weizhepei's picture
Model save
8d0ad9b verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 148,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.033783783783783786,
"grad_norm": 8.114141209696948,
"learning_rate": 3.125e-05,
"loss": 0.8109,
"step": 5
},
{
"epoch": 0.06756756756756757,
"grad_norm": 15.984610470967208,
"learning_rate": 4.9977343997179584e-05,
"loss": 0.569,
"step": 10
},
{
"epoch": 0.10135135135135136,
"grad_norm": 6.486203461616051,
"learning_rate": 4.97229876633906e-05,
"loss": 0.4567,
"step": 15
},
{
"epoch": 0.13513513513513514,
"grad_norm": 4.827853937931762,
"learning_rate": 4.91891643656567e-05,
"loss": 0.3269,
"step": 20
},
{
"epoch": 0.16891891891891891,
"grad_norm": 15.84631605931727,
"learning_rate": 4.838258724167838e-05,
"loss": 0.4273,
"step": 25
},
{
"epoch": 0.20270270270270271,
"grad_norm": 2.8760912276623753,
"learning_rate": 4.731339946677661e-05,
"loss": 0.361,
"step": 30
},
{
"epoch": 0.23648648648648649,
"grad_norm": 2.2048113082064313,
"learning_rate": 4.599504669757798e-05,
"loss": 0.3022,
"step": 35
},
{
"epoch": 0.2702702702702703,
"grad_norm": 2.7630825852517455,
"learning_rate": 4.444410798508125e-05,
"loss": 0.2922,
"step": 40
},
{
"epoch": 0.30405405405405406,
"grad_norm": 2.1921387790394316,
"learning_rate": 4.268008728347168e-05,
"loss": 0.2562,
"step": 45
},
{
"epoch": 0.33783783783783783,
"grad_norm": 2.0129512745038576,
"learning_rate": 4.072516817658065e-05,
"loss": 0.261,
"step": 50
},
{
"epoch": 0.3716216216216216,
"grad_norm": 2.0594810872433453,
"learning_rate": 3.860393490644781e-05,
"loss": 0.2945,
"step": 55
},
{
"epoch": 0.40540540540540543,
"grad_norm": 1.9791833079464716,
"learning_rate": 3.634306321221328e-05,
"loss": 0.2295,
"step": 60
},
{
"epoch": 0.4391891891891892,
"grad_norm": 2.116642693222838,
"learning_rate": 3.397098486722039e-05,
"loss": 0.2588,
"step": 65
},
{
"epoch": 0.47297297297297297,
"grad_norm": 1.5573192171310222,
"learning_rate": 3.1517530132969326e-05,
"loss": 0.2452,
"step": 70
},
{
"epoch": 0.5067567567567568,
"grad_norm": 1.7299357696784277,
"learning_rate": 2.9013552626270894e-05,
"loss": 0.2702,
"step": 75
},
{
"epoch": 0.5405405405405406,
"grad_norm": 1.6102605170270818,
"learning_rate": 2.6490541317113427e-05,
"loss": 0.215,
"step": 80
},
{
"epoch": 0.5743243243243243,
"grad_norm": 1.598946897431238,
"learning_rate": 2.3980224536594803e-05,
"loss": 0.2339,
"step": 85
},
{
"epoch": 0.6081081081081081,
"grad_norm": 1.588134782955536,
"learning_rate": 2.1514170974749814e-05,
"loss": 0.2117,
"step": 90
},
{
"epoch": 0.6418918918918919,
"grad_norm": 1.2441724175033286,
"learning_rate": 1.9123392685956238e-05,
"loss": 0.2135,
"step": 95
},
{
"epoch": 0.6756756756756757,
"grad_norm": 1.4345021992064273,
"learning_rate": 1.6837955094357533e-05,
"loss": 0.177,
"step": 100
},
{
"epoch": 0.7094594594594594,
"grad_norm": 1.1856924570160123,
"learning_rate": 1.468659890370983e-05,
"loss": 0.2133,
"step": 105
},
{
"epoch": 0.7432432432432432,
"grad_norm": 1.2429313237168909,
"learning_rate": 1.2696378666356468e-05,
"loss": 0.1859,
"step": 110
},
{
"epoch": 0.777027027027027,
"grad_norm": 1.2054353549516497,
"learning_rate": 1.0892322556534839e-05,
"loss": 0.1643,
"step": 115
},
{
"epoch": 0.8108108108108109,
"grad_norm": 1.3649942337642955,
"learning_rate": 9.297117626563687e-06,
"loss": 0.2296,
"step": 120
},
{
"epoch": 0.8445945945945946,
"grad_norm": 1.5853935569724023,
"learning_rate": 7.930824503996856e-06,
"loss": 0.1947,
"step": 125
},
{
"epoch": 0.8783783783783784,
"grad_norm": 1.2105867106797965,
"learning_rate": 6.810625117592363e-06,
"loss": 0.1814,
"step": 130
},
{
"epoch": 0.9121621621621622,
"grad_norm": 1.2923575683789774,
"learning_rate": 5.950606624589065e-06,
"loss": 0.1556,
"step": 135
},
{
"epoch": 0.9459459459459459,
"grad_norm": 0.9780632942146374,
"learning_rate": 5.361584256530833e-06,
"loss": 0.186,
"step": 140
},
{
"epoch": 0.9797297297297297,
"grad_norm": 0.8558531397152385,
"learning_rate": 5.050965311454739e-06,
"loss": 0.1568,
"step": 145
},
{
"epoch": 1.0,
"step": 148,
"total_flos": 87185003380736.0,
"train_loss": 0.2745462021714932,
"train_runtime": 3032.1637,
"train_samples_per_second": 3.12,
"train_steps_per_second": 0.049
}
],
"logging_steps": 5,
"max_steps": 148,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"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": 87185003380736.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}