| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0058953574060427415, | |
| "eval_steps": 5, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005895357406042742, | |
| "eval_loss": 11.93494987487793, | |
| "eval_runtime": 22.1509, | |
| "eval_samples_per_second": 128.979, | |
| "eval_steps_per_second": 16.162, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0017686072218128224, | |
| "grad_norm": 0.40249624848365784, | |
| "learning_rate": 3e-05, | |
| "loss": 11.9355, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0029476787030213707, | |
| "eval_loss": 11.932616233825684, | |
| "eval_runtime": 21.2141, | |
| "eval_samples_per_second": 134.675, | |
| "eval_steps_per_second": 16.876, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.003537214443625645, | |
| "grad_norm": 0.31879347562789917, | |
| "learning_rate": 6e-05, | |
| "loss": 11.9335, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005305821665438467, | |
| "grad_norm": 0.3556462526321411, | |
| "learning_rate": 9e-05, | |
| "loss": 11.9286, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0058953574060427415, | |
| "eval_loss": 11.923737525939941, | |
| "eval_runtime": 21.1557, | |
| "eval_samples_per_second": 135.047, | |
| "eval_steps_per_second": 16.922, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 11017912320000.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |