| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.040115331578287575, |
| "eval_steps": 500, |
| "global_step": 200, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0020057665789143786, |
| "grad_norm": 0.0, |
| "learning_rate": 3.0080213903743316e-07, |
| "loss": 0.0, |
| "mean_token_accuracy": 0.0, |
| "num_tokens": 36673.0, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.004011533157828757, |
| "grad_norm": 0.0, |
| "learning_rate": 6.350267379679145e-07, |
| "loss": 0.0, |
| "mean_token_accuracy": 0.0, |
| "num_tokens": 73344.0, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.006017299736743136, |
| "grad_norm": 0.0, |
| "learning_rate": 9.692513368983958e-07, |
| "loss": 0.0, |
| "mean_token_accuracy": 0.0, |
| "num_tokens": 110756.0, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.008023066315657515, |
| "grad_norm": 0.0, |
| "learning_rate": 1.3034759358288772e-06, |
| "loss": 0.0, |
| "mean_token_accuracy": 0.0, |
| "num_tokens": 147094.0, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.010028832894571894, |
| "grad_norm": 0.0, |
| "learning_rate": 1.6377005347593583e-06, |
| "loss": 0.0, |
| "mean_token_accuracy": 0.0, |
| "num_tokens": 184910.0, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.012034599473486273, |
| "grad_norm": 0.0, |
| "learning_rate": 1.9719251336898394e-06, |
| "loss": 0.0, |
| "mean_token_accuracy": 0.0, |
| "num_tokens": 222083.0, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.014040366052400652, |
| "grad_norm": 0.0, |
| "learning_rate": 2.306149732620321e-06, |
| "loss": 0.0, |
| "mean_token_accuracy": 0.0, |
| "num_tokens": 259469.0, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.01604613263131503, |
| "grad_norm": 0.0, |
| "learning_rate": 2.6403743315508026e-06, |
| "loss": 0.0, |
| "mean_token_accuracy": 0.0, |
| "num_tokens": 296196.0, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.01805189921022941, |
| "grad_norm": 0.0, |
| "learning_rate": 2.9745989304812837e-06, |
| "loss": 0.0, |
| "mean_token_accuracy": 0.0, |
| "num_tokens": 333651.0, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.020057665789143787, |
| "grad_norm": 0.0, |
| "learning_rate": 3.308823529411765e-06, |
| "loss": 0.0, |
| "mean_token_accuracy": 0.0, |
| "num_tokens": 371196.0, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.022063432368058168, |
| "grad_norm": 0.0, |
| "learning_rate": 3.643048128342246e-06, |
| "loss": 0.0, |
| "mean_token_accuracy": 0.0, |
| "num_tokens": 408430.0, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.024069198946972545, |
| "grad_norm": 0.0, |
| "learning_rate": 3.9772727272727275e-06, |
| "loss": 0.0, |
| "mean_token_accuracy": 0.0, |
| "num_tokens": 445095.0, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.026074965525886926, |
| "grad_norm": 0.0, |
| "learning_rate": 4.311497326203208e-06, |
| "loss": 0.0, |
| "mean_token_accuracy": 0.0, |
| "num_tokens": 483443.0, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.028080732104801304, |
| "grad_norm": 0.0, |
| "learning_rate": 4.64572192513369e-06, |
| "loss": 0.0, |
| "mean_token_accuracy": 0.0, |
| "num_tokens": 519939.0, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.03008649868371568, |
| "grad_norm": 0.0, |
| "learning_rate": 4.979946524064171e-06, |
| "loss": 0.0, |
| "mean_token_accuracy": 0.0, |
| "num_tokens": 557291.0, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.03209226526263006, |
| "grad_norm": 0.0, |
| "learning_rate": 5.314171122994652e-06, |
| "loss": 0.0, |
| "mean_token_accuracy": 0.0, |
| "num_tokens": 594842.0, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.03409803184154444, |
| "grad_norm": 0.0, |
| "learning_rate": 5.648395721925134e-06, |
| "loss": 0.0, |
| "mean_token_accuracy": 0.0, |
| "num_tokens": 630588.0, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.03610379842045882, |
| "grad_norm": 0.0, |
| "learning_rate": 5.982620320855615e-06, |
| "loss": 0.0, |
| "mean_token_accuracy": 0.0, |
| "num_tokens": 666902.0, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.0381095649993732, |
| "grad_norm": 0.0, |
| "learning_rate": 6.316844919786097e-06, |
| "loss": 0.0, |
| "mean_token_accuracy": 0.0, |
| "num_tokens": 704018.0, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.040115331578287575, |
| "grad_norm": 0.0, |
| "learning_rate": 6.651069518716578e-06, |
| "loss": 0.0, |
| "mean_token_accuracy": 0.0, |
| "num_tokens": 741862.0, |
| "step": 200 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 14958, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.660951199643648e+16, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
