| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.1593625498007968, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006374501992031873, | |
| "grad_norm": 0.5776119828224182, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.3356, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006374501992031873, | |
| "eval_loss": 1.051254153251648, | |
| "eval_runtime": 29.2997, | |
| "eval_samples_per_second": 9.044, | |
| "eval_steps_per_second": 4.539, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.012749003984063745, | |
| "grad_norm": 0.6642381548881531, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 0.4101, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.019123505976095617, | |
| "grad_norm": 0.6346176862716675, | |
| "learning_rate": 0.0001, | |
| "loss": 0.404, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.02549800796812749, | |
| "grad_norm": 0.5157294273376465, | |
| "learning_rate": 9.99524110790929e-05, | |
| "loss": 0.3433, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03187250996015936, | |
| "grad_norm": 0.4020949900150299, | |
| "learning_rate": 9.980973490458728e-05, | |
| "loss": 0.2673, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03824701195219123, | |
| "grad_norm": 0.4330461621284485, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.2404, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.04462151394422311, | |
| "grad_norm": 0.3167223036289215, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 0.1883, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.05099601593625498, | |
| "grad_norm": 0.7258068919181824, | |
| "learning_rate": 9.881480035599667e-05, | |
| "loss": 0.1843, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.05737051792828685, | |
| "grad_norm": 0.3239709734916687, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.1234, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.06374501992031872, | |
| "grad_norm": 0.3959621787071228, | |
| "learning_rate": 9.768584753741134e-05, | |
| "loss": 0.1336, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0701195219123506, | |
| "grad_norm": 0.5370655655860901, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.1147, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.07649402390438247, | |
| "grad_norm": 0.7307567596435547, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.1131, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.08286852589641434, | |
| "grad_norm": 0.46945270895957947, | |
| "learning_rate": 9.53153893518325e-05, | |
| "loss": 0.0875, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.08924302788844622, | |
| "grad_norm": 0.2729243040084839, | |
| "learning_rate": 9.435054165891109e-05, | |
| "loss": 0.0752, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.09561752988047809, | |
| "grad_norm": 0.2799117863178253, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.0803, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.10199203187250996, | |
| "grad_norm": 0.3926849663257599, | |
| "learning_rate": 9.21695722906443e-05, | |
| "loss": 0.0718, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.10836653386454183, | |
| "grad_norm": 0.3918418288230896, | |
| "learning_rate": 9.09576022144496e-05, | |
| "loss": 0.0657, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.1147410358565737, | |
| "grad_norm": 0.3637863099575043, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.05, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.12111553784860558, | |
| "grad_norm": 0.3199478089809418, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 0.0562, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.12749003984063745, | |
| "grad_norm": 0.3835548758506775, | |
| "learning_rate": 8.68638668405062e-05, | |
| "loss": 0.0716, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.13386454183266933, | |
| "grad_norm": 0.5802797675132751, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0534, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.1402390438247012, | |
| "grad_norm": 0.3737954795360565, | |
| "learning_rate": 8.377951038078302e-05, | |
| "loss": 0.0325, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.14661354581673305, | |
| "grad_norm": 0.3237304091453552, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 0.054, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.15298804780876493, | |
| "grad_norm": 0.2729124128818512, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.0204, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.1593625498007968, | |
| "grad_norm": 0.36050495505332947, | |
| "learning_rate": 7.86788218175523e-05, | |
| "loss": 0.0357, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1593625498007968, | |
| "eval_loss": 0.07187294214963913, | |
| "eval_runtime": 28.4766, | |
| "eval_samples_per_second": 9.306, | |
| "eval_steps_per_second": 4.671, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.6502401196032e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |