CS-GY-6613-Project / checkpoint-3024 /trainer_state.json
MJ
Added checkpoint folder
93f09cb
raw
history blame
4.08 kB
{
"best_metric": 0.9327176213264465,
"best_model_checkpoint": "Bert-Patent-Model-2/checkpoint-252",
"epoch": 11.979202772963605,
"global_step": 3024,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"eval_accuracy": 0.5560809324829558,
"eval_loss": 0.9327176213264465,
"eval_runtime": 61.1572,
"eval_samples_per_second": 148.699,
"eval_steps_per_second": 37.183,
"step": 252
},
{
"epoch": 1.98,
"learning_rate": 4.173280423280423e-05,
"loss": 0.7132,
"step": 500
},
{
"epoch": 2.0,
"eval_accuracy": 0.5373872883219706,
"eval_loss": 1.062583327293396,
"eval_runtime": 61.2847,
"eval_samples_per_second": 148.389,
"eval_steps_per_second": 37.106,
"step": 504
},
{
"epoch": 3.0,
"eval_accuracy": 0.5458544095007697,
"eval_loss": 1.1494050025939941,
"eval_runtime": 61.066,
"eval_samples_per_second": 148.921,
"eval_steps_per_second": 37.238,
"step": 757
},
{
"epoch": 3.96,
"learning_rate": 3.3465608465608464e-05,
"loss": 0.4843,
"step": 1000
},
{
"epoch": 4.0,
"eval_accuracy": 0.5184737189355619,
"eval_loss": 1.3940870761871338,
"eval_runtime": 61.4358,
"eval_samples_per_second": 148.024,
"eval_steps_per_second": 37.014,
"step": 1009
},
{
"epoch": 5.0,
"eval_accuracy": 0.5200131955135254,
"eval_loss": 1.6256372928619385,
"eval_runtime": 61.3848,
"eval_samples_per_second": 148.147,
"eval_steps_per_second": 37.045,
"step": 1262
},
{
"epoch": 5.94,
"learning_rate": 2.521494708994709e-05,
"loss": 0.2345,
"step": 1500
},
{
"epoch": 6.0,
"eval_accuracy": 0.5346382230041786,
"eval_loss": 1.928905963897705,
"eval_runtime": 61.7798,
"eval_samples_per_second": 147.2,
"eval_steps_per_second": 36.808,
"step": 1514
},
{
"epoch": 7.0,
"eval_accuracy": 0.535188036067737,
"eval_loss": 2.1018900871276855,
"eval_runtime": 61.981,
"eval_samples_per_second": 146.722,
"eval_steps_per_second": 36.689,
"step": 1767
},
{
"epoch": 7.92,
"learning_rate": 1.6947751322751323e-05,
"loss": 0.1136,
"step": 2000
},
{
"epoch": 8.0,
"eval_accuracy": 0.5215526720914889,
"eval_loss": 2.4479029178619385,
"eval_runtime": 61.734,
"eval_samples_per_second": 147.309,
"eval_steps_per_second": 36.835,
"step": 2019
},
{
"epoch": 9.0,
"eval_accuracy": 0.5127556630745547,
"eval_loss": 2.633791923522949,
"eval_runtime": 61.3331,
"eval_samples_per_second": 148.272,
"eval_steps_per_second": 37.076,
"step": 2271
},
{
"epoch": 9.9,
"learning_rate": 8.680555555555556e-06,
"loss": 0.0521,
"step": 2500
},
{
"epoch": 10.0,
"eval_accuracy": 0.5292500549813064,
"eval_loss": 3.018095016479492,
"eval_runtime": 62.0026,
"eval_samples_per_second": 146.671,
"eval_steps_per_second": 36.676,
"step": 2524
},
{
"epoch": 11.0,
"eval_accuracy": 0.522542335605894,
"eval_loss": 3.2116775512695312,
"eval_runtime": 61.5454,
"eval_samples_per_second": 147.761,
"eval_steps_per_second": 36.948,
"step": 2776
},
{
"epoch": 11.88,
"learning_rate": 4.133597883597884e-07,
"loss": 0.0222,
"step": 3000
},
{
"epoch": 11.98,
"eval_accuracy": 0.5235319991202991,
"eval_loss": 3.3195860385894775,
"eval_runtime": 61.2862,
"eval_samples_per_second": 148.386,
"eval_steps_per_second": 37.105,
"step": 3024
}
],
"max_steps": 3024,
"num_train_epochs": 12,
"total_flos": 2.563329616742707e+16,
"trial_name": null,
"trial_params": null
}