| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.1530221882172915, |
| "eval_steps": 13, |
| "global_step": 50, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.00306044376434583, |
| "eval_loss": 0.834145188331604, |
| "eval_runtime": 6.2625, |
| "eval_samples_per_second": 22.036, |
| "eval_steps_per_second": 11.018, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.030604437643458302, |
| "grad_norm": 0.5659714341163635, |
| "learning_rate": 0.0001, |
| "loss": 0.7283, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.03978576893649579, |
| "eval_loss": 0.6105126142501831, |
| "eval_runtime": 5.1744, |
| "eval_samples_per_second": 26.67, |
| "eval_steps_per_second": 13.335, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.061208875286916604, |
| "grad_norm": 0.6774999499320984, |
| "learning_rate": 8.535533905932738e-05, |
| "loss": 0.5548, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.07957153787299158, |
| "eval_loss": 0.45831599831581116, |
| "eval_runtime": 5.1833, |
| "eval_samples_per_second": 26.624, |
| "eval_steps_per_second": 13.312, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.09181331293037491, |
| "grad_norm": 0.5139346122741699, |
| "learning_rate": 5e-05, |
| "loss": 0.4389, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.11935730680948738, |
| "eval_loss": 0.43966734409332275, |
| "eval_runtime": 5.1801, |
| "eval_samples_per_second": 26.64, |
| "eval_steps_per_second": 13.32, |
| "step": 39 |
| }, |
| { |
| "epoch": 0.12241775057383321, |
| "grad_norm": 0.4938279986381531, |
| "learning_rate": 1.4644660940672627e-05, |
| "loss": 0.4451, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.1530221882172915, |
| "grad_norm": 0.5841078758239746, |
| "learning_rate": 0.0, |
| "loss": 0.452, |
| "step": 50 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 50, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 13, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.1282341913690112e+16, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
