aleegis09's picture
Training in progress, step 50, checkpoint
c2677f7 verified
raw
history blame
10.2 kB
{
"best_metric": 1.0394631624221802,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.03244646333549643,
"eval_steps": 25,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0006489292667099286,
"grad_norm": 2.683505058288574,
"learning_rate": 2e-05,
"loss": 3.5951,
"step": 1
},
{
"epoch": 0.0006489292667099286,
"eval_loss": 1.4502065181732178,
"eval_runtime": 148.1881,
"eval_samples_per_second": 17.518,
"eval_steps_per_second": 2.193,
"step": 1
},
{
"epoch": 0.0012978585334198572,
"grad_norm": 3.0936529636383057,
"learning_rate": 4e-05,
"loss": 3.7839,
"step": 2
},
{
"epoch": 0.001946787800129786,
"grad_norm": 2.257113456726074,
"learning_rate": 6e-05,
"loss": 3.907,
"step": 3
},
{
"epoch": 0.0025957170668397143,
"grad_norm": 2.010742425918579,
"learning_rate": 8e-05,
"loss": 3.6334,
"step": 4
},
{
"epoch": 0.003244646333549643,
"grad_norm": 3.200777769088745,
"learning_rate": 0.0001,
"loss": 3.932,
"step": 5
},
{
"epoch": 0.003893575600259572,
"grad_norm": 2.122283935546875,
"learning_rate": 9.987820251299122e-05,
"loss": 3.7128,
"step": 6
},
{
"epoch": 0.004542504866969501,
"grad_norm": 1.8623450994491577,
"learning_rate": 9.951340343707852e-05,
"loss": 3.7839,
"step": 7
},
{
"epoch": 0.005191434133679429,
"grad_norm": 2.3359696865081787,
"learning_rate": 9.890738003669029e-05,
"loss": 3.7878,
"step": 8
},
{
"epoch": 0.005840363400389357,
"grad_norm": 1.9105135202407837,
"learning_rate": 9.806308479691595e-05,
"loss": 3.8119,
"step": 9
},
{
"epoch": 0.006489292667099286,
"grad_norm": 1.7457245588302612,
"learning_rate": 9.698463103929542e-05,
"loss": 3.7471,
"step": 10
},
{
"epoch": 0.007138221933809215,
"grad_norm": 2.1727206707000732,
"learning_rate": 9.567727288213005e-05,
"loss": 3.9428,
"step": 11
},
{
"epoch": 0.007787151200519144,
"grad_norm": 1.9664866924285889,
"learning_rate": 9.414737964294636e-05,
"loss": 3.9362,
"step": 12
},
{
"epoch": 0.008436080467229072,
"grad_norm": 2.474402904510498,
"learning_rate": 9.24024048078213e-05,
"loss": 3.9396,
"step": 13
},
{
"epoch": 0.009085009733939001,
"grad_norm": 3.0328118801116943,
"learning_rate": 9.045084971874738e-05,
"loss": 3.6997,
"step": 14
},
{
"epoch": 0.00973393900064893,
"grad_norm": 2.00704026222229,
"learning_rate": 8.83022221559489e-05,
"loss": 3.9555,
"step": 15
},
{
"epoch": 0.010382868267358857,
"grad_norm": 1.9274024963378906,
"learning_rate": 8.596699001693255e-05,
"loss": 3.6365,
"step": 16
},
{
"epoch": 0.011031797534068787,
"grad_norm": 2.011793851852417,
"learning_rate": 8.345653031794292e-05,
"loss": 4.1249,
"step": 17
},
{
"epoch": 0.011680726800778715,
"grad_norm": 2.1976027488708496,
"learning_rate": 8.07830737662829e-05,
"loss": 4.2458,
"step": 18
},
{
"epoch": 0.012329656067488644,
"grad_norm": 1.9308854341506958,
"learning_rate": 7.795964517353735e-05,
"loss": 4.0175,
"step": 19
},
{
"epoch": 0.012978585334198572,
"grad_norm": 2.092264175415039,
"learning_rate": 7.500000000000001e-05,
"loss": 4.0406,
"step": 20
},
{
"epoch": 0.0136275146009085,
"grad_norm": 2.3463144302368164,
"learning_rate": 7.191855733945387e-05,
"loss": 4.1564,
"step": 21
},
{
"epoch": 0.01427644386761843,
"grad_norm": 2.3224618434906006,
"learning_rate": 6.873032967079561e-05,
"loss": 3.9462,
"step": 22
},
{
"epoch": 0.014925373134328358,
"grad_norm": 2.443256139755249,
"learning_rate": 6.545084971874738e-05,
"loss": 3.692,
"step": 23
},
{
"epoch": 0.015574302401038288,
"grad_norm": 3.4629366397857666,
"learning_rate": 6.209609477998338e-05,
"loss": 4.3253,
"step": 24
},
{
"epoch": 0.016223231667748216,
"grad_norm": 2.778249740600586,
"learning_rate": 5.868240888334653e-05,
"loss": 4.1526,
"step": 25
},
{
"epoch": 0.016223231667748216,
"eval_loss": 1.1567610502243042,
"eval_runtime": 148.826,
"eval_samples_per_second": 17.443,
"eval_steps_per_second": 2.184,
"step": 25
},
{
"epoch": 0.016872160934458143,
"grad_norm": 423.1258239746094,
"learning_rate": 5.522642316338268e-05,
"loss": 4.3783,
"step": 26
},
{
"epoch": 0.01752109020116807,
"grad_norm": 19.292482376098633,
"learning_rate": 5.174497483512506e-05,
"loss": 3.7328,
"step": 27
},
{
"epoch": 0.018170019467878003,
"grad_norm": 3.9839913845062256,
"learning_rate": 4.825502516487497e-05,
"loss": 3.9131,
"step": 28
},
{
"epoch": 0.01881894873458793,
"grad_norm": 5.250899314880371,
"learning_rate": 4.477357683661734e-05,
"loss": 3.8158,
"step": 29
},
{
"epoch": 0.01946787800129786,
"grad_norm": 3.4630203247070312,
"learning_rate": 4.131759111665349e-05,
"loss": 4.1871,
"step": 30
},
{
"epoch": 0.020116807268007787,
"grad_norm": 4.317551612854004,
"learning_rate": 3.790390522001662e-05,
"loss": 4.7563,
"step": 31
},
{
"epoch": 0.020765736534717714,
"grad_norm": 4.866771221160889,
"learning_rate": 3.4549150281252636e-05,
"loss": 4.3659,
"step": 32
},
{
"epoch": 0.021414665801427646,
"grad_norm": 5.2690839767456055,
"learning_rate": 3.12696703292044e-05,
"loss": 4.1365,
"step": 33
},
{
"epoch": 0.022063595068137574,
"grad_norm": 5.08319091796875,
"learning_rate": 2.8081442660546125e-05,
"loss": 4.5015,
"step": 34
},
{
"epoch": 0.0227125243348475,
"grad_norm": 4.986558437347412,
"learning_rate": 2.500000000000001e-05,
"loss": 4.2522,
"step": 35
},
{
"epoch": 0.02336145360155743,
"grad_norm": 5.291998386383057,
"learning_rate": 2.2040354826462668e-05,
"loss": 3.7079,
"step": 36
},
{
"epoch": 0.024010382868267358,
"grad_norm": 7.075346946716309,
"learning_rate": 1.9216926233717085e-05,
"loss": 4.3515,
"step": 37
},
{
"epoch": 0.02465931213497729,
"grad_norm": 6.59442663192749,
"learning_rate": 1.6543469682057106e-05,
"loss": 4.4537,
"step": 38
},
{
"epoch": 0.025308241401687217,
"grad_norm": 7.289731502532959,
"learning_rate": 1.4033009983067452e-05,
"loss": 4.6425,
"step": 39
},
{
"epoch": 0.025957170668397145,
"grad_norm": 8.14652156829834,
"learning_rate": 1.1697777844051105e-05,
"loss": 4.7023,
"step": 40
},
{
"epoch": 0.026606099935107073,
"grad_norm": 8.087379455566406,
"learning_rate": 9.549150281252633e-06,
"loss": 4.0411,
"step": 41
},
{
"epoch": 0.027255029201817,
"grad_norm": 8.625016212463379,
"learning_rate": 7.597595192178702e-06,
"loss": 4.4971,
"step": 42
},
{
"epoch": 0.027903958468526932,
"grad_norm": 8.698261260986328,
"learning_rate": 5.852620357053651e-06,
"loss": 4.0275,
"step": 43
},
{
"epoch": 0.02855288773523686,
"grad_norm": 9.690203666687012,
"learning_rate": 4.322727117869951e-06,
"loss": 4.6694,
"step": 44
},
{
"epoch": 0.029201817001946788,
"grad_norm": 10.64246940612793,
"learning_rate": 3.0153689607045845e-06,
"loss": 4.3358,
"step": 45
},
{
"epoch": 0.029850746268656716,
"grad_norm": 9.350142478942871,
"learning_rate": 1.9369152030840556e-06,
"loss": 3.6146,
"step": 46
},
{
"epoch": 0.030499675535366644,
"grad_norm": 9.56218433380127,
"learning_rate": 1.0926199633097157e-06,
"loss": 3.4644,
"step": 47
},
{
"epoch": 0.031148604802076575,
"grad_norm": 16.128480911254883,
"learning_rate": 4.865965629214819e-07,
"loss": 5.3455,
"step": 48
},
{
"epoch": 0.0317975340687865,
"grad_norm": 15.799928665161133,
"learning_rate": 1.2179748700879012e-07,
"loss": 4.5824,
"step": 49
},
{
"epoch": 0.03244646333549643,
"grad_norm": 13.623414993286133,
"learning_rate": 0.0,
"loss": 3.5276,
"step": 50
},
{
"epoch": 0.03244646333549643,
"eval_loss": 1.0394631624221802,
"eval_runtime": 148.7645,
"eval_samples_per_second": 17.45,
"eval_steps_per_second": 2.185,
"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": 6.09238892150784e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}