fasthypernet-16k2 / checkpoint-300 /trainer_state.json
aixk's picture
Upload folder using huggingface_hub
6fcf022 verified
Raw
History Blame Contribute Delete
5.89 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.0008786876507040851,
"eval_steps": 500,
"global_step": 300,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 2.9289588356802836e-05,
"grad_norm": 43.412994384765625,
"learning_rate": 4.8e-07,
"loss": 9.4322,
"step": 10
},
{
"epoch": 5.857917671360567e-05,
"grad_norm": 24.38200569152832,
"learning_rate": 1.0799999999999998e-06,
"loss": 9.4165,
"step": 20
},
{
"epoch": 8.786876507040851e-05,
"grad_norm": 25.624269485473633,
"learning_rate": 1.6799999999999998e-06,
"loss": 9.3983,
"step": 30
},
{
"epoch": 0.00011715835342721134,
"grad_norm": 25.8831729888916,
"learning_rate": 2.2799999999999998e-06,
"loss": 9.4015,
"step": 40
},
{
"epoch": 0.00014644794178401418,
"grad_norm": 18.858943939208984,
"learning_rate": 2.8799999999999995e-06,
"loss": 9.369,
"step": 50
},
{
"epoch": 0.00017573753014081702,
"grad_norm": 32.19478225708008,
"learning_rate": 3.4799999999999993e-06,
"loss": 9.3743,
"step": 60
},
{
"epoch": 0.00020502711849761985,
"grad_norm": 29.089111328125,
"learning_rate": 4.079999999999999e-06,
"loss": 9.3628,
"step": 70
},
{
"epoch": 0.0002343167068544227,
"grad_norm": 45.67530822753906,
"learning_rate": 4.679999999999999e-06,
"loss": 9.359,
"step": 80
},
{
"epoch": 0.0002636062952112255,
"grad_norm": 33.06043243408203,
"learning_rate": 5.28e-06,
"loss": 9.3381,
"step": 90
},
{
"epoch": 0.00029289588356802836,
"grad_norm": 32.19873809814453,
"learning_rate": 5.88e-06,
"loss": 9.3304,
"step": 100
},
{
"epoch": 0.0003221854719248312,
"grad_norm": 39.30705261230469,
"learning_rate": 6.48e-06,
"loss": 9.3144,
"step": 110
},
{
"epoch": 0.00035147506028163403,
"grad_norm": 42.05266189575195,
"learning_rate": 7.079999999999999e-06,
"loss": 9.3104,
"step": 120
},
{
"epoch": 0.00038076464863843687,
"grad_norm": 33.91127014160156,
"learning_rate": 7.68e-06,
"loss": 9.3218,
"step": 130
},
{
"epoch": 0.0004100542369952397,
"grad_norm": 31.721614837646484,
"learning_rate": 8.279999999999999e-06,
"loss": 9.3045,
"step": 140
},
{
"epoch": 0.00043934382535204254,
"grad_norm": 59.37827682495117,
"learning_rate": 8.88e-06,
"loss": 9.3054,
"step": 150
},
{
"epoch": 0.0004686334137088454,
"grad_norm": 74.16336059570312,
"learning_rate": 9.48e-06,
"loss": 9.2952,
"step": 160
},
{
"epoch": 0.0004979230020656483,
"grad_norm": 33.57463836669922,
"learning_rate": 1.0079999999999998e-05,
"loss": 9.2887,
"step": 170
},
{
"epoch": 0.000527212590422451,
"grad_norm": 37.42033386230469,
"learning_rate": 1.068e-05,
"loss": 9.2839,
"step": 180
},
{
"epoch": 0.0005565021787792539,
"grad_norm": 33.58783721923828,
"learning_rate": 1.1279999999999999e-05,
"loss": 9.2869,
"step": 190
},
{
"epoch": 0.0005857917671360567,
"grad_norm": 33.92068862915039,
"learning_rate": 1.188e-05,
"loss": 9.2636,
"step": 200
},
{
"epoch": 0.0006150813554928596,
"grad_norm": 36.4366455078125,
"learning_rate": 1.2479999999999999e-05,
"loss": 9.2653,
"step": 210
},
{
"epoch": 0.0006443709438496624,
"grad_norm": 27.894250869750977,
"learning_rate": 1.3079999999999998e-05,
"loss": 9.2699,
"step": 220
},
{
"epoch": 0.0006736605322064653,
"grad_norm": 39.57080078125,
"learning_rate": 1.3559999999999997e-05,
"loss": 9.2491,
"step": 230
},
{
"epoch": 0.0007029501205632681,
"grad_norm": 18.53085708618164,
"learning_rate": 1.4159999999999998e-05,
"loss": 9.2552,
"step": 240
},
{
"epoch": 0.000732239708920071,
"grad_norm": 41.72337341308594,
"learning_rate": 1.476e-05,
"loss": 9.2611,
"step": 250
},
{
"epoch": 0.0007615292972768737,
"grad_norm": 21.73541831970215,
"learning_rate": 1.536e-05,
"loss": 9.2928,
"step": 260
},
{
"epoch": 0.0007908188856336766,
"grad_norm": 59.771385192871094,
"learning_rate": 1.5959999999999996e-05,
"loss": 9.2558,
"step": 270
},
{
"epoch": 0.0008201084739904794,
"grad_norm": 75.89784240722656,
"learning_rate": 1.6559999999999997e-05,
"loss": 9.2438,
"step": 280
},
{
"epoch": 0.0008493980623472823,
"grad_norm": 33.123294830322266,
"learning_rate": 1.716e-05,
"loss": 9.278,
"step": 290
},
{
"epoch": 0.0008786876507040851,
"grad_norm": 39.20044708251953,
"learning_rate": 1.776e-05,
"loss": 9.2508,
"step": 300
}
],
"logging_steps": 10,
"max_steps": 1000000,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 100,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 780676104192000.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}