| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0003745283283864383, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.7452832838643834e-05, | |
| "grad_norm": 0.14270928502082825, | |
| "learning_rate": 2e-05, | |
| "loss": 1.1844, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.7452832838643834e-05, | |
| "eval_loss": 1.2873841524124146, | |
| "eval_runtime": 214.4452, | |
| "eval_samples_per_second": 52.428, | |
| "eval_steps_per_second": 26.216, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 7.490566567728767e-05, | |
| "grad_norm": 0.10465919971466064, | |
| "learning_rate": 4e-05, | |
| "loss": 1.0468, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0001123584985159315, | |
| "grad_norm": 0.1087426021695137, | |
| "learning_rate": 6e-05, | |
| "loss": 1.2124, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0001123584985159315, | |
| "eval_loss": 1.2873289585113525, | |
| "eval_runtime": 212.8085, | |
| "eval_samples_per_second": 52.832, | |
| "eval_steps_per_second": 26.418, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00014981133135457534, | |
| "grad_norm": 0.11172080785036087, | |
| "learning_rate": 8e-05, | |
| "loss": 1.249, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00018726416419321916, | |
| "grad_norm": 0.11104849725961685, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1149, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.000224716997031863, | |
| "grad_norm": 0.09549488127231598, | |
| "learning_rate": 0.00012, | |
| "loss": 1.3714, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.000224716997031863, | |
| "eval_loss": 1.2868678569793701, | |
| "eval_runtime": 208.5624, | |
| "eval_samples_per_second": 53.907, | |
| "eval_steps_per_second": 26.956, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0002621698298705068, | |
| "grad_norm": 0.14891448616981506, | |
| "learning_rate": 0.00014, | |
| "loss": 1.2866, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00029962266270915067, | |
| "grad_norm": 0.14372538030147552, | |
| "learning_rate": 0.00016, | |
| "loss": 1.5797, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00033707549554779447, | |
| "grad_norm": 0.11284895986318588, | |
| "learning_rate": 0.00018, | |
| "loss": 0.8815, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00033707549554779447, | |
| "eval_loss": 1.2854689359664917, | |
| "eval_runtime": 205.8891, | |
| "eval_samples_per_second": 54.607, | |
| "eval_steps_per_second": 27.306, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0003745283283864383, | |
| "grad_norm": 0.13710124790668488, | |
| "learning_rate": 0.0002, | |
| "loss": 0.973, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 441241162481664.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |