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:d7053cf0c48a0b513cf04cfb869888df0bbabb2e65494745876a31086590feed
+oid sha256:8766347f449532efab219dc598d5a304e94b194073892863393d8c5099bd4f37
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09f5ae971b8207e918aeccdedcb2b1eda54d0465dc96d9a706732da93004b8aa
+oid sha256:a3f9d01b8fe589cb738904591ab4f7082b5b7caf6e0a636b0ea00c24892e69d9
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccd1574947e49e066e75130f0763899ec12b864a5ed89b94808408d4da676a13
+oid sha256:49ba7598c1d0cfdd44ffe49c303fb8b51ec0600e8e2134c278d45670ae3566af
 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": 1.6344908475875854,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0017504704389304626,
+  "best_metric": 1.5172053575515747,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.003500940877860925,
   "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": 5.908,
       "eval_steps_per_second": 2.954,
       "step": 10
+    },
+    {
+      "epoch": 0.001925517482823509,
+      "grad_norm": 1.3951776027679443,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 5.2835,
+      "step": 11
+    },
+    {
+      "epoch": 0.002100564526716555,
+      "grad_norm": 1.2195020914077759,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 5.6981,
+      "step": 12
+    },
+    {
+      "epoch": 0.0022756115706096015,
+      "grad_norm": 1.0527544021606445,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 6.3586,
+      "step": 13
+    },
+    {
+      "epoch": 0.0024506586145026476,
+      "grad_norm": 1.6312555074691772,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 6.1024,
+      "step": 14
+    },
+    {
+      "epoch": 0.0026257056583956937,
+      "grad_norm": 0.9510515928268433,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 5.9786,
+      "step": 15
+    },
+    {
+      "epoch": 0.0026257056583956937,
+      "eval_loss": 1.5309654474258423,
+      "eval_runtime": 409.8829,
+      "eval_samples_per_second": 5.87,
+      "eval_steps_per_second": 2.935,
+      "step": 15
+    },
+    {
+      "epoch": 0.0028007527022887403,
+      "grad_norm": 1.1782293319702148,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 6.5324,
+      "step": 16
+    },
+    {
+      "epoch": 0.0029757997461817864,
+      "grad_norm": 1.6559582948684692,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 6.5493,
+      "step": 17
+    },
+    {
+      "epoch": 0.0031508467900748325,
+      "grad_norm": 1.4915060997009277,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 6.1002,
+      "step": 18
+    },
+    {
+      "epoch": 0.003325893833967879,
+      "grad_norm": 1.6910254955291748,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 6.0799,
+      "step": 19
+    },
+    {
+      "epoch": 0.003500940877860925,
+      "grad_norm": 1.761253833770752,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 7.1205,
+      "step": 20
+    },
+    {
+      "epoch": 0.003500940877860925,
+      "eval_loss": 1.5172053575515747,
+      "eval_runtime": 405.8316,
+      "eval_samples_per_second": 5.929,
+      "eval_steps_per_second": 2.964,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2239530207805440.0,
+  "total_flos": 4967685188222976.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null