hft3 / trainer_state.json
SatyaSriVelpuri's picture
Upload trainer_state.json with huggingface_hub
700436e verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.6835016835016834,
"eval_steps": 500,
"global_step": 1000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.04208754208754209,
"grad_norm": 44.5,
"learning_rate": 2.222222222222222e-06,
"loss": 9.708373413085937,
"step": 25
},
{
"epoch": 0.08417508417508418,
"grad_norm": 20.5,
"learning_rate": 4.537037037037038e-06,
"loss": 7.022988891601562,
"step": 50
},
{
"epoch": 0.12626262626262627,
"grad_norm": 13.375,
"learning_rate": 4.94212962962963e-06,
"loss": 4.4798516845703125,
"step": 75
},
{
"epoch": 0.16835016835016836,
"grad_norm": 35.75,
"learning_rate": 4.869791666666667e-06,
"loss": 3.579981384277344,
"step": 100
},
{
"epoch": 0.21043771043771045,
"grad_norm": 33.0,
"learning_rate": 4.797453703703704e-06,
"loss": 2.9001919555664064,
"step": 125
},
{
"epoch": 0.25252525252525254,
"grad_norm": 38.5,
"learning_rate": 4.725115740740741e-06,
"loss": 2.722982177734375,
"step": 150
},
{
"epoch": 0.2946127946127946,
"grad_norm": 98.0,
"learning_rate": 4.652777777777779e-06,
"loss": 2.658799133300781,
"step": 175
},
{
"epoch": 0.3367003367003367,
"grad_norm": 37.5,
"learning_rate": 4.580439814814815e-06,
"loss": 2.5711898803710938,
"step": 200
},
{
"epoch": 0.3787878787878788,
"grad_norm": 148.0,
"learning_rate": 4.508101851851852e-06,
"loss": 2.5608544921875,
"step": 225
},
{
"epoch": 0.4208754208754209,
"grad_norm": 100.0,
"learning_rate": 4.435763888888889e-06,
"loss": 2.5246621704101564,
"step": 250
},
{
"epoch": 0.46296296296296297,
"grad_norm": 111.0,
"learning_rate": 4.363425925925927e-06,
"loss": 2.504690399169922,
"step": 275
},
{
"epoch": 0.5050505050505051,
"grad_norm": 74.5,
"learning_rate": 4.2910879629629634e-06,
"loss": 2.456527099609375,
"step": 300
},
{
"epoch": 0.5471380471380471,
"grad_norm": 84.0,
"learning_rate": 4.21875e-06,
"loss": 2.476842498779297,
"step": 325
},
{
"epoch": 0.5892255892255892,
"grad_norm": 26.125,
"learning_rate": 4.1464120370370375e-06,
"loss": 2.447265930175781,
"step": 350
},
{
"epoch": 0.6313131313131313,
"grad_norm": 38.5,
"learning_rate": 4.074074074074074e-06,
"loss": 2.3707008361816406,
"step": 375
},
{
"epoch": 0.6734006734006734,
"grad_norm": 23.375,
"learning_rate": 4.001736111111112e-06,
"loss": 2.374063720703125,
"step": 400
},
{
"epoch": 0.7154882154882155,
"grad_norm": 21.875,
"learning_rate": 3.929398148148148e-06,
"loss": 2.3581019592285157,
"step": 425
},
{
"epoch": 0.7575757575757576,
"grad_norm": 21.25,
"learning_rate": 3.857060185185186e-06,
"loss": 2.3752615356445315,
"step": 450
},
{
"epoch": 0.7996632996632996,
"grad_norm": 48.0,
"learning_rate": 3.7847222222222224e-06,
"loss": 2.309081726074219,
"step": 475
},
{
"epoch": 0.8417508417508418,
"grad_norm": 17.375,
"learning_rate": 3.7123842592592594e-06,
"loss": 2.265882568359375,
"step": 500
},
{
"epoch": 0.8838383838383839,
"grad_norm": 38.5,
"learning_rate": 3.640046296296297e-06,
"loss": 2.245345458984375,
"step": 525
},
{
"epoch": 0.9259259259259259,
"grad_norm": 26.875,
"learning_rate": 3.5677083333333335e-06,
"loss": 2.2155528259277344,
"step": 550
},
{
"epoch": 0.968013468013468,
"grad_norm": 40.0,
"learning_rate": 3.4953703703703706e-06,
"loss": 2.2166319274902344,
"step": 575
},
{
"epoch": 1.0101010101010102,
"grad_norm": 141.0,
"learning_rate": 3.423032407407408e-06,
"loss": 2.2579159545898437,
"step": 600
},
{
"epoch": 1.0521885521885521,
"grad_norm": 19.75,
"learning_rate": 3.3506944444444447e-06,
"loss": 2.1792347717285154,
"step": 625
},
{
"epoch": 1.0942760942760943,
"grad_norm": 159.0,
"learning_rate": 3.2783564814814817e-06,
"loss": 2.1700653076171874,
"step": 650
},
{
"epoch": 1.1363636363636362,
"grad_norm": 26.125,
"learning_rate": 3.2060185185185188e-06,
"loss": 2.1729795837402346,
"step": 675
},
{
"epoch": 1.1784511784511784,
"grad_norm": 112.0,
"learning_rate": 3.1336805555555562e-06,
"loss": 2.1509564208984373,
"step": 700
},
{
"epoch": 1.2205387205387206,
"grad_norm": 18.5,
"learning_rate": 3.061342592592593e-06,
"loss": 2.1331724548339843,
"step": 725
},
{
"epoch": 1.2626262626262625,
"grad_norm": 72.0,
"learning_rate": 2.98900462962963e-06,
"loss": 2.0941813659667967,
"step": 750
},
{
"epoch": 1.3047138047138047,
"grad_norm": 56.0,
"learning_rate": 2.916666666666667e-06,
"loss": 2.122632598876953,
"step": 775
},
{
"epoch": 1.3468013468013469,
"grad_norm": 22.75,
"learning_rate": 2.8443287037037036e-06,
"loss": 2.120499572753906,
"step": 800
},
{
"epoch": 1.3888888888888888,
"grad_norm": 27.5,
"learning_rate": 2.771990740740741e-06,
"loss": 2.1208335876464846,
"step": 825
},
{
"epoch": 1.430976430976431,
"grad_norm": 19.125,
"learning_rate": 2.699652777777778e-06,
"loss": 2.1359043884277344,
"step": 850
},
{
"epoch": 1.4730639730639732,
"grad_norm": 18.5,
"learning_rate": 2.6273148148148148e-06,
"loss": 2.1154779052734374,
"step": 875
},
{
"epoch": 1.5151515151515151,
"grad_norm": 25.625,
"learning_rate": 2.554976851851852e-06,
"loss": 2.107982635498047,
"step": 900
},
{
"epoch": 1.557239057239057,
"grad_norm": 17.375,
"learning_rate": 2.4826388888888893e-06,
"loss": 2.086489410400391,
"step": 925
},
{
"epoch": 1.5993265993265995,
"grad_norm": 23.125,
"learning_rate": 2.410300925925926e-06,
"loss": 2.1238157653808596,
"step": 950
},
{
"epoch": 1.6414141414141414,
"grad_norm": 17.25,
"learning_rate": 2.3379629629629634e-06,
"loss": 2.0812089538574217,
"step": 975
},
{
"epoch": 1.6835016835016834,
"grad_norm": 19.5,
"learning_rate": 2.265625e-06,
"loss": 2.041307220458984,
"step": 1000
}
],
"logging_steps": 25,
"max_steps": 1782,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 9.185883303947796e+17,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}