azherali's picture
Training in progress, step 4000, checkpoint
80f7428 verified
raw
history blame
7.84 kB
{
"best_global_step": 4000,
"best_metric": 0.9586218246722099,
"best_model_checkpoint": "CodeGenDetect-CodeBert_Lora/checkpoint-4000",
"epoch": 0.128,
"eval_steps": 4000,
"global_step": 4000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0032,
"grad_norm": 1.3923053741455078,
"learning_rate": 3.96e-06,
"loss": 0.685,
"step": 100
},
{
"epoch": 0.0064,
"grad_norm": 1.665050983428955,
"learning_rate": 7.960000000000002e-06,
"loss": 0.6654,
"step": 200
},
{
"epoch": 0.0096,
"grad_norm": 3.1655123233795166,
"learning_rate": 1.196e-05,
"loss": 0.6169,
"step": 300
},
{
"epoch": 0.0128,
"grad_norm": 3.3807435035705566,
"learning_rate": 1.5960000000000003e-05,
"loss": 0.4635,
"step": 400
},
{
"epoch": 0.016,
"grad_norm": 0.7963143587112427,
"learning_rate": 1.9960000000000002e-05,
"loss": 0.2886,
"step": 500
},
{
"epoch": 0.0192,
"grad_norm": 1.5362155437469482,
"learning_rate": 1.9987287319422154e-05,
"loss": 0.2605,
"step": 600
},
{
"epoch": 0.0224,
"grad_norm": 3.649484395980835,
"learning_rate": 1.9974446227929375e-05,
"loss": 0.2194,
"step": 700
},
{
"epoch": 0.0256,
"grad_norm": 1.402876377105713,
"learning_rate": 1.99616051364366e-05,
"loss": 0.2367,
"step": 800
},
{
"epoch": 0.0288,
"grad_norm": 2.708932399749756,
"learning_rate": 1.994876404494382e-05,
"loss": 0.2061,
"step": 900
},
{
"epoch": 0.032,
"grad_norm": 2.4827463626861572,
"learning_rate": 1.9935922953451046e-05,
"loss": 0.1892,
"step": 1000
},
{
"epoch": 0.0352,
"grad_norm": 0.9402571320533752,
"learning_rate": 1.9923081861958268e-05,
"loss": 0.1819,
"step": 1100
},
{
"epoch": 0.0384,
"grad_norm": 0.8088085055351257,
"learning_rate": 1.9910240770465493e-05,
"loss": 0.1894,
"step": 1200
},
{
"epoch": 0.0416,
"grad_norm": 2.8913955688476562,
"learning_rate": 1.9897399678972714e-05,
"loss": 0.1733,
"step": 1300
},
{
"epoch": 0.0448,
"grad_norm": 1.9755029678344727,
"learning_rate": 1.988455858747994e-05,
"loss": 0.1748,
"step": 1400
},
{
"epoch": 0.048,
"grad_norm": 2.659393310546875,
"learning_rate": 1.987171749598716e-05,
"loss": 0.1557,
"step": 1500
},
{
"epoch": 0.0512,
"grad_norm": 10.118029594421387,
"learning_rate": 1.9858876404494382e-05,
"loss": 0.1702,
"step": 1600
},
{
"epoch": 0.0544,
"grad_norm": 3.736616373062134,
"learning_rate": 1.9846035313001607e-05,
"loss": 0.1694,
"step": 1700
},
{
"epoch": 0.0576,
"grad_norm": 4.140033721923828,
"learning_rate": 1.9833194221508828e-05,
"loss": 0.1615,
"step": 1800
},
{
"epoch": 0.0608,
"grad_norm": 4.504345893859863,
"learning_rate": 1.9820353130016053e-05,
"loss": 0.1425,
"step": 1900
},
{
"epoch": 0.064,
"grad_norm": 5.786899089813232,
"learning_rate": 1.9807512038523274e-05,
"loss": 0.1588,
"step": 2000
},
{
"epoch": 0.0672,
"grad_norm": 9.956130027770996,
"learning_rate": 1.97946709470305e-05,
"loss": 0.1399,
"step": 2100
},
{
"epoch": 0.0704,
"grad_norm": 11.86201286315918,
"learning_rate": 1.978182985553772e-05,
"loss": 0.173,
"step": 2200
},
{
"epoch": 0.0736,
"grad_norm": 0.6308254599571228,
"learning_rate": 1.9768988764044946e-05,
"loss": 0.1428,
"step": 2300
},
{
"epoch": 0.0768,
"grad_norm": 3.123718023300171,
"learning_rate": 1.9756147672552167e-05,
"loss": 0.1365,
"step": 2400
},
{
"epoch": 0.08,
"grad_norm": 3.8000500202178955,
"learning_rate": 1.9743306581059392e-05,
"loss": 0.1528,
"step": 2500
},
{
"epoch": 0.0832,
"grad_norm": 2.9149184226989746,
"learning_rate": 1.9730465489566613e-05,
"loss": 0.1568,
"step": 2600
},
{
"epoch": 0.0864,
"grad_norm": 8.345555305480957,
"learning_rate": 1.9717624398073838e-05,
"loss": 0.139,
"step": 2700
},
{
"epoch": 0.0896,
"grad_norm": 1.785736322402954,
"learning_rate": 1.970478330658106e-05,
"loss": 0.1509,
"step": 2800
},
{
"epoch": 0.0928,
"grad_norm": 5.256857872009277,
"learning_rate": 1.9691942215088284e-05,
"loss": 0.1284,
"step": 2900
},
{
"epoch": 0.096,
"grad_norm": 2.305225133895874,
"learning_rate": 1.967910112359551e-05,
"loss": 0.1249,
"step": 3000
},
{
"epoch": 0.0992,
"grad_norm": 1.1149404048919678,
"learning_rate": 1.966626003210273e-05,
"loss": 0.1223,
"step": 3100
},
{
"epoch": 0.1024,
"grad_norm": 0.24498392641544342,
"learning_rate": 1.9653418940609955e-05,
"loss": 0.1415,
"step": 3200
},
{
"epoch": 0.1056,
"grad_norm": 3.027209520339966,
"learning_rate": 1.9640577849117177e-05,
"loss": 0.133,
"step": 3300
},
{
"epoch": 0.1088,
"grad_norm": 10.783885955810547,
"learning_rate": 1.9627736757624402e-05,
"loss": 0.1309,
"step": 3400
},
{
"epoch": 0.112,
"grad_norm": 7.116244316101074,
"learning_rate": 1.9614895666131623e-05,
"loss": 0.1056,
"step": 3500
},
{
"epoch": 0.1152,
"grad_norm": 8.193492889404297,
"learning_rate": 1.9602054574638848e-05,
"loss": 0.1201,
"step": 3600
},
{
"epoch": 0.1184,
"grad_norm": 0.9174596071243286,
"learning_rate": 1.958921348314607e-05,
"loss": 0.12,
"step": 3700
},
{
"epoch": 0.1216,
"grad_norm": 3.436502695083618,
"learning_rate": 1.957637239165329e-05,
"loss": 0.1257,
"step": 3800
},
{
"epoch": 0.1248,
"grad_norm": 9.131117820739746,
"learning_rate": 1.9563531300160516e-05,
"loss": 0.1139,
"step": 3900
},
{
"epoch": 0.128,
"grad_norm": 0.3150777518749237,
"learning_rate": 1.9550690208667737e-05,
"loss": 0.1381,
"step": 4000
},
{
"epoch": 0.128,
"eval_accuracy": 0.9586,
"eval_f1": 0.9586218246722099,
"eval_loss": 0.1626722663640976,
"eval_precision": 0.9598553600795934,
"eval_recall": 0.9586,
"eval_runtime": 815.7025,
"eval_samples_per_second": 122.594,
"eval_steps_per_second": 7.662,
"step": 4000
}
],
"logging_steps": 100,
"max_steps": 156250,
"num_input_tokens_seen": 0,
"num_train_epochs": 5,
"save_steps": 4000,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 3,
"early_stopping_threshold": 0.0
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1.6992838343814144e+16,
"train_batch_size": 16,
"trial_name": null,
"trial_params": null
}