vdos's picture
Training in progress, step 50, checkpoint
3a55088 verified
{
"best_metric": 1.4205576181411743,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.7920792079207921,
"eval_steps": 25,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.015841584158415842,
"grad_norm": 116.92999267578125,
"learning_rate": 5e-05,
"loss": 3.8832,
"step": 1
},
{
"epoch": 0.015841584158415842,
"eval_loss": 4.637433052062988,
"eval_runtime": 21.0893,
"eval_samples_per_second": 20.2,
"eval_steps_per_second": 2.561,
"step": 1
},
{
"epoch": 0.031683168316831684,
"grad_norm": 131.46612548828125,
"learning_rate": 0.0001,
"loss": 4.2831,
"step": 2
},
{
"epoch": 0.047524752475247525,
"grad_norm": 126.66082763671875,
"learning_rate": 9.989294616193017e-05,
"loss": 3.9478,
"step": 3
},
{
"epoch": 0.06336633663366337,
"grad_norm": 71.32660675048828,
"learning_rate": 9.957224306869053e-05,
"loss": 2.8603,
"step": 4
},
{
"epoch": 0.07920792079207921,
"grad_norm": 54.61603546142578,
"learning_rate": 9.903926402016153e-05,
"loss": 2.356,
"step": 5
},
{
"epoch": 0.09504950495049505,
"grad_norm": 35.58620834350586,
"learning_rate": 9.829629131445342e-05,
"loss": 2.1134,
"step": 6
},
{
"epoch": 0.11089108910891089,
"grad_norm": 20.115825653076172,
"learning_rate": 9.73465064747553e-05,
"loss": 1.7411,
"step": 7
},
{
"epoch": 0.12673267326732673,
"grad_norm": 11.28286075592041,
"learning_rate": 9.619397662556435e-05,
"loss": 1.5849,
"step": 8
},
{
"epoch": 0.14257425742574256,
"grad_norm": 11.435465812683105,
"learning_rate": 9.484363707663442e-05,
"loss": 1.6331,
"step": 9
},
{
"epoch": 0.15841584158415842,
"grad_norm": 9.596415519714355,
"learning_rate": 9.330127018922194e-05,
"loss": 1.4195,
"step": 10
},
{
"epoch": 0.17425742574257425,
"grad_norm": 7.852958679199219,
"learning_rate": 9.157348061512727e-05,
"loss": 1.4109,
"step": 11
},
{
"epoch": 0.1900990099009901,
"grad_norm": 8.66879653930664,
"learning_rate": 8.966766701456177e-05,
"loss": 1.5046,
"step": 12
},
{
"epoch": 0.20594059405940593,
"grad_norm": 16.069547653198242,
"learning_rate": 8.759199037394887e-05,
"loss": 1.7543,
"step": 13
},
{
"epoch": 0.22178217821782178,
"grad_norm": 24.858217239379883,
"learning_rate": 8.535533905932738e-05,
"loss": 1.9357,
"step": 14
},
{
"epoch": 0.2376237623762376,
"grad_norm": 13.183930397033691,
"learning_rate": 8.296729075500344e-05,
"loss": 1.6216,
"step": 15
},
{
"epoch": 0.25346534653465347,
"grad_norm": 9.433813095092773,
"learning_rate": 8.043807145043604e-05,
"loss": 1.4612,
"step": 16
},
{
"epoch": 0.2693069306930693,
"grad_norm": 6.984700679779053,
"learning_rate": 7.777851165098012e-05,
"loss": 1.4995,
"step": 17
},
{
"epoch": 0.2851485148514851,
"grad_norm": 6.329092979431152,
"learning_rate": 7.500000000000001e-05,
"loss": 1.3562,
"step": 18
},
{
"epoch": 0.300990099009901,
"grad_norm": 7.003969192504883,
"learning_rate": 7.211443451095007e-05,
"loss": 1.2849,
"step": 19
},
{
"epoch": 0.31683168316831684,
"grad_norm": 5.927999973297119,
"learning_rate": 6.91341716182545e-05,
"loss": 1.3567,
"step": 20
},
{
"epoch": 0.3326732673267327,
"grad_norm": 7.590511322021484,
"learning_rate": 6.607197326515808e-05,
"loss": 1.3672,
"step": 21
},
{
"epoch": 0.3485148514851485,
"grad_norm": 10.127204895019531,
"learning_rate": 6.294095225512603e-05,
"loss": 1.4314,
"step": 22
},
{
"epoch": 0.36435643564356435,
"grad_norm": 7.6939826011657715,
"learning_rate": 5.9754516100806423e-05,
"loss": 1.3994,
"step": 23
},
{
"epoch": 0.3801980198019802,
"grad_norm": 7.435072422027588,
"learning_rate": 5.6526309611002594e-05,
"loss": 1.3335,
"step": 24
},
{
"epoch": 0.39603960396039606,
"grad_norm": 10.735369682312012,
"learning_rate": 5.327015646150716e-05,
"loss": 1.5439,
"step": 25
},
{
"epoch": 0.39603960396039606,
"eval_loss": 1.4605278968811035,
"eval_runtime": 21.1192,
"eval_samples_per_second": 20.171,
"eval_steps_per_second": 2.557,
"step": 25
},
{
"epoch": 0.41188118811881186,
"grad_norm": 12.851859092712402,
"learning_rate": 5e-05,
"loss": 1.6169,
"step": 26
},
{
"epoch": 0.4277227722772277,
"grad_norm": 10.011022567749023,
"learning_rate": 4.6729843538492847e-05,
"loss": 1.6847,
"step": 27
},
{
"epoch": 0.44356435643564357,
"grad_norm": 7.418447017669678,
"learning_rate": 4.347369038899744e-05,
"loss": 1.4793,
"step": 28
},
{
"epoch": 0.4594059405940594,
"grad_norm": 7.6047749519348145,
"learning_rate": 4.0245483899193595e-05,
"loss": 1.4387,
"step": 29
},
{
"epoch": 0.4752475247524752,
"grad_norm": 7.529312610626221,
"learning_rate": 3.705904774487396e-05,
"loss": 1.2696,
"step": 30
},
{
"epoch": 0.4910891089108911,
"grad_norm": 5.887645244598389,
"learning_rate": 3.392802673484193e-05,
"loss": 1.2813,
"step": 31
},
{
"epoch": 0.5069306930693069,
"grad_norm": 4.471807479858398,
"learning_rate": 3.086582838174551e-05,
"loss": 1.2555,
"step": 32
},
{
"epoch": 0.5227722772277228,
"grad_norm": 4.865562915802002,
"learning_rate": 2.7885565489049946e-05,
"loss": 1.3376,
"step": 33
},
{
"epoch": 0.5386138613861386,
"grad_norm": 4.343969345092773,
"learning_rate": 2.500000000000001e-05,
"loss": 1.3163,
"step": 34
},
{
"epoch": 0.5544554455445545,
"grad_norm": 4.894163608551025,
"learning_rate": 2.2221488349019903e-05,
"loss": 1.3629,
"step": 35
},
{
"epoch": 0.5702970297029702,
"grad_norm": 5.443630695343018,
"learning_rate": 1.9561928549563968e-05,
"loss": 1.3183,
"step": 36
},
{
"epoch": 0.5861386138613861,
"grad_norm": 9.0098876953125,
"learning_rate": 1.703270924499656e-05,
"loss": 1.4488,
"step": 37
},
{
"epoch": 0.601980198019802,
"grad_norm": 6.921519756317139,
"learning_rate": 1.4644660940672627e-05,
"loss": 1.5777,
"step": 38
},
{
"epoch": 0.6178217821782178,
"grad_norm": 8.694135665893555,
"learning_rate": 1.2408009626051137e-05,
"loss": 1.6112,
"step": 39
},
{
"epoch": 0.6336633663366337,
"grad_norm": 6.186464786529541,
"learning_rate": 1.0332332985438248e-05,
"loss": 1.5085,
"step": 40
},
{
"epoch": 0.6495049504950495,
"grad_norm": 5.976185321807861,
"learning_rate": 8.426519384872733e-06,
"loss": 1.3798,
"step": 41
},
{
"epoch": 0.6653465346534654,
"grad_norm": 5.398346900939941,
"learning_rate": 6.698729810778065e-06,
"loss": 1.3313,
"step": 42
},
{
"epoch": 0.6811881188118812,
"grad_norm": 4.827998161315918,
"learning_rate": 5.156362923365588e-06,
"loss": 1.3266,
"step": 43
},
{
"epoch": 0.697029702970297,
"grad_norm": 4.136651515960693,
"learning_rate": 3.8060233744356633e-06,
"loss": 1.3478,
"step": 44
},
{
"epoch": 0.7128712871287128,
"grad_norm": 4.079899787902832,
"learning_rate": 2.653493525244721e-06,
"loss": 1.2925,
"step": 45
},
{
"epoch": 0.7287128712871287,
"grad_norm": 4.743795871734619,
"learning_rate": 1.70370868554659e-06,
"loss": 1.3243,
"step": 46
},
{
"epoch": 0.7445544554455445,
"grad_norm": 5.614559173583984,
"learning_rate": 9.607359798384785e-07,
"loss": 1.3783,
"step": 47
},
{
"epoch": 0.7603960396039604,
"grad_norm": 5.586382865905762,
"learning_rate": 4.277569313094809e-07,
"loss": 1.4069,
"step": 48
},
{
"epoch": 0.7762376237623763,
"grad_norm": 7.032140254974365,
"learning_rate": 1.0705383806982606e-07,
"loss": 1.3624,
"step": 49
},
{
"epoch": 0.7920792079207921,
"grad_norm": 10.226324081420898,
"learning_rate": 0.0,
"loss": 1.3784,
"step": 50
},
{
"epoch": 0.7920792079207921,
"eval_loss": 1.4205576181411743,
"eval_runtime": 21.0936,
"eval_samples_per_second": 20.196,
"eval_steps_per_second": 2.56,
"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": 1.0952750720352256e+18,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}