ClankerCode-Checkpoint1 / trainer_state.json
coderofpears's picture
Upload folder using huggingface_hub
5a69a54 verified
Raw
History Blame
7.81 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.5213934239254407,
"eval_steps": 500,
"global_step": 2000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.013034835598136018,
"grad_norm": 2.765625,
"learning_rate": 4.936131386861314e-05,
"loss": 1.2665106964111328,
"step": 50
},
{
"epoch": 0.026069671196272036,
"grad_norm": 2.859375,
"learning_rate": 4.870959332638165e-05,
"loss": 1.239681167602539,
"step": 100
},
{
"epoch": 0.03910450679440806,
"grad_norm": 2.59375,
"learning_rate": 4.805787278415016e-05,
"loss": 1.2344681549072265,
"step": 150
},
{
"epoch": 0.05213934239254407,
"grad_norm": 2.6875,
"learning_rate": 4.740615224191866e-05,
"loss": 1.2345462036132813,
"step": 200
},
{
"epoch": 0.0651741779906801,
"grad_norm": 2.25,
"learning_rate": 4.675443169968718e-05,
"loss": 1.222108154296875,
"step": 250
},
{
"epoch": 0.07820901358881611,
"grad_norm": 2.421875,
"learning_rate": 4.6102711157455685e-05,
"loss": 1.2145355224609375,
"step": 300
},
{
"epoch": 0.09124384918695214,
"grad_norm": 2.390625,
"learning_rate": 4.5450990615224195e-05,
"loss": 1.211650161743164,
"step": 350
},
{
"epoch": 0.10427868478508814,
"grad_norm": 2.234375,
"learning_rate": 4.4799270072992706e-05,
"loss": 1.1886522674560547,
"step": 400
},
{
"epoch": 0.11731352038322417,
"grad_norm": 2.875,
"learning_rate": 4.414754953076121e-05,
"loss": 1.1931777954101563,
"step": 450
},
{
"epoch": 0.1303483559813602,
"grad_norm": 2.03125,
"learning_rate": 4.349582898852972e-05,
"loss": 1.191826629638672,
"step": 500
},
{
"epoch": 0.1433831915794962,
"grad_norm": 1.984375,
"learning_rate": 4.284410844629823e-05,
"loss": 1.1870919799804687,
"step": 550
},
{
"epoch": 0.15641802717763223,
"grad_norm": 2.40625,
"learning_rate": 4.2192387904066736e-05,
"loss": 1.1914781188964845,
"step": 600
},
{
"epoch": 0.16945286277576824,
"grad_norm": 2.484375,
"learning_rate": 4.1540667361835246e-05,
"loss": 1.1839387512207031,
"step": 650
},
{
"epoch": 0.18248769837390427,
"grad_norm": 2.28125,
"learning_rate": 4.088894681960376e-05,
"loss": 1.1656275939941407,
"step": 700
},
{
"epoch": 0.19552253397204028,
"grad_norm": 2.15625,
"learning_rate": 4.023722627737226e-05,
"loss": 1.1594437408447265,
"step": 750
},
{
"epoch": 0.2085573695701763,
"grad_norm": 2.265625,
"learning_rate": 3.958550573514077e-05,
"loss": 1.16203369140625,
"step": 800
},
{
"epoch": 0.22159220516831232,
"grad_norm": 2.15625,
"learning_rate": 3.893378519290928e-05,
"loss": 1.172977752685547,
"step": 850
},
{
"epoch": 0.23462704076644833,
"grad_norm": 2.125,
"learning_rate": 3.828206465067779e-05,
"loss": 1.1549080657958983,
"step": 900
},
{
"epoch": 0.24766187636458434,
"grad_norm": 2.46875,
"learning_rate": 3.7630344108446304e-05,
"loss": 1.1490896606445313,
"step": 950
},
{
"epoch": 0.2606967119627204,
"grad_norm": 1.7890625,
"learning_rate": 3.697862356621481e-05,
"loss": 1.1234033966064454,
"step": 1000
},
{
"epoch": 0.2737315475608564,
"grad_norm": 2.34375,
"learning_rate": 3.632690302398332e-05,
"loss": 1.1447408294677734,
"step": 1050
},
{
"epoch": 0.2867663831589924,
"grad_norm": 2.15625,
"learning_rate": 3.567518248175183e-05,
"loss": 1.1448504638671875,
"step": 1100
},
{
"epoch": 0.29980121875712845,
"grad_norm": 1.8828125,
"learning_rate": 3.5023461939520333e-05,
"loss": 1.112318344116211,
"step": 1150
},
{
"epoch": 0.31283605435526446,
"grad_norm": 2.0,
"learning_rate": 3.4371741397288844e-05,
"loss": 1.1291159057617188,
"step": 1200
},
{
"epoch": 0.32587088995340047,
"grad_norm": 2.140625,
"learning_rate": 3.3720020855057355e-05,
"loss": 1.1280142211914062,
"step": 1250
},
{
"epoch": 0.3389057255515365,
"grad_norm": 2.171875,
"learning_rate": 3.306830031282586e-05,
"loss": 1.1144158935546875,
"step": 1300
},
{
"epoch": 0.3519405611496725,
"grad_norm": 2.0625,
"learning_rate": 3.241657977059437e-05,
"loss": 1.1240755462646483,
"step": 1350
},
{
"epoch": 0.36497539674780854,
"grad_norm": 1.8984375,
"learning_rate": 3.176485922836288e-05,
"loss": 1.1407569885253905,
"step": 1400
},
{
"epoch": 0.37801023234594455,
"grad_norm": 2.125,
"learning_rate": 3.111313868613139e-05,
"loss": 1.1473193359375,
"step": 1450
},
{
"epoch": 0.39104506794408056,
"grad_norm": 2.0,
"learning_rate": 3.0461418143899895e-05,
"loss": 1.0902942657470702,
"step": 1500
},
{
"epoch": 0.40407990354221657,
"grad_norm": 2.203125,
"learning_rate": 2.9809697601668406e-05,
"loss": 1.1144374847412108,
"step": 1550
},
{
"epoch": 0.4171147391403526,
"grad_norm": 1.953125,
"learning_rate": 2.9157977059436913e-05,
"loss": 1.0878910827636719,
"step": 1600
},
{
"epoch": 0.43014957473848864,
"grad_norm": 2.0625,
"learning_rate": 2.8506256517205427e-05,
"loss": 1.1090828704833984,
"step": 1650
},
{
"epoch": 0.44318441033662465,
"grad_norm": 2.390625,
"learning_rate": 2.7854535974973935e-05,
"loss": 1.1102208709716797,
"step": 1700
},
{
"epoch": 0.45621924593476065,
"grad_norm": 1.8515625,
"learning_rate": 2.720281543274244e-05,
"loss": 1.118812026977539,
"step": 1750
},
{
"epoch": 0.46925408153289666,
"grad_norm": 2.046875,
"learning_rate": 2.6551094890510953e-05,
"loss": 1.1233943939208983,
"step": 1800
},
{
"epoch": 0.48228891713103267,
"grad_norm": 2.09375,
"learning_rate": 2.589937434827946e-05,
"loss": 1.056346435546875,
"step": 1850
},
{
"epoch": 0.4953237527291687,
"grad_norm": 2.265625,
"learning_rate": 2.5247653806047968e-05,
"loss": 1.0784915924072265,
"step": 1900
},
{
"epoch": 0.5083585883273047,
"grad_norm": 2.015625,
"learning_rate": 2.4595933263816475e-05,
"loss": 1.0717469024658204,
"step": 1950
},
{
"epoch": 0.5213934239254407,
"grad_norm": 2.125,
"learning_rate": 2.3944212721584986e-05,
"loss": 1.0828059387207032,
"step": 2000
}
],
"logging_steps": 50,
"max_steps": 3836,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 1000,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 6.488306500239483e+17,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}