| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.020709911883307612, | |
| "eval_steps": 10, | |
| "global_step": 26, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007965350724349081, | |
| "eval_loss": NaN, | |
| "eval_runtime": 257.2896, | |
| "eval_samples_per_second": 32.873, | |
| "eval_steps_per_second": 4.112, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007965350724349082, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007965350724349082, | |
| "eval_loss": NaN, | |
| "eval_runtime": 255.6607, | |
| "eval_samples_per_second": 33.083, | |
| "eval_steps_per_second": 4.138, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.015930701448698164, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.015930701448698164, | |
| "eval_loss": NaN, | |
| "eval_runtime": 255.6473, | |
| "eval_samples_per_second": 33.085, | |
| "eval_steps_per_second": 4.139, | |
| "step": 20 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.169555349458125e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |