16-clusters-imbalanced-4 / trainer_state.json
MHGanainy's picture
MHGanainy/16-clusters-imbalanced-4
cc7933e verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 2018,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.049554013875123884,
"grad_norm": 0.09496160596609116,
"learning_rate": 6.666666666666667e-06,
"loss": 2.3288,
"step": 100
},
{
"epoch": 0.09910802775024777,
"grad_norm": 0.21523982286453247,
"learning_rate": 1.3333333333333333e-05,
"loss": 2.2852,
"step": 200
},
{
"epoch": 0.14866204162537167,
"grad_norm": 0.3396208584308624,
"learning_rate": 2e-05,
"loss": 2.2673,
"step": 300
},
{
"epoch": 0.19821605550049554,
"grad_norm": 0.455649197101593,
"learning_rate": 1.9833270328249614e-05,
"loss": 2.167,
"step": 400
},
{
"epoch": 0.24777006937561943,
"grad_norm": 0.5028106570243835,
"learning_rate": 1.933864106968685e-05,
"loss": 2.1722,
"step": 500
},
{
"epoch": 0.29732408325074333,
"grad_norm": 0.5224338173866272,
"learning_rate": 1.8532606099095376e-05,
"loss": 2.1245,
"step": 600
},
{
"epoch": 0.3468780971258672,
"grad_norm": 0.6227980256080627,
"learning_rate": 1.7442043405688393e-05,
"loss": 2.054,
"step": 700
},
{
"epoch": 0.39643211100099107,
"grad_norm": 0.6063210368156433,
"learning_rate": 1.61033188214449e-05,
"loss": 2.0739,
"step": 800
},
{
"epoch": 0.44598612487611494,
"grad_norm": 0.6256656646728516,
"learning_rate": 1.4561073368463916e-05,
"loss": 2.0641,
"step": 900
},
{
"epoch": 0.49554013875123887,
"grad_norm": 0.7533057332038879,
"learning_rate": 1.2866734662372244e-05,
"loss": 2.0057,
"step": 1000
},
{
"epoch": 0.5450941526263627,
"grad_norm": 0.6291965842247009,
"learning_rate": 1.107680201043002e-05,
"loss": 2.0111,
"step": 1100
},
{
"epoch": 0.5946481665014867,
"grad_norm": 0.782930850982666,
"learning_rate": 9.250962389339966e-06,
"loss": 2.0145,
"step": 1200
},
{
"epoch": 0.6442021803766105,
"grad_norm": 0.7603575587272644,
"learning_rate": 7.450100127240713e-06,
"loss": 1.9896,
"step": 1300
},
{
"epoch": 0.6937561942517344,
"grad_norm": 0.7139636874198914,
"learning_rate": 5.7342666588977705e-06,
"loss": 2.0316,
"step": 1400
},
{
"epoch": 0.7433102081268583,
"grad_norm": 0.7095770835876465,
"learning_rate": 4.160678054502153e-06,
"loss": 1.9755,
"step": 1500
},
{
"epoch": 0.7928642220019821,
"grad_norm": 0.7470089197158813,
"learning_rate": 2.7818070963500776e-06,
"loss": 1.934,
"step": 1600
},
{
"epoch": 0.8424182358771061,
"grad_norm": 0.9231148362159729,
"learning_rate": 1.643633524889301e-06,
"loss": 2.0226,
"step": 1700
},
{
"epoch": 0.8919722497522299,
"grad_norm": 0.8875738978385925,
"learning_rate": 7.841108013127585e-07,
"loss": 1.9803,
"step": 1800
},
{
"epoch": 0.9415262636273538,
"grad_norm": 0.9144193530082703,
"learning_rate": 2.3190051393322754e-07,
"loss": 1.9554,
"step": 1900
},
{
"epoch": 0.9910802775024777,
"grad_norm": 0.7741144299507141,
"learning_rate": 5.41663074110188e-09,
"loss": 1.9692,
"step": 2000
},
{
"epoch": 1.0,
"step": 2018,
"total_flos": 3.6664480530432e+16,
"train_loss": 2.0711384613521036,
"train_runtime": 629.2276,
"train_samples_per_second": 6.413,
"train_steps_per_second": 3.207
}
],
"logging_steps": 100,
"max_steps": 2018,
"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": 3.6664480530432e+16,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}