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:b561772d3c754512a945c3fb18f4c77dc5229588002eb3199281faf28a059c8c
+oid sha256:04460730a843597d7156cb8b4b43d3f29bcec6fad5f607de5e69d78dc9245a28
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc61e298652cff87eef3d8afb96a7f62b0b2c448aeef658bdf1fb6dd19f650c3
+oid sha256:3dd234dc65dfca869fcefc6537938ba5f4e344006b9d23fb529077a91c816774
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5af4cbe6dd62788676ba2597afaddb6a97ff06bf7b18f8e3a0ce4190a674ccd8
+oid sha256:2dc3e5265caade9b4765ce3bea88afed07b875a6b1b6dbe83b1b96d505d55d4b
 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": 3.0784964561462402,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.006697923643670462,
+  "best_metric": 2.7820396423339844,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.013395847287340924,
   "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": 4.999,
       "eval_steps_per_second": 2.504,
       "step": 10
+    },
+    {
+      "epoch": 0.007367716008037508,
+      "grad_norm": 49.211883544921875,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 14.7968,
+      "step": 11
+    },
+    {
+      "epoch": 0.008037508372404554,
+      "grad_norm": 30.02019500732422,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 10.412,
+      "step": 12
+    },
+    {
+      "epoch": 0.008707300736771601,
+      "grad_norm": 34.77397537231445,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 11.8404,
+      "step": 13
+    },
+    {
+      "epoch": 0.009377093101138647,
+      "grad_norm": 37.78995895385742,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 11.643,
+      "step": 14
+    },
+    {
+      "epoch": 0.010046885465505693,
+      "grad_norm": 37.61135482788086,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 11.3571,
+      "step": 15
+    },
+    {
+      "epoch": 0.010046885465505693,
+      "eval_loss": 2.9143412113189697,
+      "eval_runtime": 124.2648,
+      "eval_samples_per_second": 5.062,
+      "eval_steps_per_second": 2.535,
+      "step": 15
+    },
+    {
+      "epoch": 0.010716677829872739,
+      "grad_norm": 30.211618423461914,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 10.1207,
+      "step": 16
+    },
+    {
+      "epoch": 0.011386470194239785,
+      "grad_norm": 32.74803161621094,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 11.6455,
+      "step": 17
+    },
+    {
+      "epoch": 0.012056262558606833,
+      "grad_norm": 42.23529815673828,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 12.6393,
+      "step": 18
+    },
+    {
+      "epoch": 0.012726054922973878,
+      "grad_norm": 47.026275634765625,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 11.7427,
+      "step": 19
+    },
+    {
+      "epoch": 0.013395847287340924,
+      "grad_norm": 44.214298248291016,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 11.9615,
+      "step": 20
+    },
+    {
+      "epoch": 0.013395847287340924,
+      "eval_loss": 2.7820396423339844,
+      "eval_runtime": 124.547,
+      "eval_samples_per_second": 5.05,
+      "eval_steps_per_second": 2.529,
+      "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