| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.18124150430448574, | |
| "eval_steps": 9, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0018124150430448573, | |
| "eval_loss": NaN, | |
| "eval_runtime": 7.2824, | |
| "eval_samples_per_second": 269.416, | |
| "eval_steps_per_second": 33.78, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009062075215224286, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.75e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.016311735387403714, | |
| "eval_loss": NaN, | |
| "eval_runtime": 6.8853, | |
| "eval_samples_per_second": 284.955, | |
| "eval_steps_per_second": 35.728, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01812415043044857, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.5e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02718622564567286, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001125, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03262347077480743, | |
| "eval_loss": NaN, | |
| "eval_runtime": 6.9012, | |
| "eval_samples_per_second": 284.299, | |
| "eval_steps_per_second": 35.646, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.03624830086089714, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.045310376076121435, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014855889603024227, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04893520616221115, | |
| "eval_loss": NaN, | |
| "eval_runtime": 6.8843, | |
| "eval_samples_per_second": 284.997, | |
| "eval_steps_per_second": 35.734, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.05437245129134572, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001442909649383465, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06343452650657, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001373602209226909, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.06524694154961486, | |
| "eval_loss": NaN, | |
| "eval_runtime": 6.8754, | |
| "eval_samples_per_second": 285.366, | |
| "eval_steps_per_second": 35.78, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.07249660172179428, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012803300858899104, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.08155867693701857, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011666776747647015, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.08155867693701857, | |
| "eval_loss": NaN, | |
| "eval_runtime": 6.8846, | |
| "eval_samples_per_second": 284.982, | |
| "eval_steps_per_second": 35.732, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.09062075215224287, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010370125742738173, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0978704123244223, | |
| "eval_loss": NaN, | |
| "eval_runtime": 6.869, | |
| "eval_samples_per_second": 285.63, | |
| "eval_steps_per_second": 35.813, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.09968282736746716, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.963177415120962e-05, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.10874490258269144, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.5e-05, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.11418214771182601, | |
| "eval_loss": NaN, | |
| "eval_runtime": 6.8709, | |
| "eval_samples_per_second": 285.551, | |
| "eval_steps_per_second": 35.803, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.11780697779791573, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.036822584879038e-05, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.12686905301314, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.6298742572618266e-05, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.1304938830992297, | |
| "eval_loss": NaN, | |
| "eval_runtime": 6.8861, | |
| "eval_samples_per_second": 284.921, | |
| "eval_steps_per_second": 35.724, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.13593112822836428, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.333223252352985e-05, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.14499320344358857, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1966991411008938e-05, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.14680561848663343, | |
| "eval_loss": NaN, | |
| "eval_runtime": 6.8785, | |
| "eval_samples_per_second": 285.236, | |
| "eval_steps_per_second": 35.764, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.15405527865881286, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2639779077309098e-05, | |
| "loss": 0.0, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.16311735387403714, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.709035061653494e-06, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.16311735387403714, | |
| "eval_loss": NaN, | |
| "eval_runtime": 6.8949, | |
| "eval_samples_per_second": 284.559, | |
| "eval_steps_per_second": 35.679, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.17217942908926145, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4411039697577175e-06, | |
| "loss": 0.0, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.17942908926144088, | |
| "eval_loss": NaN, | |
| "eval_runtime": 6.8976, | |
| "eval_samples_per_second": 284.445, | |
| "eval_steps_per_second": 35.664, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.18124150430448574, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 9, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1790853827788800.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |