| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0114285714285713, | |
| "eval_steps": 5, | |
| "global_step": 22, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.045714285714285714, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3.8417, | |
| "eval_samples_per_second": 38.524, | |
| "eval_steps_per_second": 4.946, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.22857142857142856, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.8524, | |
| "eval_samples_per_second": 51.886, | |
| "eval_steps_per_second": 6.661, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.45714285714285713, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.45714285714285713, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.9025, | |
| "eval_samples_per_second": 50.991, | |
| "eval_steps_per_second": 6.546, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.6857142857142857, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.8482, | |
| "eval_samples_per_second": 51.962, | |
| "eval_steps_per_second": 6.671, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.9142857142857143, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.9142857142857143, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.8362, | |
| "eval_samples_per_second": 52.183, | |
| "eval_steps_per_second": 6.699, | |
| "step": 20 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 22, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 6, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.1415298699689984e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |