codet5_qlora / checkpoint-2829 /trainer_state.json
gpol13's picture
Upload folder using huggingface_hub
9eb7f59 verified
{
"best_global_step": 2829,
"best_metric": 0.9667777874331811,
"best_model_checkpoint": "./codet5-qlora-k8s/checkpoint-2829",
"epoch": 1.0,
"eval_steps": 500,
"global_step": 2829,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.017674089784376106,
"grad_norm": 1.1207759380340576,
"learning_rate": 0.00029898197242841994,
"loss": 3.2886,
"step": 50
},
{
"epoch": 0.03534817956875221,
"grad_norm": 1.2978123426437378,
"learning_rate": 0.0002979215270413573,
"loss": 1.8567,
"step": 100
},
{
"epoch": 0.053022269353128315,
"grad_norm": 1.624740719795227,
"learning_rate": 0.0002968610816542948,
"loss": 1.5695,
"step": 150
},
{
"epoch": 0.07069635913750442,
"grad_norm": 1.7711330652236938,
"learning_rate": 0.0002958006362672322,
"loss": 1.4205,
"step": 200
},
{
"epoch": 0.08837044892188052,
"grad_norm": 1.62517511844635,
"learning_rate": 0.0002947401908801697,
"loss": 1.2732,
"step": 250
},
{
"epoch": 0.10604453870625663,
"grad_norm": 2.038139820098877,
"learning_rate": 0.00029367974549310706,
"loss": 1.1913,
"step": 300
},
{
"epoch": 0.12371862849063273,
"grad_norm": 2.262789487838745,
"learning_rate": 0.00029264050901378576,
"loss": 1.117,
"step": 350
},
{
"epoch": 0.14139271827500885,
"grad_norm": 3.121687650680542,
"learning_rate": 0.0002915800636267232,
"loss": 1.0202,
"step": 400
},
{
"epoch": 0.15906680805938495,
"grad_norm": 2.0951812267303467,
"learning_rate": 0.0002905196182396606,
"loss": 0.9499,
"step": 450
},
{
"epoch": 0.17674089784376104,
"grad_norm": 2.670121192932129,
"learning_rate": 0.00028945917285259806,
"loss": 0.9707,
"step": 500
},
{
"epoch": 0.19441498762813716,
"grad_norm": 2.3631107807159424,
"learning_rate": 0.00028841993637327676,
"loss": 0.7961,
"step": 550
},
{
"epoch": 0.21208907741251326,
"grad_norm": 2.10772705078125,
"learning_rate": 0.0002873594909862142,
"loss": 0.8912,
"step": 600
},
{
"epoch": 0.22976316719688936,
"grad_norm": 2.360686779022217,
"learning_rate": 0.00028629904559915163,
"loss": 0.871,
"step": 650
},
{
"epoch": 0.24743725698126545,
"grad_norm": 2.191119432449341,
"learning_rate": 0.0002852598091198303,
"loss": 0.758,
"step": 700
},
{
"epoch": 0.2651113467656416,
"grad_norm": 1.7646818161010742,
"learning_rate": 0.00028419936373276776,
"loss": 0.8244,
"step": 750
},
{
"epoch": 0.2827854365500177,
"grad_norm": 2.3776354789733887,
"learning_rate": 0.00028313891834570514,
"loss": 0.7664,
"step": 800
},
{
"epoch": 0.30045952633439377,
"grad_norm": 2.8682475090026855,
"learning_rate": 0.00028207847295864263,
"loss": 0.6942,
"step": 850
},
{
"epoch": 0.3181336161187699,
"grad_norm": 2.353091239929199,
"learning_rate": 0.00028101802757158,
"loss": 0.7323,
"step": 900
},
{
"epoch": 0.335807705903146,
"grad_norm": 1.9457337856292725,
"learning_rate": 0.00027995758218451745,
"loss": 0.6474,
"step": 950
},
{
"epoch": 0.3534817956875221,
"grad_norm": 2.510075330734253,
"learning_rate": 0.00027889713679745494,
"loss": 0.6801,
"step": 1000
},
{
"epoch": 0.3711558854718982,
"grad_norm": 1.7497014999389648,
"learning_rate": 0.0002778366914103923,
"loss": 0.656,
"step": 1050
},
{
"epoch": 0.38882997525627433,
"grad_norm": 2.862682342529297,
"learning_rate": 0.0002767762460233298,
"loss": 0.6238,
"step": 1100
},
{
"epoch": 0.4065040650406504,
"grad_norm": 1.998961091041565,
"learning_rate": 0.0002757158006362672,
"loss": 0.6306,
"step": 1150
},
{
"epoch": 0.4241781548250265,
"grad_norm": 1.854942798614502,
"learning_rate": 0.0002746553552492047,
"loss": 0.5689,
"step": 1200
},
{
"epoch": 0.4418522446094026,
"grad_norm": 1.8994203805923462,
"learning_rate": 0.00027359490986214206,
"loss": 0.6595,
"step": 1250
},
{
"epoch": 0.4595263343937787,
"grad_norm": 1.6235908269882202,
"learning_rate": 0.0002725344644750795,
"loss": 0.5665,
"step": 1300
},
{
"epoch": 0.47720042417815484,
"grad_norm": 2.291989803314209,
"learning_rate": 0.00027147401908801693,
"loss": 0.5761,
"step": 1350
},
{
"epoch": 0.4948745139625309,
"grad_norm": 1.4632915258407593,
"learning_rate": 0.00027041357370095437,
"loss": 0.5171,
"step": 1400
},
{
"epoch": 0.512548603746907,
"grad_norm": 2.1687259674072266,
"learning_rate": 0.0002693531283138918,
"loss": 0.6183,
"step": 1450
},
{
"epoch": 0.5302226935312832,
"grad_norm": 1.734108805656433,
"learning_rate": 0.00026829268292682924,
"loss": 0.5411,
"step": 1500
},
{
"epoch": 0.5478967833156593,
"grad_norm": 1.3890644311904907,
"learning_rate": 0.00026723223753976667,
"loss": 0.5092,
"step": 1550
},
{
"epoch": 0.5655708731000354,
"grad_norm": 1.98700749874115,
"learning_rate": 0.0002661717921527041,
"loss": 0.4804,
"step": 1600
},
{
"epoch": 0.5832449628844114,
"grad_norm": 1.1181468963623047,
"learning_rate": 0.00026511134676564154,
"loss": 0.5148,
"step": 1650
},
{
"epoch": 0.6009190526687875,
"grad_norm": 1.7994420528411865,
"learning_rate": 0.000264050901378579,
"loss": 0.4231,
"step": 1700
},
{
"epoch": 0.6185931424531637,
"grad_norm": 2.032198667526245,
"learning_rate": 0.0002629904559915164,
"loss": 0.5106,
"step": 1750
},
{
"epoch": 0.6362672322375398,
"grad_norm": 3.585948944091797,
"learning_rate": 0.00026193001060445385,
"loss": 0.4717,
"step": 1800
},
{
"epoch": 0.6539413220219159,
"grad_norm": 1.8610371351242065,
"learning_rate": 0.0002608695652173913,
"loss": 0.4765,
"step": 1850
},
{
"epoch": 0.671615411806292,
"grad_norm": 1.2324624061584473,
"learning_rate": 0.0002598091198303287,
"loss": 0.4643,
"step": 1900
},
{
"epoch": 0.689289501590668,
"grad_norm": 2.391714572906494,
"learning_rate": 0.00025874867444326615,
"loss": 0.4512,
"step": 1950
},
{
"epoch": 0.7069635913750442,
"grad_norm": 1.8863242864608765,
"learning_rate": 0.0002576882290562036,
"loss": 0.4115,
"step": 2000
},
{
"epoch": 0.7246376811594203,
"grad_norm": 0.7850649356842041,
"learning_rate": 0.000256627783669141,
"loss": 0.4341,
"step": 2050
},
{
"epoch": 0.7423117709437964,
"grad_norm": 1.5869959592819214,
"learning_rate": 0.00025556733828207846,
"loss": 0.4172,
"step": 2100
},
{
"epoch": 0.7599858607281725,
"grad_norm": 1.2584971189498901,
"learning_rate": 0.0002545068928950159,
"loss": 0.4384,
"step": 2150
},
{
"epoch": 0.7776599505125487,
"grad_norm": 2.560710906982422,
"learning_rate": 0.00025344644750795333,
"loss": 0.4558,
"step": 2200
},
{
"epoch": 0.7953340402969247,
"grad_norm": 2.2893359661102295,
"learning_rate": 0.00025238600212089076,
"loss": 0.4345,
"step": 2250
},
{
"epoch": 0.8130081300813008,
"grad_norm": 1.5244982242584229,
"learning_rate": 0.0002513255567338282,
"loss": 0.4071,
"step": 2300
},
{
"epoch": 0.8306822198656769,
"grad_norm": 1.384102463722229,
"learning_rate": 0.00025026511134676563,
"loss": 0.3612,
"step": 2350
},
{
"epoch": 0.848356309650053,
"grad_norm": 1.3080965280532837,
"learning_rate": 0.00024920466595970307,
"loss": 0.3556,
"step": 2400
},
{
"epoch": 0.8660303994344292,
"grad_norm": 1.3324400186538696,
"learning_rate": 0.00024814422057264045,
"loss": 0.3985,
"step": 2450
},
{
"epoch": 0.8837044892188052,
"grad_norm": 1.7705445289611816,
"learning_rate": 0.00024708377518557794,
"loss": 0.3895,
"step": 2500
},
{
"epoch": 0.9013785790031813,
"grad_norm": 1.352480173110962,
"learning_rate": 0.0002460233297985153,
"loss": 0.426,
"step": 2550
},
{
"epoch": 0.9190526687875574,
"grad_norm": 1.479979157447815,
"learning_rate": 0.0002449628844114528,
"loss": 0.4057,
"step": 2600
},
{
"epoch": 0.9367267585719335,
"grad_norm": 2.1380653381347656,
"learning_rate": 0.00024390243902439022,
"loss": 0.3689,
"step": 2650
},
{
"epoch": 0.9544008483563097,
"grad_norm": 1.9099682569503784,
"learning_rate": 0.00024284199363732768,
"loss": 0.3991,
"step": 2700
},
{
"epoch": 0.9720749381406858,
"grad_norm": 1.399566411972046,
"learning_rate": 0.0002417815482502651,
"loss": 0.3412,
"step": 2750
},
{
"epoch": 0.9897490279250618,
"grad_norm": 2.508267879486084,
"learning_rate": 0.00024072110286320252,
"loss": 0.3828,
"step": 2800
},
{
"epoch": 1.0,
"eval_bertscore_f1": 0.9667777874331811,
"eval_bleu": 0.5973566262792636,
"eval_loss": 0.27053505182266235,
"eval_runtime": 1054.1237,
"eval_samples_per_second": 6.132,
"eval_steps_per_second": 0.767,
"step": 2829
}
],
"logging_steps": 50,
"max_steps": 14145,
"num_input_tokens_seen": 0,
"num_train_epochs": 5,
"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": 3460097079115776.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}