k4black's picture
Training in progress, step 3000
5b79e79
raw
history blame
3.59 kB
{
"best_metric": 0.8118048310279846,
"best_model_checkpoint": "/home2/s5431786/jb-internship/results/Salesforce-codet5-small-CodeXGLUE-CONCODE-w_special_tokens/checkpoint-3000",
"epoch": 0.96,
"global_step": 3000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.16,
"learning_rate": 3.160588611644274e-05,
"loss": 2.7739,
"step": 500
},
{
"epoch": 0.16,
"eval_bleu": 0.11002405260920435,
"eval_exact_match": 0.136,
"eval_loss": 0.9681498408317566,
"eval_rouge1": 0.5324111683230927,
"eval_rouge2": 0.3516111966646144,
"eval_rougeL": 0.5130793573577244,
"eval_runtime": 23.6738,
"eval_samples_per_second": 84.482,
"eval_steps_per_second": 2.661,
"step": 500
},
{
"epoch": 0.32,
"learning_rate": 6.35956493921945e-05,
"loss": 0.8968,
"step": 1000
},
{
"epoch": 0.32,
"eval_bleu": 0.11661343796568427,
"eval_exact_match": 0.148,
"eval_loss": 0.8933660984039307,
"eval_rouge1": 0.5490713398258988,
"eval_rouge2": 0.3737481223472951,
"eval_rougeL": 0.5313359382235461,
"eval_runtime": 21.9288,
"eval_samples_per_second": 91.204,
"eval_steps_per_second": 2.873,
"step": 1000
},
{
"epoch": 0.48,
"learning_rate": 9.558541266794626e-05,
"loss": 0.8139,
"step": 1500
},
{
"epoch": 0.48,
"eval_bleu": 0.11428222214709638,
"eval_exact_match": 0.148,
"eval_loss": 0.8664323687553406,
"eval_rouge1": 0.5501019947483123,
"eval_rouge2": 0.37606920276228095,
"eval_rougeL": 0.5316473251371836,
"eval_runtime": 21.9364,
"eval_samples_per_second": 91.173,
"eval_steps_per_second": 2.872,
"step": 1500
},
{
"epoch": 0.64,
"learning_rate": 9.854818607471284e-05,
"loss": 0.7535,
"step": 2000
},
{
"epoch": 0.64,
"eval_bleu": 0.12118583002054595,
"eval_exact_match": 0.152,
"eval_loss": 0.8371005058288574,
"eval_rouge1": 0.5554072128917051,
"eval_rouge2": 0.37994480723664975,
"eval_rougeL": 0.5360569772635451,
"eval_runtime": 21.9828,
"eval_samples_per_second": 90.98,
"eval_steps_per_second": 2.866,
"step": 2000
},
{
"epoch": 0.8,
"learning_rate": 9.686394718226834e-05,
"loss": 0.7267,
"step": 2500
},
{
"epoch": 0.8,
"eval_bleu": 0.1221326088002123,
"eval_exact_match": 0.1555,
"eval_loss": 0.8262679576873779,
"eval_rouge1": 0.5599864774843732,
"eval_rouge2": 0.3892847835247521,
"eval_rougeL": 0.5434109433715582,
"eval_runtime": 22.0553,
"eval_samples_per_second": 90.681,
"eval_steps_per_second": 2.856,
"step": 2500
},
{
"epoch": 0.96,
"learning_rate": 9.517970828982384e-05,
"loss": 0.7044,
"step": 3000
},
{
"epoch": 0.96,
"eval_bleu": 0.12264834126055617,
"eval_exact_match": 0.161,
"eval_loss": 0.8118048310279846,
"eval_rouge1": 0.5584777889931278,
"eval_rouge2": 0.38793170420432566,
"eval_rougeL": 0.539366409663261,
"eval_runtime": 21.8691,
"eval_samples_per_second": 91.453,
"eval_steps_per_second": 2.881,
"step": 3000
}
],
"max_steps": 31250,
"num_train_epochs": 10,
"total_flos": 1.0857609928114176e+16,
"trial_name": null,
"trial_params": null
}