| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0024904119141305973, | |
| "eval_steps": 9, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 9.961647656522389e-05, | |
| "grad_norm": 0.3748319745063782, | |
| "learning_rate": 1e-05, | |
| "loss": 1.6077, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 9.961647656522389e-05, | |
| "eval_loss": 1.0737049579620361, | |
| "eval_runtime": 1789.5077, | |
| "eval_samples_per_second": 4.724, | |
| "eval_steps_per_second": 0.591, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00019923295313044778, | |
| "grad_norm": 0.47770676016807556, | |
| "learning_rate": 2e-05, | |
| "loss": 2.0602, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0002988494296956717, | |
| "grad_norm": 0.4726722538471222, | |
| "learning_rate": 3e-05, | |
| "loss": 2.2152, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00039846590626089557, | |
| "grad_norm": 0.509148359298706, | |
| "learning_rate": 4e-05, | |
| "loss": 2.2219, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0004980823828261194, | |
| "grad_norm": 0.6239567399024963, | |
| "learning_rate": 5e-05, | |
| "loss": 2.3138, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0005976988593913434, | |
| "grad_norm": 0.5875715017318726, | |
| "learning_rate": 6e-05, | |
| "loss": 2.3489, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0006973153359565673, | |
| "grad_norm": 0.47263002395629883, | |
| "learning_rate": 7e-05, | |
| "loss": 1.813, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0007969318125217911, | |
| "grad_norm": 0.5967614054679871, | |
| "learning_rate": 8e-05, | |
| "loss": 2.1826, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.000896548289087015, | |
| "grad_norm": 0.750761866569519, | |
| "learning_rate": 9e-05, | |
| "loss": 2.2517, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.000896548289087015, | |
| "eval_loss": 1.023254632949829, | |
| "eval_runtime": 1791.5954, | |
| "eval_samples_per_second": 4.719, | |
| "eval_steps_per_second": 0.59, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0009961647656522388, | |
| "grad_norm": 0.7320921421051025, | |
| "learning_rate": 0.0001, | |
| "loss": 2.3192, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0010957812422174628, | |
| "grad_norm": 0.6750331521034241, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 1.9599, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0011953977187826868, | |
| "grad_norm": 0.7737115025520325, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 2.0029, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0012950141953479105, | |
| "grad_norm": 0.7610511183738708, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 1.983, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0013946306719131345, | |
| "grad_norm": 0.739033043384552, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 2.0262, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0014942471484783583, | |
| "grad_norm": 1.2172285318374634, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 1.9857, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0015938636250435823, | |
| "grad_norm": 1.3501102924346924, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 2.0328, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.001693480101608806, | |
| "grad_norm": 1.155712366104126, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 1.8468, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.00179309657817403, | |
| "grad_norm": 0.8886969089508057, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 1.7503, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00179309657817403, | |
| "eval_loss": 0.855793833732605, | |
| "eval_runtime": 1791.6889, | |
| "eval_samples_per_second": 4.718, | |
| "eval_steps_per_second": 0.59, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0018927130547392538, | |
| "grad_norm": 0.7103469967842102, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 1.5929, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0019923295313044776, | |
| "grad_norm": 0.7840328812599182, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 1.5679, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0020919460078697018, | |
| "grad_norm": 0.91854327917099, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 1.5348, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0021915624844349255, | |
| "grad_norm": 0.937053918838501, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 1.6614, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0022911789610001493, | |
| "grad_norm": 0.7176125049591064, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 1.42, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0023907954375653735, | |
| "grad_norm": 0.6584264636039734, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 1.4349, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0024904119141305973, | |
| "grad_norm": 0.8029303550720215, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.5511, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "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": 3.237393280794624e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |