dima806's picture
Upload folder using huggingface_hub
85c6868 verified
{
"best_metric": 0.0018343485426157713,
"best_model_checkpoint": "crime_cctv_image_detection/checkpoint-35616",
"epoch": 1.0,
"eval_steps": 500,
"global_step": 35616,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01403863432165319,
"grad_norm": 2.2540955543518066,
"learning_rate": 4.936737333408312e-06,
"loss": 0.3677,
"step": 500
},
{
"epoch": 0.02807726864330638,
"grad_norm": 0.3683418333530426,
"learning_rate": 4.866445481639769e-06,
"loss": 0.1387,
"step": 1000
},
{
"epoch": 0.04211590296495957,
"grad_norm": 2.055499315261841,
"learning_rate": 4.796153629871226e-06,
"loss": 0.0746,
"step": 1500
},
{
"epoch": 0.05615453728661276,
"grad_norm": 0.4821561276912689,
"learning_rate": 4.725861778102682e-06,
"loss": 0.0555,
"step": 2000
},
{
"epoch": 0.07019317160826595,
"grad_norm": 0.058730773627758026,
"learning_rate": 4.65556992633414e-06,
"loss": 0.0372,
"step": 2500
},
{
"epoch": 0.08423180592991913,
"grad_norm": 0.047011394053697586,
"learning_rate": 4.585278074565597e-06,
"loss": 0.0316,
"step": 3000
},
{
"epoch": 0.09827044025157233,
"grad_norm": 0.07243060320615768,
"learning_rate": 4.514986222797054e-06,
"loss": 0.0252,
"step": 3500
},
{
"epoch": 0.11230907457322552,
"grad_norm": 1.2735100984573364,
"learning_rate": 4.44469437102851e-06,
"loss": 0.0215,
"step": 4000
},
{
"epoch": 0.1263477088948787,
"grad_norm": 0.06371872127056122,
"learning_rate": 4.3744025192599675e-06,
"loss": 0.0197,
"step": 4500
},
{
"epoch": 0.1403863432165319,
"grad_norm": 0.02829303778707981,
"learning_rate": 4.304110667491425e-06,
"loss": 0.0173,
"step": 5000
},
{
"epoch": 0.1544249775381851,
"grad_norm": 0.8642438054084778,
"learning_rate": 4.233818815722882e-06,
"loss": 0.0204,
"step": 5500
},
{
"epoch": 0.16846361185983827,
"grad_norm": 1.70051109790802,
"learning_rate": 4.163526963954338e-06,
"loss": 0.0168,
"step": 6000
},
{
"epoch": 0.18250224618149147,
"grad_norm": 0.022161871194839478,
"learning_rate": 4.093235112185795e-06,
"loss": 0.0142,
"step": 6500
},
{
"epoch": 0.19654088050314467,
"grad_norm": 0.01454980205744505,
"learning_rate": 4.022943260417253e-06,
"loss": 0.0143,
"step": 7000
},
{
"epoch": 0.21057951482479784,
"grad_norm": 0.013489379547536373,
"learning_rate": 3.95265140864871e-06,
"loss": 0.0185,
"step": 7500
},
{
"epoch": 0.22461814914645103,
"grad_norm": 0.030154425650835037,
"learning_rate": 3.882359556880167e-06,
"loss": 0.0079,
"step": 8000
},
{
"epoch": 0.23865678346810423,
"grad_norm": 0.008808434009552002,
"learning_rate": 3.812067705111624e-06,
"loss": 0.0078,
"step": 8500
},
{
"epoch": 0.2526954177897574,
"grad_norm": 0.041154589504003525,
"learning_rate": 3.741775853343081e-06,
"loss": 0.0113,
"step": 9000
},
{
"epoch": 0.2667340521114106,
"grad_norm": 0.06076955050230026,
"learning_rate": 3.671484001574538e-06,
"loss": 0.0095,
"step": 9500
},
{
"epoch": 0.2807726864330638,
"grad_norm": 11.470385551452637,
"learning_rate": 3.6011921498059948e-06,
"loss": 0.0095,
"step": 10000
},
{
"epoch": 0.294811320754717,
"grad_norm": 0.028795696794986725,
"learning_rate": 3.530900298037452e-06,
"loss": 0.0069,
"step": 10500
},
{
"epoch": 0.3088499550763702,
"grad_norm": 0.005583739373832941,
"learning_rate": 3.4606084462689087e-06,
"loss": 0.0074,
"step": 11000
},
{
"epoch": 0.32288858939802334,
"grad_norm": 28.45262908935547,
"learning_rate": 3.390316594500366e-06,
"loss": 0.0062,
"step": 11500
},
{
"epoch": 0.33692722371967654,
"grad_norm": 0.004062952473759651,
"learning_rate": 3.3200247427318226e-06,
"loss": 0.0074,
"step": 12000
},
{
"epoch": 0.35096585804132974,
"grad_norm": 0.0044929939322173595,
"learning_rate": 3.24973289096328e-06,
"loss": 0.0051,
"step": 12500
},
{
"epoch": 0.36500449236298294,
"grad_norm": 0.004134790506213903,
"learning_rate": 3.1794410391947366e-06,
"loss": 0.0078,
"step": 13000
},
{
"epoch": 0.37904312668463613,
"grad_norm": 7.079535007476807,
"learning_rate": 3.1091491874261938e-06,
"loss": 0.0061,
"step": 13500
},
{
"epoch": 0.39308176100628933,
"grad_norm": 0.004242467228323221,
"learning_rate": 3.0388573356576505e-06,
"loss": 0.0047,
"step": 14000
},
{
"epoch": 0.4071203953279425,
"grad_norm": 0.002898386912420392,
"learning_rate": 2.9685654838891077e-06,
"loss": 0.0061,
"step": 14500
},
{
"epoch": 0.4211590296495957,
"grad_norm": 0.003967393655329943,
"learning_rate": 2.8982736321205645e-06,
"loss": 0.0047,
"step": 15000
},
{
"epoch": 0.43519766397124887,
"grad_norm": 0.012381095439195633,
"learning_rate": 2.827981780352022e-06,
"loss": 0.0053,
"step": 15500
},
{
"epoch": 0.44923629829290207,
"grad_norm": 0.004116687458008528,
"learning_rate": 2.7576899285834793e-06,
"loss": 0.0039,
"step": 16000
},
{
"epoch": 0.46327493261455527,
"grad_norm": 0.0028485700022429228,
"learning_rate": 2.687398076814936e-06,
"loss": 0.005,
"step": 16500
},
{
"epoch": 0.47731356693620847,
"grad_norm": 0.003679895307868719,
"learning_rate": 2.617106225046393e-06,
"loss": 0.0083,
"step": 17000
},
{
"epoch": 0.4913522012578616,
"grad_norm": 0.0029314851853996515,
"learning_rate": 2.54681437327785e-06,
"loss": 0.0049,
"step": 17500
},
{
"epoch": 0.5053908355795148,
"grad_norm": 0.0026076321955770254,
"learning_rate": 2.476522521509307e-06,
"loss": 0.0019,
"step": 18000
},
{
"epoch": 0.519429469901168,
"grad_norm": 0.31449854373931885,
"learning_rate": 2.406230669740764e-06,
"loss": 0.006,
"step": 18500
},
{
"epoch": 0.5334681042228212,
"grad_norm": 0.0019357282435521483,
"learning_rate": 2.335938817972221e-06,
"loss": 0.0044,
"step": 19000
},
{
"epoch": 0.5475067385444744,
"grad_norm": 0.0032386407256126404,
"learning_rate": 2.265646966203678e-06,
"loss": 0.0033,
"step": 19500
},
{
"epoch": 0.5615453728661276,
"grad_norm": 0.0018261801451444626,
"learning_rate": 2.195355114435135e-06,
"loss": 0.0034,
"step": 20000
},
{
"epoch": 0.5755840071877808,
"grad_norm": 0.004736597184091806,
"learning_rate": 2.1250632626665918e-06,
"loss": 0.0031,
"step": 20500
},
{
"epoch": 0.589622641509434,
"grad_norm": 0.0029593773651868105,
"learning_rate": 2.054771410898049e-06,
"loss": 0.0043,
"step": 21000
},
{
"epoch": 0.6036612758310872,
"grad_norm": 0.005192001815885305,
"learning_rate": 1.9844795591295057e-06,
"loss": 0.0036,
"step": 21500
},
{
"epoch": 0.6176999101527404,
"grad_norm": 0.0015726613346487284,
"learning_rate": 1.914187707360963e-06,
"loss": 0.0031,
"step": 22000
},
{
"epoch": 0.6317385444743935,
"grad_norm": 0.03450402989983559,
"learning_rate": 1.8438958555924199e-06,
"loss": 0.0023,
"step": 22500
},
{
"epoch": 0.6457771787960467,
"grad_norm": 0.0018297949573025107,
"learning_rate": 1.7736040038238768e-06,
"loss": 0.0021,
"step": 23000
},
{
"epoch": 0.6598158131176999,
"grad_norm": 0.0027218444738537073,
"learning_rate": 1.7033121520553338e-06,
"loss": 0.0029,
"step": 23500
},
{
"epoch": 0.6738544474393531,
"grad_norm": 0.003406788455322385,
"learning_rate": 1.6330203002867908e-06,
"loss": 0.0035,
"step": 24000
},
{
"epoch": 0.6878930817610063,
"grad_norm": 0.0023123128339648247,
"learning_rate": 1.5627284485182477e-06,
"loss": 0.0021,
"step": 24500
},
{
"epoch": 0.7019317160826595,
"grad_norm": 0.031573791056871414,
"learning_rate": 1.4924365967497047e-06,
"loss": 0.0036,
"step": 25000
},
{
"epoch": 0.7159703504043127,
"grad_norm": 0.0018060826696455479,
"learning_rate": 1.4221447449811619e-06,
"loss": 0.0016,
"step": 25500
},
{
"epoch": 0.7300089847259659,
"grad_norm": 0.0012375499354675412,
"learning_rate": 1.351852893212619e-06,
"loss": 0.0025,
"step": 26000
},
{
"epoch": 0.7440476190476191,
"grad_norm": 0.001357385073788464,
"learning_rate": 1.281561041444076e-06,
"loss": 0.0022,
"step": 26500
},
{
"epoch": 0.7580862533692723,
"grad_norm": 0.07056614011526108,
"learning_rate": 1.211269189675533e-06,
"loss": 0.0026,
"step": 27000
},
{
"epoch": 0.7721248876909255,
"grad_norm": 0.0016634552739560604,
"learning_rate": 1.14097733790699e-06,
"loss": 0.0008,
"step": 27500
},
{
"epoch": 0.7861635220125787,
"grad_norm": 0.0011704576900228858,
"learning_rate": 1.070685486138447e-06,
"loss": 0.0021,
"step": 28000
},
{
"epoch": 0.8002021563342318,
"grad_norm": 0.0016124300891533494,
"learning_rate": 1.000393634369904e-06,
"loss": 0.0016,
"step": 28500
},
{
"epoch": 0.814240790655885,
"grad_norm": 0.0013027675449848175,
"learning_rate": 9.301017826013609e-07,
"loss": 0.0016,
"step": 29000
},
{
"epoch": 0.8282794249775381,
"grad_norm": 0.0010345893679186702,
"learning_rate": 8.59809930832818e-07,
"loss": 0.0015,
"step": 29500
},
{
"epoch": 0.8423180592991913,
"grad_norm": 0.0011269532842561603,
"learning_rate": 7.895180790642749e-07,
"loss": 0.0019,
"step": 30000
},
{
"epoch": 0.8563566936208445,
"grad_norm": 0.0012310410384088755,
"learning_rate": 7.192262272957319e-07,
"loss": 0.0015,
"step": 30500
},
{
"epoch": 0.8703953279424977,
"grad_norm": 0.000949531386140734,
"learning_rate": 6.489343755271889e-07,
"loss": 0.0026,
"step": 31000
},
{
"epoch": 0.8844339622641509,
"grad_norm": 0.0009439759887754917,
"learning_rate": 5.78642523758646e-07,
"loss": 0.0017,
"step": 31500
},
{
"epoch": 0.8984725965858041,
"grad_norm": 0.0011304657673463225,
"learning_rate": 5.083506719901029e-07,
"loss": 0.0013,
"step": 32000
},
{
"epoch": 0.9125112309074573,
"grad_norm": 0.001100945402868092,
"learning_rate": 4.3805882022155994e-07,
"loss": 0.0035,
"step": 32500
},
{
"epoch": 0.9265498652291105,
"grad_norm": 0.0013464086223393679,
"learning_rate": 3.6776696845301697e-07,
"loss": 0.0005,
"step": 33000
},
{
"epoch": 0.9405884995507637,
"grad_norm": 0.20621608197689056,
"learning_rate": 2.9747511668447394e-07,
"loss": 0.0019,
"step": 33500
},
{
"epoch": 0.9546271338724169,
"grad_norm": 0.0010597273940220475,
"learning_rate": 2.2718326491593096e-07,
"loss": 0.0012,
"step": 34000
},
{
"epoch": 0.9686657681940701,
"grad_norm": 0.0010197610827162862,
"learning_rate": 1.5689141314738796e-07,
"loss": 0.0023,
"step": 34500
},
{
"epoch": 0.9827044025157232,
"grad_norm": 0.001147901057265699,
"learning_rate": 8.659956137884498e-08,
"loss": 0.0013,
"step": 35000
},
{
"epoch": 0.9967430368373764,
"grad_norm": 0.0009662679512985051,
"learning_rate": 1.6307709610301975e-08,
"loss": 0.0017,
"step": 35500
},
{
"epoch": 1.0,
"eval_accuracy": 0.9994630236506495,
"eval_loss": 0.0018343485426157713,
"eval_model_preparation_time": 0.0057,
"eval_runtime": 1346.829,
"eval_samples_per_second": 94.025,
"eval_steps_per_second": 11.754,
"step": 35616
}
],
"logging_steps": 500,
"max_steps": 35616,
"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": 8.831839548364666e+19,
"train_batch_size": 32,
"trial_name": null,
"trial_params": null
}