| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0033668333249162502, | |
| "eval_steps": 5, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 6.7336666498325e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1835.8254, | |
| "eval_samples_per_second": 13.624, | |
| "eval_steps_per_second": 1.703, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000202009999494975, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.000336683332491625, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1836.1211, | |
| "eval_samples_per_second": 13.622, | |
| "eval_steps_per_second": 1.703, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00040401999898995, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.000606029998484925, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00067336666498325, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1837.914, | |
| "eval_samples_per_second": 13.609, | |
| "eval_steps_per_second": 1.701, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0008080399979799, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0010100499974748751, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0010100499974748751, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1837.3679, | |
| "eval_samples_per_second": 13.613, | |
| "eval_steps_per_second": 1.702, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00121205999696985, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0013467333299665, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1834.612, | |
| "eval_samples_per_second": 13.633, | |
| "eval_steps_per_second": 1.704, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.001414069996464825, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.247240241650918e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0016160799959598, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0016834166624581251, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1834.5109, | |
| "eval_samples_per_second": 13.634, | |
| "eval_steps_per_second": 1.705, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.001818089995454775, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.167226819279528e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0020200999949497502, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0020200999949497502, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1833.8204, | |
| "eval_samples_per_second": 13.639, | |
| "eval_steps_per_second": 1.705, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.002222109994444725, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.832773180720475e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.002356783327441375, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1834.8435, | |
| "eval_samples_per_second": 13.632, | |
| "eval_steps_per_second": 1.704, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0024241199939397, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.002626129993434675, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7527597583490822e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.002693466659933, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1835.1009, | |
| "eval_samples_per_second": 13.63, | |
| "eval_steps_per_second": 1.704, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.00282813999292965, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.003030149992424625, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.003030149992424625, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1835.1611, | |
| "eval_samples_per_second": 13.629, | |
| "eval_steps_per_second": 1.704, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0032321599919196, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.15582970243117e-07, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0033668333249162502, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1835.6612, | |
| "eval_samples_per_second": 13.626, | |
| "eval_steps_per_second": 1.703, | |
| "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": 7.693419251603866e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |