| { | |
| "best_metric": 0.7037115097045898, | |
| "best_model_checkpoint": "/home2/s5431786/jb-internship/results/t5-small-CodeXGLUE-CONCODE-faster/checkpoint-13000", | |
| "epoch": 4.16, | |
| "global_step": 13000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 7.968e-05, | |
| "loss": 3.6878, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_bleu": 0.0323034964768643, | |
| "eval_exact_match": 0.0035, | |
| "eval_loss": 1.9745688438415527, | |
| "eval_rouge1": 0.3491207907520632, | |
| "eval_rouge2": 0.14656678100405174, | |
| "eval_rougeL": 0.3285981582102612, | |
| "eval_runtime": 36.246, | |
| "eval_samples_per_second": 55.178, | |
| "eval_steps_per_second": 1.738, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.00015968, | |
| "loss": 1.7625, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_bleu": 0.038749091873206375, | |
| "eval_exact_match": 0.0145, | |
| "eval_loss": 1.4567848443984985, | |
| "eval_rouge1": 0.35498006740689036, | |
| "eval_rouge2": 0.13946738339077275, | |
| "eval_rougeL": 0.3327171698914647, | |
| "eval_runtime": 34.5773, | |
| "eval_samples_per_second": 57.841, | |
| "eval_steps_per_second": 1.822, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.00023952, | |
| "loss": 1.3575, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_bleu": 0.04388514972808356, | |
| "eval_exact_match": 0.053, | |
| "eval_loss": 1.1938430070877075, | |
| "eval_rouge1": 0.4102062635539608, | |
| "eval_rouge2": 0.21783150768420984, | |
| "eval_rougeL": 0.3907330178570455, | |
| "eval_runtime": 34.9414, | |
| "eval_samples_per_second": 57.239, | |
| "eval_steps_per_second": 1.803, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.00031952000000000006, | |
| "loss": 1.1187, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_bleu": 0.05024016948621801, | |
| "eval_exact_match": 0.0735, | |
| "eval_loss": 1.0715276002883911, | |
| "eval_rouge1": 0.44133744346838355, | |
| "eval_rouge2": 0.25777725613931946, | |
| "eval_rougeL": 0.4219959477894215, | |
| "eval_runtime": 35.3166, | |
| "eval_samples_per_second": 56.631, | |
| "eval_steps_per_second": 1.784, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.00039952, | |
| "loss": 1.0062, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_bleu": 0.0525791651130599, | |
| "eval_exact_match": 0.0815, | |
| "eval_loss": 0.9908952116966248, | |
| "eval_rouge1": 0.46270763973625095, | |
| "eval_rouge2": 0.2836027818482203, | |
| "eval_rougeL": 0.4457626023912316, | |
| "eval_runtime": 35.2306, | |
| "eval_samples_per_second": 56.769, | |
| "eval_steps_per_second": 1.788, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.00047952, | |
| "loss": 0.9314, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_bleu": 0.056618620209005335, | |
| "eval_exact_match": 0.0845, | |
| "eval_loss": 0.9375063180923462, | |
| "eval_rouge1": 0.4688436524948581, | |
| "eval_rouge2": 0.2932255323307211, | |
| "eval_rougeL": 0.45301193641551707, | |
| "eval_runtime": 37.1868, | |
| "eval_samples_per_second": 53.783, | |
| "eval_steps_per_second": 1.694, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.0004968673684210526, | |
| "loss": 0.8581, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "eval_bleu": 0.05920053067894586, | |
| "eval_exact_match": 0.0855, | |
| "eval_loss": 0.8949318528175354, | |
| "eval_rouge1": 0.475736898014815, | |
| "eval_rouge2": 0.30127214832048377, | |
| "eval_rougeL": 0.45988834774964316, | |
| "eval_runtime": 35.9797, | |
| "eval_samples_per_second": 55.587, | |
| "eval_steps_per_second": 1.751, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.0004926568421052632, | |
| "loss": 0.8077, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "eval_bleu": 0.060850014141887766, | |
| "eval_exact_match": 0.088, | |
| "eval_loss": 0.8577723503112793, | |
| "eval_rouge1": 0.4857568042531289, | |
| "eval_rouge2": 0.3123549789085296, | |
| "eval_rougeL": 0.47152130323710484, | |
| "eval_runtime": 35.0315, | |
| "eval_samples_per_second": 57.091, | |
| "eval_steps_per_second": 1.798, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 0.0004884463157894737, | |
| "loss": 0.7742, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "eval_bleu": 0.060679509741740224, | |
| "eval_exact_match": 0.091, | |
| "eval_loss": 0.8396906852722168, | |
| "eval_rouge1": 0.48584317956376577, | |
| "eval_rouge2": 0.31707363805938765, | |
| "eval_rougeL": 0.47246293765798464, | |
| "eval_runtime": 35.6286, | |
| "eval_samples_per_second": 56.135, | |
| "eval_steps_per_second": 1.768, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.00048423578947368425, | |
| "loss": 0.7556, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "eval_bleu": 0.062181241480247514, | |
| "eval_exact_match": 0.094, | |
| "eval_loss": 0.8199761509895325, | |
| "eval_rouge1": 0.49335199051744105, | |
| "eval_rouge2": 0.3273247481525058, | |
| "eval_rougeL": 0.47992085377826155, | |
| "eval_runtime": 37.2571, | |
| "eval_samples_per_second": 53.681, | |
| "eval_steps_per_second": 1.691, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 0.00048002526315789475, | |
| "loss": 0.7246, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "eval_bleu": 0.06360201700239017, | |
| "eval_exact_match": 0.096, | |
| "eval_loss": 0.7979766726493835, | |
| "eval_rouge1": 0.49459857323152784, | |
| "eval_rouge2": 0.32742424566936434, | |
| "eval_rougeL": 0.4795144854855635, | |
| "eval_runtime": 38.3013, | |
| "eval_samples_per_second": 52.218, | |
| "eval_steps_per_second": 1.645, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 0.0004758147368421053, | |
| "loss": 0.7045, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "eval_bleu": 0.06323253320022208, | |
| "eval_exact_match": 0.099, | |
| "eval_loss": 0.7866926193237305, | |
| "eval_rouge1": 0.49270311763410307, | |
| "eval_rouge2": 0.3310082026030387, | |
| "eval_rougeL": 0.4800440014525599, | |
| "eval_runtime": 35.9272, | |
| "eval_samples_per_second": 55.668, | |
| "eval_steps_per_second": 1.754, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 0.0004716042105263158, | |
| "loss": 0.6778, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "eval_bleu": 0.06526774731233032, | |
| "eval_exact_match": 0.097, | |
| "eval_loss": 0.7727072834968567, | |
| "eval_rouge1": 0.5015386585306862, | |
| "eval_rouge2": 0.3327019592611423, | |
| "eval_rougeL": 0.4858921391142662, | |
| "eval_runtime": 36.8788, | |
| "eval_samples_per_second": 54.232, | |
| "eval_steps_per_second": 1.708, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 0.0004673936842105263, | |
| "loss": 0.652, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "eval_bleu": 0.06603832460136996, | |
| "eval_exact_match": 0.0945, | |
| "eval_loss": 0.7700557708740234, | |
| "eval_rouge1": 0.5007155856518921, | |
| "eval_rouge2": 0.33660838962730144, | |
| "eval_rougeL": 0.48704095883836096, | |
| "eval_runtime": 36.0428, | |
| "eval_samples_per_second": 55.49, | |
| "eval_steps_per_second": 1.748, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 0.0004631831578947369, | |
| "loss": 0.6477, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "eval_bleu": 0.0637326815837752, | |
| "eval_exact_match": 0.1015, | |
| "eval_loss": 0.7626734375953674, | |
| "eval_rouge1": 0.5067175865244784, | |
| "eval_rouge2": 0.3418343311421686, | |
| "eval_rougeL": 0.4932440074450731, | |
| "eval_runtime": 36.8678, | |
| "eval_samples_per_second": 54.248, | |
| "eval_steps_per_second": 1.709, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 0.0004589726315789474, | |
| "loss": 0.6337, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "eval_bleu": 0.06513339878553655, | |
| "eval_exact_match": 0.1015, | |
| "eval_loss": 0.7461714148521423, | |
| "eval_rouge1": 0.4982517321430179, | |
| "eval_rouge2": 0.33681326926227717, | |
| "eval_rougeL": 0.4849838232405096, | |
| "eval_runtime": 36.8056, | |
| "eval_samples_per_second": 54.34, | |
| "eval_steps_per_second": 1.712, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 0.00045476210526315794, | |
| "loss": 0.6278, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "eval_bleu": 0.06459301207154695, | |
| "eval_exact_match": 0.0995, | |
| "eval_loss": 0.7355420589447021, | |
| "eval_rouge1": 0.503290317947929, | |
| "eval_rouge2": 0.34354898330754957, | |
| "eval_rougeL": 0.49001424087111184, | |
| "eval_runtime": 36.3871, | |
| "eval_samples_per_second": 54.965, | |
| "eval_steps_per_second": 1.731, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 0.00045055157894736844, | |
| "loss": 0.6224, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "eval_bleu": 0.06439506753752011, | |
| "eval_exact_match": 0.102, | |
| "eval_loss": 0.7340560555458069, | |
| "eval_rouge1": 0.5052438839482049, | |
| "eval_rouge2": 0.34484226789208994, | |
| "eval_rougeL": 0.4921510782769857, | |
| "eval_runtime": 37.3894, | |
| "eval_samples_per_second": 53.491, | |
| "eval_steps_per_second": 1.685, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 0.000446341052631579, | |
| "loss": 0.6008, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "eval_bleu": 0.06461231818263671, | |
| "eval_exact_match": 0.101, | |
| "eval_loss": 0.7321618795394897, | |
| "eval_rouge1": 0.5033575057087202, | |
| "eval_rouge2": 0.3421619427853616, | |
| "eval_rougeL": 0.4902835308639695, | |
| "eval_runtime": 36.6808, | |
| "eval_samples_per_second": 54.524, | |
| "eval_steps_per_second": 1.718, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 0.0004421305263157895, | |
| "loss": 0.589, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "eval_bleu": 0.06509490313536258, | |
| "eval_exact_match": 0.1005, | |
| "eval_loss": 0.7238326668739319, | |
| "eval_rouge1": 0.5044211940127038, | |
| "eval_rouge2": 0.34197306671723443, | |
| "eval_rougeL": 0.4906146460856744, | |
| "eval_runtime": 35.0879, | |
| "eval_samples_per_second": 57.0, | |
| "eval_steps_per_second": 1.795, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 0.00043792, | |
| "loss": 0.5708, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "eval_bleu": 0.06631228557498069, | |
| "eval_exact_match": 0.0995, | |
| "eval_loss": 0.715421736240387, | |
| "eval_rouge1": 0.5068028046779569, | |
| "eval_rouge2": 0.34473925417295426, | |
| "eval_rougeL": 0.49254925133943384, | |
| "eval_runtime": 35.4516, | |
| "eval_samples_per_second": 56.415, | |
| "eval_steps_per_second": 1.777, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 0.00043370947368421057, | |
| "loss": 0.5712, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "eval_bleu": 0.06578551089272082, | |
| "eval_exact_match": 0.102, | |
| "eval_loss": 0.7109146118164062, | |
| "eval_rouge1": 0.5061889557930622, | |
| "eval_rouge2": 0.34828839953790597, | |
| "eval_rougeL": 0.4934676685845075, | |
| "eval_runtime": 35.6977, | |
| "eval_samples_per_second": 56.026, | |
| "eval_steps_per_second": 1.765, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "learning_rate": 0.0004295157894736842, | |
| "loss": 0.5655, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "eval_bleu": 0.06635467115197174, | |
| "eval_exact_match": 0.1015, | |
| "eval_loss": 0.7136749029159546, | |
| "eval_rouge1": 0.5101572079631966, | |
| "eval_rouge2": 0.3491129312343716, | |
| "eval_rougeL": 0.49647385739953515, | |
| "eval_runtime": 35.4035, | |
| "eval_samples_per_second": 56.492, | |
| "eval_steps_per_second": 1.779, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "learning_rate": 0.00042530526315789473, | |
| "loss": 0.5593, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "eval_bleu": 0.06743929871449864, | |
| "eval_exact_match": 0.104, | |
| "eval_loss": 0.7079191207885742, | |
| "eval_rouge1": 0.5109229447218538, | |
| "eval_rouge2": 0.3498840589135052, | |
| "eval_rougeL": 0.49719053454192585, | |
| "eval_runtime": 35.9294, | |
| "eval_samples_per_second": 55.665, | |
| "eval_steps_per_second": 1.753, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 0.00042109473684210524, | |
| "loss": 0.5501, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_bleu": 0.06587822883992077, | |
| "eval_exact_match": 0.0965, | |
| "eval_loss": 0.7067587971687317, | |
| "eval_rouge1": 0.5063077878070544, | |
| "eval_rouge2": 0.34684822407233706, | |
| "eval_rougeL": 0.49414991531075403, | |
| "eval_runtime": 26.7311, | |
| "eval_samples_per_second": 74.819, | |
| "eval_steps_per_second": 2.357, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "learning_rate": 0.0004168842105263158, | |
| "loss": 0.5349, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "eval_bleu": 0.06621007420514197, | |
| "eval_exact_match": 0.1035, | |
| "eval_loss": 0.7037115097045898, | |
| "eval_rouge1": 0.5099136668737985, | |
| "eval_rouge2": 0.35113419695580583, | |
| "eval_rougeL": 0.4975205835514277, | |
| "eval_runtime": 25.9643, | |
| "eval_samples_per_second": 77.029, | |
| "eval_steps_per_second": 2.426, | |
| "step": 13000 | |
| } | |
| ], | |
| "max_steps": 62500, | |
| "num_train_epochs": 20, | |
| "total_flos": 5.438352482264678e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |