Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c1f88f8ce7734f92c6cc5707e9697616e0d95ddae47a2373808f90710d36e00
+oid sha256:a36f5bd5d0ad1556c52f9f480daca9f2062b8320e542e37fa3e3963a265eb2f0
 size 34456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99f92e679081f7bf8fb478a1013a652ee7f4a44783622f4802190ac8942b8bff
+oid sha256:fb6b00d2d8bd11b1fb863b6590f3af154723b2315e8964a991b65b92fc6d1d01
 size 73222

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75d0ded002e575ea39a93c71f4622d85c624f310c3b54d1c86fe2abb111f2dc1
+oid sha256:b8625fedd3b9dc2863863f55c5492f9f19129ebb32ca4aaf69e253c36d8a964a
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd976b7910c38e9d7cbb28d931cabfc9ee8ac0d9a0773c9686ddc40d96885369
+oid sha256:73e6dcf1460ea7765eeac51329d67195a6b02bdebb383a09ea802662d04e8de4
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb238bbaaba5c30824400878d0c61a6f806b128927fde119e0e03f2cf9129135
+oid sha256:3b1b35b0f664045580bb0fb8d31c5e9c16a3b52acb352756eba04df3d7ab228f
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec08508bb4ed535af8d85bb3c7bca305a4394cfb45c5697f24a2c786e0c64e01
+oid sha256:b59be4835310cc0387e66fc5dc9a31a8823a5c37cc47f802bf122fcb0703091f
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07f57fcd3d353dc0c7a43d1c5c4a640482773d4f76801417098bb006f6e3c8c8
+oid sha256:95d34ef9f406f4b540792946d48014e4c3b43ed63134619c7e56de5b23b9ff12
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c594d5fc789b37d398086c11f95ebc7839d15afe722e0f967c896ec4314f990
+oid sha256:ba9a935bde0998eb5beb8ad9f02538be3794135029ee891eb59fdc9367216645
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3c38b818bf1e3b58f82b59d732f67d6db8661f3f14aa7ce2e48f21bad646794
+oid sha256:f434a1ddedf09bc507bcdb9ff9313a8e70a9a3b14c12ef13d399b119a912edd2
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:313fdffea8c545c83433ae5b92e229e28b12f8e1bea94304b69c2d3b445a6b24
+oid sha256:109824638a377a3740ee4bb046fb134f5685c1d80904f971ccdbfe1ad86b4bbd
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c25700fa02b1ba16d5100b9812d6be24bedf61472c056044f3d06568d18d4f2
+oid sha256:fb09a39c6de2a486cc682371c416a0e1cf0414a01cda4f261ed6b472bbdffd62
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 11.5,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.9803921568627451,
+  "epoch": 1.9607843137254903,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -373,6 +373,364 @@
       "eval_samples_per_second": 1064.006,
       "eval_steps_per_second": 34.023,
       "step": 50
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.0001408671378158033,
+      "learning_rate": 7.204195804195805e-05,
+      "loss": 46.0,
+      "step": 51
+    },
+    {
+      "epoch": 1.0196078431372548,
+      "grad_norm": 0.00018512530368752778,
+      "learning_rate": 7.133566433566433e-05,
+      "loss": 46.0,
+      "step": 52
+    },
+    {
+      "epoch": 1.0392156862745099,
+      "grad_norm": 0.00012292621249798685,
+      "learning_rate": 7.062937062937062e-05,
+      "loss": 46.0,
+      "step": 53
+    },
+    {
+      "epoch": 1.0588235294117647,
+      "grad_norm": 0.00018587136582937092,
+      "learning_rate": 6.992307692307692e-05,
+      "loss": 46.0,
+      "step": 54
+    },
+    {
+      "epoch": 1.0784313725490196,
+      "grad_norm": 0.00020599419076461345,
+      "learning_rate": 6.921678321678321e-05,
+      "loss": 46.0,
+      "step": 55
+    },
+    {
+      "epoch": 1.0980392156862746,
+      "grad_norm": 0.00018194003496319056,
+      "learning_rate": 6.851048951048951e-05,
+      "loss": 46.0,
+      "step": 56
+    },
+    {
+      "epoch": 1.1176470588235294,
+      "grad_norm": 0.00020641495939344168,
+      "learning_rate": 6.78041958041958e-05,
+      "loss": 46.0,
+      "step": 57
+    },
+    {
+      "epoch": 1.1372549019607843,
+      "grad_norm": 0.00022939956397749484,
+      "learning_rate": 6.70979020979021e-05,
+      "loss": 46.0,
+      "step": 58
+    },
+    {
+      "epoch": 1.156862745098039,
+      "grad_norm": 0.00016353426326531917,
+      "learning_rate": 6.639160839160838e-05,
+      "loss": 46.0,
+      "step": 59
+    },
+    {
+      "epoch": 1.1764705882352942,
+      "grad_norm": 0.000171757405041717,
+      "learning_rate": 6.568531468531468e-05,
+      "loss": 46.0,
+      "step": 60
+    },
+    {
+      "epoch": 1.196078431372549,
+      "grad_norm": 0.00018360056856181473,
+      "learning_rate": 6.497902097902097e-05,
+      "loss": 46.0,
+      "step": 61
+    },
+    {
+      "epoch": 1.215686274509804,
+      "grad_norm": 0.00025392137467861176,
+      "learning_rate": 6.427272727272727e-05,
+      "loss": 46.0,
+      "step": 62
+    },
+    {
+      "epoch": 1.2352941176470589,
+      "grad_norm": 0.0002807354903779924,
+      "learning_rate": 6.356643356643356e-05,
+      "loss": 46.0,
+      "step": 63
+    },
+    {
+      "epoch": 1.2549019607843137,
+      "grad_norm": 0.00026548118330538273,
+      "learning_rate": 6.286013986013986e-05,
+      "loss": 46.0,
+      "step": 64
+    },
+    {
+      "epoch": 1.2745098039215685,
+      "grad_norm": 0.00016954861348494887,
+      "learning_rate": 6.215384615384615e-05,
+      "loss": 46.0,
+      "step": 65
+    },
+    {
+      "epoch": 1.2941176470588236,
+      "grad_norm": 0.0002116493706125766,
+      "learning_rate": 6.144755244755245e-05,
+      "loss": 46.0,
+      "step": 66
+    },
+    {
+      "epoch": 1.3137254901960784,
+      "grad_norm": 0.00016135629266500473,
+      "learning_rate": 6.074125874125874e-05,
+      "loss": 46.0,
+      "step": 67
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.00022329531202558428,
+      "learning_rate": 6.0034965034965033e-05,
+      "loss": 46.0,
+      "step": 68
+    },
+    {
+      "epoch": 1.3529411764705883,
+      "grad_norm": 0.00028010981623083353,
+      "learning_rate": 5.932867132867133e-05,
+      "loss": 46.0,
+      "step": 69
+    },
+    {
+      "epoch": 1.3725490196078431,
+      "grad_norm": 0.00031517096795141697,
+      "learning_rate": 5.8622377622377624e-05,
+      "loss": 46.0,
+      "step": 70
+    },
+    {
+      "epoch": 1.392156862745098,
+      "grad_norm": 0.00030739433714188635,
+      "learning_rate": 5.791608391608392e-05,
+      "loss": 46.0,
+      "step": 71
+    },
+    {
+      "epoch": 1.4117647058823528,
+      "grad_norm": 0.00018070408259518445,
+      "learning_rate": 5.7209790209790215e-05,
+      "loss": 46.0,
+      "step": 72
+    },
+    {
+      "epoch": 1.4313725490196079,
+      "grad_norm": 0.00026431979495100677,
+      "learning_rate": 5.650349650349651e-05,
+      "loss": 46.0,
+      "step": 73
+    },
+    {
+      "epoch": 1.4509803921568627,
+      "grad_norm": 0.00020367998513393104,
+      "learning_rate": 5.579720279720279e-05,
+      "loss": 46.0,
+      "step": 74
+    },
+    {
+      "epoch": 1.4705882352941178,
+      "grad_norm": 0.00026323492056690156,
+      "learning_rate": 5.509090909090909e-05,
+      "loss": 46.0,
+      "step": 75
+    },
+    {
+      "epoch": 1.4901960784313726,
+      "grad_norm": 0.00034865838824771345,
+      "learning_rate": 5.438461538461538e-05,
+      "loss": 46.0,
+      "step": 76
+    },
+    {
+      "epoch": 1.5098039215686274,
+      "grad_norm": 0.00023557976237498224,
+      "learning_rate": 5.367832167832168e-05,
+      "loss": 46.0,
+      "step": 77
+    },
+    {
+      "epoch": 1.5294117647058822,
+      "grad_norm": 0.00021717116760555655,
+      "learning_rate": 5.2972027972027974e-05,
+      "loss": 46.0,
+      "step": 78
+    },
+    {
+      "epoch": 1.5490196078431373,
+      "grad_norm": 0.00027765179402194917,
+      "learning_rate": 5.226573426573427e-05,
+      "loss": 46.0,
+      "step": 79
+    },
+    {
+      "epoch": 1.5686274509803921,
+      "grad_norm": 0.00025422070757485926,
+      "learning_rate": 5.1559440559440565e-05,
+      "loss": 46.0,
+      "step": 80
+    },
+    {
+      "epoch": 1.5882352941176472,
+      "grad_norm": 0.0003297334478702396,
+      "learning_rate": 5.085314685314686e-05,
+      "loss": 46.0,
+      "step": 81
+    },
+    {
+      "epoch": 1.607843137254902,
+      "grad_norm": 0.0004201807314530015,
+      "learning_rate": 5.014685314685315e-05,
+      "loss": 46.0,
+      "step": 82
+    },
+    {
+      "epoch": 1.6274509803921569,
+      "grad_norm": 0.0003534739080350846,
+      "learning_rate": 4.9440559440559444e-05,
+      "loss": 46.0,
+      "step": 83
+    },
+    {
+      "epoch": 1.6470588235294117,
+      "grad_norm": 0.00024288770509883761,
+      "learning_rate": 4.873426573426573e-05,
+      "loss": 46.0,
+      "step": 84
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.0002575070830062032,
+      "learning_rate": 4.802797202797203e-05,
+      "loss": 46.0,
+      "step": 85
+    },
+    {
+      "epoch": 1.6862745098039216,
+      "grad_norm": 0.00034273709752596915,
+      "learning_rate": 4.7321678321678324e-05,
+      "loss": 46.0,
+      "step": 86
+    },
+    {
+      "epoch": 1.7058823529411766,
+      "grad_norm": 0.0003354206564836204,
+      "learning_rate": 4.661538461538462e-05,
+      "loss": 46.0,
+      "step": 87
+    },
+    {
+      "epoch": 1.7254901960784315,
+      "grad_norm": 0.0002988223859574646,
+      "learning_rate": 4.590909090909091e-05,
+      "loss": 46.0,
+      "step": 88
+    },
+    {
+      "epoch": 1.7450980392156863,
+      "grad_norm": 0.0003722968394868076,
+      "learning_rate": 4.52027972027972e-05,
+      "loss": 46.0,
+      "step": 89
+    },
+    {
+      "epoch": 1.7647058823529411,
+      "grad_norm": 0.00026949227321892977,
+      "learning_rate": 4.44965034965035e-05,
+      "loss": 46.0,
+      "step": 90
+    },
+    {
+      "epoch": 1.784313725490196,
+      "grad_norm": 0.0003130983968731016,
+      "learning_rate": 4.379020979020979e-05,
+      "loss": 46.0,
+      "step": 91
+    },
+    {
+      "epoch": 1.803921568627451,
+      "grad_norm": 0.00026243989123031497,
+      "learning_rate": 4.308391608391608e-05,
+      "loss": 46.0,
+      "step": 92
+    },
+    {
+      "epoch": 1.8235294117647058,
+      "grad_norm": 0.00027229124680161476,
+      "learning_rate": 4.237762237762238e-05,
+      "loss": 46.0,
+      "step": 93
+    },
+    {
+      "epoch": 1.843137254901961,
+      "grad_norm": 0.00035372612182982266,
+      "learning_rate": 4.167132867132867e-05,
+      "loss": 46.0,
+      "step": 94
+    },
+    {
+      "epoch": 1.8627450980392157,
+      "grad_norm": 0.00039300689240917563,
+      "learning_rate": 4.096503496503496e-05,
+      "loss": 46.0,
+      "step": 95
+    },
+    {
+      "epoch": 1.8823529411764706,
+      "grad_norm": 0.0002876557700801641,
+      "learning_rate": 4.025874125874126e-05,
+      "loss": 46.0,
+      "step": 96
+    },
+    {
+      "epoch": 1.9019607843137254,
+      "grad_norm": 0.00022314459783956409,
+      "learning_rate": 3.955244755244755e-05,
+      "loss": 46.0,
+      "step": 97
+    },
+    {
+      "epoch": 1.9215686274509802,
+      "grad_norm": 0.00026848912239074707,
+      "learning_rate": 3.884615384615385e-05,
+      "loss": 46.0,
+      "step": 98
+    },
+    {
+      "epoch": 1.9411764705882353,
+      "grad_norm": 0.00027283094823360443,
+      "learning_rate": 3.8139860139860137e-05,
+      "loss": 46.0,
+      "step": 99
+    },
+    {
+      "epoch": 1.9607843137254903,
+      "grad_norm": 0.0004197805537842214,
+      "learning_rate": 3.743356643356643e-05,
+      "loss": 46.0,
+      "step": 100
+    },
+    {
+      "epoch": 1.9607843137254903,
+      "eval_loss": 11.5,
+      "eval_runtime": 0.4631,
+      "eval_samples_per_second": 1485.776,
+      "eval_steps_per_second": 47.51,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -387,7 +745,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -401,7 +759,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 64316925542400.0,
+  "total_flos": 128633851084800.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null