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:da7213c84e06002f8f596ce68498e458f3de7c74b0be945cec96288652324767
+oid sha256:cdf1b29c94c39c58cf82ced671c608e4502bd7a178f2c3177dcdfa44c0201aac
 size 59933632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64ecb978c8cff6bc026f764acfede9a8cadf66a3a1618483226f780f1c4471d9
+oid sha256:2e03484da3c01e164b29c9e6c81be893cddb4f068455e776e31e63bbe8309eda
 size 31822948

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b0959b5e9e0e795488fd06c14f6a3e9380afd1a45a8f81e87894a28f39b0bf3
+oid sha256:eebcfb1ae254997c92616d83af93e361bb5b009b301f11af138466c07c45b3e1
 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": 1.199088215827942,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.00031336665465427825,
+  "best_metric": 0.21979251503944397,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0006267333093085565,
   "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": 5.924,
       "eval_steps_per_second": 2.962,
       "step": 10
+    },
+    {
+      "epoch": 0.00034470332011970605,
+      "grad_norm": 1.4347280263900757,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 1.1284,
+      "step": 11
+    },
+    {
+      "epoch": 0.0003760399855851339,
+      "grad_norm": 1.2413074970245361,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 0.9404,
+      "step": 12
+    },
+    {
+      "epoch": 0.0004073766510505617,
+      "grad_norm": 1.1735608577728271,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.7941,
+      "step": 13
+    },
+    {
+      "epoch": 0.00043871331651598955,
+      "grad_norm": 1.4002755880355835,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 0.813,
+      "step": 14
+    },
+    {
+      "epoch": 0.00047004998198141735,
+      "grad_norm": 1.322905421257019,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.6099,
+      "step": 15
+    },
+    {
+      "epoch": 0.00047004998198141735,
+      "eval_loss": 0.604054868221283,
+      "eval_runtime": 2282.3164,
+      "eval_samples_per_second": 5.887,
+      "eval_steps_per_second": 2.944,
+      "step": 15
+    },
+    {
+      "epoch": 0.0005013866474468452,
+      "grad_norm": 1.8949304819107056,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.6544,
+      "step": 16
+    },
+    {
+      "epoch": 0.000532723312912273,
+      "grad_norm": 1.84648597240448,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 0.4435,
+      "step": 17
+    },
+    {
+      "epoch": 0.0005640599783777008,
+      "grad_norm": 1.6775842905044556,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 0.3557,
+      "step": 18
+    },
+    {
+      "epoch": 0.0005953966438431286,
+      "grad_norm": 1.4471125602722168,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.1882,
+      "step": 19
+    },
+    {
+      "epoch": 0.0006267333093085565,
+      "grad_norm": 1.4307396411895752,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.295,
+      "step": 20
+    },
+    {
+      "epoch": 0.0006267333093085565,
+      "eval_loss": 0.21979251503944397,
+      "eval_runtime": 2283.5485,
+      "eval_samples_per_second": 5.884,
+      "eval_steps_per_second": 2.942,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 685606636093440.0,
+  "total_flos": 1371213272186880.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null