| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.023507287259050307, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004701457451810061, | |
| "eval_loss": NaN, | |
| "eval_runtime": 73.554, | |
| "eval_samples_per_second": 12.182, | |
| "eval_steps_per_second": 6.091, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0023507287259050304, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004701457451810061, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004701457451810061, | |
| "eval_loss": NaN, | |
| "eval_runtime": 64.9436, | |
| "eval_samples_per_second": 13.797, | |
| "eval_steps_per_second": 6.898, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007052186177715092, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.009402914903620122, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.009402914903620122, | |
| "eval_loss": NaN, | |
| "eval_runtime": 64.8708, | |
| "eval_samples_per_second": 13.812, | |
| "eval_steps_per_second": 6.906, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.011753643629525154, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.014104372355430184, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.014104372355430184, | |
| "eval_loss": NaN, | |
| "eval_runtime": 64.8613, | |
| "eval_samples_per_second": 13.814, | |
| "eval_steps_per_second": 6.907, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.016455101081335213, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.018805829807240243, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.018805829807240243, | |
| "eval_loss": NaN, | |
| "eval_runtime": 64.8846, | |
| "eval_samples_per_second": 13.809, | |
| "eval_steps_per_second": 6.905, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.021156558533145273, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.023507287259050307, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.023507287259050307, | |
| "eval_loss": NaN, | |
| "eval_runtime": 64.8806, | |
| "eval_samples_per_second": 13.81, | |
| "eval_steps_per_second": 6.905, | |
| "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": 9982222673117184.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |