| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.003923645851725424, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.847291703450846e-05, | |
| "eval_loss": 9.440312385559082, | |
| "eval_runtime": 178.4372, | |
| "eval_samples_per_second": 30.072, | |
| "eval_steps_per_second": 15.036, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00039236458517254234, | |
| "grad_norm": 10.191022872924805, | |
| "learning_rate": 5e-05, | |
| "loss": 9.1741, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0007847291703450847, | |
| "grad_norm": 13.922800064086914, | |
| "learning_rate": 0.0001, | |
| "loss": 8.4145, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0007847291703450847, | |
| "eval_loss": 7.324878215789795, | |
| "eval_runtime": 179.7113, | |
| "eval_samples_per_second": 29.859, | |
| "eval_steps_per_second": 14.93, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.001177093755517627, | |
| "grad_norm": 19.77543067932129, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 5.9276, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0015694583406901694, | |
| "grad_norm": 7.978977203369141, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.5234, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0015694583406901694, | |
| "eval_loss": 2.3124942779541016, | |
| "eval_runtime": 179.6305, | |
| "eval_samples_per_second": 29.872, | |
| "eval_steps_per_second": 14.936, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.001961822925862712, | |
| "grad_norm": 8.624098777770996, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.6678, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.002354187511035254, | |
| "grad_norm": 7.205264568328857, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6164, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.002354187511035254, | |
| "eval_loss": 0.5965997576713562, | |
| "eval_runtime": 179.9007, | |
| "eval_samples_per_second": 29.828, | |
| "eval_steps_per_second": 14.914, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0027465520962077963, | |
| "grad_norm": 8.6773099899292, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.6068, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0031389166813803387, | |
| "grad_norm": 7.56188440322876, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.5115, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0031389166813803387, | |
| "eval_loss": 0.5395087599754333, | |
| "eval_runtime": 179.6605, | |
| "eval_samples_per_second": 29.867, | |
| "eval_steps_per_second": 14.934, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0035312812665528807, | |
| "grad_norm": 9.424992561340332, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.507, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.003923645851725424, | |
| "grad_norm": 10.194769859313965, | |
| "learning_rate": 0.0, | |
| "loss": 0.5211, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.003923645851725424, | |
| "eval_loss": 0.5438435077667236, | |
| "eval_runtime": 179.8406, | |
| "eval_samples_per_second": 29.838, | |
| "eval_steps_per_second": 14.919, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1202727577190400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |