| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00046602448492643803, | |
| "eval_steps": 13, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 9.32048969852876e-06, | |
| "eval_loss": 2.281832695007324, | |
| "eval_runtime": 760.5207, | |
| "eval_samples_per_second": 29.701, | |
| "eval_steps_per_second": 14.85, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 9.320489698528761e-05, | |
| "grad_norm": 1.4629062414169312, | |
| "learning_rate": 0.0002, | |
| "loss": 2.2493, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00012116636608087389, | |
| "eval_loss": 2.169867992401123, | |
| "eval_runtime": 769.47, | |
| "eval_samples_per_second": 29.355, | |
| "eval_steps_per_second": 14.678, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.00018640979397057522, | |
| "grad_norm": 1.6473357677459717, | |
| "learning_rate": 0.0002, | |
| "loss": 2.1333, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00024233273216174778, | |
| "eval_loss": 2.1360559463500977, | |
| "eval_runtime": 768.4076, | |
| "eval_samples_per_second": 29.396, | |
| "eval_steps_per_second": 14.698, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0002796146909558628, | |
| "grad_norm": 1.422183871269226, | |
| "learning_rate": 0.0002, | |
| "loss": 2.1517, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00036349909824262165, | |
| "eval_loss": 2.125126600265503, | |
| "eval_runtime": 769.9464, | |
| "eval_samples_per_second": 29.337, | |
| "eval_steps_per_second": 14.669, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.00037281958794115045, | |
| "grad_norm": 1.4730262756347656, | |
| "learning_rate": 0.0002, | |
| "loss": 2.067, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.00046602448492643803, | |
| "grad_norm": 1.2356326580047607, | |
| "learning_rate": 0.0002, | |
| "loss": 2.0745, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1954848181321728.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |