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:bf541b868591075fc98a028c61daa96040ffab5edbd1aeb899e497da5fa4a65f
+oid sha256:46ff8ed128566f07db35e60bf41cd4fd755471bcadb4a91a46c51b302229ce19
 size 180385008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd1ba2a9592ccf1ca8abcdc1843d84d39d30ef5b2c2d880ac35958647e76b887
+oid sha256:063b1cf299ae6f89c3d44c3d6fd6a07c67a6d3e4e23b9f9e7e293a31f4914b66
 size 91850362

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6adef2222a8499ae340103a14decdb644c8f7e241adf1db03c8bc0b5158729ea
+oid sha256:4821aad5553a38918c21c349fdea46338fd9f63066dcf6887289fcd0a2e4a40d
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3f42f41f56d804a52654f15da65a6bffed2b2bc2be17f60261f927a5bdd9b6e
+oid sha256:8e4faed9ff56a41c734b159c83edf0d491550c8797645a9ec65e2ab65c53f98b
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9adf3eeaf8b296e455c785fed305dd308e41002bb99da709670d19b2f936dd1
+oid sha256:7811cf39dffdc04210f1455d2f5083d206fb53cb80683869972bde86cd2a7d65
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b94ab1fccd114694efd0b5f259fcc3481800701a8cf1747a60096f91b98e60b
+oid sha256:a8e87dad838389218c66351cb4925b55cb7351905089c91a94e87ac3d4e966a6
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a77b37703a28a01cb2682281d1fa28c4e1876d1917e935c2250a5e0a396c473b
+oid sha256:ff7cd68fad2ac2060db6c98dfe9cf4f5f2e107fd2fefd14d9273e28fe38f7726
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98d0998adba33c518beebc7f6af15e92f6551ec4d7d10614a90a6b43e93fcdac
+oid sha256:05200abf3f4a6f62f29fbdc73844ea98bbbef6ff0049b76e08ba068c4df01997
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71219b6b2eb4b8f07c2b4423bf60c16c3c45a0ca15be26b71099e89690eb38f5
+oid sha256:30b054831bf4695c7807bfa1663e8625fc596e38c493ff2bc903dc3b3780920d
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de73dd2f2975940073e069851f9fb563280683dc2998be52c0fddfa0641275ab
+oid sha256:8c763d9c7eac8adaa5f924f8b3271097d9cd20b1ab357ac23167fc032ef89615
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b7e7d044a338e6b420016be2e48e692869df520a6f768a0f5ba8de63e9bb378
+oid sha256:f6b2f615f21faa4fde4442b48613d92f84c55cd5ef4fb4d04d8e3f819305ce14
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.176622986793518,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.11764705882352941,
+  "best_metric": 1.0883766412734985,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 0.23529411764705882,
   "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": 421.05,
       "eval_steps_per_second": 13.165,
       "step": 50
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.671344518661499,
+      "learning_rate": 7.920526315789474e-05,
+      "loss": 1.4253,
+      "step": 51
+    },
+    {
+      "epoch": 0.1223529411764706,
+      "grad_norm": 0.5880969166755676,
+      "learning_rate": 7.867368421052631e-05,
+      "loss": 1.3348,
+      "step": 52
+    },
+    {
+      "epoch": 0.12470588235294118,
+      "grad_norm": 0.6282343864440918,
+      "learning_rate": 7.814210526315789e-05,
+      "loss": 1.2422,
+      "step": 53
+    },
+    {
+      "epoch": 0.12705882352941175,
+      "grad_norm": 0.5805298089981079,
+      "learning_rate": 7.761052631578946e-05,
+      "loss": 1.1409,
+      "step": 54
+    },
+    {
+      "epoch": 0.12941176470588237,
+      "grad_norm": 0.6550160050392151,
+      "learning_rate": 7.707894736842105e-05,
+      "loss": 1.0416,
+      "step": 55
+    },
+    {
+      "epoch": 0.13176470588235295,
+      "grad_norm": 0.8028090596199036,
+      "learning_rate": 7.654736842105264e-05,
+      "loss": 0.9202,
+      "step": 56
+    },
+    {
+      "epoch": 0.13411764705882354,
+      "grad_norm": 0.5485410690307617,
+      "learning_rate": 7.601578947368422e-05,
+      "loss": 1.3603,
+      "step": 57
+    },
+    {
+      "epoch": 0.13647058823529412,
+      "grad_norm": 0.5518571138381958,
+      "learning_rate": 7.548421052631579e-05,
+      "loss": 1.293,
+      "step": 58
+    },
+    {
+      "epoch": 0.1388235294117647,
+      "grad_norm": 0.5716201066970825,
+      "learning_rate": 7.495263157894737e-05,
+      "loss": 1.2133,
+      "step": 59
+    },
+    {
+      "epoch": 0.1411764705882353,
+      "grad_norm": 0.6243718266487122,
+      "learning_rate": 7.442105263157894e-05,
+      "loss": 1.1545,
+      "step": 60
+    },
+    {
+      "epoch": 0.14352941176470588,
+      "grad_norm": 0.68055260181427,
+      "learning_rate": 7.388947368421053e-05,
+      "loss": 1.1208,
+      "step": 61
+    },
+    {
+      "epoch": 0.14588235294117646,
+      "grad_norm": 0.7047899961471558,
+      "learning_rate": 7.335789473684211e-05,
+      "loss": 0.9698,
+      "step": 62
+    },
+    {
+      "epoch": 0.14823529411764705,
+      "grad_norm": 0.6293048858642578,
+      "learning_rate": 7.282631578947368e-05,
+      "loss": 1.2973,
+      "step": 63
+    },
+    {
+      "epoch": 0.15058823529411763,
+      "grad_norm": 0.556554913520813,
+      "learning_rate": 7.229473684210527e-05,
+      "loss": 1.3389,
+      "step": 64
+    },
+    {
+      "epoch": 0.15294117647058825,
+      "grad_norm": 0.5991462469100952,
+      "learning_rate": 7.176315789473685e-05,
+      "loss": 1.2742,
+      "step": 65
+    },
+    {
+      "epoch": 0.15529411764705883,
+      "grad_norm": 0.6164782643318176,
+      "learning_rate": 7.123157894736842e-05,
+      "loss": 1.2032,
+      "step": 66
+    },
+    {
+      "epoch": 0.15764705882352942,
+      "grad_norm": 0.6064922213554382,
+      "learning_rate": 7.07e-05,
+      "loss": 1.056,
+      "step": 67
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.6620113849639893,
+      "learning_rate": 7.016842105263159e-05,
+      "loss": 1.0083,
+      "step": 68
+    },
+    {
+      "epoch": 0.1623529411764706,
+      "grad_norm": 0.6773979067802429,
+      "learning_rate": 6.963684210526316e-05,
+      "loss": 1.1461,
+      "step": 69
+    },
+    {
+      "epoch": 0.16470588235294117,
+      "grad_norm": 0.5662854313850403,
+      "learning_rate": 6.910526315789474e-05,
+      "loss": 1.3559,
+      "step": 70
+    },
+    {
+      "epoch": 0.16705882352941176,
+      "grad_norm": 0.5798998475074768,
+      "learning_rate": 6.857368421052631e-05,
+      "loss": 1.2389,
+      "step": 71
+    },
+    {
+      "epoch": 0.16941176470588235,
+      "grad_norm": 0.6113397479057312,
+      "learning_rate": 6.80421052631579e-05,
+      "loss": 1.1883,
+      "step": 72
+    },
+    {
+      "epoch": 0.17176470588235293,
+      "grad_norm": 0.6429812908172607,
+      "learning_rate": 6.751052631578948e-05,
+      "loss": 1.0725,
+      "step": 73
+    },
+    {
+      "epoch": 0.17411764705882352,
+      "grad_norm": 0.669151782989502,
+      "learning_rate": 6.697894736842105e-05,
+      "loss": 0.9818,
+      "step": 74
+    },
+    {
+      "epoch": 0.17647058823529413,
+      "grad_norm": 0.7604007124900818,
+      "learning_rate": 6.644736842105264e-05,
+      "loss": 0.8495,
+      "step": 75
+    },
+    {
+      "epoch": 0.17882352941176471,
+      "grad_norm": 0.541003942489624,
+      "learning_rate": 6.591578947368422e-05,
+      "loss": 1.3588,
+      "step": 76
+    },
+    {
+      "epoch": 0.1811764705882353,
+      "grad_norm": 0.6061081290245056,
+      "learning_rate": 6.538421052631579e-05,
+      "loss": 1.2932,
+      "step": 77
+    },
+    {
+      "epoch": 0.18352941176470589,
+      "grad_norm": 0.6060153841972351,
+      "learning_rate": 6.485263157894737e-05,
+      "loss": 1.1908,
+      "step": 78
+    },
+    {
+      "epoch": 0.18588235294117647,
+      "grad_norm": 0.6308295726776123,
+      "learning_rate": 6.432105263157894e-05,
+      "loss": 1.1446,
+      "step": 79
+    },
+    {
+      "epoch": 0.18823529411764706,
+      "grad_norm": 0.6454964280128479,
+      "learning_rate": 6.378947368421053e-05,
+      "loss": 0.9889,
+      "step": 80
+    },
+    {
+      "epoch": 0.19058823529411764,
+      "grad_norm": 0.7258140444755554,
+      "learning_rate": 6.32578947368421e-05,
+      "loss": 0.886,
+      "step": 81
+    },
+    {
+      "epoch": 0.19294117647058823,
+      "grad_norm": 0.5802991986274719,
+      "learning_rate": 6.27263157894737e-05,
+      "loss": 1.3406,
+      "step": 82
+    },
+    {
+      "epoch": 0.1952941176470588,
+      "grad_norm": 0.6241512894630432,
+      "learning_rate": 6.219473684210527e-05,
+      "loss": 1.3188,
+      "step": 83
+    },
+    {
+      "epoch": 0.1976470588235294,
+      "grad_norm": 0.6080717444419861,
+      "learning_rate": 6.166315789473685e-05,
+      "loss": 1.1992,
+      "step": 84
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.6189625263214111,
+      "learning_rate": 6.113157894736842e-05,
+      "loss": 1.1226,
+      "step": 85
+    },
+    {
+      "epoch": 0.2023529411764706,
+      "grad_norm": 0.6604960560798645,
+      "learning_rate": 6.0599999999999996e-05,
+      "loss": 1.0563,
+      "step": 86
+    },
+    {
+      "epoch": 0.20470588235294118,
+      "grad_norm": 0.7085356116294861,
+      "learning_rate": 6.006842105263158e-05,
+      "loss": 0.9438,
+      "step": 87
+    },
+    {
+      "epoch": 0.20705882352941177,
+      "grad_norm": 0.6556686162948608,
+      "learning_rate": 5.953684210526315e-05,
+      "loss": 1.3147,
+      "step": 88
+    },
+    {
+      "epoch": 0.20941176470588235,
+      "grad_norm": 0.637535572052002,
+      "learning_rate": 5.900526315789474e-05,
+      "loss": 1.2895,
+      "step": 89
+    },
+    {
+      "epoch": 0.21176470588235294,
+      "grad_norm": 0.5857135057449341,
+      "learning_rate": 5.847368421052632e-05,
+      "loss": 1.2138,
+      "step": 90
+    },
+    {
+      "epoch": 0.21411764705882352,
+      "grad_norm": 0.6470074653625488,
+      "learning_rate": 5.79421052631579e-05,
+      "loss": 1.1728,
+      "step": 91
+    },
+    {
+      "epoch": 0.2164705882352941,
+      "grad_norm": 0.6902785301208496,
+      "learning_rate": 5.7410526315789475e-05,
+      "loss": 1.0183,
+      "step": 92
+    },
+    {
+      "epoch": 0.2188235294117647,
+      "grad_norm": 0.721517026424408,
+      "learning_rate": 5.687894736842105e-05,
+      "loss": 0.9262,
+      "step": 93
+    },
+    {
+      "epoch": 0.2211764705882353,
+      "grad_norm": 0.7650291919708252,
+      "learning_rate": 5.6347368421052625e-05,
+      "loss": 1.1511,
+      "step": 94
+    },
+    {
+      "epoch": 0.2235294117647059,
+      "grad_norm": 0.6252285838127136,
+      "learning_rate": 5.5815789473684214e-05,
+      "loss": 1.3332,
+      "step": 95
+    },
+    {
+      "epoch": 0.22588235294117648,
+      "grad_norm": 0.6287341117858887,
+      "learning_rate": 5.5284210526315796e-05,
+      "loss": 1.1899,
+      "step": 96
+    },
+    {
+      "epoch": 0.22823529411764706,
+      "grad_norm": 0.7121133208274841,
+      "learning_rate": 5.475263157894737e-05,
+      "loss": 1.1943,
+      "step": 97
+    },
+    {
+      "epoch": 0.23058823529411765,
+      "grad_norm": 0.6616747379302979,
+      "learning_rate": 5.422105263157895e-05,
+      "loss": 1.0497,
+      "step": 98
+    },
+    {
+      "epoch": 0.23294117647058823,
+      "grad_norm": 0.7290382385253906,
+      "learning_rate": 5.368947368421053e-05,
+      "loss": 0.9758,
+      "step": 99
+    },
+    {
+      "epoch": 0.23529411764705882,
+      "grad_norm": 0.783645749092102,
+      "learning_rate": 5.3157894736842104e-05,
+      "loss": 0.8081,
+      "step": 100
+    },
+    {
+      "epoch": 0.23529411764705882,
+      "eval_loss": 1.0883766412734985,
+      "eval_runtime": 13.5365,
+      "eval_samples_per_second": 422.93,
+      "eval_steps_per_second": 13.224,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -401,7 +759,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.017734594356838e+16,
+  "total_flos": 1.6030464357276058e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null