Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30b47be2e5c8ba096474c09a23aa9f64c25accd73650c890f1832d5e5196ccbb
+oid sha256:75e866a3485218ede0f1236a22d47bb3517e6f07a98b05320d49dcd8751e21f7
 size 94412008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bf4d35e6138fdaa9295aff6fdf376bae5ed90a2074fec7d2c415321b926c016
+oid sha256:6441f01c6a4d5436ad5afa49d608f08504dce3235eaec078274ac97dc3d37daa
 size 48260756

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:865ff2bc4f2afb8b6b3d1752c4292046dbabc9acdb822c1bc25226039228e3e6
+oid sha256:2883b55283aa08466a16415bc71e27a29af0f45f41ed6640488845068b9b5ac7
 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": 1.096996784210205,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0017617264919621229,
+  "best_metric": 0.6148508787155151,
+  "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": 4.206,
       "eval_steps_per_second": 2.104,
       "step": 10
+    },
+    {
+      "epoch": 0.0019378991411583351,
+      "grad_norm": 2.7614033222198486,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 4.675,
+      "step": 11
+    },
+    {
+      "epoch": 0.0021140717903545474,
+      "grad_norm": 2.6491050720214844,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 4.0089,
+      "step": 12
+    },
+    {
+      "epoch": 0.00229024443955076,
+      "grad_norm": 2.7330145835876465,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 3.738,
+      "step": 13
+    },
+    {
+      "epoch": 0.002466417088746972,
+      "grad_norm": 3.899129629135132,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 3.2485,
+      "step": 14
+    },
+    {
+      "epoch": 0.0026425897379431843,
+      "grad_norm": 3.724151134490967,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 3.1852,
+      "step": 15
+    },
+    {
+      "epoch": 0.0026425897379431843,
+      "eval_loss": 0.7521843910217285,
+      "eval_runtime": 569.0183,
+      "eval_samples_per_second": 4.202,
+      "eval_steps_per_second": 2.102,
+      "step": 15
+    },
+    {
+      "epoch": 0.0028187623871393968,
+      "grad_norm": 3.3071093559265137,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 3.0237,
+      "step": 16
+    },
+    {
+      "epoch": 0.002994935036335609,
+      "grad_norm": 3.8211424350738525,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 2.8587,
+      "step": 17
+    },
+    {
+      "epoch": 0.0031711076855318212,
+      "grad_norm": 4.257937908172607,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 2.7275,
+      "step": 18
+    },
+    {
+      "epoch": 0.0033472803347280333,
+      "grad_norm": 5.022490501403809,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 2.5972,
+      "step": 19
+    },
+    {
+      "epoch": 0.0035234529839242457,
+      "grad_norm": 6.477492332458496,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 2.4925,
+      "step": 20
+    },
+    {
+      "epoch": 0.0035234529839242457,
+      "eval_loss": 0.6148508787155151,
+      "eval_runtime": 568.4307,
+      "eval_samples_per_second": 4.206,
+      "eval_steps_per_second": 2.104,
+      "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