Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4959d02b9c37da3e509863a47169358d0c22fd4b108ad2b2641da2c7e5e191be
+oid sha256:a4a596d0d880ecb672b7bfc1fe6c58feecf830b7f67d9f8401a9aac5acc9e0e8
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5406f0178b65205f6cb5f4e466b75c948a2b467094819751f941efc55da73403
+oid sha256:f31fdcb329cdea928e3792729da78f283d30c7c764f34a8b957558d7f9d3bef0
 size 323290986

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52b84ce5f2ff0cb6b9af0a4dee62b360407acb99279aa1490395a7b1c26d8eca
+oid sha256:fc381df12185aaae24afc9b9cb123ba6ef0d6cdefe3858b98a5823ff276b1037
 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": 1.0362653029005742e-06,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.010691756655618518,
+  "best_metric": 7.289086170203518e-07,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.021383513311237036,
   "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": 3.13,
       "eval_steps_per_second": 1.566,
       "step": 25
+    },
+    {
+      "epoch": 0.01111942692184326,
+      "grad_norm": 4.8767116823000833e-05,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.011547097188068,
+      "grad_norm": 6.502281758002937e-05,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.01197476745429274,
+      "grad_norm": 6.602615758311003e-05,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.012402437720517481,
+      "grad_norm": 5.0644768634811044e-05,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.012830107986742221,
+      "grad_norm": 5.069350663688965e-05,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.013257778252966963,
+      "grad_norm": 5.2160845370963216e-05,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.013685448519191703,
+      "grad_norm": 6.362736894516274e-05,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.014113118785416445,
+      "grad_norm": 3.193640077370219e-05,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.014540789051641185,
+      "grad_norm": 4.6847257181070745e-05,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.014968459317865926,
+      "grad_norm": 5.645761848427355e-05,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.015396129584090666,
+      "grad_norm": 5.42275702173356e-05,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.015823799850315408,
+      "grad_norm": 3.7983110814820975e-05,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.016251470116540146,
+      "grad_norm": 5.3667157771997154e-05,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.016679140382764888,
+      "grad_norm": 6.712380127282813e-05,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.01710681064898963,
+      "grad_norm": 5.945265002083033e-05,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.01753448091521437,
+      "grad_norm": 8.635499398224056e-05,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.01796215118143911,
+      "grad_norm": 4.466330574359745e-05,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.01838982144766385,
+      "grad_norm": 8.208598592318594e-05,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.018817491713888593,
+      "grad_norm": 4.9784361181082204e-05,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.01924516198011333,
+      "grad_norm": 4.904253364657052e-05,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.019672832246338073,
+      "grad_norm": 4.512963641900569e-05,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.020100502512562814,
+      "grad_norm": 0.0003454079560469836,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.020528172778787556,
+      "grad_norm": 3.0036284442758188e-05,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.020955843045012294,
+      "grad_norm": 2.3758571842336096e-05,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.021383513311237036,
+      "grad_norm": 3.3361844543833286e-05,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.021383513311237036,
+      "eval_loss": 7.289086170203518e-07,
+      "eval_runtime": 314.8067,
+      "eval_samples_per_second": 3.129,
+      "eval_steps_per_second": 1.566,
+      "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": 3.49519346663424e+16,
+  "total_flos": 6.99038693326848e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null