| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.002395388876412905, | |
| "eval_steps": 4, | |
| "global_step": 8, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002994236095516131, | |
| "grad_norm": 16.735450744628906, | |
| "learning_rate": 2e-05, | |
| "loss": 10.969, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002994236095516131, | |
| "eval_loss": 11.57262897491455, | |
| "eval_runtime": 82.9715, | |
| "eval_samples_per_second": 8.485, | |
| "eval_steps_per_second": 8.485, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005988472191032262, | |
| "grad_norm": 10.167157173156738, | |
| "learning_rate": 4e-05, | |
| "loss": 10.7129, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0008982708286548395, | |
| "grad_norm": 15.215925216674805, | |
| "learning_rate": 6e-05, | |
| "loss": 10.434, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0011976944382064525, | |
| "grad_norm": 15.04845142364502, | |
| "learning_rate": 8e-05, | |
| "loss": 9.5194, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0011976944382064525, | |
| "eval_loss": 11.429813385009766, | |
| "eval_runtime": 85.0662, | |
| "eval_samples_per_second": 8.276, | |
| "eval_steps_per_second": 8.276, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0014971180477580657, | |
| "grad_norm": 17.0161075592041, | |
| "learning_rate": 0.0001, | |
| "loss": 10.8734, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001796541657309679, | |
| "grad_norm": 17.905702590942383, | |
| "learning_rate": 0.00012, | |
| "loss": 11.8788, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002095965266861292, | |
| "grad_norm": 21.928312301635742, | |
| "learning_rate": 0.00014, | |
| "loss": 10.4667, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.002395388876412905, | |
| "grad_norm": 13.790472030639648, | |
| "learning_rate": 0.00016, | |
| "loss": 9.8745, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.002395388876412905, | |
| "eval_loss": 9.637001037597656, | |
| "eval_runtime": 85.1568, | |
| "eval_samples_per_second": 8.267, | |
| "eval_steps_per_second": 8.267, | |
| "step": 8 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 4, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2967549134241792.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |