HireFlow / checkpoint-500 /trainer_state.json
somriksur's picture
Upload folder using huggingface_hub
7cd626a verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.5159332321699543,
"eval_steps": 500,
"global_step": 500,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.030349013657056147,
"grad_norm": 0.49088624119758606,
"learning_rate": 1.8e-05,
"loss": 2.5243,
"step": 10
},
{
"epoch": 0.06069802731411229,
"grad_norm": 0.6470591425895691,
"learning_rate": 3.8e-05,
"loss": 2.389,
"step": 20
},
{
"epoch": 0.09104704097116843,
"grad_norm": 0.5612089037895203,
"learning_rate": 5.8e-05,
"loss": 2.164,
"step": 30
},
{
"epoch": 0.12139605462822459,
"grad_norm": 1.2414666414260864,
"learning_rate": 7.800000000000001e-05,
"loss": 1.8563,
"step": 40
},
{
"epoch": 0.15174506828528073,
"grad_norm": 0.7067261934280396,
"learning_rate": 9.8e-05,
"loss": 1.3996,
"step": 50
},
{
"epoch": 0.18209408194233687,
"grad_norm": 0.6404679417610168,
"learning_rate": 0.000118,
"loss": 1.0518,
"step": 60
},
{
"epoch": 0.212443095599393,
"grad_norm": 0.7477788329124451,
"learning_rate": 0.000138,
"loss": 0.8398,
"step": 70
},
{
"epoch": 0.24279210925644917,
"grad_norm": 0.7206103205680847,
"learning_rate": 0.00015800000000000002,
"loss": 0.6644,
"step": 80
},
{
"epoch": 0.2731411229135053,
"grad_norm": 0.6917621493339539,
"learning_rate": 0.00017800000000000002,
"loss": 0.5447,
"step": 90
},
{
"epoch": 0.30349013657056145,
"grad_norm": 0.7294086813926697,
"learning_rate": 0.00019800000000000002,
"loss": 0.4877,
"step": 100
},
{
"epoch": 0.3338391502276176,
"grad_norm": 0.7436180114746094,
"learning_rate": 0.00019797752808988766,
"loss": 0.4499,
"step": 110
},
{
"epoch": 0.36418816388467373,
"grad_norm": 0.7850086688995361,
"learning_rate": 0.0001957303370786517,
"loss": 0.4262,
"step": 120
},
{
"epoch": 0.3945371775417299,
"grad_norm": 0.69960618019104,
"learning_rate": 0.00019348314606741572,
"loss": 0.4107,
"step": 130
},
{
"epoch": 0.424886191198786,
"grad_norm": 0.5339717864990234,
"learning_rate": 0.0001912359550561798,
"loss": 0.4023,
"step": 140
},
{
"epoch": 0.4552352048558422,
"grad_norm": 0.7217109203338623,
"learning_rate": 0.00018898876404494384,
"loss": 0.3713,
"step": 150
},
{
"epoch": 0.48558421851289835,
"grad_norm": 0.5403777360916138,
"learning_rate": 0.00018674157303370787,
"loss": 0.3451,
"step": 160
},
{
"epoch": 0.5159332321699545,
"grad_norm": 0.7086395621299744,
"learning_rate": 0.00018449438202247192,
"loss": 0.3433,
"step": 170
},
{
"epoch": 0.5462822458270106,
"grad_norm": 0.5336319804191589,
"learning_rate": 0.00018224719101123598,
"loss": 0.3467,
"step": 180
},
{
"epoch": 0.5766312594840668,
"grad_norm": 0.5295460224151611,
"learning_rate": 0.00018,
"loss": 0.3625,
"step": 190
},
{
"epoch": 0.6069802731411229,
"grad_norm": 0.6301100254058838,
"learning_rate": 0.00017775280898876404,
"loss": 0.342,
"step": 200
},
{
"epoch": 0.637329286798179,
"grad_norm": 0.5921112298965454,
"learning_rate": 0.0001755056179775281,
"loss": 0.3418,
"step": 210
},
{
"epoch": 0.6676783004552352,
"grad_norm": 0.7228449583053589,
"learning_rate": 0.00017325842696629216,
"loss": 0.3276,
"step": 220
},
{
"epoch": 0.6980273141122914,
"grad_norm": 0.6273078918457031,
"learning_rate": 0.00017101123595505619,
"loss": 0.3226,
"step": 230
},
{
"epoch": 0.7283763277693475,
"grad_norm": 0.5710306167602539,
"learning_rate": 0.00016876404494382024,
"loss": 0.3238,
"step": 240
},
{
"epoch": 0.7587253414264037,
"grad_norm": 0.43547865748405457,
"learning_rate": 0.00016651685393258427,
"loss": 0.3264,
"step": 250
},
{
"epoch": 0.7890743550834598,
"grad_norm": 0.4803106188774109,
"learning_rate": 0.00016426966292134833,
"loss": 0.3125,
"step": 260
},
{
"epoch": 0.8194233687405159,
"grad_norm": 0.45547714829444885,
"learning_rate": 0.00016202247191011236,
"loss": 0.3015,
"step": 270
},
{
"epoch": 0.849772382397572,
"grad_norm": 0.4463222622871399,
"learning_rate": 0.00015977528089887642,
"loss": 0.3006,
"step": 280
},
{
"epoch": 0.8801213960546282,
"grad_norm": 0.6434076428413391,
"learning_rate": 0.00015752808988764045,
"loss": 0.3159,
"step": 290
},
{
"epoch": 0.9104704097116844,
"grad_norm": 0.5581756830215454,
"learning_rate": 0.0001552808988764045,
"loss": 0.3042,
"step": 300
},
{
"epoch": 0.9408194233687405,
"grad_norm": 0.5555682182312012,
"learning_rate": 0.00015303370786516856,
"loss": 0.3011,
"step": 310
},
{
"epoch": 0.9711684370257967,
"grad_norm": 0.47584882378578186,
"learning_rate": 0.0001507865168539326,
"loss": 0.2971,
"step": 320
},
{
"epoch": 1.0,
"grad_norm": 0.9439553618431091,
"learning_rate": 0.00014853932584269662,
"loss": 0.3148,
"step": 330
},
{
"epoch": 1.0303490136570561,
"grad_norm": 0.41724225878715515,
"learning_rate": 0.00014629213483146068,
"loss": 0.2885,
"step": 340
},
{
"epoch": 1.0606980273141122,
"grad_norm": 0.6222860813140869,
"learning_rate": 0.00014404494382022474,
"loss": 0.2941,
"step": 350
},
{
"epoch": 1.0910470409711683,
"grad_norm": 0.43433964252471924,
"learning_rate": 0.00014179775280898877,
"loss": 0.2825,
"step": 360
},
{
"epoch": 1.1213960546282247,
"grad_norm": 0.5504065752029419,
"learning_rate": 0.0001395505617977528,
"loss": 0.2917,
"step": 370
},
{
"epoch": 1.1517450682852808,
"grad_norm": 0.4902341663837433,
"learning_rate": 0.00013730337078651686,
"loss": 0.2803,
"step": 380
},
{
"epoch": 1.182094081942337,
"grad_norm": 0.5374056100845337,
"learning_rate": 0.00013505617977528091,
"loss": 0.2799,
"step": 390
},
{
"epoch": 1.212443095599393,
"grad_norm": 0.47176507115364075,
"learning_rate": 0.00013280898876404494,
"loss": 0.2783,
"step": 400
},
{
"epoch": 1.2427921092564491,
"grad_norm": 0.4779718816280365,
"learning_rate": 0.000130561797752809,
"loss": 0.2819,
"step": 410
},
{
"epoch": 1.2731411229135052,
"grad_norm": 0.4197782278060913,
"learning_rate": 0.00012831460674157303,
"loss": 0.279,
"step": 420
},
{
"epoch": 1.3034901365705616,
"grad_norm": 0.3616682291030884,
"learning_rate": 0.0001260674157303371,
"loss": 0.2732,
"step": 430
},
{
"epoch": 1.3338391502276177,
"grad_norm": 0.4093301594257355,
"learning_rate": 0.00012382022471910112,
"loss": 0.2719,
"step": 440
},
{
"epoch": 1.3641881638846738,
"grad_norm": 0.389291375875473,
"learning_rate": 0.00012157303370786516,
"loss": 0.2774,
"step": 450
},
{
"epoch": 1.39453717754173,
"grad_norm": 0.41108396649360657,
"learning_rate": 0.0001193258426966292,
"loss": 0.274,
"step": 460
},
{
"epoch": 1.424886191198786,
"grad_norm": 0.45677822828292847,
"learning_rate": 0.00011707865168539326,
"loss": 0.2701,
"step": 470
},
{
"epoch": 1.4552352048558421,
"grad_norm": 0.45333346724510193,
"learning_rate": 0.00011483146067415731,
"loss": 0.27,
"step": 480
},
{
"epoch": 1.4855842185128982,
"grad_norm": 0.4619373679161072,
"learning_rate": 0.00011258426966292135,
"loss": 0.2619,
"step": 490
},
{
"epoch": 1.5159332321699543,
"grad_norm": 0.36644256114959717,
"learning_rate": 0.00011033707865168538,
"loss": 0.2606,
"step": 500
}
],
"logging_steps": 10,
"max_steps": 990,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 9.144895527714816e+16,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}