{
"best_metric": 1.2591822147369385,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.06623064823246957,
"eval_steps": 25,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0013246129646493916,
"grad_norm": 1.6651402711868286,
"learning_rate": 5e-05,
"loss": 1.8853,
"step": 1
},
{
"epoch": 0.0013246129646493916,
"eval_loss": 2.9228813648223877,
"eval_runtime": 46.4133,
"eval_samples_per_second": 109.581,
"eval_steps_per_second": 13.703,
"step": 1
},
{
"epoch": 0.002649225929298783,
"grad_norm": 2.6424856185913086,
"learning_rate": 0.0001,
"loss": 2.6317,
"step": 2
},
{
"epoch": 0.0039738388939481745,
"grad_norm": 2.5490546226501465,
"learning_rate": 9.989294616193017e-05,
"loss": 2.6714,
"step": 3
},
{
"epoch": 0.005298451858597566,
"grad_norm": 2.1160619258880615,
"learning_rate": 9.957224306869053e-05,
"loss": 2.516,
"step": 4
},
{
"epoch": 0.006623064823246957,
"grad_norm": 1.8555885553359985,
"learning_rate": 9.903926402016153e-05,
"loss": 2.3066,
"step": 5
},
{
"epoch": 0.007947677787896349,
"grad_norm": 1.7924107313156128,
"learning_rate": 9.829629131445342e-05,
"loss": 2.1378,
"step": 6
},
{
"epoch": 0.00927229075254574,
"grad_norm": 1.6732336282730103,
"learning_rate": 9.73465064747553e-05,
"loss": 2.0216,
"step": 7
},
{
"epoch": 0.010596903717195133,
"grad_norm": 1.4387348890304565,
"learning_rate": 9.619397662556435e-05,
"loss": 1.9742,
"step": 8
},
{
"epoch": 0.011921516681844524,
"grad_norm": 1.6523858308792114,
"learning_rate": 9.484363707663442e-05,
"loss": 1.7795,
"step": 9
},
{
"epoch": 0.013246129646493915,
"grad_norm": 1.2928249835968018,
"learning_rate": 9.330127018922194e-05,
"loss": 1.7545,
"step": 10
},
{
"epoch": 0.014570742611143307,
"grad_norm": 1.051326036453247,
"learning_rate": 9.157348061512727e-05,
"loss": 1.8031,
"step": 11
},
{
"epoch": 0.015895355575792698,
"grad_norm": 0.9771145582199097,
"learning_rate": 8.966766701456177e-05,
"loss": 1.7973,
"step": 12
},
{
"epoch": 0.01721996854044209,
"grad_norm": 1.4944615364074707,
"learning_rate": 8.759199037394887e-05,
"loss": 1.3543,
"step": 13
},
{
"epoch": 0.01854458150509148,
"grad_norm": 1.0355734825134277,
"learning_rate": 8.535533905932738e-05,
"loss": 1.5243,
"step": 14
},
{
"epoch": 0.01986919446974087,
"grad_norm": 0.9531193971633911,
"learning_rate": 8.296729075500344e-05,
"loss": 1.5243,
"step": 15
},
{
"epoch": 0.021193807434390265,
"grad_norm": 0.9820343255996704,
"learning_rate": 8.043807145043604e-05,
"loss": 1.4443,
"step": 16
},
{
"epoch": 0.022518420399039656,
"grad_norm": 0.8732142448425293,
"learning_rate": 7.777851165098012e-05,
"loss": 1.4796,
"step": 17
},
{
"epoch": 0.023843033363689047,
"grad_norm": 0.8378395438194275,
"learning_rate": 7.500000000000001e-05,
"loss": 1.4862,
"step": 18
},
{
"epoch": 0.025167646328338438,
"grad_norm": 0.8844391107559204,
"learning_rate": 7.211443451095007e-05,
"loss": 1.4568,
"step": 19
},
{
"epoch": 0.02649225929298783,
"grad_norm": 0.7522854804992676,
"learning_rate": 6.91341716182545e-05,
"loss": 1.3976,
"step": 20
},
{
"epoch": 0.02781687225763722,
"grad_norm": 0.7832819819450378,
"learning_rate": 6.607197326515808e-05,
"loss": 1.4092,
"step": 21
},
{
"epoch": 0.029141485222286614,
"grad_norm": 0.7286955118179321,
"learning_rate": 6.294095225512603e-05,
"loss": 1.3441,
"step": 22
},
{
"epoch": 0.030466098186936005,
"grad_norm": 0.7381780743598938,
"learning_rate": 5.9754516100806423e-05,
"loss": 1.3408,
"step": 23
},
{
"epoch": 0.031790711151585396,
"grad_norm": 0.9339249134063721,
"learning_rate": 5.6526309611002594e-05,
"loss": 1.5154,
"step": 24
},
{
"epoch": 0.03311532411623479,
"grad_norm": 1.063729166984558,
"learning_rate": 5.327015646150716e-05,
"loss": 1.7674,
"step": 25
},
{
"epoch": 0.03311532411623479,
"eval_loss": 1.3550173044204712,
"eval_runtime": 46.4029,
"eval_samples_per_second": 109.605,
"eval_steps_per_second": 13.706,
"step": 25
},
{
"epoch": 0.03443993708088418,
"grad_norm": 0.9062424302101135,
"learning_rate": 5e-05,
"loss": 1.1765,
"step": 26
},
{
"epoch": 0.03576455004553357,
"grad_norm": 1.0838007926940918,
"learning_rate": 4.6729843538492847e-05,
"loss": 1.2994,
"step": 27
},
{
"epoch": 0.03708916301018296,
"grad_norm": 0.9461883306503296,
"learning_rate": 4.347369038899744e-05,
"loss": 1.3542,
"step": 28
},
{
"epoch": 0.03841377597483235,
"grad_norm": 0.8317744731903076,
"learning_rate": 4.0245483899193595e-05,
"loss": 1.2322,
"step": 29
},
{
"epoch": 0.03973838893948174,
"grad_norm": 0.7142109274864197,
"learning_rate": 3.705904774487396e-05,
"loss": 1.2406,
"step": 30
},
{
"epoch": 0.04106300190413114,
"grad_norm": 0.7453699111938477,
"learning_rate": 3.392802673484193e-05,
"loss": 1.2433,
"step": 31
},
{
"epoch": 0.04238761486878053,
"grad_norm": 0.789333701133728,
"learning_rate": 3.086582838174551e-05,
"loss": 1.1953,
"step": 32
},
{
"epoch": 0.04371222783342992,
"grad_norm": 0.7830644249916077,
"learning_rate": 2.7885565489049946e-05,
"loss": 1.2084,
"step": 33
},
{
"epoch": 0.04503684079807931,
"grad_norm": 0.8268360495567322,
"learning_rate": 2.500000000000001e-05,
"loss": 1.1753,
"step": 34
},
{
"epoch": 0.046361453762728703,
"grad_norm": 0.779362142086029,
"learning_rate": 2.2221488349019903e-05,
"loss": 1.0616,
"step": 35
},
{
"epoch": 0.047686066727378094,
"grad_norm": 1.0241578817367554,
"learning_rate": 1.9561928549563968e-05,
"loss": 1.4833,
"step": 36
},
{
"epoch": 0.049010679692027485,
"grad_norm": 1.0823919773101807,
"learning_rate": 1.703270924499656e-05,
"loss": 1.511,
"step": 37
},
{
"epoch": 0.050335292656676876,
"grad_norm": 0.7731306552886963,
"learning_rate": 1.4644660940672627e-05,
"loss": 1.1544,
"step": 38
},
{
"epoch": 0.05165990562132627,
"grad_norm": 0.6504825949668884,
"learning_rate": 1.2408009626051137e-05,
"loss": 1.3165,
"step": 39
},
{
"epoch": 0.05298451858597566,
"grad_norm": 0.7699246406555176,
"learning_rate": 1.0332332985438248e-05,
"loss": 1.2854,
"step": 40
},
{
"epoch": 0.05430913155062505,
"grad_norm": 0.757817268371582,
"learning_rate": 8.426519384872733e-06,
"loss": 1.2113,
"step": 41
},
{
"epoch": 0.05563374451527444,
"grad_norm": 0.7197378873825073,
"learning_rate": 6.698729810778065e-06,
"loss": 1.1451,
"step": 42
},
{
"epoch": 0.05695835747992384,
"grad_norm": 0.8140779137611389,
"learning_rate": 5.156362923365588e-06,
"loss": 1.2653,
"step": 43
},
{
"epoch": 0.05828297044457323,
"grad_norm": 0.7058303356170654,
"learning_rate": 3.8060233744356633e-06,
"loss": 1.2601,
"step": 44
},
{
"epoch": 0.05960758340922262,
"grad_norm": 0.6862402558326721,
"learning_rate": 2.653493525244721e-06,
"loss": 1.1989,
"step": 45
},
{
"epoch": 0.06093219637387201,
"grad_norm": 0.6720271110534668,
"learning_rate": 1.70370868554659e-06,
"loss": 1.1027,
"step": 46
},
{
"epoch": 0.0622568093385214,
"grad_norm": 0.6878005266189575,
"learning_rate": 9.607359798384785e-07,
"loss": 1.131,
"step": 47
},
{
"epoch": 0.06358142230317079,
"grad_norm": 0.6762499213218689,
"learning_rate": 4.277569313094809e-07,
"loss": 1.1932,
"step": 48
},
{
"epoch": 0.06490603526782018,
"grad_norm": 0.6740577816963196,
"learning_rate": 1.0705383806982606e-07,
"loss": 1.3074,
"step": 49
},
{
"epoch": 0.06623064823246957,
"grad_norm": 0.9326754808425903,
"learning_rate": 0.0,
"loss": 1.5912,
"step": 50
},
{
"epoch": 0.06623064823246957,
"eval_loss": 1.2591822147369385,
"eval_runtime": 46.4061,
"eval_samples_per_second": 109.598,
"eval_steps_per_second": 13.705,
"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": 8.33416392081408e+16,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}