{
"best_metric": 0.3135169446468353,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.22148394241417496,
"eval_steps": 25,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.004429678848283499,
"grad_norm": 90.43601989746094,
"learning_rate": 5e-05,
"loss": 186.7866,
"step": 1
},
{
"epoch": 0.004429678848283499,
"eval_loss": 11.860960006713867,
"eval_runtime": 59.9491,
"eval_samples_per_second": 25.372,
"eval_steps_per_second": 3.186,
"step": 1
},
{
"epoch": 0.008859357696566999,
"grad_norm": 92.87113952636719,
"learning_rate": 0.0001,
"loss": 191.192,
"step": 2
},
{
"epoch": 0.013289036544850499,
"grad_norm": 95.75019836425781,
"learning_rate": 9.989294616193017e-05,
"loss": 186.3358,
"step": 3
},
{
"epoch": 0.017718715393133997,
"grad_norm": 131.21568298339844,
"learning_rate": 9.957224306869053e-05,
"loss": 169.4684,
"step": 4
},
{
"epoch": 0.0221483942414175,
"grad_norm": 133.9580535888672,
"learning_rate": 9.903926402016153e-05,
"loss": 140.7173,
"step": 5
},
{
"epoch": 0.026578073089700997,
"grad_norm": 115.58403015136719,
"learning_rate": 9.829629131445342e-05,
"loss": 116.9708,
"step": 6
},
{
"epoch": 0.031007751937984496,
"grad_norm": 114.49787139892578,
"learning_rate": 9.73465064747553e-05,
"loss": 95.8174,
"step": 7
},
{
"epoch": 0.035437430786267994,
"grad_norm": 112.3747329711914,
"learning_rate": 9.619397662556435e-05,
"loss": 76.4804,
"step": 8
},
{
"epoch": 0.03986710963455149,
"grad_norm": 134.6016845703125,
"learning_rate": 9.484363707663442e-05,
"loss": 52.7218,
"step": 9
},
{
"epoch": 0.044296788482835,
"grad_norm": 140.690673828125,
"learning_rate": 9.330127018922194e-05,
"loss": 28.0401,
"step": 10
},
{
"epoch": 0.048726467331118496,
"grad_norm": 73.04218292236328,
"learning_rate": 9.157348061512727e-05,
"loss": 13.6756,
"step": 11
},
{
"epoch": 0.053156146179401995,
"grad_norm": 81.19536590576172,
"learning_rate": 8.966766701456177e-05,
"loss": 11.1729,
"step": 12
},
{
"epoch": 0.05758582502768549,
"grad_norm": 56.66990661621094,
"learning_rate": 8.759199037394887e-05,
"loss": 9.8869,
"step": 13
},
{
"epoch": 0.06201550387596899,
"grad_norm": 28.945405960083008,
"learning_rate": 8.535533905932738e-05,
"loss": 9.031,
"step": 14
},
{
"epoch": 0.0664451827242525,
"grad_norm": 36.69380569458008,
"learning_rate": 8.296729075500344e-05,
"loss": 8.7398,
"step": 15
},
{
"epoch": 0.07087486157253599,
"grad_norm": 22.542613983154297,
"learning_rate": 8.043807145043604e-05,
"loss": 8.2923,
"step": 16
},
{
"epoch": 0.0753045404208195,
"grad_norm": 76.44745635986328,
"learning_rate": 7.777851165098012e-05,
"loss": 9.5592,
"step": 17
},
{
"epoch": 0.07973421926910298,
"grad_norm": 60.888092041015625,
"learning_rate": 7.500000000000001e-05,
"loss": 7.8758,
"step": 18
},
{
"epoch": 0.08416389811738649,
"grad_norm": 66.46916198730469,
"learning_rate": 7.211443451095007e-05,
"loss": 6.9583,
"step": 19
},
{
"epoch": 0.08859357696567,
"grad_norm": 67.2452163696289,
"learning_rate": 6.91341716182545e-05,
"loss": 8.2272,
"step": 20
},
{
"epoch": 0.09302325581395349,
"grad_norm": 53.93881607055664,
"learning_rate": 6.607197326515808e-05,
"loss": 7.0548,
"step": 21
},
{
"epoch": 0.09745293466223699,
"grad_norm": 80.97118377685547,
"learning_rate": 6.294095225512603e-05,
"loss": 7.2771,
"step": 22
},
{
"epoch": 0.10188261351052048,
"grad_norm": 37.07639694213867,
"learning_rate": 5.9754516100806423e-05,
"loss": 6.2439,
"step": 23
},
{
"epoch": 0.10631229235880399,
"grad_norm": 53.39252471923828,
"learning_rate": 5.6526309611002594e-05,
"loss": 6.0297,
"step": 24
},
{
"epoch": 0.11074197120708748,
"grad_norm": 50.96709442138672,
"learning_rate": 5.327015646150716e-05,
"loss": 5.7838,
"step": 25
},
{
"epoch": 0.11074197120708748,
"eval_loss": 0.4496269226074219,
"eval_runtime": 59.8952,
"eval_samples_per_second": 25.394,
"eval_steps_per_second": 3.189,
"step": 25
},
{
"epoch": 0.11517165005537099,
"grad_norm": 43.56239318847656,
"learning_rate": 5e-05,
"loss": 8.002,
"step": 26
},
{
"epoch": 0.11960132890365449,
"grad_norm": 42.219730377197266,
"learning_rate": 4.6729843538492847e-05,
"loss": 7.7278,
"step": 27
},
{
"epoch": 0.12403100775193798,
"grad_norm": 51.25581741333008,
"learning_rate": 4.347369038899744e-05,
"loss": 7.8858,
"step": 28
},
{
"epoch": 0.12846068660022147,
"grad_norm": 28.833730697631836,
"learning_rate": 4.0245483899193595e-05,
"loss": 7.4616,
"step": 29
},
{
"epoch": 0.132890365448505,
"grad_norm": 36.36983108520508,
"learning_rate": 3.705904774487396e-05,
"loss": 5.8613,
"step": 30
},
{
"epoch": 0.13732004429678848,
"grad_norm": 24.915283203125,
"learning_rate": 3.392802673484193e-05,
"loss": 6.0989,
"step": 31
},
{
"epoch": 0.14174972314507198,
"grad_norm": 26.047985076904297,
"learning_rate": 3.086582838174551e-05,
"loss": 5.5893,
"step": 32
},
{
"epoch": 0.1461794019933555,
"grad_norm": 17.464637756347656,
"learning_rate": 2.7885565489049946e-05,
"loss": 5.6094,
"step": 33
},
{
"epoch": 0.150609080841639,
"grad_norm": 19.809972763061523,
"learning_rate": 2.500000000000001e-05,
"loss": 5.3021,
"step": 34
},
{
"epoch": 0.15503875968992248,
"grad_norm": 29.769086837768555,
"learning_rate": 2.2221488349019903e-05,
"loss": 5.5138,
"step": 35
},
{
"epoch": 0.15946843853820597,
"grad_norm": 25.799795150756836,
"learning_rate": 1.9561928549563968e-05,
"loss": 4.979,
"step": 36
},
{
"epoch": 0.1638981173864895,
"grad_norm": 25.358388900756836,
"learning_rate": 1.703270924499656e-05,
"loss": 3.709,
"step": 37
},
{
"epoch": 0.16832779623477298,
"grad_norm": 26.125646591186523,
"learning_rate": 1.4644660940672627e-05,
"loss": 4.5807,
"step": 38
},
{
"epoch": 0.17275747508305647,
"grad_norm": 20.812122344970703,
"learning_rate": 1.2408009626051137e-05,
"loss": 6.1171,
"step": 39
},
{
"epoch": 0.17718715393134,
"grad_norm": 20.470781326293945,
"learning_rate": 1.0332332985438248e-05,
"loss": 6.5875,
"step": 40
},
{
"epoch": 0.18161683277962348,
"grad_norm": 17.11683464050293,
"learning_rate": 8.426519384872733e-06,
"loss": 6.203,
"step": 41
},
{
"epoch": 0.18604651162790697,
"grad_norm": 15.608457565307617,
"learning_rate": 6.698729810778065e-06,
"loss": 4.9995,
"step": 42
},
{
"epoch": 0.19047619047619047,
"grad_norm": 14.48198127746582,
"learning_rate": 5.156362923365588e-06,
"loss": 5.2074,
"step": 43
},
{
"epoch": 0.19490586932447398,
"grad_norm": 17.412363052368164,
"learning_rate": 3.8060233744356633e-06,
"loss": 5.2764,
"step": 44
},
{
"epoch": 0.19933554817275748,
"grad_norm": 26.537670135498047,
"learning_rate": 2.653493525244721e-06,
"loss": 5.5755,
"step": 45
},
{
"epoch": 0.20376522702104097,
"grad_norm": 25.966537475585938,
"learning_rate": 1.70370868554659e-06,
"loss": 5.1873,
"step": 46
},
{
"epoch": 0.2081949058693245,
"grad_norm": 19.112852096557617,
"learning_rate": 9.607359798384785e-07,
"loss": 5.2322,
"step": 47
},
{
"epoch": 0.21262458471760798,
"grad_norm": 19.956279754638672,
"learning_rate": 4.277569313094809e-07,
"loss": 5.3597,
"step": 48
},
{
"epoch": 0.21705426356589147,
"grad_norm": 26.704853057861328,
"learning_rate": 1.0705383806982606e-07,
"loss": 4.1194,
"step": 49
},
{
"epoch": 0.22148394241417496,
"grad_norm": 22.032495498657227,
"learning_rate": 0.0,
"loss": 3.1469,
"step": 50
},
{
"epoch": 0.22148394241417496,
"eval_loss": 0.3135169446468353,
"eval_runtime": 59.89,
"eval_samples_per_second": 25.397,
"eval_steps_per_second": 3.189,
"step": 50
}
],
"logging_steps": 1,
"max_steps": 50,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 25,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 1,
"early_stopping_threshold": 0.0
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 1.0205684108886016e+18,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}