| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 9.0, | |
| "eval_steps": 500, | |
| "global_step": 2862, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.0064516129032258064, | |
| "eval_loss": NaN, | |
| "eval_runtime": 5.5627, | |
| "eval_samples_per_second": 557.281, | |
| "eval_steps_per_second": 11.685, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 1.5723270440251573, | |
| "grad_norm": 107346.4609375, | |
| "learning_rate": 1.650593990216632e-05, | |
| "loss": 0.0, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.0064516129032258064, | |
| "eval_loss": NaN, | |
| "eval_runtime": 6.3989, | |
| "eval_samples_per_second": 484.455, | |
| "eval_steps_per_second": 10.158, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.0064516129032258064, | |
| "eval_loss": NaN, | |
| "eval_runtime": 5.2542, | |
| "eval_samples_per_second": 590.003, | |
| "eval_steps_per_second": 12.371, | |
| "step": 954 | |
| }, | |
| { | |
| "epoch": 3.1446540880503147, | |
| "grad_norm": 456344.875, | |
| "learning_rate": 1.3011879804332637e-05, | |
| "loss": 0.0, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.0064516129032258064, | |
| "eval_loss": NaN, | |
| "eval_runtime": 6.0513, | |
| "eval_samples_per_second": 512.289, | |
| "eval_steps_per_second": 10.742, | |
| "step": 1272 | |
| }, | |
| { | |
| "epoch": 4.716981132075472, | |
| "grad_norm": 1599939.625, | |
| "learning_rate": 9.517819706498952e-06, | |
| "loss": 0.0, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.0064516129032258064, | |
| "eval_loss": NaN, | |
| "eval_runtime": 7.6981, | |
| "eval_samples_per_second": 402.698, | |
| "eval_steps_per_second": 8.444, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.0064516129032258064, | |
| "eval_loss": NaN, | |
| "eval_runtime": 5.5405, | |
| "eval_samples_per_second": 559.52, | |
| "eval_steps_per_second": 11.732, | |
| "step": 1908 | |
| }, | |
| { | |
| "epoch": 6.289308176100629, | |
| "grad_norm": 2051973.25, | |
| "learning_rate": 6.02375960866527e-06, | |
| "loss": 0.0, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.0064516129032258064, | |
| "eval_loss": NaN, | |
| "eval_runtime": 7.2366, | |
| "eval_samples_per_second": 428.376, | |
| "eval_steps_per_second": 8.982, | |
| "step": 2226 | |
| }, | |
| { | |
| "epoch": 7.861635220125786, | |
| "grad_norm": 2201488.75, | |
| "learning_rate": 2.5296995108315863e-06, | |
| "loss": 0.0, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.0064516129032258064, | |
| "eval_loss": NaN, | |
| "eval_runtime": 5.4473, | |
| "eval_samples_per_second": 569.089, | |
| "eval_steps_per_second": 11.933, | |
| "step": 2544 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 2862, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 9, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 651155886807636.0, | |
| "train_batch_size": 48, | |
| "trial_name": null, | |
| "trial_params": { | |
| "alpha": 0.3670751935915354, | |
| "num_train_epochs": 9, | |
| "temperature": 12 | |
| } | |
| } | |