k4black's picture
Training in progress, step 22000
10465d2
{
"best_metric": 1.528552770614624,
"best_model_checkpoint": "/home2/s5431786/jb-internship-repr/results/Salesforce-codet5-small-java-small-selected-wo-tokens/checkpoint-2000",
"epoch": 3.051740879456235,
"global_step": 22000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.28,
"learning_rate": 9.94363646983237e-05,
"loss": 2.1009,
"step": 2000
},
{
"epoch": 0.28,
"eval_exact_match": 0.31785774198959904,
"eval_loss": 1.528552770614624,
"eval_rouge1": 0.5232290073169683,
"eval_rouge2": 0.24795642157242634,
"eval_rougeL": 0.5233033679411545,
"eval_runtime": 163.446,
"eval_samples_per_second": 145.883,
"eval_steps_per_second": 1.523,
"step": 2000
},
{
"epoch": 0.55,
"learning_rate": 9.359558437007184e-05,
"loss": 1.3098,
"step": 4000
},
{
"epoch": 0.55,
"eval_exact_match": 0.29667840966280823,
"eval_loss": 1.5582195520401,
"eval_rouge1": 0.499918373090859,
"eval_rouge2": 0.22982882883486827,
"eval_rougeL": 0.49974542584946463,
"eval_runtime": 169.5108,
"eval_samples_per_second": 140.664,
"eval_steps_per_second": 1.469,
"step": 4000
},
{
"epoch": 0.83,
"learning_rate": 8.775480404182e-05,
"loss": 1.1968,
"step": 6000
},
{
"epoch": 0.83,
"eval_exact_match": 0.321003187384667,
"eval_loss": 1.551592469215393,
"eval_rouge1": 0.5260578932396776,
"eval_rouge2": 0.25462429236963685,
"eval_rougeL": 0.5257669098334219,
"eval_runtime": 163.9432,
"eval_samples_per_second": 145.441,
"eval_steps_per_second": 1.519,
"step": 6000
},
{
"epoch": 1.11,
"learning_rate": 8.191402371356814e-05,
"loss": 1.1145,
"step": 8000
},
{
"epoch": 1.11,
"eval_exact_match": 0.31735447072638817,
"eval_loss": 1.572016954421997,
"eval_rouge1": 0.5094747473558878,
"eval_rouge2": 0.2465356707776194,
"eval_rougeL": 0.5091592701411148,
"eval_runtime": 163.415,
"eval_samples_per_second": 145.911,
"eval_steps_per_second": 1.524,
"step": 8000
},
{
"epoch": 1.39,
"learning_rate": 7.607908416564453e-05,
"loss": 1.0477,
"step": 10000
},
{
"epoch": 1.39,
"eval_exact_match": 0.33387854386847843,
"eval_loss": 1.5617761611938477,
"eval_rouge1": 0.5280223151246797,
"eval_rouge2": 0.2615585801921996,
"eval_rougeL": 0.5274734242132477,
"eval_runtime": 165.805,
"eval_samples_per_second": 143.807,
"eval_steps_per_second": 1.502,
"step": 10000
},
{
"epoch": 1.66,
"learning_rate": 7.023830383739268e-05,
"loss": 1.0219,
"step": 12000
},
{
"epoch": 1.66,
"eval_exact_match": 0.32372924006039255,
"eval_loss": 1.5944069623947144,
"eval_rouge1": 0.5133412941637794,
"eval_rouge2": 0.24304376784560536,
"eval_rougeL": 0.5128045498112566,
"eval_runtime": 164.4858,
"eval_samples_per_second": 144.961,
"eval_steps_per_second": 1.514,
"step": 12000
},
{
"epoch": 1.94,
"learning_rate": 6.440044389930495e-05,
"loss": 1.0027,
"step": 14000
},
{
"epoch": 1.94,
"eval_exact_match": 0.3238550578761953,
"eval_loss": 1.5750421285629272,
"eval_rouge1": 0.5206336041126007,
"eval_rouge2": 0.24470678869584325,
"eval_rougeL": 0.5202257107678057,
"eval_runtime": 161.6161,
"eval_samples_per_second": 147.535,
"eval_steps_per_second": 1.541,
"step": 14000
},
{
"epoch": 2.22,
"learning_rate": 5.856258396121722e-05,
"loss": 0.9263,
"step": 16000
},
{
"epoch": 2.22,
"eval_exact_match": 0.33018788793826537,
"eval_loss": 1.5776818990707397,
"eval_rouge1": 0.5179861628783158,
"eval_rouge2": 0.24451742588852704,
"eval_rougeL": 0.5176686731279507,
"eval_runtime": 165.4256,
"eval_samples_per_second": 144.137,
"eval_steps_per_second": 1.505,
"step": 16000
},
{
"epoch": 2.5,
"learning_rate": 5.272180363296537e-05,
"loss": 0.9054,
"step": 18000
},
{
"epoch": 2.5,
"eval_exact_match": 0.3242325113236034,
"eval_loss": 1.6233525276184082,
"eval_rouge1": 0.5204582779286969,
"eval_rouge2": 0.24576987021627228,
"eval_rougeL": 0.520011433933161,
"eval_runtime": 164.3556,
"eval_samples_per_second": 145.076,
"eval_steps_per_second": 1.515,
"step": 18000
},
{
"epoch": 2.77,
"learning_rate": 4.688102330471351e-05,
"loss": 0.8921,
"step": 20000
},
{
"epoch": 2.77,
"eval_exact_match": 0.3301459486663312,
"eval_loss": 1.5790328979492188,
"eval_rouge1": 0.5328535938777187,
"eval_rouge2": 0.2582260548148201,
"eval_rougeL": 0.5322687769671152,
"eval_runtime": 166.1094,
"eval_samples_per_second": 143.544,
"eval_steps_per_second": 1.499,
"step": 20000
},
{
"epoch": 3.05,
"learning_rate": 4.104316336662578e-05,
"loss": 0.8781,
"step": 22000
},
{
"epoch": 3.05,
"eval_exact_match": 0.3254906894816306,
"eval_loss": 1.6439645290374756,
"eval_rouge1": 0.5162815076416999,
"eval_rouge2": 0.24675202503744387,
"eval_rougeL": 0.5156010398670283,
"eval_runtime": 164.6699,
"eval_samples_per_second": 144.799,
"eval_steps_per_second": 1.512,
"step": 22000
}
],
"max_steps": 36045,
"num_train_epochs": 5,
"total_flos": 2.8580534242246656e+17,
"trial_name": null,
"trial_params": null
}