| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.01278118609406953, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002556237218813906, | |
| "eval_loss": 20.340166091918945, | |
| "eval_runtime": 12.1761, | |
| "eval_samples_per_second": 135.348, | |
| "eval_steps_per_second": 67.674, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001278118609406953, | |
| "grad_norm": 806.2634887695312, | |
| "learning_rate": 5e-05, | |
| "loss": 85.3687, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002556237218813906, | |
| "grad_norm": 614.0523681640625, | |
| "learning_rate": 0.0001, | |
| "loss": 82.5967, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002556237218813906, | |
| "eval_loss": 20.30628776550293, | |
| "eval_runtime": 11.5713, | |
| "eval_samples_per_second": 142.422, | |
| "eval_steps_per_second": 71.211, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.003834355828220859, | |
| "grad_norm": 721.6196899414062, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 74.5537, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.005112474437627812, | |
| "grad_norm": 770.1486206054688, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 93.181, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005112474437627812, | |
| "eval_loss": 20.2139949798584, | |
| "eval_runtime": 11.7008, | |
| "eval_samples_per_second": 140.846, | |
| "eval_steps_per_second": 70.423, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.006390593047034765, | |
| "grad_norm": 868.2890625, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 77.0789, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.007668711656441718, | |
| "grad_norm": 654.0535888671875, | |
| "learning_rate": 5e-05, | |
| "loss": 79.6657, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.007668711656441718, | |
| "eval_loss": 20.094011306762695, | |
| "eval_runtime": 11.6588, | |
| "eval_samples_per_second": 141.352, | |
| "eval_steps_per_second": 70.676, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00894683026584867, | |
| "grad_norm": 1161.23974609375, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 89.0292, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.010224948875255624, | |
| "grad_norm": 1144.7630615234375, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 86.0579, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.010224948875255624, | |
| "eval_loss": 20.039480209350586, | |
| "eval_runtime": 11.7921, | |
| "eval_samples_per_second": 139.755, | |
| "eval_steps_per_second": 69.877, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.011503067484662576, | |
| "grad_norm": 621.7279663085938, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 73.1134, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.01278118609406953, | |
| "grad_norm": 887.598388671875, | |
| "learning_rate": 0.0, | |
| "loss": 69.3403, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01278118609406953, | |
| "eval_loss": 20.029600143432617, | |
| "eval_runtime": 11.5521, | |
| "eval_samples_per_second": 142.658, | |
| "eval_steps_per_second": 71.329, | |
| "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": 55374879129600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |