| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.06335797254487856, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0021119324181626186, | |
| "eval_loss": NaN, | |
| "eval_runtime": 7.3062, | |
| "eval_samples_per_second": 27.374, | |
| "eval_steps_per_second": 13.687, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006335797254487857, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.010559662090813094, | |
| "eval_loss": NaN, | |
| "eval_runtime": 7.2559, | |
| "eval_samples_per_second": 27.564, | |
| "eval_steps_per_second": 13.782, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.012671594508975714, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01900739176346357, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.021119324181626188, | |
| "eval_loss": NaN, | |
| "eval_runtime": 7.2129, | |
| "eval_samples_per_second": 27.728, | |
| "eval_steps_per_second": 13.864, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.025343189017951427, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03167898627243928, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03167898627243928, | |
| "eval_loss": NaN, | |
| "eval_runtime": 7.2445, | |
| "eval_samples_per_second": 27.607, | |
| "eval_steps_per_second": 13.804, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03801478352692714, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.042238648363252376, | |
| "eval_loss": NaN, | |
| "eval_runtime": 7.248, | |
| "eval_samples_per_second": 27.594, | |
| "eval_steps_per_second": 13.797, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.044350580781414996, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.050686378035902854, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.05279831045406547, | |
| "eval_loss": NaN, | |
| "eval_runtime": 7.2384, | |
| "eval_samples_per_second": 27.63, | |
| "eval_steps_per_second": 13.815, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.057022175290390706, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.06335797254487856, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06335797254487856, | |
| "eval_loss": NaN, | |
| "eval_runtime": 7.1919, | |
| "eval_samples_per_second": 27.809, | |
| "eval_steps_per_second": 13.905, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 476752851763200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |