Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b336c7028dc9c76a65e3d4107812721e5abd6fea0ab548ad65111d27e8d3c752
+oid sha256:95054becb4d4b8cf655cd8e6bf230ea6b6fe8bb51a29bbbf1eaab7871504a164
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c0df0ecca2e8ec04d4ff2380a9179174806545d5ce4b773be58e6b047973935
+oid sha256:489ecea0daa164762eae7608fcf56a5580523c9e54ea4d91c2775bd44ad7ae4a
 size 166439638

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e3d41de716736e12dafbd11be068ea31ebe2d631b929e5d1da2c9c1c8750fc7
+oid sha256:8dda35150537efcaa35f5dc9a353ae196533e259e9b0a38fc01ee055b5232095
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ea7ff16b0c30a914eb0d145e3fb06ff9027c6cd2408e766ce8a09accab89a4d
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7356017231941223,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.00839278220730172,
+  "best_metric": 0.7258085012435913,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.01678556441460344,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 5.934,
       "eval_steps_per_second": 2.969,
       "step": 25
+    },
+    {
+      "epoch": 0.008728493495593789,
+      "grad_norm": 0.47435083985328674,
+      "learning_rate": 0.0001,
+      "loss": 0.829,
+      "step": 26
+    },
+    {
+      "epoch": 0.009064204783885858,
+      "grad_norm": 0.4807548224925995,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 0.7353,
+      "step": 27
+    },
+    {
+      "epoch": 0.009399916072177926,
+      "grad_norm": 0.43215635418891907,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 0.776,
+      "step": 28
+    },
+    {
+      "epoch": 0.009735627360469996,
+      "grad_norm": 0.398535817861557,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 0.778,
+      "step": 29
+    },
+    {
+      "epoch": 0.010071338648762064,
+      "grad_norm": 0.4872318208217621,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 0.8021,
+      "step": 30
+    },
+    {
+      "epoch": 0.010407049937054134,
+      "grad_norm": 0.4282318651676178,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 0.8409,
+      "step": 31
+    },
+    {
+      "epoch": 0.010742761225346202,
+      "grad_norm": 0.412360280752182,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 0.641,
+      "step": 32
+    },
+    {
+      "epoch": 0.011078472513638271,
+      "grad_norm": 0.44958484172821045,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 0.7708,
+      "step": 33
+    },
+    {
+      "epoch": 0.01141418380193034,
+      "grad_norm": 0.5542835593223572,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.8557,
+      "step": 34
+    },
+    {
+      "epoch": 0.01174989509022241,
+      "grad_norm": 0.506291925907135,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 0.703,
+      "step": 35
+    },
+    {
+      "epoch": 0.012085606378514477,
+      "grad_norm": 0.5930730700492859,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 0.907,
+      "step": 36
+    },
+    {
+      "epoch": 0.012421317666806547,
+      "grad_norm": 0.44674548506736755,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 0.6435,
+      "step": 37
+    },
+    {
+      "epoch": 0.012757028955098615,
+      "grad_norm": 0.5273513793945312,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.9527,
+      "step": 38
+    },
+    {
+      "epoch": 0.013092740243390685,
+      "grad_norm": 0.48624753952026367,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 0.8207,
+      "step": 39
+    },
+    {
+      "epoch": 0.013428451531682753,
+      "grad_norm": 0.5799288153648376,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 0.7522,
+      "step": 40
+    },
+    {
+      "epoch": 0.013764162819974822,
+      "grad_norm": 0.4889924228191376,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 0.7454,
+      "step": 41
+    },
+    {
+      "epoch": 0.01409987410826689,
+      "grad_norm": 0.5171151161193848,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 0.7182,
+      "step": 42
+    },
+    {
+      "epoch": 0.01443558539655896,
+      "grad_norm": 0.5659388899803162,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 0.7468,
+      "step": 43
+    },
+    {
+      "epoch": 0.014771296684851028,
+      "grad_norm": 0.5659289360046387,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.7714,
+      "step": 44
+    },
+    {
+      "epoch": 0.015107007973143098,
+      "grad_norm": 0.60720294713974,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 0.7841,
+      "step": 45
+    },
+    {
+      "epoch": 0.015442719261435166,
+      "grad_norm": 0.6002097129821777,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 0.8471,
+      "step": 46
+    },
+    {
+      "epoch": 0.015778430549727235,
+      "grad_norm": 0.653490424156189,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 0.6657,
+      "step": 47
+    },
+    {
+      "epoch": 0.016114141838019302,
+      "grad_norm": 0.6233632564544678,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 0.7918,
+      "step": 48
+    },
+    {
+      "epoch": 0.01644985312631137,
+      "grad_norm": 0.7531246542930603,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 0.7391,
+      "step": 49
+    },
+    {
+      "epoch": 0.01678556441460344,
+      "grad_norm": 0.7968045473098755,
+      "learning_rate": 0.0,
+      "loss": 0.636,
+      "step": 50
+    },
+    {
+      "epoch": 0.01678556441460344,
+      "eval_loss": 0.7258085012435913,
+      "eval_runtime": 211.581,
+      "eval_samples_per_second": 5.932,
+      "eval_steps_per_second": 2.968,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.00529829052416e+16,
+  "total_flos": 2.01059658104832e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null