16-clusters-balanced-0 / trainer_state.json
MHGanainy's picture
MHGanainy/16-clusters-balanced-0
3eb8df5 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 5075,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.019704433497536946,
"grad_norm": 0.10910622030496597,
"learning_rate": 6.666666666666667e-06,
"loss": 2.5706,
"step": 100
},
{
"epoch": 0.03940886699507389,
"grad_norm": 0.20892710983753204,
"learning_rate": 1.3333333333333333e-05,
"loss": 2.57,
"step": 200
},
{
"epoch": 0.059113300492610835,
"grad_norm": 0.27884677052497864,
"learning_rate": 2e-05,
"loss": 2.5123,
"step": 300
},
{
"epoch": 0.07881773399014778,
"grad_norm": 0.342856228351593,
"learning_rate": 1.9978364530054465e-05,
"loss": 2.4414,
"step": 400
},
{
"epoch": 0.09852216748768473,
"grad_norm": 0.3985110819339752,
"learning_rate": 1.9913551738929803e-05,
"loss": 2.4046,
"step": 500
},
{
"epoch": 0.11822660098522167,
"grad_norm": 0.41609734296798706,
"learning_rate": 1.9805842077664913e-05,
"loss": 2.4027,
"step": 600
},
{
"epoch": 0.13793103448275862,
"grad_norm": 0.47523200511932373,
"learning_rate": 1.965570161608762e-05,
"loss": 2.366,
"step": 700
},
{
"epoch": 0.15763546798029557,
"grad_norm": 0.5708157420158386,
"learning_rate": 1.9463780026086735e-05,
"loss": 2.3633,
"step": 800
},
{
"epoch": 0.17733990147783252,
"grad_norm": 0.5442431569099426,
"learning_rate": 1.9230907770420737e-05,
"loss": 2.3376,
"step": 900
},
{
"epoch": 0.19704433497536947,
"grad_norm": 0.5139783024787903,
"learning_rate": 1.8958092509227347e-05,
"loss": 2.3146,
"step": 1000
},
{
"epoch": 0.21674876847290642,
"grad_norm": 0.5480104088783264,
"learning_rate": 1.8646514739783404e-05,
"loss": 2.35,
"step": 1100
},
{
"epoch": 0.23645320197044334,
"grad_norm": 0.6360939741134644,
"learning_rate": 1.829752268838222e-05,
"loss": 2.3358,
"step": 1200
},
{
"epoch": 0.2561576354679803,
"grad_norm": 0.5676900148391724,
"learning_rate": 1.7912626476431648e-05,
"loss": 2.3478,
"step": 1300
},
{
"epoch": 0.27586206896551724,
"grad_norm": 0.6030612587928772,
"learning_rate": 1.749349158601686e-05,
"loss": 2.3352,
"step": 1400
},
{
"epoch": 0.2955665024630542,
"grad_norm": 0.629601001739502,
"learning_rate": 1.7041931653202788e-05,
"loss": 2.295,
"step": 1500
},
{
"epoch": 0.31527093596059114,
"grad_norm": 0.6521029472351074,
"learning_rate": 1.6559900620260435e-05,
"loss": 2.3241,
"step": 1600
},
{
"epoch": 0.33497536945812806,
"grad_norm": 0.640565037727356,
"learning_rate": 1.6049484280775012e-05,
"loss": 2.3203,
"step": 1700
},
{
"epoch": 0.35467980295566504,
"grad_norm": 0.6734690070152283,
"learning_rate": 1.5512891254221046e-05,
"loss": 2.2914,
"step": 1800
},
{
"epoch": 0.37438423645320196,
"grad_norm": 0.645145058631897,
"learning_rate": 1.4952443429058334e-05,
"loss": 2.2953,
"step": 1900
},
{
"epoch": 0.39408866995073893,
"grad_norm": 0.5360440611839294,
"learning_rate": 1.437056591570235e-05,
"loss": 2.3016,
"step": 2000
},
{
"epoch": 0.41379310344827586,
"grad_norm": 0.8069554567337036,
"learning_rate": 1.3769776552843532e-05,
"loss": 2.2995,
"step": 2100
},
{
"epoch": 0.43349753694581283,
"grad_norm": 0.8273342847824097,
"learning_rate": 1.3152675012522629e-05,
"loss": 2.3064,
"step": 2200
},
{
"epoch": 0.45320197044334976,
"grad_norm": 0.7718985676765442,
"learning_rate": 1.2521931551105427e-05,
"loss": 2.2789,
"step": 2300
},
{
"epoch": 0.4729064039408867,
"grad_norm": 0.7059099674224854,
"learning_rate": 1.1880275454832493e-05,
"loss": 2.2968,
"step": 2400
},
{
"epoch": 0.49261083743842365,
"grad_norm": 0.7038087844848633,
"learning_rate": 1.1230483229941092e-05,
"loss": 2.2938,
"step": 2500
},
{
"epoch": 0.5123152709359606,
"grad_norm": 0.6673246026039124,
"learning_rate": 1.057536658846171e-05,
"loss": 2.2904,
"step": 2600
},
{
"epoch": 0.5320197044334976,
"grad_norm": 0.6626957654953003,
"learning_rate": 9.917760281675867e-06,
"loss": 2.2847,
"step": 2700
},
{
"epoch": 0.5517241379310345,
"grad_norm": 0.5862464904785156,
"learning_rate": 9.260509833880848e-06,
"loss": 2.3083,
"step": 2800
},
{
"epoch": 0.5714285714285714,
"grad_norm": 0.7855656147003174,
"learning_rate": 8.606459229538645e-06,
"loss": 2.2528,
"step": 2900
},
{
"epoch": 0.5911330049261084,
"grad_norm": 0.6560063362121582,
"learning_rate": 7.958438607087884e-06,
"loss": 2.2603,
"step": 3000
},
{
"epoch": 0.6108374384236454,
"grad_norm": 0.6811918020248413,
"learning_rate": 7.31925201266879e-06,
"loss": 2.2595,
"step": 3100
},
{
"epoch": 0.6305418719211823,
"grad_norm": 0.7110552191734314,
"learning_rate": 6.6916652667519855e-06,
"loss": 2.2942,
"step": 3200
},
{
"epoch": 0.6502463054187192,
"grad_norm": 0.756984531879425,
"learning_rate": 6.078393996173375e-06,
"loss": 2.2998,
"step": 3300
},
{
"epoch": 0.6699507389162561,
"grad_norm": 0.7634550333023071,
"learning_rate": 5.482091883361571e-06,
"loss": 2.2621,
"step": 3400
},
{
"epoch": 0.6896551724137931,
"grad_norm": 0.7362731099128723,
"learning_rate": 4.905339183604614e-06,
"loss": 2.2404,
"step": 3500
},
{
"epoch": 0.7093596059113301,
"grad_norm": 0.6360520124435425,
"learning_rate": 4.350631560042821e-06,
"loss": 2.279,
"step": 3600
},
{
"epoch": 0.729064039408867,
"grad_norm": 0.7496645450592041,
"learning_rate": 3.820369284699823e-06,
"loss": 2.2731,
"step": 3700
},
{
"epoch": 0.7487684729064039,
"grad_norm": 0.6917762160301208,
"learning_rate": 3.316846852279907e-06,
"loss": 2.2594,
"step": 3800
},
{
"epoch": 0.7684729064039408,
"grad_norm": 0.8420236706733704,
"learning_rate": 2.8422430516737733e-06,
"loss": 2.2788,
"step": 3900
},
{
"epoch": 0.7881773399014779,
"grad_norm": 0.7719976902008057,
"learning_rate": 2.3986115381342347e-06,
"loss": 2.2725,
"step": 4000
},
{
"epoch": 0.8078817733990148,
"grad_norm": 0.7222814559936523,
"learning_rate": 1.9878719469169104e-06,
"loss": 2.2757,
"step": 4100
},
{
"epoch": 0.8275862068965517,
"grad_norm": 0.7240573763847351,
"learning_rate": 1.6118015868380387e-06,
"loss": 2.2578,
"step": 4200
},
{
"epoch": 0.8472906403940886,
"grad_norm": 1.020925760269165,
"learning_rate": 1.272027749692203e-06,
"loss": 2.2644,
"step": 4300
},
{
"epoch": 0.8669950738916257,
"grad_norm": 0.7947157025337219,
"learning_rate": 9.700206688077707e-07,
"loss": 2.258,
"step": 4400
},
{
"epoch": 0.8866995073891626,
"grad_norm": 0.7513715028762817,
"learning_rate": 7.070871572091076e-07,
"loss": 2.2852,
"step": 4500
},
{
"epoch": 0.9064039408866995,
"grad_norm": 0.6654150485992432,
"learning_rate": 4.843649529137861e-07,
"loss": 2.2908,
"step": 4600
},
{
"epoch": 0.9261083743842364,
"grad_norm": 1.0206929445266724,
"learning_rate": 3.028177958332512e-07,
"loss": 2.2609,
"step": 4700
},
{
"epoch": 0.9458128078817734,
"grad_norm": 1.0804613828659058,
"learning_rate": 1.6323125757964799e-07,
"loss": 2.2608,
"step": 4800
},
{
"epoch": 0.9655172413793104,
"grad_norm": 0.8179888725280762,
"learning_rate": 6.62093422236132e-08,
"loss": 2.2613,
"step": 4900
},
{
"epoch": 0.9852216748768473,
"grad_norm": 0.8453041911125183,
"learning_rate": 1.2171872711895794e-08,
"loss": 2.2603,
"step": 5000
},
{
"epoch": 1.0,
"step": 5075,
"total_flos": 9.22200279810048e+16,
"train_loss": 2.313905820047914,
"train_runtime": 1612.0801,
"train_samples_per_second": 6.296,
"train_steps_per_second": 3.148
}
],
"logging_steps": 100,
"max_steps": 5075,
"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": 9.22200279810048e+16,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}