| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 4.0, |
| "eval_steps": 500, |
| "global_step": 64, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.3252032520325203, |
| "grad_norm": 1.3156858682632446, |
| "learning_rate": 4.951963201008076e-05, |
| "loss": 2.2304, |
| "num_input_tokens_seen": 119024, |
| "step": 5, |
| "train_runtime": 28.3475, |
| "train_tokens_per_second": 4198.75 |
| }, |
| { |
| "epoch": 0.6504065040650406, |
| "grad_norm": 0.7530735731124878, |
| "learning_rate": 4.759973232808609e-05, |
| "loss": 2.147, |
| "num_input_tokens_seen": 238880, |
| "step": 10, |
| "train_runtime": 55.416, |
| "train_tokens_per_second": 4310.67 |
| }, |
| { |
| "epoch": 0.975609756097561, |
| "grad_norm": 0.6344960927963257, |
| "learning_rate": 4.4325261334068426e-05, |
| "loss": 1.9562, |
| "num_input_tokens_seen": 358608, |
| "step": 15, |
| "train_runtime": 82.5363, |
| "train_tokens_per_second": 4344.849 |
| }, |
| { |
| "epoch": 1.2601626016260163, |
| "grad_norm": 0.5793188214302063, |
| "learning_rate": 3.9892482612310836e-05, |
| "loss": 1.5887, |
| "num_input_tokens_seen": 463568, |
| "step": 20, |
| "train_runtime": 106.4581, |
| "train_tokens_per_second": 4354.466 |
| }, |
| { |
| "epoch": 1.5853658536585367, |
| "grad_norm": 0.5236935615539551, |
| "learning_rate": 3.456708580912725e-05, |
| "loss": 1.7952, |
| "num_input_tokens_seen": 583360, |
| "step": 25, |
| "train_runtime": 133.8831, |
| "train_tokens_per_second": 4357.233 |
| }, |
| { |
| "epoch": 1.910569105691057, |
| "grad_norm": 0.6524015665054321, |
| "learning_rate": 2.8668261861384045e-05, |
| "loss": 1.7717, |
| "num_input_tokens_seen": 702656, |
| "step": 30, |
| "train_runtime": 161.3217, |
| "train_tokens_per_second": 4355.62 |
| }, |
| { |
| "epoch": 2.1951219512195124, |
| "grad_norm": 0.5044527053833008, |
| "learning_rate": 2.2549571491760986e-05, |
| "loss": 1.5037, |
| "num_input_tokens_seen": 807312, |
| "step": 35, |
| "train_runtime": 185.3057, |
| "train_tokens_per_second": 4356.649 |
| }, |
| { |
| "epoch": 2.5203252032520327, |
| "grad_norm": 0.5686483979225159, |
| "learning_rate": 1.65777536651945e-05, |
| "loss": 1.7171, |
| "num_input_tokens_seen": 926384, |
| "step": 40, |
| "train_runtime": 212.6983, |
| "train_tokens_per_second": 4355.389 |
| }, |
| { |
| "epoch": 2.845528455284553, |
| "grad_norm": 0.4782630205154419, |
| "learning_rate": 1.1110744174509952e-05, |
| "loss": 1.6151, |
| "num_input_tokens_seen": 1046896, |
| "step": 45, |
| "train_runtime": 240.4926, |
| "train_tokens_per_second": 4353.132 |
| }, |
| { |
| "epoch": 3.130081300813008, |
| "grad_norm": 0.518913745880127, |
| "learning_rate": 6.476221866126029e-06, |
| "loss": 1.4855, |
| "num_input_tokens_seen": 1151200, |
| "step": 50, |
| "train_runtime": 264.5411, |
| "train_tokens_per_second": 4351.686 |
| }, |
| { |
| "epoch": 3.4552845528455283, |
| "grad_norm": 0.5394554734230042, |
| "learning_rate": 2.9519683912911266e-06, |
| "loss": 1.6717, |
| "num_input_tokens_seen": 1270640, |
| "step": 55, |
| "train_runtime": 291.9391, |
| "train_tokens_per_second": 4352.414 |
| }, |
| { |
| "epoch": 3.7804878048780486, |
| "grad_norm": 0.7331702709197998, |
| "learning_rate": 7.492186701364007e-07, |
| "loss": 1.6515, |
| "num_input_tokens_seen": 1390528, |
| "step": 60, |
| "train_runtime": 319.5924, |
| "train_tokens_per_second": 4350.941 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 64, |
| "num_input_tokens_seen": 1471136, |
| "num_train_epochs": 4, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 6.135952763047117e+16, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
