fst-1 / checkpoint-200 /trainer_state.json
aixk's picture
Upload folder using huggingface_hub
57869b9 verified
Raw
History Blame Contribute Delete
4.44 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.013872271064176595,
"eval_steps": 500,
"global_step": 200,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0006936135532088297,
"grad_norm": 80.97769927978516,
"learning_rate": 2.0833333333333334e-06,
"loss": 39.45225219726562,
"step": 10
},
{
"epoch": 0.0013872271064176594,
"grad_norm": 69.19830322265625,
"learning_rate": 6.25e-06,
"loss": 38.231222534179686,
"step": 20
},
{
"epoch": 0.0020808406596264893,
"grad_norm": 55.03429412841797,
"learning_rate": 1.0416666666666666e-05,
"loss": 37.07829284667969,
"step": 30
},
{
"epoch": 0.002774454212835319,
"grad_norm": 36.03839874267578,
"learning_rate": 1.4583333333333333e-05,
"loss": 35.945098876953125,
"step": 40
},
{
"epoch": 0.0034680677660441487,
"grad_norm": 48.63792419433594,
"learning_rate": 1.875e-05,
"loss": 34.40289306640625,
"step": 50
},
{
"epoch": 0.004161681319252979,
"grad_norm": 41.98967361450195,
"learning_rate": 2.2916666666666667e-05,
"loss": 33.45003662109375,
"step": 60
},
{
"epoch": 0.004855294872461808,
"grad_norm": 81.57576751708984,
"learning_rate": 2.7083333333333335e-05,
"loss": 32.02000427246094,
"step": 70
},
{
"epoch": 0.005548908425670638,
"grad_norm": 60.575645446777344,
"learning_rate": 3.125e-05,
"loss": 30.74504699707031,
"step": 80
},
{
"epoch": 0.006242521978879467,
"grad_norm": 61.149410247802734,
"learning_rate": 3.541666666666667e-05,
"loss": 29.49912109375,
"step": 90
},
{
"epoch": 0.006936135532088297,
"grad_norm": 69.96782684326172,
"learning_rate": 3.958333333333333e-05,
"loss": 28.152670288085936,
"step": 100
},
{
"epoch": 0.007629749085297127,
"grad_norm": 33.35784149169922,
"learning_rate": 4.375e-05,
"loss": 27.86654052734375,
"step": 110
},
{
"epoch": 0.008323362638505957,
"grad_norm": 42.682308197021484,
"learning_rate": 4.791666666666667e-05,
"loss": 27.098068237304688,
"step": 120
},
{
"epoch": 0.009016976191714786,
"grad_norm": 45.40013122558594,
"learning_rate": 5.208333333333334e-05,
"loss": 25.768472290039064,
"step": 130
},
{
"epoch": 0.009710589744923616,
"grad_norm": 36.54875564575195,
"learning_rate": 5.6250000000000005e-05,
"loss": 25.419296264648438,
"step": 140
},
{
"epoch": 0.010404203298132445,
"grad_norm": 54.964447021484375,
"learning_rate": 6.041666666666667e-05,
"loss": 24.5228759765625,
"step": 150
},
{
"epoch": 0.011097816851341275,
"grad_norm": 62.00859451293945,
"learning_rate": 6.458333333333334e-05,
"loss": 23.92150115966797,
"step": 160
},
{
"epoch": 0.011791430404550106,
"grad_norm": 50.303070068359375,
"learning_rate": 6.875e-05,
"loss": 23.61223449707031,
"step": 170
},
{
"epoch": 0.012485043957758934,
"grad_norm": 40.088356018066406,
"learning_rate": 7.291666666666667e-05,
"loss": 23.29130401611328,
"step": 180
},
{
"epoch": 0.013178657510967764,
"grad_norm": 58.86671829223633,
"learning_rate": 7.708333333333334e-05,
"loss": 23.32776794433594,
"step": 190
},
{
"epoch": 0.013872271064176595,
"grad_norm": 38.86407470703125,
"learning_rate": 8.125000000000001e-05,
"loss": 23.280059814453125,
"step": 200
}
],
"logging_steps": 10,
"max_steps": 100000,
"num_input_tokens_seen": 0,
"num_train_epochs": 7,
"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": 2167255492608000.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}