| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.05193306405077899, | |
| "eval_steps": 9, | |
| "global_step": 45, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001154068090017311, | |
| "eval_loss": 2.0465598106384277, | |
| "eval_runtime": 103.0211, | |
| "eval_samples_per_second": 14.172, | |
| "eval_steps_per_second": 1.776, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003462204270051933, | |
| "grad_norm": 8.097893714904785, | |
| "learning_rate": 3e-05, | |
| "loss": 8.0719, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006924408540103866, | |
| "grad_norm": 5.514200210571289, | |
| "learning_rate": 6e-05, | |
| "loss": 8.0211, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0103866128101558, | |
| "grad_norm": 5.214906692504883, | |
| "learning_rate": 9e-05, | |
| "loss": 8.0571, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0103866128101558, | |
| "eval_loss": 1.9573053121566772, | |
| "eval_runtime": 104.5011, | |
| "eval_samples_per_second": 13.971, | |
| "eval_steps_per_second": 1.751, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.013848817080207732, | |
| "grad_norm": 4.61670446395874, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 7.7237, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.017311021350259664, | |
| "grad_norm": 4.776439666748047, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 7.5723, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0207732256203116, | |
| "grad_norm": 3.863844394683838, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 7.8625, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0207732256203116, | |
| "eval_loss": 1.938367247581482, | |
| "eval_runtime": 104.6138, | |
| "eval_samples_per_second": 13.956, | |
| "eval_steps_per_second": 1.749, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.024235429890363532, | |
| "grad_norm": 3.75036358833313, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 7.5972, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.027697634160415464, | |
| "grad_norm": 3.694056510925293, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 7.325, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.031159838430467397, | |
| "grad_norm": 3.767008066177368, | |
| "learning_rate": 9.145187862775209e-05, | |
| "loss": 7.8502, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.031159838430467397, | |
| "eval_loss": 1.9282969236373901, | |
| "eval_runtime": 104.5512, | |
| "eval_samples_per_second": 13.964, | |
| "eval_steps_per_second": 1.75, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03462204270051933, | |
| "grad_norm": 3.892972230911255, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 7.737, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.038084246970571264, | |
| "grad_norm": 4.205379962921143, | |
| "learning_rate": 8.473291852294987e-05, | |
| "loss": 7.7768, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0415464512406232, | |
| "grad_norm": 4.217511177062988, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 7.7462, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0415464512406232, | |
| "eval_loss": 1.9257190227508545, | |
| "eval_runtime": 104.5925, | |
| "eval_samples_per_second": 13.959, | |
| "eval_steps_per_second": 1.75, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.04500865551067513, | |
| "grad_norm": 4.240529537200928, | |
| "learning_rate": 7.649596321166024e-05, | |
| "loss": 7.9651, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.048470859780727064, | |
| "grad_norm": 4.575836658477783, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 7.7481, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.05193306405077899, | |
| "grad_norm": 4.351076126098633, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 7.9443, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.05193306405077899, | |
| "eval_loss": 1.9247784614562988, | |
| "eval_runtime": 104.5498, | |
| "eval_samples_per_second": 13.965, | |
| "eval_steps_per_second": 1.75, | |
| "step": 45 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 9, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.309618477170688e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |