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:ecbe442b30b6c71cd40dd851753a1e1d55c551845b4b13fe0545da506ad4071c
+oid sha256:bc4450456e428209fed6a9f910be8e2ffda4d6de663156479144261f095de5bd
 size 72936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8469869d3fceef8d228df3f342af406566042f39c72efdeed06cdc844490ffd
+oid sha256:e7afcd819a48068c6c3755421597990e1b18a1d3ffc8554c56c8a64b6fc89615
 size 151106

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8946fa62afdd702d6f910bffd1daa5c2f346677489bf504783b07d243c459702
+oid sha256:aeb68b4d933f407fc169d8465a10c1ba8d22f46948e82239edb2283aaeb0a27a
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:479842a97f2f703c73992aac3e410ecf1dd8279f6c9b7825a03e47a8859e0fe4
+oid sha256:4c176f023fc4bc7b64b14735744c93381ae37c2fb7d7d13ebe8235d0ed1b05f9
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17e3767e573f378d1b71ab9b73d7e6e6660a0ea0e5d7cfb7d09ed12c5c38d24d
+oid sha256:826d85cca0d24c8713f1aa1300d2bb759fac390e64727beb53682cdd6d8aa6c9
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a417347deb38343804b550bb9b2147b69f15a3dc5779fec340d425a071141766
+oid sha256:c0ba98a8093d8f8357b313af17ff94286d41a72aa47485b0d05efdd5d6495132
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be8caf7fa4463f33e63c7d7f3ff1f11334d94ec08dbec4c73589ab9b45fd5604
+oid sha256:8a20c0f89ca7f58eda7b6ab063126b28fbe8e0698e5edc060f51e51ea7d3446d
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2dd3450974231b138d365e9f96bb1a26c9e2f215e52c2f6824d2b9a5aa3643de
+oid sha256:8b5a9eeb3c49f2a3fc242c05cdade0cbbae6ff3e87b25cac7e94cb4ba49fd562
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16189952275c40abaeccdaea25b1da792adb3764a540505f210730ad53738b36
+oid sha256:44c4848811ec259ac5a2430c7e5b3843eb237ac5e4312cebf9c61a8346e8b76f
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06c96c81992fa12ed09b604dace16a12ed8e1543e02c57e0cef46015394eebf8
+oid sha256:c39eede1bbb36efb3e12c37350edee2e14e6b0a1b782f46190e15ebdea48d8a5
 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": 12.44759750366211,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.9803921568627451,
+  "best_metric": 12.426092147827148,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "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": 869.826,
       "eval_steps_per_second": 27.814,
       "step": 50
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.11416830867528915,
+      "learning_rate": 7.204195804195805e-05,
+      "loss": 12.453,
+      "step": 51
+    },
+    {
+      "epoch": 1.0196078431372548,
+      "grad_norm": 0.08539585024118423,
+      "learning_rate": 7.133566433566433e-05,
+      "loss": 12.4519,
+      "step": 52
+    },
+    {
+      "epoch": 1.0392156862745099,
+      "grad_norm": 0.11319365352392197,
+      "learning_rate": 7.062937062937062e-05,
+      "loss": 12.448,
+      "step": 53
+    },
+    {
+      "epoch": 1.0588235294117647,
+      "grad_norm": 0.14616349339485168,
+      "learning_rate": 6.992307692307692e-05,
+      "loss": 12.4479,
+      "step": 54
+    },
+    {
+      "epoch": 1.0784313725490196,
+      "grad_norm": 0.15833082795143127,
+      "learning_rate": 6.921678321678321e-05,
+      "loss": 12.4471,
+      "step": 55
+    },
+    {
+      "epoch": 1.0980392156862746,
+      "grad_norm": 0.19201552867889404,
+      "learning_rate": 6.851048951048951e-05,
+      "loss": 12.4455,
+      "step": 56
+    },
+    {
+      "epoch": 1.1176470588235294,
+      "grad_norm": 0.23073577880859375,
+      "learning_rate": 6.78041958041958e-05,
+      "loss": 12.442,
+      "step": 57
+    },
+    {
+      "epoch": 1.1372549019607843,
+      "grad_norm": 0.13355469703674316,
+      "learning_rate": 6.70979020979021e-05,
+      "loss": 12.4496,
+      "step": 58
+    },
+    {
+      "epoch": 1.156862745098039,
+      "grad_norm": 0.15398786962032318,
+      "learning_rate": 6.639160839160838e-05,
+      "loss": 12.4465,
+      "step": 59
+    },
+    {
+      "epoch": 1.1764705882352942,
+      "grad_norm": 0.1663445234298706,
+      "learning_rate": 6.568531468531468e-05,
+      "loss": 12.4482,
+      "step": 60
+    },
+    {
+      "epoch": 1.196078431372549,
+      "grad_norm": 0.2090064436197281,
+      "learning_rate": 6.497902097902097e-05,
+      "loss": 12.4475,
+      "step": 61
+    },
+    {
+      "epoch": 1.215686274509804,
+      "grad_norm": 0.2399904429912567,
+      "learning_rate": 6.427272727272727e-05,
+      "loss": 12.4436,
+      "step": 62
+    },
+    {
+      "epoch": 1.2352941176470589,
+      "grad_norm": 0.24960361421108246,
+      "learning_rate": 6.356643356643356e-05,
+      "loss": 12.444,
+      "step": 63
+    },
+    {
+      "epoch": 1.2549019607843137,
+      "grad_norm": 0.18903537094593048,
+      "learning_rate": 6.286013986013986e-05,
+      "loss": 12.4457,
+      "step": 64
+    },
+    {
+      "epoch": 1.2745098039215685,
+      "grad_norm": 0.16718223690986633,
+      "learning_rate": 6.215384615384615e-05,
+      "loss": 12.4481,
+      "step": 65
+    },
+    {
+      "epoch": 1.2941176470588236,
+      "grad_norm": 0.2060553878545761,
+      "learning_rate": 6.144755244755245e-05,
+      "loss": 12.4452,
+      "step": 66
+    },
+    {
+      "epoch": 1.3137254901960784,
+      "grad_norm": 0.22543393075466156,
+      "learning_rate": 6.074125874125874e-05,
+      "loss": 12.4413,
+      "step": 67
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.27220749855041504,
+      "learning_rate": 6.0034965034965033e-05,
+      "loss": 12.4421,
+      "step": 68
+    },
+    {
+      "epoch": 1.3529411764705883,
+      "grad_norm": 0.2713835835456848,
+      "learning_rate": 5.932867132867133e-05,
+      "loss": 12.4424,
+      "step": 69
+    },
+    {
+      "epoch": 1.3725490196078431,
+      "grad_norm": 0.23676316440105438,
+      "learning_rate": 5.8622377622377624e-05,
+      "loss": 12.4398,
+      "step": 70
+    },
+    {
+      "epoch": 1.392156862745098,
+      "grad_norm": 0.1754506677389145,
+      "learning_rate": 5.791608391608392e-05,
+      "loss": 12.4448,
+      "step": 71
+    },
+    {
+      "epoch": 1.4117647058823528,
+      "grad_norm": 0.2169537991285324,
+      "learning_rate": 5.7209790209790215e-05,
+      "loss": 12.4407,
+      "step": 72
+    },
+    {
+      "epoch": 1.4313725490196079,
+      "grad_norm": 0.2186908721923828,
+      "learning_rate": 5.650349650349651e-05,
+      "loss": 12.4367,
+      "step": 73
+    },
+    {
+      "epoch": 1.4509803921568627,
+      "grad_norm": 0.24410758912563324,
+      "learning_rate": 5.579720279720279e-05,
+      "loss": 12.4392,
+      "step": 74
+    },
+    {
+      "epoch": 1.4705882352941178,
+      "grad_norm": 0.2627074122428894,
+      "learning_rate": 5.509090909090909e-05,
+      "loss": 12.4316,
+      "step": 75
+    },
+    {
+      "epoch": 1.4901960784313726,
+      "grad_norm": 0.2872616946697235,
+      "learning_rate": 5.438461538461538e-05,
+      "loss": 12.4323,
+      "step": 76
+    },
+    {
+      "epoch": 1.5098039215686274,
+      "grad_norm": 0.13781462609767914,
+      "learning_rate": 5.367832167832168e-05,
+      "loss": 12.443,
+      "step": 77
+    },
+    {
+      "epoch": 1.5294117647058822,
+      "grad_norm": 0.19649550318717957,
+      "learning_rate": 5.2972027972027974e-05,
+      "loss": 12.4353,
+      "step": 78
+    },
+    {
+      "epoch": 1.5490196078431373,
+      "grad_norm": 0.19505800306797028,
+      "learning_rate": 5.226573426573427e-05,
+      "loss": 12.4398,
+      "step": 79
+    },
+    {
+      "epoch": 1.5686274509803921,
+      "grad_norm": 0.20190319418907166,
+      "learning_rate": 5.1559440559440565e-05,
+      "loss": 12.4362,
+      "step": 80
+    },
+    {
+      "epoch": 1.5882352941176472,
+      "grad_norm": 0.18724848330020905,
+      "learning_rate": 5.085314685314686e-05,
+      "loss": 12.434,
+      "step": 81
+    },
+    {
+      "epoch": 1.607843137254902,
+      "grad_norm": 0.2352747619152069,
+      "learning_rate": 5.014685314685315e-05,
+      "loss": 12.4278,
+      "step": 82
+    },
+    {
+      "epoch": 1.6274509803921569,
+      "grad_norm": 0.14110158383846283,
+      "learning_rate": 4.9440559440559444e-05,
+      "loss": 12.4396,
+      "step": 83
+    },
+    {
+      "epoch": 1.6470588235294117,
+      "grad_norm": 0.1315547674894333,
+      "learning_rate": 4.873426573426573e-05,
+      "loss": 12.4396,
+      "step": 84
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.13215842843055725,
+      "learning_rate": 4.802797202797203e-05,
+      "loss": 12.4354,
+      "step": 85
+    },
+    {
+      "epoch": 1.6862745098039216,
+      "grad_norm": 0.14507846534252167,
+      "learning_rate": 4.7321678321678324e-05,
+      "loss": 12.4371,
+      "step": 86
+    },
+    {
+      "epoch": 1.7058823529411766,
+      "grad_norm": 0.1558404117822647,
+      "learning_rate": 4.661538461538462e-05,
+      "loss": 12.4326,
+      "step": 87
+    },
+    {
+      "epoch": 1.7254901960784315,
+      "grad_norm": 0.16582131385803223,
+      "learning_rate": 4.590909090909091e-05,
+      "loss": 12.4294,
+      "step": 88
+    },
+    {
+      "epoch": 1.7450980392156863,
+      "grad_norm": 0.12328918278217316,
+      "learning_rate": 4.52027972027972e-05,
+      "loss": 12.4346,
+      "step": 89
+    },
+    {
+      "epoch": 1.7647058823529411,
+      "grad_norm": 0.10181323438882828,
+      "learning_rate": 4.44965034965035e-05,
+      "loss": 12.4404,
+      "step": 90
+    },
+    {
+      "epoch": 1.784313725490196,
+      "grad_norm": 0.11123471707105637,
+      "learning_rate": 4.379020979020979e-05,
+      "loss": 12.435,
+      "step": 91
+    },
+    {
+      "epoch": 1.803921568627451,
+      "grad_norm": 0.11661916226148605,
+      "learning_rate": 4.308391608391608e-05,
+      "loss": 12.4312,
+      "step": 92
+    },
+    {
+      "epoch": 1.8235294117647058,
+      "grad_norm": 0.09935862571001053,
+      "learning_rate": 4.237762237762238e-05,
+      "loss": 12.4318,
+      "step": 93
+    },
+    {
+      "epoch": 1.843137254901961,
+      "grad_norm": 0.12922266125679016,
+      "learning_rate": 4.167132867132867e-05,
+      "loss": 12.4327,
+      "step": 94
+    },
+    {
+      "epoch": 1.8627450980392157,
+      "grad_norm": 0.1282566338777542,
+      "learning_rate": 4.096503496503496e-05,
+      "loss": 12.4311,
+      "step": 95
+    },
+    {
+      "epoch": 1.8823529411764706,
+      "grad_norm": 0.07856478542089462,
+      "learning_rate": 4.025874125874126e-05,
+      "loss": 12.4363,
+      "step": 96
+    },
+    {
+      "epoch": 1.9019607843137254,
+      "grad_norm": 0.09109707176685333,
+      "learning_rate": 3.955244755244755e-05,
+      "loss": 12.4274,
+      "step": 97
+    },
+    {
+      "epoch": 1.9215686274509802,
+      "grad_norm": 0.09043984115123749,
+      "learning_rate": 3.884615384615385e-05,
+      "loss": 12.4345,
+      "step": 98
+    },
+    {
+      "epoch": 1.9411764705882353,
+      "grad_norm": 0.09672176837921143,
+      "learning_rate": 3.8139860139860137e-05,
+      "loss": 12.4294,
+      "step": 99
+    },
+    {
+      "epoch": 1.9607843137254903,
+      "grad_norm": 0.104476198554039,
+      "learning_rate": 3.743356643356643e-05,
+      "loss": 12.4295,
+      "step": 100
+    },
+    {
+      "epoch": 1.9607843137254903,
+      "eval_loss": 12.426092147827148,
+      "eval_runtime": 0.7943,
+      "eval_samples_per_second": 866.219,
+      "eval_steps_per_second": 27.699,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -401,7 +759,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1542665011200.0,
+  "total_flos": 3085330022400.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null