| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.011841326228537596, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0011841326228537595, | |
| "grad_norm": 1.1909741163253784, | |
| "learning_rate": 2e-05, | |
| "loss": 2.1562, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002368265245707519, | |
| "grad_norm": 0.7653021216392517, | |
| "learning_rate": 4e-05, | |
| "loss": 0.7487, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.003552397868561279, | |
| "grad_norm": 0.8750675320625305, | |
| "learning_rate": 6e-05, | |
| "loss": 1.6945, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003552397868561279, | |
| "eval_loss": 1.6560570001602173, | |
| "eval_runtime": 25.1693, | |
| "eval_samples_per_second": 14.144, | |
| "eval_steps_per_second": 7.072, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004736530491415038, | |
| "grad_norm": 1.1762977838516235, | |
| "learning_rate": 8e-05, | |
| "loss": 1.7185, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.005920663114268798, | |
| "grad_norm": 0.8054398894309998, | |
| "learning_rate": 0.0001, | |
| "loss": 1.534, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.007104795737122558, | |
| "grad_norm": 1.14064621925354, | |
| "learning_rate": 0.00012, | |
| "loss": 1.2122, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.007104795737122558, | |
| "eval_loss": 1.6312814950942993, | |
| "eval_runtime": 24.9872, | |
| "eval_samples_per_second": 14.247, | |
| "eval_steps_per_second": 7.124, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.008288928359976317, | |
| "grad_norm": 0.8956174254417419, | |
| "learning_rate": 0.00014, | |
| "loss": 1.8952, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.009473060982830076, | |
| "grad_norm": 0.7665032148361206, | |
| "learning_rate": 0.00016, | |
| "loss": 1.8163, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.010657193605683837, | |
| "grad_norm": 0.8271414637565613, | |
| "learning_rate": 0.00018, | |
| "loss": 1.7996, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.010657193605683837, | |
| "eval_loss": 1.5794999599456787, | |
| "eval_runtime": 25.1052, | |
| "eval_samples_per_second": 14.18, | |
| "eval_steps_per_second": 7.09, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.011841326228537596, | |
| "grad_norm": 1.0583250522613525, | |
| "learning_rate": 0.0002, | |
| "loss": 2.0317, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 133557245706240.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |