Files
DS-LLM-TEMPLATE-FINETUNING/outputs/checkpoint-60/trainer_state.json
T
2025-08-13 23:50:20 +00:00

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
}