| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0936768149882904, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00936768149882904, | |
| "grad_norm": 6.368039608001709, | |
| "learning_rate": 2e-05, | |
| "loss": 4.4132, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00936768149882904, | |
| "eval_loss": 4.584343910217285, | |
| "eval_runtime": 1.5787, | |
| "eval_samples_per_second": 28.504, | |
| "eval_steps_per_second": 14.569, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01873536299765808, | |
| "grad_norm": 6.159457206726074, | |
| "learning_rate": 4e-05, | |
| "loss": 4.7323, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.02810304449648712, | |
| "grad_norm": 4.918649196624756, | |
| "learning_rate": 6e-05, | |
| "loss": 4.2704, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.02810304449648712, | |
| "eval_loss": 4.497150897979736, | |
| "eval_runtime": 1.576, | |
| "eval_samples_per_second": 28.553, | |
| "eval_steps_per_second": 14.594, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03747072599531616, | |
| "grad_norm": 7.36662483215332, | |
| "learning_rate": 8e-05, | |
| "loss": 4.5219, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0468384074941452, | |
| "grad_norm": 5.468144416809082, | |
| "learning_rate": 0.0001, | |
| "loss": 4.2752, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.05620608899297424, | |
| "grad_norm": 7.327942848205566, | |
| "learning_rate": 0.00012, | |
| "loss": 3.9791, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.05620608899297424, | |
| "eval_loss": 3.585860252380371, | |
| "eval_runtime": 1.5859, | |
| "eval_samples_per_second": 28.376, | |
| "eval_steps_per_second": 14.503, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.06557377049180328, | |
| "grad_norm": 5.858588695526123, | |
| "learning_rate": 0.00014, | |
| "loss": 3.4795, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.07494145199063232, | |
| "grad_norm": 4.332945346832275, | |
| "learning_rate": 0.00016, | |
| "loss": 3.3594, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.08430913348946135, | |
| "grad_norm": 4.136591911315918, | |
| "learning_rate": 0.00018, | |
| "loss": 2.9449, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.08430913348946135, | |
| "eval_loss": 2.907849073410034, | |
| "eval_runtime": 1.5744, | |
| "eval_samples_per_second": 28.583, | |
| "eval_steps_per_second": 14.609, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0936768149882904, | |
| "grad_norm": 4.591249942779541, | |
| "learning_rate": 0.0002, | |
| "loss": 2.5761, | |
| "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": 1911091416268800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |