| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.024052916416115455, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0024052916416115455, | |
| "grad_norm": 0.8320359587669373, | |
| "learning_rate": 2e-05, | |
| "loss": 2.956, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0024052916416115455, | |
| "eval_loss": 2.335012674331665, | |
| "eval_runtime": 3.0463, | |
| "eval_samples_per_second": 57.447, | |
| "eval_steps_per_second": 28.888, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004810583283223091, | |
| "grad_norm": 0.46148884296417236, | |
| "learning_rate": 4e-05, | |
| "loss": 2.5331, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0072158749248346366, | |
| "grad_norm": 0.4285103380680084, | |
| "learning_rate": 6e-05, | |
| "loss": 2.1726, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0072158749248346366, | |
| "eval_loss": 2.3345694541931152, | |
| "eval_runtime": 1.6203, | |
| "eval_samples_per_second": 108.004, | |
| "eval_steps_per_second": 54.311, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.009621166566446182, | |
| "grad_norm": 0.661216139793396, | |
| "learning_rate": 8e-05, | |
| "loss": 2.8089, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.012026458208057728, | |
| "grad_norm": 0.5148930549621582, | |
| "learning_rate": 0.0001, | |
| "loss": 2.2827, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.014431749849669273, | |
| "grad_norm": 0.5082727074623108, | |
| "learning_rate": 0.00012, | |
| "loss": 2.4523, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.014431749849669273, | |
| "eval_loss": 2.3254380226135254, | |
| "eval_runtime": 1.7012, | |
| "eval_samples_per_second": 102.866, | |
| "eval_steps_per_second": 51.727, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01683704149128082, | |
| "grad_norm": 0.641490638256073, | |
| "learning_rate": 0.00014, | |
| "loss": 2.6408, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.019242333132892364, | |
| "grad_norm": 0.8065205216407776, | |
| "learning_rate": 0.00016, | |
| "loss": 2.6962, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02164762477450391, | |
| "grad_norm": 0.5643328428268433, | |
| "learning_rate": 0.00018, | |
| "loss": 2.5749, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02164762477450391, | |
| "eval_loss": 2.298651933670044, | |
| "eval_runtime": 1.6814, | |
| "eval_samples_per_second": 104.081, | |
| "eval_steps_per_second": 52.338, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.024052916416115455, | |
| "grad_norm": 0.4997113049030304, | |
| "learning_rate": 0.0002, | |
| "loss": 2.6017, | |
| "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": 42008496832512.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |