| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.002366023896841358, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.732047793682716e-05, | |
| "eval_loss": 3.664626121520996, | |
| "eval_runtime": 482.4927, | |
| "eval_samples_per_second": 18.442, | |
| "eval_steps_per_second": 9.221, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002366023896841358, | |
| "grad_norm": 3.212240695953369, | |
| "learning_rate": 5e-05, | |
| "loss": 3.7942, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0004732047793682716, | |
| "grad_norm": 2.939304828643799, | |
| "learning_rate": 0.0001, | |
| "loss": 3.3818, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0004732047793682716, | |
| "eval_loss": 3.0477569103240967, | |
| "eval_runtime": 479.8462, | |
| "eval_samples_per_second": 18.543, | |
| "eval_steps_per_second": 9.272, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0007098071690524074, | |
| "grad_norm": 2.273364543914795, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.8257, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0009464095587365432, | |
| "grad_norm": 2.0559322834014893, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.4455, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0009464095587365432, | |
| "eval_loss": 2.4915196895599365, | |
| "eval_runtime": 480.3832, | |
| "eval_samples_per_second": 18.523, | |
| "eval_steps_per_second": 9.261, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.001183011948420679, | |
| "grad_norm": 2.213008165359497, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.3943, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0014196143381048148, | |
| "grad_norm": 2.0624654293060303, | |
| "learning_rate": 5e-05, | |
| "loss": 2.4572, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0014196143381048148, | |
| "eval_loss": 2.3600924015045166, | |
| "eval_runtime": 486.8969, | |
| "eval_samples_per_second": 18.275, | |
| "eval_steps_per_second": 9.137, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0016562167277889507, | |
| "grad_norm": 2.3414666652679443, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.5394, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0018928191174730864, | |
| "grad_norm": 1.8477317094802856, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.3016, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0018928191174730864, | |
| "eval_loss": 2.320326089859009, | |
| "eval_runtime": 479.6252, | |
| "eval_samples_per_second": 18.552, | |
| "eval_steps_per_second": 9.276, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0021294215071572223, | |
| "grad_norm": 1.9243817329406738, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.2242, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.002366023896841358, | |
| "grad_norm": 1.7884491682052612, | |
| "learning_rate": 0.0, | |
| "loss": 2.2997, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.002366023896841358, | |
| "eval_loss": 2.3137450218200684, | |
| "eval_runtime": 481.1437, | |
| "eval_samples_per_second": 18.493, | |
| "eval_steps_per_second": 9.247, | |
| "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": 2500486653542400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |