Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40d6b4a6aba33561f82f8330f397a2a2730a47875f6b10b0a81e621f67229b3f
+oid sha256:80c437b5bb72a75dd0cba6ed0fbed2acde50884afe1d17d8ba31631c4874f73a
 size 194563400

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8f7d4d1f0fac0820e1f07d77246b1da74c16f99bc59dc3fe7d0617471a143b4
+oid sha256:4cf67e28753b88e70027ffdd7e7187285538c2569b161144fef872939874a28b
 size 99235764

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cafc874e4753c081d53f8e3b32dbf44f60bc29079ed71792f4c209b16df2911d
+oid sha256:fb0f23d2af760b7c2adbb5a16871b880893d3a4ef741c98abe0c19a644eb57ed
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:321b462a2538632d6d720f0cf198c8f471dee11f51db9b50cc50d1fa7f132bbe
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0437217950820923,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.02386634844868735,
+  "best_metric": 0.8748182654380798,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0477326968973747,
   "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": 3.369,
       "eval_steps_per_second": 1.694,
       "step": 10
+    },
+    {
+      "epoch": 0.026252983293556086,
+      "grad_norm": 0.6162827610969543,
+      "learning_rate": 0.0001999979446958366,
+      "loss": 1.037,
+      "step": 11
+    },
+    {
+      "epoch": 0.028639618138424822,
+      "grad_norm": 0.7912341356277466,
+      "learning_rate": 0.00019999177886783194,
+      "loss": 0.9055,
+      "step": 12
+    },
+    {
+      "epoch": 0.031026252983293555,
+      "grad_norm": 0.7281938791275024,
+      "learning_rate": 0.00019998150276943902,
+      "loss": 1.1855,
+      "step": 13
+    },
+    {
+      "epoch": 0.03341288782816229,
+      "grad_norm": 0.5928153991699219,
+      "learning_rate": 0.000199967116823068,
+      "loss": 0.6797,
+      "step": 14
+    },
+    {
+      "epoch": 0.03579952267303103,
+      "grad_norm": 0.5825729370117188,
+      "learning_rate": 0.0001999486216200688,
+      "loss": 1.4463,
+      "step": 15
+    },
+    {
+      "epoch": 0.03579952267303103,
+      "eval_loss": 0.9187370538711548,
+      "eval_runtime": 52.4578,
+      "eval_samples_per_second": 3.374,
+      "eval_steps_per_second": 1.697,
+      "step": 15
+    },
+    {
+      "epoch": 0.03818615751789976,
+      "grad_norm": 0.6294780969619751,
+      "learning_rate": 0.00019992601792070679,
+      "loss": 0.8622,
+      "step": 16
+    },
+    {
+      "epoch": 0.0405727923627685,
+      "grad_norm": 0.7047346830368042,
+      "learning_rate": 0.00019989930665413147,
+      "loss": 0.9514,
+      "step": 17
+    },
+    {
+      "epoch": 0.04295942720763723,
+      "grad_norm": 0.6274527907371521,
+      "learning_rate": 0.00019986848891833845,
+      "loss": 1.1009,
+      "step": 18
+    },
+    {
+      "epoch": 0.045346062052505964,
+      "grad_norm": 0.6628918647766113,
+      "learning_rate": 0.0001998335659801241,
+      "loss": 0.7443,
+      "step": 19
+    },
+    {
+      "epoch": 0.0477326968973747,
+      "grad_norm": 0.7120680809020996,
+      "learning_rate": 0.00019979453927503364,
+      "loss": 0.7956,
+      "step": 20
+    },
+    {
+      "epoch": 0.0477326968973747,
+      "eval_loss": 0.8748182654380798,
+      "eval_runtime": 52.5712,
+      "eval_samples_per_second": 3.367,
+      "eval_steps_per_second": 1.693,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5637488844472320.0,
+  "total_flos": 1.127497768894464e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null