| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9302325581395349, | |
| "eval_steps": 5, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.018604651162790697, | |
| "eval_loss": NaN, | |
| "eval_runtime": 6.5542, | |
| "eval_samples_per_second": 13.884, | |
| "eval_steps_per_second": 1.831, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05581395348837209, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.09302325581395349, | |
| "eval_loss": NaN, | |
| "eval_runtime": 6.0621, | |
| "eval_samples_per_second": 15.011, | |
| "eval_steps_per_second": 1.979, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.11162790697674418, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.16744186046511628, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.18604651162790697, | |
| "eval_loss": NaN, | |
| "eval_runtime": 6.0725, | |
| "eval_samples_per_second": 14.985, | |
| "eval_steps_per_second": 1.976, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.22325581395348837, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.27906976744186046, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.27906976744186046, | |
| "eval_loss": NaN, | |
| "eval_runtime": 6.0998, | |
| "eval_samples_per_second": 14.918, | |
| "eval_steps_per_second": 1.967, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.33488372093023255, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.37209302325581395, | |
| "eval_loss": NaN, | |
| "eval_runtime": 6.1073, | |
| "eval_samples_per_second": 14.9, | |
| "eval_steps_per_second": 1.965, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.39069767441860465, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.247240241650918e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.44651162790697674, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.46511627906976744, | |
| "eval_loss": NaN, | |
| "eval_runtime": 6.117, | |
| "eval_samples_per_second": 14.877, | |
| "eval_steps_per_second": 1.962, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5023255813953489, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.167226819279528e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.5581395348837209, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5581395348837209, | |
| "eval_loss": NaN, | |
| "eval_runtime": 6.1212, | |
| "eval_samples_per_second": 14.866, | |
| "eval_steps_per_second": 1.96, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.6139534883720931, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.832773180720475e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.6511627906976745, | |
| "eval_loss": NaN, | |
| "eval_runtime": 6.119, | |
| "eval_samples_per_second": 14.872, | |
| "eval_steps_per_second": 1.961, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.6697674418604651, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.7255813953488373, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7527597583490822e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.7441860465116279, | |
| "eval_loss": NaN, | |
| "eval_runtime": 6.1164, | |
| "eval_samples_per_second": 14.878, | |
| "eval_steps_per_second": 1.962, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.7813953488372093, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.8372093023255814, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.8372093023255814, | |
| "eval_loss": NaN, | |
| "eval_runtime": 6.1176, | |
| "eval_samples_per_second": 14.875, | |
| "eval_steps_per_second": 1.962, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.8930232558139535, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.15582970243117e-07, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.9302325581395349, | |
| "eval_loss": NaN, | |
| "eval_runtime": 6.1169, | |
| "eval_samples_per_second": 14.877, | |
| "eval_steps_per_second": 1.962, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.1094434267136e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |