| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0007731560228854183, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.731560228854182e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 7.731560228854182e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 304.7038, | |
| "eval_samples_per_second": 17.873, | |
| "eval_steps_per_second": 8.937, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00015463120457708364, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0002319468068656255, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0002319468068656255, | |
| "eval_loss": NaN, | |
| "eval_runtime": 303.5024, | |
| "eval_samples_per_second": 17.944, | |
| "eval_steps_per_second": 8.972, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0003092624091541673, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 5.5497, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00038657801144270914, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.000463893613731251, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.000463893613731251, | |
| "eval_loss": NaN, | |
| "eval_runtime": 303.8208, | |
| "eval_samples_per_second": 17.925, | |
| "eval_steps_per_second": 8.963, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0005412092160197928, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014, | |
| "loss": 2.5284, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0006185248183083346, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016, | |
| "loss": 7.4339, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0006958404205968764, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0006958404205968764, | |
| "eval_loss": NaN, | |
| "eval_runtime": 303.8797, | |
| "eval_samples_per_second": 17.922, | |
| "eval_steps_per_second": 8.961, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0007731560228854183, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 3.3372, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3461526803447808.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |