| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0012672665061462425, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002534533012292485, | |
| "grad_norm": 0.15731649100780487, | |
| "learning_rate": 1e-05, | |
| "loss": 1.1278, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002534533012292485, | |
| "eval_loss": 1.122056245803833, | |
| "eval_runtime": 318.3944, | |
| "eval_samples_per_second": 20.873, | |
| "eval_steps_per_second": 10.437, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000506906602458497, | |
| "grad_norm": 0.15816837549209595, | |
| "learning_rate": 2e-05, | |
| "loss": 1.1772, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.000506906602458497, | |
| "eval_loss": 1.117799162864685, | |
| "eval_runtime": 384.6376, | |
| "eval_samples_per_second": 17.279, | |
| "eval_steps_per_second": 8.639, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0007603599036877456, | |
| "grad_norm": 0.15520311892032623, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1812, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.001013813204916994, | |
| "grad_norm": 0.15153363347053528, | |
| "learning_rate": 4e-05, | |
| "loss": 1.069, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.001013813204916994, | |
| "eval_loss": 1.113523006439209, | |
| "eval_runtime": 255.6171, | |
| "eval_samples_per_second": 26.0, | |
| "eval_steps_per_second": 13.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0012672665061462425, | |
| "grad_norm": 0.14156576991081238, | |
| "learning_rate": 5e-05, | |
| "loss": 1.0487, | |
| "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": 3280194659942400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |