| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.18331805682859761, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.007332722273143905, | |
| "grad_norm": 28.16514015197754, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 9.2674, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007332722273143905, | |
| "eval_loss": 9.866511344909668, | |
| "eval_runtime": 19.2647, | |
| "eval_samples_per_second": 5.969, | |
| "eval_steps_per_second": 3.011, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01466544454628781, | |
| "grad_norm": 24.430660247802734, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 9.5029, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.021998166819431713, | |
| "grad_norm": 26.187023162841797, | |
| "learning_rate": 0.0001, | |
| "loss": 8.6161, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.02933088909257562, | |
| "grad_norm": 34.216064453125, | |
| "learning_rate": 9.99524110790929e-05, | |
| "loss": 6.4504, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03666361136571952, | |
| "grad_norm": 19.48601722717285, | |
| "learning_rate": 9.980973490458728e-05, | |
| "loss": 2.3852, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.043996333638863426, | |
| "grad_norm": 12.056840896606445, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.3161, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.051329055912007336, | |
| "grad_norm": 11.642943382263184, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 1.0061, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.05866177818515124, | |
| "grad_norm": 11.32752799987793, | |
| "learning_rate": 9.881480035599667e-05, | |
| "loss": 0.8541, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.06599450045829514, | |
| "grad_norm": 9.898649215698242, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.9269, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.07332722273143905, | |
| "grad_norm": 7.723211765289307, | |
| "learning_rate": 9.768584753741134e-05, | |
| "loss": 0.8073, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08065994500458296, | |
| "grad_norm": 5.739726543426514, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.8241, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.08799266727772685, | |
| "grad_norm": 4.319146156311035, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.795, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.09532538955087076, | |
| "grad_norm": 3.2486860752105713, | |
| "learning_rate": 9.53153893518325e-05, | |
| "loss": 0.7032, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.10265811182401467, | |
| "grad_norm": 4.425631046295166, | |
| "learning_rate": 9.435054165891109e-05, | |
| "loss": 0.8337, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.10999083409715857, | |
| "grad_norm": 6.929285526275635, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.9103, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.11732355637030248, | |
| "grad_norm": 3.867265224456787, | |
| "learning_rate": 9.21695722906443e-05, | |
| "loss": 0.7631, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.12465627864344637, | |
| "grad_norm": 2.8584396839141846, | |
| "learning_rate": 9.09576022144496e-05, | |
| "loss": 0.7623, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.13198900091659027, | |
| "grad_norm": 12.93197250366211, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.8318, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.13932172318973418, | |
| "grad_norm": 3.614393949508667, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 0.7725, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.1466544454628781, | |
| "grad_norm": 2.7207541465759277, | |
| "learning_rate": 8.68638668405062e-05, | |
| "loss": 0.7097, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.153987167736022, | |
| "grad_norm": 2.9660866260528564, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.7359, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.1613198900091659, | |
| "grad_norm": 4.409785747528076, | |
| "learning_rate": 8.377951038078302e-05, | |
| "loss": 0.7975, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.1686526122823098, | |
| "grad_norm": 3.662649631500244, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 0.7338, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.1759853345554537, | |
| "grad_norm": 2.1172139644622803, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.7364, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.18331805682859761, | |
| "grad_norm": 5.383273601531982, | |
| "learning_rate": 7.86788218175523e-05, | |
| "loss": 0.8608, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.18331805682859761, | |
| "eval_loss": 0.7034161686897278, | |
| "eval_runtime": 19.0608, | |
| "eval_samples_per_second": 6.033, | |
| "eval_steps_per_second": 3.043, | |
| "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": 3.73005226082304e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |