| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.9876543209876543, |
| "eval_steps": 500, |
| "global_step": 100, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "entropy": 0.23424072265625, |
| "epoch": 0.09876543209876543, |
| "grad_norm": 2.8012847900390625, |
| "learning_rate": 4.997139532754547e-06, |
| "loss": 0.5476476669311523, |
| "mean_token_accuracy": 0.8658089742064476, |
| "num_tokens": 7303586.0, |
| "step": 10 |
| }, |
| { |
| "entropy": 0.36380615234375, |
| "epoch": 0.19753086419753085, |
| "grad_norm": 0.9290825128555298, |
| "learning_rate": 4.9464686742003e-06, |
| "loss": 0.33961148262023927, |
| "mean_token_accuracy": 0.8832358054816722, |
| "num_tokens": 14813382.0, |
| "step": 20 |
| }, |
| { |
| "entropy": 0.27252197265625, |
| "epoch": 0.2962962962962963, |
| "grad_norm": 0.9668920040130615, |
| "learning_rate": 4.833712860686666e-06, |
| "loss": 0.28450584411621094, |
| "mean_token_accuracy": 0.8983814604580402, |
| "num_tokens": 22473968.0, |
| "step": 30 |
| }, |
| { |
| "entropy": 0.28291015625, |
| "epoch": 0.3950617283950617, |
| "grad_norm": 1.1789610385894775, |
| "learning_rate": 4.661733538868256e-06, |
| "loss": 0.27588281631469724, |
| "mean_token_accuracy": 0.8961905054748058, |
| "num_tokens": 30023021.0, |
| "step": 40 |
| }, |
| { |
| "entropy": 0.2694091796875, |
| "epoch": 0.49382716049382713, |
| "grad_norm": 0.8277121782302856, |
| "learning_rate": 4.434895092626883e-06, |
| "loss": 0.269238543510437, |
| "mean_token_accuracy": 0.8999109908938407, |
| "num_tokens": 37583230.0, |
| "step": 50 |
| }, |
| { |
| "entropy": 0.2652099609375, |
| "epoch": 0.5925925925925926, |
| "grad_norm": 0.7671821117401123, |
| "learning_rate": 4.158954086461603e-06, |
| "loss": 0.2563727617263794, |
| "mean_token_accuracy": 0.9032368950545788, |
| "num_tokens": 45171080.0, |
| "step": 60 |
| }, |
| { |
| "entropy": 0.25435791015625, |
| "epoch": 0.691358024691358, |
| "grad_norm": 0.8128501176834106, |
| "learning_rate": 3.84091317898803e-06, |
| "loss": 0.24829578399658203, |
| "mean_token_accuracy": 0.9061719521880149, |
| "num_tokens": 52615858.0, |
| "step": 70 |
| }, |
| { |
| "entropy": 0.2535888671875, |
| "epoch": 0.7901234567901234, |
| "grad_norm": 0.8221994638442993, |
| "learning_rate": 3.488843413838963e-06, |
| "loss": 0.2477095603942871, |
| "mean_token_accuracy": 0.9068119570612907, |
| "num_tokens": 60109828.0, |
| "step": 80 |
| }, |
| { |
| "entropy": 0.2525390625, |
| "epoch": 0.8888888888888888, |
| "grad_norm": 0.7399382591247559, |
| "learning_rate": 3.111679397756906e-06, |
| "loss": 0.2487654685974121, |
| "mean_token_accuracy": 0.9072466276586055, |
| "num_tokens": 67709759.0, |
| "step": 90 |
| }, |
| { |
| "entropy": 0.2582275390625, |
| "epoch": 0.9876543209876543, |
| "grad_norm": 0.7466909885406494, |
| "learning_rate": 2.7189925637210325e-06, |
| "loss": 0.24907536506652833, |
| "mean_token_accuracy": 0.9054910212755203, |
| "num_tokens": 75341044.0, |
| "step": 100 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 204, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 20, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 686829711917056.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
