| { | |
| "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": 1.0663607120513916, | |
| "eval_runtime": 133.3275, | |
| "eval_samples_per_second": 19.373, | |
| "eval_steps_per_second": 9.69, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008152284677780948, | |
| "grad_norm": 0.11302177608013153, | |
| "learning_rate": 5e-05, | |
| "loss": 1.0815, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0016304569355561896, | |
| "grad_norm": 0.10407887399196625, | |
| "learning_rate": 0.0001, | |
| "loss": 0.9289, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0016304569355561896, | |
| "eval_loss": 1.0647904872894287, | |
| "eval_runtime": 136.8984, | |
| "eval_samples_per_second": 18.868, | |
| "eval_steps_per_second": 9.438, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0024456854033342843, | |
| "grad_norm": 0.12383808940649033, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.9318, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.003260913871112379, | |
| "grad_norm": 0.13035127520561218, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.0568, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003260913871112379, | |
| "eval_loss": 1.0532459020614624, | |
| "eval_runtime": 137.4005, | |
| "eval_samples_per_second": 18.799, | |
| "eval_steps_per_second": 9.403, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004076142338890474, | |
| "grad_norm": 0.15136367082595825, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.9642, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004891370806668569, | |
| "grad_norm": 0.12287212163209915, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9845, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.004891370806668569, | |
| "eval_loss": 1.0406432151794434, | |
| "eval_runtime": 137.355, | |
| "eval_samples_per_second": 18.805, | |
| "eval_steps_per_second": 9.406, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.005706599274446664, | |
| "grad_norm": 0.35205531120300293, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.0057, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.006521827742224758, | |
| "grad_norm": 0.1731029897928238, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.0015, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.006521827742224758, | |
| "eval_loss": 1.0348747968673706, | |
| "eval_runtime": 137.9943, | |
| "eval_samples_per_second": 18.718, | |
| "eval_steps_per_second": 9.363, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0073370562100028534, | |
| "grad_norm": 0.17811691761016846, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.9535, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.008152284677780949, | |
| "grad_norm": 0.1666414737701416, | |
| "learning_rate": 0.0, | |
| "loss": 0.9758, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.008152284677780949, | |
| "eval_loss": 1.033933162689209, | |
| "eval_runtime": 136.1083, | |
| "eval_samples_per_second": 18.978, | |
| "eval_steps_per_second": 9.492, | |
| "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": 2270153806970880.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |