| { | |
| "best_metric": 2.452415943145752, | |
| "best_model_checkpoint": "dq158/pingusPongus/checkpoint-25291", | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 25291, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0004, | |
| "loss": 3.2511, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0003999995708217828, | |
| "loss": 2.8938, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00039999828328897294, | |
| "loss": 2.7835, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00039999613740709635, | |
| "loss": 2.7405, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00039999313318536277, | |
| "loss": 2.6816, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00039998927063666543, | |
| "loss": 2.7085, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00039998454977758173, | |
| "loss": 2.7713, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0003999789706283725, | |
| "loss": 2.6722, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0003999725332129823, | |
| "loss": 2.6873, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.000399965237559039, | |
| "loss": 2.6403, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00039995708369785403, | |
| "loss": 2.6328, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.000399948071664422, | |
| "loss": 2.6212, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.0003999382014974206, | |
| "loss": 2.581, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.00039992747323921036, | |
| "loss": 2.6699, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0003999158869358347, | |
| "loss": 2.6095, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.00039990344263701955, | |
| "loss": 2.6429, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.00039989014039617295, | |
| "loss": 2.6528, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0003998759802703854, | |
| "loss": 2.5395, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.000399860962320429, | |
| "loss": 2.6032, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.00039984508661075754, | |
| "loss": 2.6129, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.0003998283532095061, | |
| "loss": 2.584, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.00039981076218849077, | |
| "loss": 2.6327, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.00039979231362320845, | |
| "loss": 2.6264, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.00039977300759283627, | |
| "loss": 2.6226, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.0003997528441802316, | |
| "loss": 2.5442, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.0003997318234719313, | |
| "loss": 2.622, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.0003997099455581518, | |
| "loss": 2.5825, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.0003996872105327882, | |
| "loss": 2.6382, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.0003996636184934145, | |
| "loss": 2.5633, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.00039963916954128235, | |
| "loss": 2.5505, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.0003996138637813214, | |
| "loss": 2.5991, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.00039958770132213857, | |
| "loss": 2.5736, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.00039956068227601734, | |
| "loss": 2.5436, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.0003995328067589175, | |
| "loss": 2.5502, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.00039950407489047486, | |
| "loss": 2.5067, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.00039947448679400027, | |
| "loss": 2.6009, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.00039944404259647934, | |
| "loss": 2.5333, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.00039941274242857205, | |
| "loss": 2.5414, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.00039938058642461174, | |
| "loss": 2.5632, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.0003993475747226051, | |
| "loss": 2.5763, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.0003993137074642312, | |
| "loss": 2.619, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.00039927898479484076, | |
| "loss": 2.5508, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.0003992434068634561, | |
| "loss": 2.5927, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.00039920697382276986, | |
| "loss": 2.5342, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.0003991696858291447, | |
| "loss": 2.5948, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.0003991315430426126, | |
| "loss": 2.5893, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.0003990925456268741, | |
| "loss": 2.5284, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 0.0003990526937492976, | |
| "loss": 2.5097, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.0003990119875809187, | |
| "loss": 2.6065, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.00039897042729643934, | |
| "loss": 2.5628, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_bleu": 1.0, | |
| "eval_brevity_penalty": 1.0, | |
| "eval_length_ratio": 1.0, | |
| "eval_loss": 2.452415943145752, | |
| "eval_precisions": [ | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 1.0 | |
| ], | |
| "eval_reference_length": 1439232, | |
| "eval_runtime": 2451.7899, | |
| "eval_samples_per_second": 1.147, | |
| "eval_steps_per_second": 1.147, | |
| "eval_translation_length": 1439232, | |
| "step": 25291 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 758730, | |
| "num_train_epochs": 30, | |
| "save_steps": 500, | |
| "total_flos": 2.1666322696686797e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |