| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0016354567012838335, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00016354567012838336, | |
| "grad_norm": 0.8991327285766602, | |
| "learning_rate": 2e-05, | |
| "loss": 4.1796, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00016354567012838336, | |
| "eval_loss": 3.870612859725952, | |
| "eval_runtime": 117.3272, | |
| "eval_samples_per_second": 21.947, | |
| "eval_steps_per_second": 10.978, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003270913402567667, | |
| "grad_norm": 0.7424627542495728, | |
| "learning_rate": 4e-05, | |
| "loss": 3.2798, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00049063701038515, | |
| "grad_norm": 0.6099748611450195, | |
| "learning_rate": 6e-05, | |
| "loss": 2.8712, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00049063701038515, | |
| "eval_loss": 3.8628761768341064, | |
| "eval_runtime": 116.3535, | |
| "eval_samples_per_second": 22.131, | |
| "eval_steps_per_second": 11.07, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006541826805135334, | |
| "grad_norm": 1.0044587850570679, | |
| "learning_rate": 8e-05, | |
| "loss": 3.5739, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0008177283506419167, | |
| "grad_norm": 0.8661907315254211, | |
| "learning_rate": 0.0001, | |
| "loss": 3.6415, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0009812740207703, | |
| "grad_norm": 1.4683250188827515, | |
| "learning_rate": 0.00012, | |
| "loss": 3.7503, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0009812740207703, | |
| "eval_loss": 3.750457286834717, | |
| "eval_runtime": 116.4592, | |
| "eval_samples_per_second": 22.111, | |
| "eval_steps_per_second": 11.06, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0011448196908986834, | |
| "grad_norm": 1.0281736850738525, | |
| "learning_rate": 0.00014, | |
| "loss": 3.2902, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0013083653610270669, | |
| "grad_norm": 1.0804755687713623, | |
| "learning_rate": 0.00016, | |
| "loss": 3.4412, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0014719110311554502, | |
| "grad_norm": 1.0153733491897583, | |
| "learning_rate": 0.00018, | |
| "loss": 2.3864, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0014719110311554502, | |
| "eval_loss": 3.4244368076324463, | |
| "eval_runtime": 116.3475, | |
| "eval_samples_per_second": 22.132, | |
| "eval_steps_per_second": 11.07, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0016354567012838335, | |
| "grad_norm": 2.170130968093872, | |
| "learning_rate": 0.0002, | |
| "loss": 3.9428, | |
| "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": 3166204172697600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |