| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0017460386747566458, | |
| "eval_steps": 2, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 8.730193373783229e-05, | |
| "grad_norm": 1.6029466390609741, | |
| "learning_rate": 2e-05, | |
| "loss": 8.6163, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 8.730193373783229e-05, | |
| "eval_loss": 8.479549407958984, | |
| "eval_runtime": 103.8322, | |
| "eval_samples_per_second": 46.45, | |
| "eval_steps_per_second": 23.23, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00017460386747566458, | |
| "grad_norm": 1.4574332237243652, | |
| "learning_rate": 4e-05, | |
| "loss": 8.5938, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00017460386747566458, | |
| "eval_loss": 8.479405403137207, | |
| "eval_runtime": 103.6916, | |
| "eval_samples_per_second": 46.513, | |
| "eval_steps_per_second": 23.261, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00026190580121349685, | |
| "grad_norm": 1.5145901441574097, | |
| "learning_rate": 6e-05, | |
| "loss": 8.2675, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00034920773495132916, | |
| "grad_norm": 2.280639410018921, | |
| "learning_rate": 8e-05, | |
| "loss": 8.7145, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00034920773495132916, | |
| "eval_loss": 8.475335121154785, | |
| "eval_runtime": 103.7528, | |
| "eval_samples_per_second": 46.485, | |
| "eval_steps_per_second": 23.248, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00043650966868916146, | |
| "grad_norm": 1.6258833408355713, | |
| "learning_rate": 0.0001, | |
| "loss": 8.7465, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0005238116024269937, | |
| "grad_norm": 1.7357032299041748, | |
| "learning_rate": 0.00012, | |
| "loss": 8.6569, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0005238116024269937, | |
| "eval_loss": 8.458909034729004, | |
| "eval_runtime": 103.6326, | |
| "eval_samples_per_second": 46.539, | |
| "eval_steps_per_second": 23.275, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.000611113536164826, | |
| "grad_norm": 1.6086039543151855, | |
| "learning_rate": 0.00014, | |
| "loss": 8.5566, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0006984154699026583, | |
| "grad_norm": 1.5698775053024292, | |
| "learning_rate": 0.00016, | |
| "loss": 8.2834, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0006984154699026583, | |
| "eval_loss": 8.429530143737793, | |
| "eval_runtime": 103.6048, | |
| "eval_samples_per_second": 46.552, | |
| "eval_steps_per_second": 23.281, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0007857174036404906, | |
| "grad_norm": 1.3347610235214233, | |
| "learning_rate": 0.00018, | |
| "loss": 8.555, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0008730193373783229, | |
| "grad_norm": 1.6474040746688843, | |
| "learning_rate": 0.0002, | |
| "loss": 9.0077, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0008730193373783229, | |
| "eval_loss": 8.39326000213623, | |
| "eval_runtime": 103.6132, | |
| "eval_samples_per_second": 46.548, | |
| "eval_steps_per_second": 23.279, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0009603212711161552, | |
| "grad_norm": 1.4845318794250488, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 8.1931, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0010476232048539874, | |
| "grad_norm": 1.4644606113433838, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 8.3223, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0010476232048539874, | |
| "eval_loss": 8.353034973144531, | |
| "eval_runtime": 103.6559, | |
| "eval_samples_per_second": 46.529, | |
| "eval_steps_per_second": 23.269, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0011349251385918198, | |
| "grad_norm": 1.5357258319854736, | |
| "learning_rate": 0.00015877852522924732, | |
| "loss": 8.3197, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.001222227072329652, | |
| "grad_norm": 1.6351239681243896, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 8.5098, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.001222227072329652, | |
| "eval_loss": 8.318305015563965, | |
| "eval_runtime": 103.5949, | |
| "eval_samples_per_second": 46.556, | |
| "eval_steps_per_second": 23.283, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0013095290060674844, | |
| "grad_norm": 1.526180624961853, | |
| "learning_rate": 0.0001, | |
| "loss": 8.823, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0013968309398053166, | |
| "grad_norm": 1.3799971342086792, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 8.3398, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0013968309398053166, | |
| "eval_loss": 8.296876907348633, | |
| "eval_runtime": 103.6384, | |
| "eval_samples_per_second": 46.537, | |
| "eval_steps_per_second": 23.273, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.001484132873543149, | |
| "grad_norm": 1.414531946182251, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 7.6532, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0015714348072809812, | |
| "grad_norm": 1.379723310470581, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 8.0738, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0015714348072809812, | |
| "eval_loss": 8.285407066345215, | |
| "eval_runtime": 103.5728, | |
| "eval_samples_per_second": 46.566, | |
| "eval_steps_per_second": 23.288, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0016587367410188136, | |
| "grad_norm": 1.4528592824935913, | |
| "learning_rate": 4.8943483704846475e-06, | |
| "loss": 8.5602, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0017460386747566458, | |
| "grad_norm": 1.5250357389450073, | |
| "learning_rate": 0.0, | |
| "loss": 8.5815, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0017460386747566458, | |
| "eval_loss": 8.283023834228516, | |
| "eval_runtime": 103.5886, | |
| "eval_samples_per_second": 46.559, | |
| "eval_steps_per_second": 23.284, | |
| "step": 20 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 20, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5244683550720.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |