aleegis09's picture
Training in progress, step 50, checkpoint
69fb71a verified
raw
history blame
10.2 kB
{
"best_metric": 2.47334361076355,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.09128251939753537,
"eval_steps": 25,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0018256503879507074,
"grad_norm": 6.247039794921875,
"learning_rate": 2e-05,
"loss": 6.5554,
"step": 1
},
{
"epoch": 0.0018256503879507074,
"eval_loss": 7.477728366851807,
"eval_runtime": 13.58,
"eval_samples_per_second": 67.968,
"eval_steps_per_second": 8.542,
"step": 1
},
{
"epoch": 0.003651300775901415,
"grad_norm": 2.5168230533599854,
"learning_rate": 4e-05,
"loss": 4.1398,
"step": 2
},
{
"epoch": 0.005476951163852123,
"grad_norm": 3.0510706901550293,
"learning_rate": 6e-05,
"loss": 4.4769,
"step": 3
},
{
"epoch": 0.00730260155180283,
"grad_norm": 3.9945530891418457,
"learning_rate": 8e-05,
"loss": 5.0557,
"step": 4
},
{
"epoch": 0.009128251939753538,
"grad_norm": 4.052631855010986,
"learning_rate": 0.0001,
"loss": 4.5119,
"step": 5
},
{
"epoch": 0.010953902327704245,
"grad_norm": 14.28050422668457,
"learning_rate": 9.987820251299122e-05,
"loss": 4.429,
"step": 6
},
{
"epoch": 0.012779552715654952,
"grad_norm": 8.794904708862305,
"learning_rate": 9.951340343707852e-05,
"loss": 4.271,
"step": 7
},
{
"epoch": 0.01460520310360566,
"grad_norm": 16.489906311035156,
"learning_rate": 9.890738003669029e-05,
"loss": 4.9881,
"step": 8
},
{
"epoch": 0.016430853491556367,
"grad_norm": 16.263893127441406,
"learning_rate": 9.806308479691595e-05,
"loss": 4.0697,
"step": 9
},
{
"epoch": 0.018256503879507075,
"grad_norm": 13.221240997314453,
"learning_rate": 9.698463103929542e-05,
"loss": 3.3236,
"step": 10
},
{
"epoch": 0.020082154267457783,
"grad_norm": 24.067243576049805,
"learning_rate": 9.567727288213005e-05,
"loss": 3.4959,
"step": 11
},
{
"epoch": 0.02190780465540849,
"grad_norm": 8.679977416992188,
"learning_rate": 9.414737964294636e-05,
"loss": 2.988,
"step": 12
},
{
"epoch": 0.023733455043359195,
"grad_norm": 9.864343643188477,
"learning_rate": 9.24024048078213e-05,
"loss": 3.1601,
"step": 13
},
{
"epoch": 0.025559105431309903,
"grad_norm": 6.10977840423584,
"learning_rate": 9.045084971874738e-05,
"loss": 2.7908,
"step": 14
},
{
"epoch": 0.02738475581926061,
"grad_norm": 3.3607473373413086,
"learning_rate": 8.83022221559489e-05,
"loss": 3.0603,
"step": 15
},
{
"epoch": 0.02921040620721132,
"grad_norm": 5.995874404907227,
"learning_rate": 8.596699001693255e-05,
"loss": 2.9301,
"step": 16
},
{
"epoch": 0.031036056595162027,
"grad_norm": 6.06985330581665,
"learning_rate": 8.345653031794292e-05,
"loss": 2.8168,
"step": 17
},
{
"epoch": 0.032861706983112735,
"grad_norm": 4.3371992111206055,
"learning_rate": 8.07830737662829e-05,
"loss": 2.2175,
"step": 18
},
{
"epoch": 0.03468735737106344,
"grad_norm": 3.5999372005462646,
"learning_rate": 7.795964517353735e-05,
"loss": 2.3887,
"step": 19
},
{
"epoch": 0.03651300775901415,
"grad_norm": 2.7885711193084717,
"learning_rate": 7.500000000000001e-05,
"loss": 2.3902,
"step": 20
},
{
"epoch": 0.038338658146964855,
"grad_norm": 2.7228593826293945,
"learning_rate": 7.191855733945387e-05,
"loss": 2.3846,
"step": 21
},
{
"epoch": 0.040164308534915566,
"grad_norm": 2.608125925064087,
"learning_rate": 6.873032967079561e-05,
"loss": 2.2452,
"step": 22
},
{
"epoch": 0.04198995892286627,
"grad_norm": 2.6512441635131836,
"learning_rate": 6.545084971874738e-05,
"loss": 2.4352,
"step": 23
},
{
"epoch": 0.04381560931081698,
"grad_norm": 2.491504430770874,
"learning_rate": 6.209609477998338e-05,
"loss": 2.3273,
"step": 24
},
{
"epoch": 0.045641259698767686,
"grad_norm": 2.794949769973755,
"learning_rate": 5.868240888334653e-05,
"loss": 2.1816,
"step": 25
},
{
"epoch": 0.045641259698767686,
"eval_loss": 2.717280387878418,
"eval_runtime": 13.599,
"eval_samples_per_second": 67.873,
"eval_steps_per_second": 8.53,
"step": 25
},
{
"epoch": 0.04746691008671839,
"grad_norm": 3.201265811920166,
"learning_rate": 5.522642316338268e-05,
"loss": 2.1979,
"step": 26
},
{
"epoch": 0.0492925604746691,
"grad_norm": 3.3780765533447266,
"learning_rate": 5.174497483512506e-05,
"loss": 2.3203,
"step": 27
},
{
"epoch": 0.051118210862619806,
"grad_norm": 3.628631591796875,
"learning_rate": 4.825502516487497e-05,
"loss": 2.2478,
"step": 28
},
{
"epoch": 0.05294386125057052,
"grad_norm": 3.380159854888916,
"learning_rate": 4.477357683661734e-05,
"loss": 2.4871,
"step": 29
},
{
"epoch": 0.05476951163852122,
"grad_norm": 3.7136998176574707,
"learning_rate": 4.131759111665349e-05,
"loss": 2.5813,
"step": 30
},
{
"epoch": 0.05659516202647193,
"grad_norm": 3.7535629272460938,
"learning_rate": 3.790390522001662e-05,
"loss": 2.5976,
"step": 31
},
{
"epoch": 0.05842081241442264,
"grad_norm": 3.559950590133667,
"learning_rate": 3.4549150281252636e-05,
"loss": 2.7981,
"step": 32
},
{
"epoch": 0.06024646280237335,
"grad_norm": 4.081882953643799,
"learning_rate": 3.12696703292044e-05,
"loss": 2.6634,
"step": 33
},
{
"epoch": 0.06207211319032405,
"grad_norm": 3.7420055866241455,
"learning_rate": 2.8081442660546125e-05,
"loss": 2.8191,
"step": 34
},
{
"epoch": 0.06389776357827476,
"grad_norm": 3.7731378078460693,
"learning_rate": 2.500000000000001e-05,
"loss": 2.7214,
"step": 35
},
{
"epoch": 0.06572341396622547,
"grad_norm": 5.522697925567627,
"learning_rate": 2.2040354826462668e-05,
"loss": 2.6663,
"step": 36
},
{
"epoch": 0.06754906435417618,
"grad_norm": 8.51200008392334,
"learning_rate": 1.9216926233717085e-05,
"loss": 2.8907,
"step": 37
},
{
"epoch": 0.06937471474212688,
"grad_norm": 8.823360443115234,
"learning_rate": 1.6543469682057106e-05,
"loss": 3.0241,
"step": 38
},
{
"epoch": 0.07120036513007759,
"grad_norm": 7.192963600158691,
"learning_rate": 1.4033009983067452e-05,
"loss": 2.5329,
"step": 39
},
{
"epoch": 0.0730260155180283,
"grad_norm": 4.3827900886535645,
"learning_rate": 1.1697777844051105e-05,
"loss": 2.2836,
"step": 40
},
{
"epoch": 0.07485166590597901,
"grad_norm": 6.091566562652588,
"learning_rate": 9.549150281252633e-06,
"loss": 2.5218,
"step": 41
},
{
"epoch": 0.07667731629392971,
"grad_norm": 4.062016487121582,
"learning_rate": 7.597595192178702e-06,
"loss": 2.4963,
"step": 42
},
{
"epoch": 0.07850296668188042,
"grad_norm": 6.100872993469238,
"learning_rate": 5.852620357053651e-06,
"loss": 2.3811,
"step": 43
},
{
"epoch": 0.08032861706983113,
"grad_norm": 6.234488010406494,
"learning_rate": 4.322727117869951e-06,
"loss": 2.4821,
"step": 44
},
{
"epoch": 0.08215426745778183,
"grad_norm": 4.917290210723877,
"learning_rate": 3.0153689607045845e-06,
"loss": 2.8305,
"step": 45
},
{
"epoch": 0.08397991784573254,
"grad_norm": 4.923922538757324,
"learning_rate": 1.9369152030840556e-06,
"loss": 2.3685,
"step": 46
},
{
"epoch": 0.08580556823368325,
"grad_norm": 4.869322776794434,
"learning_rate": 1.0926199633097157e-06,
"loss": 2.1955,
"step": 47
},
{
"epoch": 0.08763121862163396,
"grad_norm": 7.294736385345459,
"learning_rate": 4.865965629214819e-07,
"loss": 3.4359,
"step": 48
},
{
"epoch": 0.08945686900958466,
"grad_norm": 6.816267967224121,
"learning_rate": 1.2179748700879012e-07,
"loss": 2.4971,
"step": 49
},
{
"epoch": 0.09128251939753537,
"grad_norm": 17.410608291625977,
"learning_rate": 0.0,
"loss": 4.105,
"step": 50
},
{
"epoch": 0.09128251939753537,
"eval_loss": 2.47334361076355,
"eval_runtime": 13.6191,
"eval_samples_per_second": 67.773,
"eval_steps_per_second": 8.517,
"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": 5,
"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": 6803618267136000.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}