{ "best_metric": 0.8577723503112793, "best_model_checkpoint": "/home2/s5431786/jb-internship/results/t5-small-CodeXGLUE-CONCODE-faster/checkpoint-4000", "epoch": 1.28, "global_step": 4000, "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 } ], "max_steps": 62500, "num_train_epochs": 20, "total_flos": 1.6762623479513088e+16, "trial_name": null, "trial_params": null }