| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0057161003493172435, | |
| "eval_steps": 3, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006351222610352493, | |
| "grad_norm": 1.9076449461863376e-05, | |
| "learning_rate": 2e-05, | |
| "loss": 46.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006351222610352493, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 3.8618, | |
| "eval_samples_per_second": 171.683, | |
| "eval_steps_per_second": 85.971, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012702445220704986, | |
| "grad_norm": 1.9467239326331764e-05, | |
| "learning_rate": 4e-05, | |
| "loss": 46.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.001905366783105748, | |
| "grad_norm": 1.6134317775140516e-05, | |
| "learning_rate": 6e-05, | |
| "loss": 46.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.001905366783105748, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 3.8548, | |
| "eval_samples_per_second": 171.994, | |
| "eval_steps_per_second": 86.127, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0025404890441409972, | |
| "grad_norm": 2.9662174711120315e-05, | |
| "learning_rate": 8e-05, | |
| "loss": 46.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0031756113051762463, | |
| "grad_norm": 3.37774763465859e-05, | |
| "learning_rate": 0.0001, | |
| "loss": 46.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.003810733566211496, | |
| "grad_norm": 3.077186192967929e-05, | |
| "learning_rate": 0.00012, | |
| "loss": 46.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.003810733566211496, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 4.0063, | |
| "eval_samples_per_second": 165.491, | |
| "eval_steps_per_second": 82.87, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004445855827246745, | |
| "grad_norm": 1.66143145179376e-05, | |
| "learning_rate": 0.00014, | |
| "loss": 46.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0050809780882819944, | |
| "grad_norm": 2.0945793949067593e-05, | |
| "learning_rate": 0.00016, | |
| "loss": 46.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0057161003493172435, | |
| "grad_norm": 2.4738705178606324e-05, | |
| "learning_rate": 0.00018, | |
| "loss": 46.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0057161003493172435, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 3.9145, | |
| "eval_samples_per_second": 169.372, | |
| "eval_steps_per_second": 84.814, | |
| "step": 9 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 189267345408.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |