Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cdbc4d377f29ffaa31227e4995d8a937843b5095fabbe43ca50f837b3aee2c4
+oid sha256:49071db05d5df0d24d97b51085ef9ccc8816970fe48f79b9c9640cf0f0034e3d
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a56776e048a39caa4463563fc748e9e4479fecb7c55b7c264e53a848311dfaab
+oid sha256:fa80c946caf383a4f7326f64af2f642267bb45d76b1c876a2850c79e18d1be6e
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4ad364e7f8279ddb4258e9e257ea0d9a40a1444fc8b4d16678147f29d222f59
+oid sha256:e797fb6926c3f4c2d2ccdbadbc6dfe459305f1a0db203359f9ee011767ae82a5
 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": 0.4394129514694214,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.00028716034315661007,
+  "best_metric": 0.4230361878871918,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0005743206863132201,
   "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": 4.781,
       "eval_steps_per_second": 2.391,
       "step": 10
+    },
+    {
+      "epoch": 0.0003158763774722711,
+      "grad_norm": 1.524711012840271,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 1.5585,
+      "step": 11
+    },
+    {
+      "epoch": 0.0003445924117879321,
+      "grad_norm": 1.4126205444335938,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 1.2898,
+      "step": 12
+    },
+    {
+      "epoch": 0.00037330844610359307,
+      "grad_norm": 1.89143967628479,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 1.7331,
+      "step": 13
+    },
+    {
+      "epoch": 0.0004020244804192541,
+      "grad_norm": 1.7866116762161255,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 1.384,
+      "step": 14
+    },
+    {
+      "epoch": 0.0004307405147349151,
+      "grad_norm": 2.72021484375,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 2.2272,
+      "step": 15
+    },
+    {
+      "epoch": 0.0004307405147349151,
+      "eval_loss": 0.42954686284065247,
+      "eval_runtime": 3093.5186,
+      "eval_samples_per_second": 4.74,
+      "eval_steps_per_second": 2.37,
+      "step": 15
+    },
+    {
+      "epoch": 0.0004594565490505761,
+      "grad_norm": 1.447580099105835,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.5618,
+      "step": 16
+    },
+    {
+      "epoch": 0.00048817258336623714,
+      "grad_norm": 1.823649287223816,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 2.2623,
+      "step": 17
+    },
+    {
+      "epoch": 0.0005168886176818981,
+      "grad_norm": 2.1619272232055664,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 1.9625,
+      "step": 18
+    },
+    {
+      "epoch": 0.0005456046519975591,
+      "grad_norm": 2.0479583740234375,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 2.052,
+      "step": 19
+    },
+    {
+      "epoch": 0.0005743206863132201,
+      "grad_norm": 1.1087257862091064,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 1.7707,
+      "step": 20
+    },
+    {
+      "epoch": 0.0005743206863132201,
+      "eval_loss": 0.4230361878871918,
+      "eval_runtime": 3099.0418,
+      "eval_samples_per_second": 4.731,
+      "eval_steps_per_second": 2.366,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1752669785948160.0,
+  "total_flos": 3505339571896320.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null