| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 35, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02857142857142857, | |
| "grad_norm": 1.1770261526107788, | |
| "learning_rate": 5e-05, | |
| "loss": 0.781, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.14285714285714285, | |
| "grad_norm": 0.7865971326828003, | |
| "learning_rate": 0.00019948693233918952, | |
| "loss": 0.6954, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.2857142857142857, | |
| "grad_norm": 0.3400590717792511, | |
| "learning_rate": 0.00018207634412072764, | |
| "loss": 0.4525, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.42857142857142855, | |
| "grad_norm": 0.24245862662792206, | |
| "learning_rate": 0.00014403941515576344, | |
| "loss": 0.306, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 0.23055194318294525, | |
| "learning_rate": 9.493508311612874e-05, | |
| "loss": 0.2153, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7142857142857143, | |
| "grad_norm": 0.25304117798805237, | |
| "learning_rate": 4.710359896730379e-05, | |
| "loss": 0.1602, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.8571428571428571, | |
| "grad_norm": 0.2968534231185913, | |
| "learning_rate": 1.2565338385541792e-05, | |
| "loss": 0.1206, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.11835439503192902, | |
| "learning_rate": 0.0, | |
| "loss": 0.111, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.11065573990345001, | |
| "eval_runtime": 10.7768, | |
| "eval_samples_per_second": 5.66, | |
| "eval_steps_per_second": 0.371, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 35, | |
| "total_flos": 5.19321114598441e+16, | |
| "train_loss": 0.29687737567084177, | |
| "train_runtime": 332.0278, | |
| "train_samples_per_second": 1.678, | |
| "train_steps_per_second": 0.105 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 35, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.19321114598441e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |