Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:931b44637c1f58f1fc86059f4683c5f3257647785f0b749e89681187af28a580
+oid sha256:824e9d4e2b8a12779f165162f6c213f8894db74c814a642b75c2bfff4d53cf91
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c2c325b2a6f7e9a4b592932e7a628dbfb63f6265730fee10dc4601e2de30a20
+oid sha256:1c90cb751c3b8c0f940e58666d7d1a16211c2e03650a7c6bd574fdd437691117
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f84b7eed8ce383f213fa2c01c69e8fe6d926bcb9bee31ed27ce8dad8d9e48e50
+oid sha256:8ac9ef8a8d750dd06f1b2f32aa7dc4ccd0792acf7e63e2006163d178a7597fee
 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": 0.015803173184394836,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.23952095808383234,
+  "best_metric": 0.0014264764031395316,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.47904191616766467,
   "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": 6.525,
       "eval_steps_per_second": 3.262,
       "step": 10
+    },
+    {
+      "epoch": 0.2634730538922156,
+      "grad_norm": 0.5950635075569153,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 0.0158,
+      "step": 11
+    },
+    {
+      "epoch": 0.2874251497005988,
+      "grad_norm": 0.2746161222457886,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 0.0066,
+      "step": 12
+    },
+    {
+      "epoch": 0.31137724550898205,
+      "grad_norm": 0.1909645050764084,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.004,
+      "step": 13
+    },
+    {
+      "epoch": 0.33532934131736525,
+      "grad_norm": 0.0654994398355484,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 0.0018,
+      "step": 14
+    },
+    {
+      "epoch": 0.3592814371257485,
+      "grad_norm": 0.04653725028038025,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.0016,
+      "step": 15
+    },
+    {
+      "epoch": 0.3592814371257485,
+      "eval_loss": 0.0017086381558328867,
+      "eval_runtime": 2.7421,
+      "eval_samples_per_second": 6.564,
+      "eval_steps_per_second": 3.282,
+      "step": 15
+    },
+    {
+      "epoch": 0.38323353293413176,
+      "grad_norm": 0.05396345630288124,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.0015,
+      "step": 16
+    },
+    {
+      "epoch": 0.40718562874251496,
+      "grad_norm": 0.05413348600268364,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 0.0018,
+      "step": 17
+    },
+    {
+      "epoch": 0.4311377245508982,
+      "grad_norm": 0.045410510152578354,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 0.0018,
+      "step": 18
+    },
+    {
+      "epoch": 0.4550898203592814,
+      "grad_norm": 0.05225275084376335,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.0018,
+      "step": 19
+    },
+    {
+      "epoch": 0.47904191616766467,
+      "grad_norm": 0.03295710310339928,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.0015,
+      "step": 20
+    },
+    {
+      "epoch": 0.47904191616766467,
+      "eval_loss": 0.0014264764031395316,
+      "eval_runtime": 2.7392,
+      "eval_samples_per_second": 6.571,
+      "eval_steps_per_second": 3.286,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 89038163804160.0,
+  "total_flos": 178076327608320.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null