| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.008152284677780949, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00016304569355561895, | |
| "eval_loss": 1.2448554039001465, | |
| "eval_runtime": 99.7518, | |
| "eval_samples_per_second": 25.894, | |
| "eval_steps_per_second": 12.952, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008152284677780948, | |
| "grad_norm": 0.6304170489311218, | |
| "learning_rate": 5e-05, | |
| "loss": 1.1856, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0016304569355561896, | |
| "grad_norm": 0.6049215197563171, | |
| "learning_rate": 0.0001, | |
| "loss": 1.0576, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0016304569355561896, | |
| "eval_loss": 1.2192050218582153, | |
| "eval_runtime": 100.1668, | |
| "eval_samples_per_second": 25.787, | |
| "eval_steps_per_second": 12.898, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0024456854033342843, | |
| "grad_norm": 0.649795413017273, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.0736, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.003260913871112379, | |
| "grad_norm": 0.6032206416130066, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.1729, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003260913871112379, | |
| "eval_loss": 1.1580919027328491, | |
| "eval_runtime": 99.6128, | |
| "eval_samples_per_second": 25.93, | |
| "eval_steps_per_second": 12.97, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004076142338890474, | |
| "grad_norm": 0.7519647479057312, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.096, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004891370806668569, | |
| "grad_norm": 0.6601759195327759, | |
| "learning_rate": 5e-05, | |
| "loss": 1.0926, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.004891370806668569, | |
| "eval_loss": 1.1310490369796753, | |
| "eval_runtime": 98.6894, | |
| "eval_samples_per_second": 26.173, | |
| "eval_steps_per_second": 13.092, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.005706599274446664, | |
| "grad_norm": 0.8596938848495483, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.0772, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.006521827742224758, | |
| "grad_norm": 0.7148851752281189, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.1107, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.006521827742224758, | |
| "eval_loss": 1.120132565498352, | |
| "eval_runtime": 98.2234, | |
| "eval_samples_per_second": 26.297, | |
| "eval_steps_per_second": 13.154, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0073370562100028534, | |
| "grad_norm": 0.7597112655639648, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.0479, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.008152284677780949, | |
| "grad_norm": 0.608223021030426, | |
| "learning_rate": 0.0, | |
| "loss": 1.0353, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.008152284677780949, | |
| "eval_loss": 1.1179903745651245, | |
| "eval_runtime": 99.164, | |
| "eval_samples_per_second": 26.048, | |
| "eval_steps_per_second": 13.029, | |
| "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": 1954432312934400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |