| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0051013901288101005, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005101390128810101, | |
| "grad_norm": 1.7509140968322754, | |
| "learning_rate": 2e-05, | |
| "loss": 1.7065, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005101390128810101, | |
| "eval_loss": 1.9787309169769287, | |
| "eval_runtime": 46.5736, | |
| "eval_samples_per_second": 17.735, | |
| "eval_steps_per_second": 8.868, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0010202780257620202, | |
| "grad_norm": 1.9949790239334106, | |
| "learning_rate": 4e-05, | |
| "loss": 1.9043, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0015304170386430302, | |
| "grad_norm": 1.9159499406814575, | |
| "learning_rate": 6e-05, | |
| "loss": 2.0236, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0015304170386430302, | |
| "eval_loss": 1.9489587545394897, | |
| "eval_runtime": 46.5911, | |
| "eval_samples_per_second": 17.729, | |
| "eval_steps_per_second": 8.864, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0020405560515240405, | |
| "grad_norm": 1.8466172218322754, | |
| "learning_rate": 8e-05, | |
| "loss": 1.7856, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0025506950644050503, | |
| "grad_norm": 1.816487193107605, | |
| "learning_rate": 0.0001, | |
| "loss": 1.73, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0030608340772860605, | |
| "grad_norm": 1.7873655557632446, | |
| "learning_rate": 0.00012, | |
| "loss": 1.7435, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0030608340772860605, | |
| "eval_loss": 1.7079496383666992, | |
| "eval_runtime": 46.6735, | |
| "eval_samples_per_second": 17.697, | |
| "eval_steps_per_second": 8.849, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0035709730901670707, | |
| "grad_norm": 1.7030155658721924, | |
| "learning_rate": 0.00014, | |
| "loss": 1.7117, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.004081112103048081, | |
| "grad_norm": 2.196129083633423, | |
| "learning_rate": 0.00016, | |
| "loss": 1.8474, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00459125111592909, | |
| "grad_norm": 0.8873904347419739, | |
| "learning_rate": 0.00018, | |
| "loss": 1.6097, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00459125111592909, | |
| "eval_loss": 1.5338075160980225, | |
| "eval_runtime": 46.6284, | |
| "eval_samples_per_second": 17.715, | |
| "eval_steps_per_second": 8.857, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0051013901288101005, | |
| "grad_norm": 0.8415577411651611, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2254, | |
| "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": 3535519120097280.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |