16-clusters-balanced-5 / trainer_state.json
MHGanainy's picture
MHGanainy/16-clusters-balanced-5
55b747f verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 2201,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.04543389368468878,
"grad_norm": 0.09712143242359161,
"learning_rate": 6.666666666666667e-06,
"loss": 2.3519,
"step": 100
},
{
"epoch": 0.09086778736937756,
"grad_norm": 0.19713231921195984,
"learning_rate": 1.3333333333333333e-05,
"loss": 2.3328,
"step": 200
},
{
"epoch": 0.13630168105406634,
"grad_norm": 0.3079201281070709,
"learning_rate": 2e-05,
"loss": 2.2889,
"step": 300
},
{
"epoch": 0.18173557473875512,
"grad_norm": 0.4669693112373352,
"learning_rate": 1.986375615936076e-05,
"loss": 2.2034,
"step": 400
},
{
"epoch": 0.22716946842344388,
"grad_norm": 0.5451923608779907,
"learning_rate": 1.945873711426545e-05,
"loss": 2.1583,
"step": 500
},
{
"epoch": 0.2726033621081327,
"grad_norm": 0.6099482774734497,
"learning_rate": 1.8795979134761248e-05,
"loss": 2.0602,
"step": 600
},
{
"epoch": 0.31803725579282144,
"grad_norm": 0.6596097350120544,
"learning_rate": 1.789354155935654e-05,
"loss": 2.0473,
"step": 700
},
{
"epoch": 0.36347114947751025,
"grad_norm": 0.7136645317077637,
"learning_rate": 1.6776014700293388e-05,
"loss": 2.0198,
"step": 800
},
{
"epoch": 0.408905043162199,
"grad_norm": 0.8438076972961426,
"learning_rate": 1.5473849787831045e-05,
"loss": 2.0392,
"step": 900
},
{
"epoch": 0.45433893684688775,
"grad_norm": 0.7616672515869141,
"learning_rate": 1.402252921173342e-05,
"loss": 1.9778,
"step": 1000
},
{
"epoch": 0.49977283053157656,
"grad_norm": 0.9710221886634827,
"learning_rate": 1.2461599669857771e-05,
"loss": 1.9924,
"step": 1100
},
{
"epoch": 0.5452067242162654,
"grad_norm": 0.8164697885513306,
"learning_rate": 1.0833594569354579e-05,
"loss": 1.9815,
"step": 1200
},
{
"epoch": 0.5906406179009541,
"grad_norm": 0.9773705005645752,
"learning_rate": 9.182875043718411e-06,
"loss": 1.9676,
"step": 1300
},
{
"epoch": 0.6360745115856429,
"grad_norm": 0.883895754814148,
"learning_rate": 7.55442116654744e-06,
"loss": 1.9931,
"step": 1400
},
{
"epoch": 0.6815084052703316,
"grad_norm": 0.8479602336883545,
"learning_rate": 5.992606299947589e-06,
"loss": 1.9691,
"step": 1500
},
{
"epoch": 0.7269422989550205,
"grad_norm": 0.749001145362854,
"learning_rate": 4.539987975077471e-06,
"loss": 1.9634,
"step": 1600
},
{
"epoch": 0.7723761926397092,
"grad_norm": 0.9302273392677307,
"learning_rate": 3.2361482518497367e-06,
"loss": 1.9703,
"step": 1700
},
{
"epoch": 0.817810086324398,
"grad_norm": 0.9604031443595886,
"learning_rate": 2.116615156558488e-06,
"loss": 1.9493,
"step": 1800
},
{
"epoch": 0.8632439800090868,
"grad_norm": 1.0161337852478027,
"learning_rate": 1.2118945869287768e-06,
"loss": 1.9529,
"step": 1900
},
{
"epoch": 0.9086778736937755,
"grad_norm": 1.0821712017059326,
"learning_rate": 5.466390639829355e-07,
"loss": 1.9312,
"step": 2000
},
{
"epoch": 0.9541117673784644,
"grad_norm": 0.974641740322113,
"learning_rate": 1.389759812114888e-07,
"loss": 1.9328,
"step": 2100
},
{
"epoch": 0.9995456610631531,
"grad_norm": 0.8598447442054749,
"learning_rate": 1.3655431158055011e-11,
"loss": 1.918,
"step": 2200
},
{
"epoch": 1.0,
"step": 2201,
"total_flos": 3.99992672354304e+16,
"train_loss": 2.0455698882488162,
"train_runtime": 686.5905,
"train_samples_per_second": 6.411,
"train_steps_per_second": 3.206
}
],
"logging_steps": 100,
"max_steps": 2201,
"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": 3.99992672354304e+16,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}