| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.11080332409972299, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00221606648199446, | |
| "eval_loss": NaN, | |
| "eval_runtime": 13.5572, | |
| "eval_samples_per_second": 14.015, | |
| "eval_steps_per_second": 7.007, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0110803324099723, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0221606648199446, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0221606648199446, | |
| "eval_loss": NaN, | |
| "eval_runtime": 20.7971, | |
| "eval_samples_per_second": 9.136, | |
| "eval_steps_per_second": 4.568, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0332409972299169, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0443213296398892, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0443213296398892, | |
| "eval_loss": NaN, | |
| "eval_runtime": 21.1459, | |
| "eval_samples_per_second": 8.985, | |
| "eval_steps_per_second": 4.493, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.055401662049861494, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0664819944598338, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0664819944598338, | |
| "eval_loss": NaN, | |
| "eval_runtime": 21.0003, | |
| "eval_samples_per_second": 9.047, | |
| "eval_steps_per_second": 4.524, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07756232686980609, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0886426592797784, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0886426592797784, | |
| "eval_loss": NaN, | |
| "eval_runtime": 21.0407, | |
| "eval_samples_per_second": 9.03, | |
| "eval_steps_per_second": 4.515, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0997229916897507, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.11080332409972299, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.11080332409972299, | |
| "eval_loss": NaN, | |
| "eval_runtime": 20.9287, | |
| "eval_samples_per_second": 9.078, | |
| "eval_steps_per_second": 4.539, | |
| "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": 9185331983155200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |