Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:780f5a73be3161d7c26edd5f72b37a0c4f0ad074ec53cf393ed552ddc51c15a8
+oid sha256:867572c755b77902a8d19d46bdbf6a76a33d2bcae0cfc098a43c968dade9a022
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bada789026b535b3ba48a4e68b81744e034dae82129051e54b5dba606481a5d8
+oid sha256:9ae0e4f0417b28d1fe56c447660563e7758acb3d1b1b1c5c260a410269d401a4
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce5dfae69638fb910dcc9ee15512c265d3c58e6003c5c9c52e763694dea6562d
+oid sha256:4ca1509ac1123603e503c593fe30d455c8e5500367e860522b67e19b5a1e193d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ea7ff16b0c30a914eb0d145e3fb06ff9027c6cd2408e766ce8a09accab89a4d
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.0031658420339226723,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.001266624445851805,
+  "best_metric": 0.001949921017512679,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.00253324889170361,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 2.854,
       "eval_steps_per_second": 1.427,
       "step": 25
+    },
+    {
+      "epoch": 0.001317289423685877,
+      "grad_norm": 0.0012040651636198163,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.0013679544015199492,
+      "grad_norm": 0.003693037200719118,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.0014186193793540216,
+      "grad_norm": 0.0011092451168224216,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.0014692843571880937,
+      "grad_norm": 0.0016942309448495507,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.0015199493350221659,
+      "grad_norm": 0.0008918177918531001,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.0015706143128562382,
+      "grad_norm": 0.0006368808099068701,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.0016212792906903104,
+      "grad_norm": 0.000868378090672195,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.0016719442685243825,
+      "grad_norm": 0.0012875277316197753,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.0017226092463584546,
+      "grad_norm": 0.001103079877793789,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.001773274224192527,
+      "grad_norm": 0.00059116369811818,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.0018239392020265991,
+      "grad_norm": 0.0006111768889240921,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.0018746041798606713,
+      "grad_norm": 0.0005457017105072737,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.0019252691576947436,
+      "grad_norm": 0.0006407860200852156,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.0019759341355288155,
+      "grad_norm": 0.025094201788306236,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 0.0001,
+      "step": 39
+    },
+    {
+      "epoch": 0.002026599113362888,
+      "grad_norm": 0.0004499408241827041,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.0020772640911969602,
+      "grad_norm": 0.0005782039952464402,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.0021279290690310324,
+      "grad_norm": 0.0006991780246607959,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.0021785940468651045,
+      "grad_norm": 0.0004409195389598608,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.0022292590246991767,
+      "grad_norm": 0.0004564693372230977,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.002279924002533249,
+      "grad_norm": 0.0004852621059399098,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.002330588980367321,
+      "grad_norm": 0.0004319900181144476,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.002381253958201393,
+      "grad_norm": 0.0018095594132319093,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.0024319189360354656,
+      "grad_norm": 0.0007907446706667542,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.0024825839138695378,
+      "grad_norm": 0.002268951153382659,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.00253324889170361,
+      "grad_norm": 0.09747433662414551,
+      "learning_rate": 0.0,
+      "loss": 0.0004,
+      "step": 50
+    },
+    {
+      "epoch": 0.00253324889170361,
+      "eval_loss": 0.001949921017512679,
+      "eval_runtime": 2915.0095,
+      "eval_samples_per_second": 2.851,
+      "eval_steps_per_second": 1.426,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.70943641780224e+16,
+  "total_flos": 7.41887283560448e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null