| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 20.0, | |
| "global_step": 3200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_bleu": 0.060808744840238495, | |
| "eval_loss": 2.7135698795318604, | |
| "eval_runtime": 315.8806, | |
| "eval_samples_per_second": 3.603, | |
| "eval_steps_per_second": 0.114, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_bleu": 0.23820890608280518, | |
| "eval_loss": 1.7017812728881836, | |
| "eval_runtime": 199.1113, | |
| "eval_samples_per_second": 5.715, | |
| "eval_steps_per_second": 0.181, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_bleu": 0.2333157930860921, | |
| "eval_loss": 1.7553855180740356, | |
| "eval_runtime": 183.4244, | |
| "eval_samples_per_second": 6.204, | |
| "eval_steps_per_second": 0.196, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 1.69125e-05, | |
| "loss": 2.1899, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_bleu": 0.24403815580286167, | |
| "eval_loss": 1.729722499847412, | |
| "eval_runtime": 199.443, | |
| "eval_samples_per_second": 5.706, | |
| "eval_steps_per_second": 0.181, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_bleu": 0.24248370965297772, | |
| "eval_loss": 1.7367736101150513, | |
| "eval_runtime": 195.0886, | |
| "eval_samples_per_second": 5.833, | |
| "eval_steps_per_second": 0.185, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_bleu": 0.24708175633139415, | |
| "eval_loss": 1.7663674354553223, | |
| "eval_runtime": 190.8193, | |
| "eval_samples_per_second": 5.964, | |
| "eval_steps_per_second": 0.189, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 6.25, | |
| "learning_rate": 1.37875e-05, | |
| "loss": 1.1629, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_bleu": 0.24734088993827677, | |
| "eval_loss": 1.8130639791488647, | |
| "eval_runtime": 185.235, | |
| "eval_samples_per_second": 6.144, | |
| "eval_steps_per_second": 0.194, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_bleu": 0.25035574867022287, | |
| "eval_loss": 1.860228419303894, | |
| "eval_runtime": 191.0903, | |
| "eval_samples_per_second": 5.955, | |
| "eval_steps_per_second": 0.188, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_bleu": 0.2550337582147487, | |
| "eval_loss": 1.9042994976043701, | |
| "eval_runtime": 192.163, | |
| "eval_samples_per_second": 5.922, | |
| "eval_steps_per_second": 0.187, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 9.38, | |
| "learning_rate": 1.06625e-05, | |
| "loss": 0.807, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_bleu": 0.255168022317063, | |
| "eval_loss": 1.9512995481491089, | |
| "eval_runtime": 193.6447, | |
| "eval_samples_per_second": 5.877, | |
| "eval_steps_per_second": 0.186, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_bleu": 0.2583105775089707, | |
| "eval_loss": 2.0014865398406982, | |
| "eval_runtime": 194.2032, | |
| "eval_samples_per_second": 5.86, | |
| "eval_steps_per_second": 0.185, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_bleu": 0.2611697071205468, | |
| "eval_loss": 2.036052942276001, | |
| "eval_runtime": 190.4985, | |
| "eval_samples_per_second": 5.974, | |
| "eval_steps_per_second": 0.189, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 12.5, | |
| "learning_rate": 7.537500000000001e-06, | |
| "loss": 0.5977, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_bleu": 0.2624028465673082, | |
| "eval_loss": 2.0794923305511475, | |
| "eval_runtime": 192.5774, | |
| "eval_samples_per_second": 5.909, | |
| "eval_steps_per_second": 0.187, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_bleu": 0.26034097889106955, | |
| "eval_loss": 2.1036157608032227, | |
| "eval_runtime": 198.097, | |
| "eval_samples_per_second": 5.745, | |
| "eval_steps_per_second": 0.182, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_bleu": 0.264538215714405, | |
| "eval_loss": 2.1185383796691895, | |
| "eval_runtime": 189.6413, | |
| "eval_samples_per_second": 6.001, | |
| "eval_steps_per_second": 0.19, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 15.62, | |
| "learning_rate": 4.4125000000000005e-06, | |
| "loss": 0.4697, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_bleu": 0.2666872542669057, | |
| "eval_loss": 2.1361563205718994, | |
| "eval_runtime": 189.4756, | |
| "eval_samples_per_second": 6.006, | |
| "eval_steps_per_second": 0.19, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_bleu": 0.2652516887552325, | |
| "eval_loss": 2.162111520767212, | |
| "eval_runtime": 193.0939, | |
| "eval_samples_per_second": 5.894, | |
| "eval_steps_per_second": 0.186, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_bleu": 0.2673360550776601, | |
| "eval_loss": 2.163081169128418, | |
| "eval_runtime": 190.9327, | |
| "eval_samples_per_second": 5.96, | |
| "eval_steps_per_second": 0.189, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 18.75, | |
| "learning_rate": 1.2875000000000002e-06, | |
| "loss": 0.4032, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_bleu": 0.2660614156233256, | |
| "eval_loss": 2.1683239936828613, | |
| "eval_runtime": 190.2616, | |
| "eval_samples_per_second": 5.981, | |
| "eval_steps_per_second": 0.189, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_bleu": 0.2674984140410235, | |
| "eval_loss": 2.173663377761841, | |
| "eval_runtime": 189.5283, | |
| "eval_samples_per_second": 6.004, | |
| "eval_steps_per_second": 0.19, | |
| "step": 3200 | |
| } | |
| ], | |
| "max_steps": 3200, | |
| "num_train_epochs": 20, | |
| "total_flos": 5.530638338624717e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |