| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0011728141675951445, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002345628335190289, | |
| "grad_norm": 9.228165626525879, | |
| "learning_rate": 1e-05, | |
| "loss": 48.408, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002345628335190289, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1914.6791, | |
| "eval_samples_per_second": 3.75, | |
| "eval_steps_per_second": 1.876, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004691256670380578, | |
| "grad_norm": 10.851334571838379, | |
| "learning_rate": 2e-05, | |
| "loss": 47.2116, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0004691256670380578, | |
| "eval_loss": 2.7150487899780273, | |
| "eval_runtime": 1681.9256, | |
| "eval_samples_per_second": 4.27, | |
| "eval_steps_per_second": 2.135, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0007036885005570867, | |
| "grad_norm": 8.586624145507812, | |
| "learning_rate": 3e-05, | |
| "loss": 35.9909, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0009382513340761156, | |
| "grad_norm": 11.132521629333496, | |
| "learning_rate": 4e-05, | |
| "loss": 47.7162, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0009382513340761156, | |
| "eval_loss": NaN, | |
| "eval_runtime": 394.1002, | |
| "eval_samples_per_second": 18.221, | |
| "eval_steps_per_second": 9.112, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0011728141675951445, | |
| "grad_norm": 13.09566879272461, | |
| "learning_rate": 5e-05, | |
| "loss": 43.3822, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 5, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6332408345395200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |