| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.013845621322256836, | |
| "eval_steps": 500, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0013845621322256837, | |
| "grad_norm": 93.77859497070312, | |
| "learning_rate": 0.0, | |
| "loss": 3.4941, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006922810661128418, | |
| "grad_norm": 341.4436950683594, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 19.3195, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.013845621322256836, | |
| "grad_norm": 45.13679885864258, | |
| "learning_rate": 6.030737921409169e-06, | |
| "loss": 17.6258, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.013845621322256836, | |
| "eval_loss": 10.07286262512207, | |
| "eval_runtime": 77.8792, | |
| "eval_samples_per_second": 26.567, | |
| "eval_steps_per_second": 1.669, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.013845621322256836, | |
| "step": 10, | |
| "total_flos": 4.971111595691213e+16, | |
| "train_loss": 16.890113639831544, | |
| "train_runtime": 487.8407, | |
| "train_samples_per_second": 1.312, | |
| "train_steps_per_second": 0.02 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.971111595691213e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |