dzungpham's picture
Upload training checkpoints and best model
9f5da22 verified
raw
history blame
10.2 kB
{
"best_global_step": 500,
"best_metric": 0.8730387325792941,
"best_model_checkpoint": "taskA-unixcoder-focal/checkpoint-500",
"epoch": 0.030588523186100575,
"eval_steps": 500,
"global_step": 500,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0006117704637220115,
"grad_norm": 5.2196149826049805,
"learning_rate": 9.178990311065784e-08,
"loss": 0.2114,
"step": 10
},
{
"epoch": 0.001223540927444023,
"grad_norm": 2.4952661991119385,
"learning_rate": 1.937786843447221e-07,
"loss": 0.179,
"step": 20
},
{
"epoch": 0.0018353113911660345,
"grad_norm": 3.8488683700561523,
"learning_rate": 2.9576746557878637e-07,
"loss": 0.1949,
"step": 30
},
{
"epoch": 0.002447081854888046,
"grad_norm": 3.7437973022460938,
"learning_rate": 3.9775624681285064e-07,
"loss": 0.2007,
"step": 40
},
{
"epoch": 0.0030588523186100575,
"grad_norm": 3.8342156410217285,
"learning_rate": 4.997450280469149e-07,
"loss": 0.1828,
"step": 50
},
{
"epoch": 0.003670622782332069,
"grad_norm": 3.510793685913086,
"learning_rate": 6.017338092809792e-07,
"loss": 0.1875,
"step": 60
},
{
"epoch": 0.0042823932460540805,
"grad_norm": 3.223860740661621,
"learning_rate": 7.037225905150434e-07,
"loss": 0.1661,
"step": 70
},
{
"epoch": 0.004894163709776092,
"grad_norm": 3.791808605194092,
"learning_rate": 8.057113717491076e-07,
"loss": 0.1762,
"step": 80
},
{
"epoch": 0.0055059341734981036,
"grad_norm": 3.8649113178253174,
"learning_rate": 9.077001529831719e-07,
"loss": 0.1774,
"step": 90
},
{
"epoch": 0.006117704637220115,
"grad_norm": 2.9645302295684814,
"learning_rate": 1.0096889342172361e-06,
"loss": 0.1741,
"step": 100
},
{
"epoch": 0.006729475100942127,
"grad_norm": 2.9103174209594727,
"learning_rate": 1.1116777154513005e-06,
"loss": 0.1808,
"step": 110
},
{
"epoch": 0.007341245564664138,
"grad_norm": 2.3954272270202637,
"learning_rate": 1.2136664966853646e-06,
"loss": 0.161,
"step": 120
},
{
"epoch": 0.00795301602838615,
"grad_norm": 3.030513048171997,
"learning_rate": 1.3156552779194289e-06,
"loss": 0.1689,
"step": 130
},
{
"epoch": 0.008564786492108161,
"grad_norm": 1.7593587636947632,
"learning_rate": 1.4176440591534932e-06,
"loss": 0.1595,
"step": 140
},
{
"epoch": 0.009176556955830173,
"grad_norm": 1.9787609577178955,
"learning_rate": 1.5196328403875573e-06,
"loss": 0.1429,
"step": 150
},
{
"epoch": 0.009788327419552184,
"grad_norm": 2.549748659133911,
"learning_rate": 1.6216216216216219e-06,
"loss": 0.154,
"step": 160
},
{
"epoch": 0.010400097883274196,
"grad_norm": 2.4056687355041504,
"learning_rate": 1.723610402855686e-06,
"loss": 0.1582,
"step": 170
},
{
"epoch": 0.011011868346996207,
"grad_norm": 3.3082435131073,
"learning_rate": 1.8255991840897503e-06,
"loss": 0.1502,
"step": 180
},
{
"epoch": 0.011623638810718219,
"grad_norm": 3.446185350418091,
"learning_rate": 1.9275879653238146e-06,
"loss": 0.1452,
"step": 190
},
{
"epoch": 0.01223540927444023,
"grad_norm": 2.6021993160247803,
"learning_rate": 2.029576746557879e-06,
"loss": 0.1404,
"step": 200
},
{
"epoch": 0.012847179738162242,
"grad_norm": 2.1967263221740723,
"learning_rate": 2.1315655277919432e-06,
"loss": 0.1421,
"step": 210
},
{
"epoch": 0.013458950201884253,
"grad_norm": 1.9831513166427612,
"learning_rate": 2.233554309026007e-06,
"loss": 0.1431,
"step": 220
},
{
"epoch": 0.014070720665606265,
"grad_norm": 1.7445921897888184,
"learning_rate": 2.3355430902600715e-06,
"loss": 0.1242,
"step": 230
},
{
"epoch": 0.014682491129328276,
"grad_norm": 2.7725071907043457,
"learning_rate": 2.4375318714941358e-06,
"loss": 0.1346,
"step": 240
},
{
"epoch": 0.015294261593050288,
"grad_norm": 1.7258802652359009,
"learning_rate": 2.5395206527282e-06,
"loss": 0.1371,
"step": 250
},
{
"epoch": 0.0159060320567723,
"grad_norm": 2.1158506870269775,
"learning_rate": 2.6415094339622644e-06,
"loss": 0.1271,
"step": 260
},
{
"epoch": 0.01651780252049431,
"grad_norm": 2.0771985054016113,
"learning_rate": 2.7434982151963283e-06,
"loss": 0.1214,
"step": 270
},
{
"epoch": 0.017129572984216322,
"grad_norm": 2.924894332885742,
"learning_rate": 2.8454869964303926e-06,
"loss": 0.1281,
"step": 280
},
{
"epoch": 0.017741343447938332,
"grad_norm": 2.122687578201294,
"learning_rate": 2.947475777664457e-06,
"loss": 0.132,
"step": 290
},
{
"epoch": 0.018353113911660345,
"grad_norm": 3.2565481662750244,
"learning_rate": 3.0494645588985217e-06,
"loss": 0.1336,
"step": 300
},
{
"epoch": 0.018964884375382355,
"grad_norm": 1.2805263996124268,
"learning_rate": 3.151453340132586e-06,
"loss": 0.1183,
"step": 310
},
{
"epoch": 0.019576654839104368,
"grad_norm": 2.420628786087036,
"learning_rate": 3.25344212136665e-06,
"loss": 0.1125,
"step": 320
},
{
"epoch": 0.020188425302826378,
"grad_norm": 2.887117862701416,
"learning_rate": 3.3554309026007142e-06,
"loss": 0.1041,
"step": 330
},
{
"epoch": 0.02080019576654839,
"grad_norm": 1.6021567583084106,
"learning_rate": 3.4574196838347786e-06,
"loss": 0.1221,
"step": 340
},
{
"epoch": 0.0214119662302704,
"grad_norm": 2.9132304191589355,
"learning_rate": 3.5594084650688425e-06,
"loss": 0.1094,
"step": 350
},
{
"epoch": 0.022023736693992414,
"grad_norm": 2.5460691452026367,
"learning_rate": 3.6613972463029068e-06,
"loss": 0.1096,
"step": 360
},
{
"epoch": 0.022635507157714424,
"grad_norm": 2.2170896530151367,
"learning_rate": 3.763386027536971e-06,
"loss": 0.0933,
"step": 370
},
{
"epoch": 0.023247277621436437,
"grad_norm": 3.799591541290283,
"learning_rate": 3.865374808771036e-06,
"loss": 0.1142,
"step": 380
},
{
"epoch": 0.023859048085158447,
"grad_norm": 4.609161376953125,
"learning_rate": 3.9673635900051e-06,
"loss": 0.0948,
"step": 390
},
{
"epoch": 0.02447081854888046,
"grad_norm": 3.329650402069092,
"learning_rate": 4.0693523712391645e-06,
"loss": 0.0944,
"step": 400
},
{
"epoch": 0.02508258901260247,
"grad_norm": 2.135805368423462,
"learning_rate": 4.171341152473228e-06,
"loss": 0.0847,
"step": 410
},
{
"epoch": 0.025694359476324483,
"grad_norm": 2.006049156188965,
"learning_rate": 4.273329933707292e-06,
"loss": 0.1077,
"step": 420
},
{
"epoch": 0.026306129940046493,
"grad_norm": 5.709030628204346,
"learning_rate": 4.375318714941357e-06,
"loss": 0.099,
"step": 430
},
{
"epoch": 0.026917900403768506,
"grad_norm": 2.466867446899414,
"learning_rate": 4.477307496175421e-06,
"loss": 0.0771,
"step": 440
},
{
"epoch": 0.027529670867490516,
"grad_norm": 2.3829548358917236,
"learning_rate": 4.579296277409485e-06,
"loss": 0.0802,
"step": 450
},
{
"epoch": 0.02814144133121253,
"grad_norm": 2.990241050720215,
"learning_rate": 4.6812850586435496e-06,
"loss": 0.1048,
"step": 460
},
{
"epoch": 0.02875321179493454,
"grad_norm": 3.7126529216766357,
"learning_rate": 4.783273839877614e-06,
"loss": 0.0879,
"step": 470
},
{
"epoch": 0.029364982258656552,
"grad_norm": 2.6238865852355957,
"learning_rate": 4.885262621111678e-06,
"loss": 0.0825,
"step": 480
},
{
"epoch": 0.029976752722378562,
"grad_norm": 2.1882681846618652,
"learning_rate": 4.987251402345742e-06,
"loss": 0.0821,
"step": 490
},
{
"epoch": 0.030588523186100575,
"grad_norm": 2.1399929523468018,
"learning_rate": 5.089240183579807e-06,
"loss": 0.0926,
"step": 500
},
{
"epoch": 0.030588523186100575,
"eval_accuracy": 0.8732,
"eval_f1_weighted": 0.8728301347090768,
"eval_loss": 0.08081420511007309,
"eval_macro_f1": 0.8730387325792941,
"eval_precision": 0.8842823474890878,
"eval_recall": 0.8732,
"eval_runtime": 1731.362,
"eval_samples_per_second": 57.758,
"eval_steps_per_second": 0.903,
"step": 500
}
],
"logging_steps": 10,
"max_steps": 16346,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 500,
"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": 4207556886230400.0,
"train_batch_size": 32,
"trial_name": null,
"trial_params": null
}