{
"best_metric": 1.9678517580032349,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.6389776357827476,
"eval_steps": 25,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.012779552715654952,
"grad_norm": 8.771577835083008,
"learning_rate": 5e-05,
"loss": 4.9321,
"step": 1
},
{
"epoch": 0.012779552715654952,
"eval_loss": 6.123461723327637,
"eval_runtime": 10.5873,
"eval_samples_per_second": 49.777,
"eval_steps_per_second": 6.234,
"step": 1
},
{
"epoch": 0.025559105431309903,
"grad_norm": 10.206089973449707,
"learning_rate": 0.0001,
"loss": 5.1275,
"step": 2
},
{
"epoch": 0.038338658146964855,
"grad_norm": 8.642292022705078,
"learning_rate": 9.989294616193017e-05,
"loss": 4.6814,
"step": 3
},
{
"epoch": 0.051118210862619806,
"grad_norm": 5.159078598022461,
"learning_rate": 9.957224306869053e-05,
"loss": 3.8052,
"step": 4
},
{
"epoch": 0.06389776357827476,
"grad_norm": 4.451505184173584,
"learning_rate": 9.903926402016153e-05,
"loss": 3.2396,
"step": 5
},
{
"epoch": 0.07667731629392971,
"grad_norm": 3.8363037109375,
"learning_rate": 9.829629131445342e-05,
"loss": 2.967,
"step": 6
},
{
"epoch": 0.08945686900958466,
"grad_norm": 3.366852045059204,
"learning_rate": 9.73465064747553e-05,
"loss": 2.959,
"step": 7
},
{
"epoch": 0.10223642172523961,
"grad_norm": 3.325381278991699,
"learning_rate": 9.619397662556435e-05,
"loss": 2.7737,
"step": 8
},
{
"epoch": 0.11501597444089456,
"grad_norm": 3.1503865718841553,
"learning_rate": 9.484363707663442e-05,
"loss": 2.4817,
"step": 9
},
{
"epoch": 0.12779552715654952,
"grad_norm": 3.248135805130005,
"learning_rate": 9.330127018922194e-05,
"loss": 2.2744,
"step": 10
},
{
"epoch": 0.14057507987220447,
"grad_norm": 3.462393283843994,
"learning_rate": 9.157348061512727e-05,
"loss": 2.1317,
"step": 11
},
{
"epoch": 0.15335463258785942,
"grad_norm": 8.443796157836914,
"learning_rate": 8.966766701456177e-05,
"loss": 1.6516,
"step": 12
},
{
"epoch": 0.16613418530351437,
"grad_norm": 10.717818260192871,
"learning_rate": 8.759199037394887e-05,
"loss": 3.1663,
"step": 13
},
{
"epoch": 0.17891373801916932,
"grad_norm": 9.05441951751709,
"learning_rate": 8.535533905932738e-05,
"loss": 3.5015,
"step": 14
},
{
"epoch": 0.19169329073482427,
"grad_norm": 6.173561096191406,
"learning_rate": 8.296729075500344e-05,
"loss": 3.0773,
"step": 15
},
{
"epoch": 0.20447284345047922,
"grad_norm": 3.482923746109009,
"learning_rate": 8.043807145043604e-05,
"loss": 2.7397,
"step": 16
},
{
"epoch": 0.21725239616613418,
"grad_norm": 2.700104236602783,
"learning_rate": 7.777851165098012e-05,
"loss": 2.5298,
"step": 17
},
{
"epoch": 0.23003194888178913,
"grad_norm": 2.708305835723877,
"learning_rate": 7.500000000000001e-05,
"loss": 2.6197,
"step": 18
},
{
"epoch": 0.24281150159744408,
"grad_norm": 3.1366517543792725,
"learning_rate": 7.211443451095007e-05,
"loss": 2.4716,
"step": 19
},
{
"epoch": 0.25559105431309903,
"grad_norm": 3.073094606399536,
"learning_rate": 6.91341716182545e-05,
"loss": 2.3725,
"step": 20
},
{
"epoch": 0.268370607028754,
"grad_norm": 2.809319019317627,
"learning_rate": 6.607197326515808e-05,
"loss": 2.2718,
"step": 21
},
{
"epoch": 0.28115015974440893,
"grad_norm": 2.4430651664733887,
"learning_rate": 6.294095225512603e-05,
"loss": 2.1776,
"step": 22
},
{
"epoch": 0.2939297124600639,
"grad_norm": 2.632463216781616,
"learning_rate": 5.9754516100806423e-05,
"loss": 1.8479,
"step": 23
},
{
"epoch": 0.30670926517571884,
"grad_norm": 3.0060150623321533,
"learning_rate": 5.6526309611002594e-05,
"loss": 1.4733,
"step": 24
},
{
"epoch": 0.3194888178913738,
"grad_norm": 5.199129581451416,
"learning_rate": 5.327015646150716e-05,
"loss": 0.6469,
"step": 25
},
{
"epoch": 0.3194888178913738,
"eval_loss": 2.1838388442993164,
"eval_runtime": 10.6013,
"eval_samples_per_second": 49.711,
"eval_steps_per_second": 6.226,
"step": 25
},
{
"epoch": 0.33226837060702874,
"grad_norm": 3.169137716293335,
"learning_rate": 5e-05,
"loss": 2.7858,
"step": 26
},
{
"epoch": 0.3450479233226837,
"grad_norm": 3.18146014213562,
"learning_rate": 4.6729843538492847e-05,
"loss": 2.6343,
"step": 27
},
{
"epoch": 0.35782747603833864,
"grad_norm": 2.7009081840515137,
"learning_rate": 4.347369038899744e-05,
"loss": 2.3969,
"step": 28
},
{
"epoch": 0.3706070287539936,
"grad_norm": 2.587928056716919,
"learning_rate": 4.0245483899193595e-05,
"loss": 2.4911,
"step": 29
},
{
"epoch": 0.38338658146964855,
"grad_norm": 2.225165367126465,
"learning_rate": 3.705904774487396e-05,
"loss": 2.435,
"step": 30
},
{
"epoch": 0.3961661341853035,
"grad_norm": 2.1750922203063965,
"learning_rate": 3.392802673484193e-05,
"loss": 2.2844,
"step": 31
},
{
"epoch": 0.40894568690095845,
"grad_norm": 2.649970531463623,
"learning_rate": 3.086582838174551e-05,
"loss": 2.2681,
"step": 32
},
{
"epoch": 0.4217252396166134,
"grad_norm": 2.4825990200042725,
"learning_rate": 2.7885565489049946e-05,
"loss": 2.1948,
"step": 33
},
{
"epoch": 0.43450479233226835,
"grad_norm": 2.7616539001464844,
"learning_rate": 2.500000000000001e-05,
"loss": 2.0973,
"step": 34
},
{
"epoch": 0.4472843450479233,
"grad_norm": 2.5977234840393066,
"learning_rate": 2.2221488349019903e-05,
"loss": 1.8398,
"step": 35
},
{
"epoch": 0.46006389776357826,
"grad_norm": 2.591003656387329,
"learning_rate": 1.9561928549563968e-05,
"loss": 1.4759,
"step": 36
},
{
"epoch": 0.4728434504792332,
"grad_norm": 3.1910948753356934,
"learning_rate": 1.703270924499656e-05,
"loss": 1.0956,
"step": 37
},
{
"epoch": 0.48562300319488816,
"grad_norm": 2.328935146331787,
"learning_rate": 1.4644660940672627e-05,
"loss": 2.2579,
"step": 38
},
{
"epoch": 0.4984025559105431,
"grad_norm": 1.9119290113449097,
"learning_rate": 1.2408009626051137e-05,
"loss": 2.339,
"step": 39
},
{
"epoch": 0.5111821086261981,
"grad_norm": 2.0242035388946533,
"learning_rate": 1.0332332985438248e-05,
"loss": 2.3039,
"step": 40
},
{
"epoch": 0.5239616613418531,
"grad_norm": 2.0701210498809814,
"learning_rate": 8.426519384872733e-06,
"loss": 2.4307,
"step": 41
},
{
"epoch": 0.536741214057508,
"grad_norm": 1.8572293519973755,
"learning_rate": 6.698729810778065e-06,
"loss": 2.2061,
"step": 42
},
{
"epoch": 0.549520766773163,
"grad_norm": 2.0586934089660645,
"learning_rate": 5.156362923365588e-06,
"loss": 2.3343,
"step": 43
},
{
"epoch": 0.5623003194888179,
"grad_norm": 2.266606092453003,
"learning_rate": 3.8060233744356633e-06,
"loss": 2.4235,
"step": 44
},
{
"epoch": 0.5750798722044729,
"grad_norm": 2.0915160179138184,
"learning_rate": 2.653493525244721e-06,
"loss": 2.1905,
"step": 45
},
{
"epoch": 0.5878594249201278,
"grad_norm": 2.243063449859619,
"learning_rate": 1.70370868554659e-06,
"loss": 2.0259,
"step": 46
},
{
"epoch": 0.6006389776357828,
"grad_norm": 2.2916998863220215,
"learning_rate": 9.607359798384785e-07,
"loss": 1.8449,
"step": 47
},
{
"epoch": 0.6134185303514377,
"grad_norm": 2.2355592250823975,
"learning_rate": 4.277569313094809e-07,
"loss": 1.5529,
"step": 48
},
{
"epoch": 0.6261980830670927,
"grad_norm": 2.450639009475708,
"learning_rate": 1.0705383806982606e-07,
"loss": 1.5336,
"step": 49
},
{
"epoch": 0.6389776357827476,
"grad_norm": 2.254504680633545,
"learning_rate": 0.0,
"loss": 0.4683,
"step": 50
},
{
"epoch": 0.6389776357827476,
"eval_loss": 1.9678517580032349,
"eval_runtime": 10.6005,
"eval_samples_per_second": 49.715,
"eval_steps_per_second": 6.226,
"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": 1.62480894509056e+17,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}