| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.013802622498274672, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0013802622498274672, | |
| "grad_norm": 2.734062671661377, | |
| "learning_rate": 2e-05, | |
| "loss": 13.3664, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013802622498274672, | |
| "eval_loss": 3.5190110206604004, | |
| "eval_runtime": 5.8539, | |
| "eval_samples_per_second": 52.102, | |
| "eval_steps_per_second": 26.136, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0027605244996549345, | |
| "grad_norm": 2.2133378982543945, | |
| "learning_rate": 4e-05, | |
| "loss": 13.9199, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004140786749482402, | |
| "grad_norm": 2.4322659969329834, | |
| "learning_rate": 6e-05, | |
| "loss": 14.2882, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004140786749482402, | |
| "eval_loss": 3.5203616619110107, | |
| "eval_runtime": 5.8747, | |
| "eval_samples_per_second": 51.917, | |
| "eval_steps_per_second": 26.044, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005521048999309869, | |
| "grad_norm": 2.11274790763855, | |
| "learning_rate": 8e-05, | |
| "loss": 13.8411, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006901311249137336, | |
| "grad_norm": 2.8045334815979004, | |
| "learning_rate": 0.0001, | |
| "loss": 13.9511, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.008281573498964804, | |
| "grad_norm": 2.7258803844451904, | |
| "learning_rate": 0.00012, | |
| "loss": 14.4021, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.008281573498964804, | |
| "eval_loss": 3.497959613800049, | |
| "eval_runtime": 6.0276, | |
| "eval_samples_per_second": 50.601, | |
| "eval_steps_per_second": 25.383, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00966183574879227, | |
| "grad_norm": 2.4813785552978516, | |
| "learning_rate": 0.00014, | |
| "loss": 12.8158, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.011042097998619738, | |
| "grad_norm": 3.0247457027435303, | |
| "learning_rate": 0.00016, | |
| "loss": 15.1249, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.012422360248447204, | |
| "grad_norm": 3.1049482822418213, | |
| "learning_rate": 0.00018, | |
| "loss": 13.6124, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.012422360248447204, | |
| "eval_loss": 3.3562123775482178, | |
| "eval_runtime": 5.9982, | |
| "eval_samples_per_second": 50.849, | |
| "eval_steps_per_second": 25.508, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.013802622498274672, | |
| "grad_norm": 3.426762104034424, | |
| "learning_rate": 0.0002, | |
| "loss": 12.7397, | |
| "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": 298729403842560.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |