| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.005845761822678558, | |
| "eval_steps": 10, | |
| "global_step": 39, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00014989132878662968, | |
| "eval_loss": 10.374155044555664, | |
| "eval_runtime": 12.5463, | |
| "eval_samples_per_second": 223.971, | |
| "eval_steps_per_second": 111.986, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007494566439331485, | |
| "grad_norm": 0.03855985030531883, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3732, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001498913287866297, | |
| "grad_norm": 0.043545596301555634, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3743, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.001498913287866297, | |
| "eval_loss": 10.373960494995117, | |
| "eval_runtime": 12.534, | |
| "eval_samples_per_second": 224.19, | |
| "eval_steps_per_second": 112.095, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0022483699317994454, | |
| "grad_norm": 0.03394381329417229, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 10.3752, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.002997826575732594, | |
| "grad_norm": 0.03582505136728287, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 10.3757, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.002997826575732594, | |
| "eval_loss": 10.373543739318848, | |
| "eval_runtime": 13.0976, | |
| "eval_samples_per_second": 214.544, | |
| "eval_steps_per_second": 107.272, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0037472832196657423, | |
| "grad_norm": 0.03206833451986313, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 10.3747, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004496739863598891, | |
| "grad_norm": 0.03807131201028824, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3744, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.004496739863598891, | |
| "eval_loss": 10.3732271194458, | |
| "eval_runtime": 13.166, | |
| "eval_samples_per_second": 213.429, | |
| "eval_steps_per_second": 106.715, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00524619650753204, | |
| "grad_norm": 0.03658220171928406, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 10.3713, | |
| "step": 35 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 504305418240.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |