Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a08df2cae236b08ed3d3c4ba41b9267a442e7ef9f3e5a88caabe88a9cafed19
+oid sha256:d3a07bb6a35ea14e1ed69c3c2d77fbf0664d1804e0dc1874fe82dd47e43cda05
 size 389074464

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:355aad01bdec33c029e90cd96e891f9d44be03148b0f798c484264e7aa5b7577
+oid sha256:d656b3e2fae6d74b6b99b062276209667100e0e05d05a48c76898b9843f72c57
 size 198011252

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecdd5bb89ec9c68beb471c163ecb5b1af122162e02433be6d17f9204ede272a4
+oid sha256:63add0586146b851f47d881f8a2c86d2e7bbd1031b34991ea727eda767e3ba6f
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09cf26cd3dd6bb70d9dce4390472239a137b21565cacd7e36fa673e7d6bee883
+oid sha256:8187a6c88d7933f4442806aa816104ffa2abe40157d1b5941b707067b0f91484
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7613e43ac11193de84dcbd90078e6c475033d15b3fdfdaf6ff74612c990642fc
+oid sha256:428d17df5bbcb9c5bba8928ed07c3ac1e2473387421762fc2dd2a18dad7163cb
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81c4163df276de90e88da6d8afcafccf67030bb43e49375bd767dea9479e9851
+oid sha256:10e76a88b495596517a8c5e8dd0c9cf73e2fa8d302cb53089a3a0a19398d0705
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:575fcb021b180e3cd90adfe12c3996bc5eaf5b422ed52065d67751caf5bee831
+oid sha256:7e07c2149652b1186dc91873797838ca755d72668f5e0d5315a9746f87efcc58
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:122bf0a275c8ff401966f200efcf261c801fa8edbada6438895e4792a2fdc738
+oid sha256:ea6c246d355698e0da22b783baa4cd562f3bf8472a265e83f06d63d516cc95c7
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96a5fb272e27d8f72e00aa73708dc4854f3c6cca545324d31775671e26b916d7
+oid sha256:55aa132a1f6a464d42b97932e211287aa777c051c2c25ed9e36ac7ddda94bf95
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b30647fe1c7cc9feda329e25de49fb56d4700f697dfec1ae0d2e33270a3cc3ab
+oid sha256:15a7d871d8fc1dcb9a693c26cb0b989af2ab985ab337aecb1daa8032f9df0a10
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:150bf6870b0c196b9e7b6e9bb409d60b878766ed64793bc24124c2f97e82bc11
+oid sha256:b323f2cb8c959ffbaf90b97d17df7a3447ef35ce5770b54457987ada42ec67f4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9605554938316345,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 1.0638297872340425,
+  "best_metric": 0.9264618754386902,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 2.127659574468085,
   "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": 162.971,
       "eval_steps_per_second": 5.149,
       "step": 50
+    },
+    {
+      "epoch": 1.0851063829787233,
+      "grad_norm": 0.3345516622066498,
+      "learning_rate": 8.704210815926495e-05,
+      "loss": 1.1487,
+      "step": 51
+    },
+    {
+      "epoch": 1.1063829787234043,
+      "grad_norm": 0.39309221506118774,
+      "learning_rate": 8.59155327244593e-05,
+      "loss": 1.0582,
+      "step": 52
+    },
+    {
+      "epoch": 1.127659574468085,
+      "grad_norm": 0.5331593751907349,
+      "learning_rate": 8.477175314518714e-05,
+      "loss": 0.8832,
+      "step": 53
+    },
+    {
+      "epoch": 1.148936170212766,
+      "grad_norm": 0.8910200595855713,
+      "learning_rate": 8.361142719844015e-05,
+      "loss": 0.2747,
+      "step": 54
+    },
+    {
+      "epoch": 1.1702127659574468,
+      "grad_norm": 0.35534268617630005,
+      "learning_rate": 8.243522217687193e-05,
+      "loss": 0.7217,
+      "step": 55
+    },
+    {
+      "epoch": 1.1914893617021276,
+      "grad_norm": 0.44460806250572205,
+      "learning_rate": 8.124381450504426e-05,
+      "loss": 1.3437,
+      "step": 56
+    },
+    {
+      "epoch": 1.2127659574468086,
+      "grad_norm": 0.37915581464767456,
+      "learning_rate": 8.00378893504216e-05,
+      "loss": 1.2378,
+      "step": 57
+    },
+    {
+      "epoch": 1.2340425531914894,
+      "grad_norm": 0.3455619513988495,
+      "learning_rate": 7.881814022933765e-05,
+      "loss": 1.1035,
+      "step": 58
+    },
+    {
+      "epoch": 1.2553191489361701,
+      "grad_norm": 0.39131176471710205,
+      "learning_rate": 7.758526860816059e-05,
+      "loss": 0.9421,
+      "step": 59
+    },
+    {
+      "epoch": 1.2765957446808511,
+      "grad_norm": 0.3872637450695038,
+      "learning_rate": 7.633998349988623e-05,
+      "loss": 0.4359,
+      "step": 60
+    },
+    {
+      "epoch": 1.297872340425532,
+      "grad_norm": 0.3637562692165375,
+      "learning_rate": 7.508300105639138e-05,
+      "loss": 0.498,
+      "step": 61
+    },
+    {
+      "epoch": 1.3191489361702127,
+      "grad_norm": 0.4627838730812073,
+      "learning_rate": 7.381504415658137e-05,
+      "loss": 1.3362,
+      "step": 62
+    },
+    {
+      "epoch": 1.3404255319148937,
+      "grad_norm": 0.40288859605789185,
+      "learning_rate": 7.253684199066931e-05,
+      "loss": 1.2646,
+      "step": 63
+    },
+    {
+      "epoch": 1.3617021276595744,
+      "grad_norm": 0.3752979636192322,
+      "learning_rate": 7.124912964082547e-05,
+      "loss": 1.0772,
+      "step": 64
+    },
+    {
+      "epoch": 1.3829787234042552,
+      "grad_norm": 0.4062426686286926,
+      "learning_rate": 6.995264765843836e-05,
+      "loss": 1.0008,
+      "step": 65
+    },
+    {
+      "epoch": 1.4042553191489362,
+      "grad_norm": 0.4707888662815094,
+      "learning_rate": 6.86481416382306e-05,
+      "loss": 0.6325,
+      "step": 66
+    },
+    {
+      "epoch": 1.425531914893617,
+      "grad_norm": 0.28356093168258667,
+      "learning_rate": 6.733636178947425e-05,
+      "loss": 0.2474,
+      "step": 67
+    },
+    {
+      "epoch": 1.4468085106382977,
+      "grad_norm": 0.44394785165786743,
+      "learning_rate": 6.601806250455254e-05,
+      "loss": 1.2399,
+      "step": 68
+    },
+    {
+      "epoch": 1.4680851063829787,
+      "grad_norm": 0.3906940519809723,
+      "learning_rate": 6.469400192511568e-05,
+      "loss": 1.2571,
+      "step": 69
+    },
+    {
+      "epoch": 1.4893617021276595,
+      "grad_norm": 0.40481507778167725,
+      "learning_rate": 6.33649415060808e-05,
+      "loss": 1.1472,
+      "step": 70
+    },
+    {
+      "epoch": 1.5106382978723403,
+      "grad_norm": 0.3902008533477783,
+      "learning_rate": 6.203164557772622e-05,
+      "loss": 1.0084,
+      "step": 71
+    },
+    {
+      "epoch": 1.5319148936170213,
+      "grad_norm": 0.47971320152282715,
+      "learning_rate": 6.069488090613228e-05,
+      "loss": 0.8643,
+      "step": 72
+    },
+    {
+      "epoch": 1.5531914893617023,
+      "grad_norm": 0.35613465309143066,
+      "learning_rate": 5.935541625222126e-05,
+      "loss": 0.072,
+      "step": 73
+    },
+    {
+      "epoch": 1.574468085106383,
+      "grad_norm": 0.4089168310165405,
+      "learning_rate": 5.801402192965016e-05,
+      "loss": 1.0347,
+      "step": 74
+    },
+    {
+      "epoch": 1.5957446808510638,
+      "grad_norm": 0.4405708909034729,
+      "learning_rate": 5.667146936181042e-05,
+      "loss": 1.2854,
+      "step": 75
+    },
+    {
+      "epoch": 1.6170212765957448,
+      "grad_norm": 0.38711073994636536,
+      "learning_rate": 5.53285306381896e-05,
+      "loss": 1.2008,
+      "step": 76
+    },
+    {
+      "epoch": 1.6382978723404256,
+      "grad_norm": 0.3995616137981415,
+      "learning_rate": 5.398597807034986e-05,
+      "loss": 1.0411,
+      "step": 77
+    },
+    {
+      "epoch": 1.6595744680851063,
+      "grad_norm": 0.4823427200317383,
+      "learning_rate": 5.2644583747778746e-05,
+      "loss": 0.8773,
+      "step": 78
+    },
+    {
+      "epoch": 1.6808510638297873,
+      "grad_norm": 0.27052074670791626,
+      "learning_rate": 5.130511909386772e-05,
+      "loss": 0.2128,
+      "step": 79
+    },
+    {
+      "epoch": 1.702127659574468,
+      "grad_norm": 0.34951841831207275,
+      "learning_rate": 4.996835442227378e-05,
+      "loss": 0.6826,
+      "step": 80
+    },
+    {
+      "epoch": 1.7234042553191489,
+      "grad_norm": 0.44672834873199463,
+      "learning_rate": 4.863505849391921e-05,
+      "loss": 1.3443,
+      "step": 81
+    },
+    {
+      "epoch": 1.7446808510638299,
+      "grad_norm": 0.37677329778671265,
+      "learning_rate": 4.7305998074884325e-05,
+      "loss": 1.1532,
+      "step": 82
+    },
+    {
+      "epoch": 1.7659574468085106,
+      "grad_norm": 0.3660067319869995,
+      "learning_rate": 4.598193749544746e-05,
+      "loss": 1.0569,
+      "step": 83
+    },
+    {
+      "epoch": 1.7872340425531914,
+      "grad_norm": 0.4302046597003937,
+      "learning_rate": 4.466363821052573e-05,
+      "loss": 0.9091,
+      "step": 84
+    },
+    {
+      "epoch": 1.8085106382978724,
+      "grad_norm": 0.3698153793811798,
+      "learning_rate": 4.335185836176942e-05,
+      "loss": 0.4112,
+      "step": 85
+    },
+    {
+      "epoch": 1.8297872340425532,
+      "grad_norm": 0.27242642641067505,
+      "learning_rate": 4.2047352341561654e-05,
+      "loss": 0.4239,
+      "step": 86
+    },
+    {
+      "epoch": 1.851063829787234,
+      "grad_norm": 0.463748574256897,
+      "learning_rate": 4.0750870359174544e-05,
+      "loss": 1.3113,
+      "step": 87
+    },
+    {
+      "epoch": 1.872340425531915,
+      "grad_norm": 0.3822973966598511,
+      "learning_rate": 3.946315800933069e-05,
+      "loss": 1.2033,
+      "step": 88
+    },
+    {
+      "epoch": 1.8936170212765957,
+      "grad_norm": 0.3759160041809082,
+      "learning_rate": 3.8184955843418635e-05,
+      "loss": 1.1545,
+      "step": 89
+    },
+    {
+      "epoch": 1.9148936170212765,
+      "grad_norm": 0.3939042091369629,
+      "learning_rate": 3.691699894360862e-05,
+      "loss": 0.9759,
+      "step": 90
+    },
+    {
+      "epoch": 1.9361702127659575,
+      "grad_norm": 0.463613361120224,
+      "learning_rate": 3.5660016500113756e-05,
+      "loss": 0.6793,
+      "step": 91
+    },
+    {
+      "epoch": 1.9574468085106385,
+      "grad_norm": 0.39532244205474854,
+      "learning_rate": 3.441473139183941e-05,
+      "loss": 1.0509,
+      "step": 92
+    },
+    {
+      "epoch": 1.978723404255319,
+      "grad_norm": 0.37965285778045654,
+      "learning_rate": 3.3181859770662366e-05,
+      "loss": 1.1558,
+      "step": 93
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.4093703627586365,
+      "learning_rate": 3.196211064957841e-05,
+      "loss": 0.9204,
+      "step": 94
+    },
+    {
+      "epoch": 2.021276595744681,
+      "grad_norm": 0.11672822386026382,
+      "learning_rate": 3.075618549495574e-05,
+      "loss": 0.0652,
+      "step": 95
+    },
+    {
+      "epoch": 2.0425531914893615,
+      "grad_norm": 0.4452710747718811,
+      "learning_rate": 2.9564777823128087e-05,
+      "loss": 1.0477,
+      "step": 96
+    },
+    {
+      "epoch": 2.0638297872340425,
+      "grad_norm": 0.4406222999095917,
+      "learning_rate": 2.8388572801559853e-05,
+      "loss": 1.2642,
+      "step": 97
+    },
+    {
+      "epoch": 2.0851063829787235,
+      "grad_norm": 0.3580534756183624,
+      "learning_rate": 2.7228246854812867e-05,
+      "loss": 1.0798,
+      "step": 98
+    },
+    {
+      "epoch": 2.106382978723404,
+      "grad_norm": 0.3822851777076721,
+      "learning_rate": 2.60844672755407e-05,
+      "loss": 1.0079,
+      "step": 99
+    },
+    {
+      "epoch": 2.127659574468085,
+      "grad_norm": 0.4569602608680725,
+      "learning_rate": 2.4957891840735056e-05,
+      "loss": 0.8454,
+      "step": 100
+    },
+    {
+      "epoch": 2.127659574468085,
+      "eval_loss": 0.9264618754386902,
+      "eval_runtime": 3.7503,
+      "eval_samples_per_second": 168.787,
+      "eval_steps_per_second": 5.333,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -401,7 +759,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.293237926592512e+17,
+  "total_flos": 4.586475853185024e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null