| { | |
| "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 | |
| } | |