| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.03790271636133923, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0012634238787113076, | |
| "eval_loss": NaN, | |
| "eval_runtime": 43.9754, | |
| "eval_samples_per_second": 7.595, | |
| "eval_steps_per_second": 3.798, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003790271636133923, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006317119393556538, | |
| "eval_loss": NaN, | |
| "eval_runtime": 44.532, | |
| "eval_samples_per_second": 7.5, | |
| "eval_steps_per_second": 3.75, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.007580543272267846, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.011370814908401769, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.012634238787113077, | |
| "eval_loss": NaN, | |
| "eval_runtime": 44.987, | |
| "eval_samples_per_second": 7.424, | |
| "eval_steps_per_second": 3.712, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.015161086544535692, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.018951358180669616, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.018951358180669616, | |
| "eval_loss": NaN, | |
| "eval_runtime": 45.0673, | |
| "eval_samples_per_second": 7.411, | |
| "eval_steps_per_second": 3.706, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.022741629816803537, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.025268477574226154, | |
| "eval_loss": NaN, | |
| "eval_runtime": 45.0648, | |
| "eval_samples_per_second": 7.412, | |
| "eval_steps_per_second": 3.706, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.026531901452937462, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.030322173089071383, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.03158559696778269, | |
| "eval_loss": NaN, | |
| "eval_runtime": 45.0544, | |
| "eval_samples_per_second": 7.413, | |
| "eval_steps_per_second": 3.707, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.034112444725205304, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03790271636133923, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03790271636133923, | |
| "eval_loss": NaN, | |
| "eval_runtime": 45.0718, | |
| "eval_samples_per_second": 7.41, | |
| "eval_steps_per_second": 3.705, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.94858446749696e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |