| { | |
| "best_metric": 0.7621653079986572, | |
| "best_model_checkpoint": "/home2/s5431786/jb-internship/results/Salesforce-codet5-small-CodeXGLUE-CONCODE-adamw/checkpoint-9000", | |
| "epoch": 3.2, | |
| "global_step": 10000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 3.166986564299425e-05, | |
| "loss": 2.3935, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_bleu": 0.11268710945019392, | |
| "eval_exact_match": 0.129, | |
| "eval_loss": 0.9724392294883728, | |
| "eval_rouge1": 0.5286362208212969, | |
| "eval_rouge2": 0.3465696747006132, | |
| "eval_rougeL": 0.5098110686689669, | |
| "eval_rougeLsum": 0.5153482514973529, | |
| "eval_runtime": 27.4689, | |
| "eval_samples_per_second": 72.81, | |
| "eval_steps_per_second": 2.294, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 6.3659628918746e-05, | |
| "loss": 0.8984, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_bleu": 0.11998407865663271, | |
| "eval_exact_match": 0.138, | |
| "eval_loss": 0.8919487595558167, | |
| "eval_rouge1": 0.546341326360675, | |
| "eval_rouge2": 0.3714077684410343, | |
| "eval_rougeL": 0.5285236062967356, | |
| "eval_rougeLsum": 0.535261365301597, | |
| "eval_runtime": 26.8866, | |
| "eval_samples_per_second": 74.386, | |
| "eval_steps_per_second": 2.343, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 9.564939219449776e-05, | |
| "loss": 0.8121, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_bleu": 0.11580804646751057, | |
| "eval_exact_match": 0.1455, | |
| "eval_loss": 0.8583337664604187, | |
| "eval_rouge1": 0.5528659122019346, | |
| "eval_rouge2": 0.3786855675064588, | |
| "eval_rougeL": 0.535002514875875, | |
| "eval_rougeLsum": 0.5425756750433103, | |
| "eval_runtime": 27.5302, | |
| "eval_samples_per_second": 72.647, | |
| "eval_steps_per_second": 2.288, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 9.854481759692796e-05, | |
| "loss": 0.7598, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_bleu": 0.11973654523564387, | |
| "eval_exact_match": 0.1485, | |
| "eval_loss": 0.8436598181724548, | |
| "eval_rouge1": 0.5541164072038078, | |
| "eval_rouge2": 0.3813328094993438, | |
| "eval_rougeL": 0.5354722356320805, | |
| "eval_rougeLsum": 0.5432424855167899, | |
| "eval_runtime": 26.6962, | |
| "eval_samples_per_second": 74.917, | |
| "eval_steps_per_second": 2.36, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 9.686057870448345e-05, | |
| "loss": 0.7289, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_bleu": 0.12215125938884584, | |
| "eval_exact_match": 0.158, | |
| "eval_loss": 0.818922758102417, | |
| "eval_rouge1": 0.5596647043092989, | |
| "eval_rouge2": 0.390646741130832, | |
| "eval_rougeL": 0.5415781749603358, | |
| "eval_rougeLsum": 0.5501483448643409, | |
| "eval_runtime": 26.4885, | |
| "eval_samples_per_second": 75.504, | |
| "eval_steps_per_second": 2.378, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 9.517633981203894e-05, | |
| "loss": 0.7053, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_bleu": 0.12223620743911237, | |
| "eval_exact_match": 0.161, | |
| "eval_loss": 0.8145434856414795, | |
| "eval_rouge1": 0.5571603682618643, | |
| "eval_rouge2": 0.3887993919896527, | |
| "eval_rougeL": 0.5392381596924516, | |
| "eval_rougeLsum": 0.5469429464366221, | |
| "eval_runtime": 27.992, | |
| "eval_samples_per_second": 71.449, | |
| "eval_steps_per_second": 2.251, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 9.349210091959444e-05, | |
| "loss": 0.6544, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "eval_bleu": 0.1260404864365832, | |
| "eval_exact_match": 0.1565, | |
| "eval_loss": 0.7981612682342529, | |
| "eval_rouge1": 0.5606467979991658, | |
| "eval_rouge2": 0.3920123242296646, | |
| "eval_rougeL": 0.5435919709288143, | |
| "eval_rougeLsum": 0.5516785996846396, | |
| "eval_runtime": 29.5652, | |
| "eval_samples_per_second": 67.647, | |
| "eval_steps_per_second": 2.131, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 9.180786202714994e-05, | |
| "loss": 0.6334, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "eval_bleu": 0.12839687243556736, | |
| "eval_exact_match": 0.1585, | |
| "eval_loss": 0.7973963618278503, | |
| "eval_rouge1": 0.5633046028358244, | |
| "eval_rouge2": 0.3905965243856279, | |
| "eval_rougeL": 0.5447842726270915, | |
| "eval_rougeLsum": 0.5529333478079217, | |
| "eval_runtime": 26.3748, | |
| "eval_samples_per_second": 75.83, | |
| "eval_steps_per_second": 2.389, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 9.012362313470542e-05, | |
| "loss": 0.6236, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "eval_bleu": 0.12748409364928656, | |
| "eval_exact_match": 0.163, | |
| "eval_loss": 0.7942736744880676, | |
| "eval_rouge1": 0.563881072938117, | |
| "eval_rouge2": 0.3930844670404538, | |
| "eval_rougeL": 0.5455192493710137, | |
| "eval_rougeLsum": 0.5541560433164279, | |
| "eval_runtime": 26.3891, | |
| "eval_samples_per_second": 75.789, | |
| "eval_steps_per_second": 2.387, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 8.843938424226093e-05, | |
| "loss": 0.6221, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "eval_bleu": 0.13095132849637034, | |
| "eval_exact_match": 0.1655, | |
| "eval_loss": 0.782397449016571, | |
| "eval_rouge1": 0.571774543234057, | |
| "eval_rouge2": 0.40112070812038864, | |
| "eval_rougeL": 0.5536602781518731, | |
| "eval_rougeLsum": 0.5621325917699274, | |
| "eval_runtime": 27.1882, | |
| "eval_samples_per_second": 73.561, | |
| "eval_steps_per_second": 2.317, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 8.675514534981643e-05, | |
| "loss": 0.608, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "eval_bleu": 0.13144704649097816, | |
| "eval_exact_match": 0.163, | |
| "eval_loss": 0.7792329788208008, | |
| "eval_rouge1": 0.5663801985181786, | |
| "eval_rouge2": 0.3996756504619762, | |
| "eval_rougeL": 0.5490225477397204, | |
| "eval_rougeLsum": 0.556696752293008, | |
| "eval_runtime": 26.3826, | |
| "eval_samples_per_second": 75.808, | |
| "eval_steps_per_second": 2.388, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 8.507090645737192e-05, | |
| "loss": 0.5956, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "eval_bleu": 0.129401969984806, | |
| "eval_exact_match": 0.1605, | |
| "eval_loss": 0.7785006165504456, | |
| "eval_rouge1": 0.5640650180352025, | |
| "eval_rouge2": 0.39806305672301234, | |
| "eval_rougeL": 0.5469935550994057, | |
| "eval_rougeLsum": 0.554556710156975, | |
| "eval_runtime": 27.3051, | |
| "eval_samples_per_second": 73.246, | |
| "eval_steps_per_second": 2.307, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 8.338666756492741e-05, | |
| "loss": 0.5701, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "eval_bleu": 0.13363680452673993, | |
| "eval_exact_match": 0.157, | |
| "eval_loss": 0.7799766063690186, | |
| "eval_rouge1": 0.5672994124585793, | |
| "eval_rouge2": 0.39553178231486497, | |
| "eval_rougeL": 0.548936720126607, | |
| "eval_rougeLsum": 0.5568480771592814, | |
| "eval_runtime": 26.8025, | |
| "eval_samples_per_second": 74.62, | |
| "eval_steps_per_second": 2.351, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 8.170242867248291e-05, | |
| "loss": 0.5378, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "eval_bleu": 0.13079743156246348, | |
| "eval_exact_match": 0.1655, | |
| "eval_loss": 0.7720439434051514, | |
| "eval_rouge1": 0.5685604278995763, | |
| "eval_rouge2": 0.3999533201987808, | |
| "eval_rougeL": 0.5504327783527796, | |
| "eval_rougeLsum": 0.5582442604826536, | |
| "eval_runtime": 26.7858, | |
| "eval_samples_per_second": 74.666, | |
| "eval_steps_per_second": 2.352, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 8.00181897800384e-05, | |
| "loss": 0.541, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "eval_bleu": 0.1312928889201776, | |
| "eval_exact_match": 0.1625, | |
| "eval_loss": 0.7708559632301331, | |
| "eval_rouge1": 0.5698993331552187, | |
| "eval_rouge2": 0.39836218536255497, | |
| "eval_rougeL": 0.5510518000592355, | |
| "eval_rougeLsum": 0.5590054429199334, | |
| "eval_runtime": 26.5491, | |
| "eval_samples_per_second": 75.332, | |
| "eval_steps_per_second": 2.373, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 7.83339508875939e-05, | |
| "loss": 0.5359, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "eval_bleu": 0.133238582586381, | |
| "eval_exact_match": 0.164, | |
| "eval_loss": 0.767312228679657, | |
| "eval_rouge1": 0.5696523576197161, | |
| "eval_rouge2": 0.40229167377006236, | |
| "eval_rougeL": 0.552121263102242, | |
| "eval_rougeLsum": 0.5600576350734027, | |
| "eval_runtime": 26.7037, | |
| "eval_samples_per_second": 74.896, | |
| "eval_steps_per_second": 2.359, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 7.664971199514939e-05, | |
| "loss": 0.5322, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "eval_bleu": 0.13498312180179964, | |
| "eval_exact_match": 0.1665, | |
| "eval_loss": 0.7641937732696533, | |
| "eval_rouge1": 0.5707696930577069, | |
| "eval_rouge2": 0.403346138073659, | |
| "eval_rougeL": 0.5527280072901636, | |
| "eval_rougeLsum": 0.5605579795104842, | |
| "eval_runtime": 26.4882, | |
| "eval_samples_per_second": 75.505, | |
| "eval_steps_per_second": 2.378, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 7.496547310270489e-05, | |
| "loss": 0.5387, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "eval_bleu": 0.13416837075728422, | |
| "eval_exact_match": 0.159, | |
| "eval_loss": 0.7621653079986572, | |
| "eval_rouge1": 0.5671758743776842, | |
| "eval_rouge2": 0.3987572074969532, | |
| "eval_rougeL": 0.5499787838213916, | |
| "eval_rougeLsum": 0.55728689293535, | |
| "eval_runtime": 26.7851, | |
| "eval_samples_per_second": 74.668, | |
| "eval_steps_per_second": 2.352, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 7.328123421026039e-05, | |
| "loss": 0.514, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "eval_bleu": 0.13519274318497243, | |
| "eval_exact_match": 0.166, | |
| "eval_loss": 0.7700380682945251, | |
| "eval_rouge1": 0.572246331088752, | |
| "eval_rouge2": 0.40519052168186803, | |
| "eval_rougeL": 0.5545858464982438, | |
| "eval_rougeLsum": 0.5618015934184992, | |
| "eval_runtime": 26.4898, | |
| "eval_samples_per_second": 75.501, | |
| "eval_steps_per_second": 2.378, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 7.159699531781589e-05, | |
| "loss": 0.4895, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "eval_bleu": 0.13587785975036965, | |
| "eval_exact_match": 0.1615, | |
| "eval_loss": 0.7675954699516296, | |
| "eval_rouge1": 0.5695980848985347, | |
| "eval_rouge2": 0.40156815801776047, | |
| "eval_rougeL": 0.551645493171788, | |
| "eval_rougeLsum": 0.5591021610099983, | |
| "eval_runtime": 28.9264, | |
| "eval_samples_per_second": 69.141, | |
| "eval_steps_per_second": 2.178, | |
| "step": 10000 | |
| } | |
| ], | |
| "max_steps": 31250, | |
| "num_train_epochs": 10, | |
| "total_flos": 4.252071441727488e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |