "eval_steps_per_second": 2.277,
       "step": 10
+    },
+    {
+      "epoch": 0.0019378991411583351,
+      "grad_norm": 2.74320125579834,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 4.5433,
+      "step": 11
+    },
+    {
+      "epoch": 0.0021140717903545474,
+      "grad_norm": 2.6060595512390137,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 3.9638,
+      "step": 12
+    },
+    {
+      "epoch": 0.00229024443955076,
+      "grad_norm": 2.681314706802368,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 3.6968,
+      "step": 13
+    },
+    {
+      "epoch": 0.002466417088746972,
+      "grad_norm": 2.7970993518829346,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 3.1747,
+      "step": 14
+    },
+    {
+      "epoch": 0.0026425897379431843,
+      "grad_norm": 3.1518383026123047,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 3.0898,
+      "step": 15
+    },
+    {
+      "epoch": 0.0026425897379431843,
+      "eval_loss": 0.7288035750389099,
+      "eval_runtime": 524.3499,
+      "eval_samples_per_second": 4.56,
+      "eval_steps_per_second": 2.281,
+      "step": 15
+    },
+    {
+      "epoch": 0.0028187623871393968,
+      "grad_norm": 3.2545006275177,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 2.909,
+      "step": 16
+    },
+    {
+      "epoch": 0.002994935036335609,
+      "grad_norm": 3.0446226596832275,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 2.7771,
+      "step": 17
+    },
+    {
+      "epoch": 0.0031711076855318212,
+      "grad_norm": 3.5716164112091064,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 2.6668,
+      "step": 18
+    },
+    {
+      "epoch": 0.0033472803347280333,
+      "grad_norm": 3.314288854598999,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 2.5392,
+      "step": 19
+    },
+    {
+      "epoch": 0.0035234529839242457,
+      "grad_norm": 3.2105391025543213,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 2.4089,
+      "step": 20
+    },
+    {
+      "epoch": 0.0035234529839242457,
+      "eval_loss": 0.5938207507133484,
+      "eval_runtime": 524.2104,
+      "eval_samples_per_second": 4.561,
+      "eval_steps_per_second": 2.282,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5562970448855040.0,
+  "total_flos": 1.126858116562944e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null