| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00381788679965639, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000763577359931278, | |
| "grad_norm": 0.2863585948944092, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6065, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000763577359931278, | |
| "eval_loss": 0.6263359189033508, | |
| "eval_runtime": 156.7565, | |
| "eval_samples_per_second": 14.073, | |
| "eval_steps_per_second": 7.036, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001527154719862556, | |
| "grad_norm": 0.2702590227127075, | |
| "learning_rate": 2e-05, | |
| "loss": 0.637, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.001527154719862556, | |
| "eval_loss": 0.6197466850280762, | |
| "eval_runtime": 77.4176, | |
| "eval_samples_per_second": 28.495, | |
| "eval_steps_per_second": 14.247, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.002290732079793834, | |
| "grad_norm": 0.2686094641685486, | |
| "learning_rate": 3e-05, | |
| "loss": 0.6843, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003054309439725112, | |
| "grad_norm": 0.22620728611946106, | |
| "learning_rate": 4e-05, | |
| "loss": 0.5546, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003054309439725112, | |
| "eval_loss": 0.6147086024284363, | |
| "eval_runtime": 77.7071, | |
| "eval_samples_per_second": 28.389, | |
| "eval_steps_per_second": 14.194, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00381788679965639, | |
| "grad_norm": 0.25145894289016724, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6068, | |
| "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": 5067055489351680.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |