455 lines
9.9 KiB
JSON
455 lines
9.9 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 60.0,
|
|
"eval_steps": 500,
|
|
"global_step": 60,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"epoch": 1.0,
|
|
"grad_norm": 2.099515914916992,
|
|
"learning_rate": 0.0,
|
|
"loss": 2.6549,
|
|
"step": 1
|
|
},
|
|
{
|
|
"epoch": 2.0,
|
|
"grad_norm": 2.1028008460998535,
|
|
"learning_rate": 4e-05,
|
|
"loss": 2.6566,
|
|
"step": 2
|
|
},
|
|
{
|
|
"epoch": 3.0,
|
|
"grad_norm": 2.096004009246826,
|
|
"learning_rate": 8e-05,
|
|
"loss": 2.6172,
|
|
"step": 3
|
|
},
|
|
{
|
|
"epoch": 4.0,
|
|
"grad_norm": 2.2220966815948486,
|
|
"learning_rate": 0.00012,
|
|
"loss": 2.4567,
|
|
"step": 4
|
|
},
|
|
{
|
|
"epoch": 5.0,
|
|
"grad_norm": 2.1684439182281494,
|
|
"learning_rate": 0.00016,
|
|
"loss": 2.0182,
|
|
"step": 5
|
|
},
|
|
{
|
|
"epoch": 6.0,
|
|
"grad_norm": 2.1147849559783936,
|
|
"learning_rate": 0.0002,
|
|
"loss": 1.4709,
|
|
"step": 6
|
|
},
|
|
{
|
|
"epoch": 7.0,
|
|
"grad_norm": 5.454170227050781,
|
|
"learning_rate": 0.00019636363636363636,
|
|
"loss": 1.0252,
|
|
"step": 7
|
|
},
|
|
{
|
|
"epoch": 8.0,
|
|
"grad_norm": 2.096377372741699,
|
|
"learning_rate": 0.00019272727272727274,
|
|
"loss": 0.7436,
|
|
"step": 8
|
|
},
|
|
{
|
|
"epoch": 9.0,
|
|
"grad_norm": 1.4990514516830444,
|
|
"learning_rate": 0.0001890909090909091,
|
|
"loss": 0.4376,
|
|
"step": 9
|
|
},
|
|
{
|
|
"epoch": 10.0,
|
|
"grad_norm": 0.6785975098609924,
|
|
"learning_rate": 0.00018545454545454545,
|
|
"loss": 0.3168,
|
|
"step": 10
|
|
},
|
|
{
|
|
"epoch": 11.0,
|
|
"grad_norm": 0.8837186098098755,
|
|
"learning_rate": 0.00018181818181818183,
|
|
"loss": 0.2594,
|
|
"step": 11
|
|
},
|
|
{
|
|
"epoch": 12.0,
|
|
"grad_norm": 0.6441168189048767,
|
|
"learning_rate": 0.0001781818181818182,
|
|
"loss": 0.2084,
|
|
"step": 12
|
|
},
|
|
{
|
|
"epoch": 13.0,
|
|
"grad_norm": 0.7236498594284058,
|
|
"learning_rate": 0.00017454545454545454,
|
|
"loss": 0.1832,
|
|
"step": 13
|
|
},
|
|
{
|
|
"epoch": 14.0,
|
|
"grad_norm": 0.7865864038467407,
|
|
"learning_rate": 0.0001709090909090909,
|
|
"loss": 0.1614,
|
|
"step": 14
|
|
},
|
|
{
|
|
"epoch": 15.0,
|
|
"grad_norm": 0.8386063575744629,
|
|
"learning_rate": 0.00016727272727272728,
|
|
"loss": 0.145,
|
|
"step": 15
|
|
},
|
|
{
|
|
"epoch": 16.0,
|
|
"grad_norm": 0.9354585409164429,
|
|
"learning_rate": 0.00016363636363636366,
|
|
"loss": 0.1331,
|
|
"step": 16
|
|
},
|
|
{
|
|
"epoch": 17.0,
|
|
"grad_norm": 1.0136165618896484,
|
|
"learning_rate": 0.00016,
|
|
"loss": 0.119,
|
|
"step": 17
|
|
},
|
|
{
|
|
"epoch": 18.0,
|
|
"grad_norm": 1.152154564857483,
|
|
"learning_rate": 0.00015636363636363637,
|
|
"loss": 0.1078,
|
|
"step": 18
|
|
},
|
|
{
|
|
"epoch": 19.0,
|
|
"grad_norm": 1.3258788585662842,
|
|
"learning_rate": 0.00015272727272727275,
|
|
"loss": 0.0945,
|
|
"step": 19
|
|
},
|
|
{
|
|
"epoch": 20.0,
|
|
"grad_norm": 1.4479986429214478,
|
|
"learning_rate": 0.0001490909090909091,
|
|
"loss": 0.0782,
|
|
"step": 20
|
|
},
|
|
{
|
|
"epoch": 21.0,
|
|
"grad_norm": 1.5057014226913452,
|
|
"learning_rate": 0.00014545454545454546,
|
|
"loss": 0.0627,
|
|
"step": 21
|
|
},
|
|
{
|
|
"epoch": 22.0,
|
|
"grad_norm": 1.353816270828247,
|
|
"learning_rate": 0.00014181818181818184,
|
|
"loss": 0.0479,
|
|
"step": 22
|
|
},
|
|
{
|
|
"epoch": 23.0,
|
|
"grad_norm": 0.9007766842842102,
|
|
"learning_rate": 0.0001381818181818182,
|
|
"loss": 0.037,
|
|
"step": 23
|
|
},
|
|
{
|
|
"epoch": 24.0,
|
|
"grad_norm": 0.44463616609573364,
|
|
"learning_rate": 0.00013454545454545455,
|
|
"loss": 0.0317,
|
|
"step": 24
|
|
},
|
|
{
|
|
"epoch": 25.0,
|
|
"grad_norm": 0.15833492577075958,
|
|
"learning_rate": 0.00013090909090909093,
|
|
"loss": 0.0279,
|
|
"step": 25
|
|
},
|
|
{
|
|
"epoch": 26.0,
|
|
"grad_norm": 0.11187602579593658,
|
|
"learning_rate": 0.00012727272727272728,
|
|
"loss": 0.0279,
|
|
"step": 26
|
|
},
|
|
{
|
|
"epoch": 27.0,
|
|
"grad_norm": 0.07458829134702682,
|
|
"learning_rate": 0.00012363636363636364,
|
|
"loss": 0.0274,
|
|
"step": 27
|
|
},
|
|
{
|
|
"epoch": 28.0,
|
|
"grad_norm": 0.05743066221475601,
|
|
"learning_rate": 0.00012,
|
|
"loss": 0.0271,
|
|
"step": 28
|
|
},
|
|
{
|
|
"epoch": 29.0,
|
|
"grad_norm": 0.08287172019481659,
|
|
"learning_rate": 0.00011636363636363636,
|
|
"loss": 0.0273,
|
|
"step": 29
|
|
},
|
|
{
|
|
"epoch": 30.0,
|
|
"grad_norm": 0.06937997788190842,
|
|
"learning_rate": 0.00011272727272727272,
|
|
"loss": 0.027,
|
|
"step": 30
|
|
},
|
|
{
|
|
"epoch": 31.0,
|
|
"grad_norm": 0.04856820032000542,
|
|
"learning_rate": 0.00010909090909090909,
|
|
"loss": 0.027,
|
|
"step": 31
|
|
},
|
|
{
|
|
"epoch": 32.0,
|
|
"grad_norm": 0.07065649330615997,
|
|
"learning_rate": 0.00010545454545454545,
|
|
"loss": 0.027,
|
|
"step": 32
|
|
},
|
|
{
|
|
"epoch": 33.0,
|
|
"grad_norm": 0.0560951754450798,
|
|
"learning_rate": 0.00010181818181818181,
|
|
"loss": 0.0268,
|
|
"step": 33
|
|
},
|
|
{
|
|
"epoch": 34.0,
|
|
"grad_norm": 0.06166462227702141,
|
|
"learning_rate": 9.818181818181818e-05,
|
|
"loss": 0.0268,
|
|
"step": 34
|
|
},
|
|
{
|
|
"epoch": 35.0,
|
|
"grad_norm": 0.06152236461639404,
|
|
"learning_rate": 9.454545454545455e-05,
|
|
"loss": 0.0269,
|
|
"step": 35
|
|
},
|
|
{
|
|
"epoch": 36.0,
|
|
"grad_norm": 0.045099712908267975,
|
|
"learning_rate": 9.090909090909092e-05,
|
|
"loss": 0.0268,
|
|
"step": 36
|
|
},
|
|
{
|
|
"epoch": 37.0,
|
|
"grad_norm": 0.01705729216337204,
|
|
"learning_rate": 8.727272727272727e-05,
|
|
"loss": 0.0267,
|
|
"step": 37
|
|
},
|
|
{
|
|
"epoch": 38.0,
|
|
"grad_norm": 0.05170425772666931,
|
|
"learning_rate": 8.363636363636364e-05,
|
|
"loss": 0.0266,
|
|
"step": 38
|
|
},
|
|
{
|
|
"epoch": 39.0,
|
|
"grad_norm": 0.06034626066684723,
|
|
"learning_rate": 8e-05,
|
|
"loss": 0.0269,
|
|
"step": 39
|
|
},
|
|
{
|
|
"epoch": 40.0,
|
|
"grad_norm": 0.03125019744038582,
|
|
"learning_rate": 7.636363636363637e-05,
|
|
"loss": 0.0268,
|
|
"step": 40
|
|
},
|
|
{
|
|
"epoch": 41.0,
|
|
"grad_norm": 0.03972804546356201,
|
|
"learning_rate": 7.272727272727273e-05,
|
|
"loss": 0.0266,
|
|
"step": 41
|
|
},
|
|
{
|
|
"epoch": 42.0,
|
|
"grad_norm": 0.05231940746307373,
|
|
"learning_rate": 6.90909090909091e-05,
|
|
"loss": 0.0267,
|
|
"step": 42
|
|
},
|
|
{
|
|
"epoch": 43.0,
|
|
"grad_norm": 0.03405136987566948,
|
|
"learning_rate": 6.545454545454546e-05,
|
|
"loss": 0.0265,
|
|
"step": 43
|
|
},
|
|
{
|
|
"epoch": 44.0,
|
|
"grad_norm": 0.010633698664605618,
|
|
"learning_rate": 6.181818181818182e-05,
|
|
"loss": 0.0265,
|
|
"step": 44
|
|
},
|
|
{
|
|
"epoch": 45.0,
|
|
"grad_norm": 0.03109440766274929,
|
|
"learning_rate": 5.818181818181818e-05,
|
|
"loss": 0.0267,
|
|
"step": 45
|
|
},
|
|
{
|
|
"epoch": 46.0,
|
|
"grad_norm": 0.027693096548318863,
|
|
"learning_rate": 5.4545454545454546e-05,
|
|
"loss": 0.0267,
|
|
"step": 46
|
|
},
|
|
{
|
|
"epoch": 47.0,
|
|
"grad_norm": 0.03655220940709114,
|
|
"learning_rate": 5.090909090909091e-05,
|
|
"loss": 0.0266,
|
|
"step": 47
|
|
},
|
|
{
|
|
"epoch": 48.0,
|
|
"grad_norm": 0.022899532690644264,
|
|
"learning_rate": 4.7272727272727275e-05,
|
|
"loss": 0.0268,
|
|
"step": 48
|
|
},
|
|
{
|
|
"epoch": 49.0,
|
|
"grad_norm": 0.01907823234796524,
|
|
"learning_rate": 4.3636363636363636e-05,
|
|
"loss": 0.0265,
|
|
"step": 49
|
|
},
|
|
{
|
|
"epoch": 50.0,
|
|
"grad_norm": 0.03373124822974205,
|
|
"learning_rate": 4e-05,
|
|
"loss": 0.0263,
|
|
"step": 50
|
|
},
|
|
{
|
|
"epoch": 51.0,
|
|
"grad_norm": 0.03454992547631264,
|
|
"learning_rate": 3.6363636363636364e-05,
|
|
"loss": 0.0266,
|
|
"step": 51
|
|
},
|
|
{
|
|
"epoch": 52.0,
|
|
"grad_norm": 0.019019270315766335,
|
|
"learning_rate": 3.272727272727273e-05,
|
|
"loss": 0.0267,
|
|
"step": 52
|
|
},
|
|
{
|
|
"epoch": 53.0,
|
|
"grad_norm": 0.0051805428229272366,
|
|
"learning_rate": 2.909090909090909e-05,
|
|
"loss": 0.0266,
|
|
"step": 53
|
|
},
|
|
{
|
|
"epoch": 54.0,
|
|
"grad_norm": 0.005404070485383272,
|
|
"learning_rate": 2.5454545454545454e-05,
|
|
"loss": 0.0266,
|
|
"step": 54
|
|
},
|
|
{
|
|
"epoch": 55.0,
|
|
"grad_norm": 0.012555314227938652,
|
|
"learning_rate": 2.1818181818181818e-05,
|
|
"loss": 0.0264,
|
|
"step": 55
|
|
},
|
|
{
|
|
"epoch": 56.0,
|
|
"grad_norm": 0.02643151953816414,
|
|
"learning_rate": 1.8181818181818182e-05,
|
|
"loss": 0.0266,
|
|
"step": 56
|
|
},
|
|
{
|
|
"epoch": 57.0,
|
|
"grad_norm": 0.015639500692486763,
|
|
"learning_rate": 1.4545454545454545e-05,
|
|
"loss": 0.0269,
|
|
"step": 57
|
|
},
|
|
{
|
|
"epoch": 58.0,
|
|
"grad_norm": 0.032283101230859756,
|
|
"learning_rate": 1.0909090909090909e-05,
|
|
"loss": 0.0264,
|
|
"step": 58
|
|
},
|
|
{
|
|
"epoch": 59.0,
|
|
"grad_norm": 0.016383344307541847,
|
|
"learning_rate": 7.272727272727272e-06,
|
|
"loss": 0.0266,
|
|
"step": 59
|
|
},
|
|
{
|
|
"epoch": 60.0,
|
|
"grad_norm": 0.005381885915994644,
|
|
"learning_rate": 3.636363636363636e-06,
|
|
"loss": 0.0267,
|
|
"step": 60
|
|
}
|
|
],
|
|
"logging_steps": 1,
|
|
"max_steps": 60,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 60,
|
|
"save_steps": 500,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": true
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 886560737599488.0,
|
|
"train_batch_size": 4,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|