| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.47619047619047616, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.023809523809523808, | |
| "eval_loss": NaN, | |
| "eval_runtime": 0.769, | |
| "eval_samples_per_second": 23.407, | |
| "eval_steps_per_second": 6.502, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07142857142857142, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.11904761904761904, | |
| "eval_loss": NaN, | |
| "eval_runtime": 0.357, | |
| "eval_samples_per_second": 50.414, | |
| "eval_steps_per_second": 14.004, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.14285714285714285, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.21428571428571427, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.23809523809523808, | |
| "eval_loss": NaN, | |
| "eval_runtime": 0.351, | |
| "eval_samples_per_second": 51.275, | |
| "eval_steps_per_second": 14.243, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2857142857142857, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.35714285714285715, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.35714285714285715, | |
| "eval_loss": NaN, | |
| "eval_runtime": 0.3577, | |
| "eval_samples_per_second": 50.317, | |
| "eval_steps_per_second": 13.977, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.42857142857142855, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.47619047619047616, | |
| "eval_loss": NaN, | |
| "eval_runtime": 0.3516, | |
| "eval_samples_per_second": 51.2, | |
| "eval_steps_per_second": 14.222, | |
| "step": 20 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 40, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 20, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 109203884605440.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |