| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 3000, |
| "global_step": 29562, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 3.382721060821325e-05, |
| "grad_norm": 86.5, |
| "learning_rate": 0.0002999898518368175, |
| "loss": 50.5, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.10148163182463973, |
| "grad_norm": 1.484375, |
| "learning_rate": 0.00026955551045260807, |
| "loss": 9.2307, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.10148163182463973, |
| "eval_loss": 7.57329797744751, |
| "eval_runtime": 107.8469, |
| "eval_samples_per_second": 875.361, |
| "eval_steps_per_second": 6.843, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.20296326364927947, |
| "grad_norm": 1.75, |
| "learning_rate": 0.0002391110209052161, |
| "loss": 8.3153, |
| "step": 6000 |
| }, |
| { |
| "epoch": 0.20296326364927947, |
| "eval_loss": 7.460958480834961, |
| "eval_runtime": 107.9107, |
| "eval_samples_per_second": 874.844, |
| "eval_steps_per_second": 6.839, |
| "step": 6000 |
| }, |
| { |
| "epoch": 0.30444489547391923, |
| "grad_norm": 1.953125, |
| "learning_rate": 0.00020866653135782423, |
| "loss": 8.245, |
| "step": 9000 |
| }, |
| { |
| "epoch": 0.30444489547391923, |
| "eval_loss": 7.405826568603516, |
| "eval_runtime": 107.9533, |
| "eval_samples_per_second": 874.498, |
| "eval_steps_per_second": 6.836, |
| "step": 9000 |
| }, |
| { |
| "epoch": 0.40592652729855894, |
| "grad_norm": 1.40625, |
| "learning_rate": 0.0001782220418104323, |
| "loss": 8.2157, |
| "step": 12000 |
| }, |
| { |
| "epoch": 0.40592652729855894, |
| "eval_loss": 7.387195110321045, |
| "eval_runtime": 107.9361, |
| "eval_samples_per_second": 874.638, |
| "eval_steps_per_second": 6.837, |
| "step": 12000 |
| }, |
| { |
| "epoch": 0.5074081591231987, |
| "grad_norm": 2.375, |
| "learning_rate": 0.00014777755226304037, |
| "loss": 8.2014, |
| "step": 15000 |
| }, |
| { |
| "epoch": 0.5074081591231987, |
| "eval_loss": 7.376355171203613, |
| "eval_runtime": 107.9488, |
| "eval_samples_per_second": 874.535, |
| "eval_steps_per_second": 6.837, |
| "step": 15000 |
| }, |
| { |
| "epoch": 0.6088897909478385, |
| "grad_norm": 1.5, |
| "learning_rate": 0.00011733306271564845, |
| "loss": 8.1962, |
| "step": 18000 |
| }, |
| { |
| "epoch": 0.6088897909478385, |
| "eval_loss": 7.373560428619385, |
| "eval_runtime": 107.921, |
| "eval_samples_per_second": 874.76, |
| "eval_steps_per_second": 6.838, |
| "step": 18000 |
| }, |
| { |
| "epoch": 0.7103714227724782, |
| "grad_norm": 1.484375, |
| "learning_rate": 8.688857316825655e-05, |
| "loss": 8.1911, |
| "step": 21000 |
| }, |
| { |
| "epoch": 0.7103714227724782, |
| "eval_loss": 7.370765686035156, |
| "eval_runtime": 108.0558, |
| "eval_samples_per_second": 873.669, |
| "eval_steps_per_second": 6.83, |
| "step": 21000 |
| }, |
| { |
| "epoch": 0.8118530545971179, |
| "grad_norm": 1.5078125, |
| "learning_rate": 5.644408362086462e-05, |
| "loss": 8.1927, |
| "step": 24000 |
| }, |
| { |
| "epoch": 0.8118530545971179, |
| "eval_loss": 7.366785049438477, |
| "eval_runtime": 108.0458, |
| "eval_samples_per_second": 873.75, |
| "eval_steps_per_second": 6.83, |
| "step": 24000 |
| }, |
| { |
| "epoch": 0.9133346864217576, |
| "grad_norm": 1.8125, |
| "learning_rate": 2.59995940734727e-05, |
| "loss": 8.1863, |
| "step": 27000 |
| }, |
| { |
| "epoch": 0.9133346864217576, |
| "eval_loss": 7.36619234085083, |
| "eval_runtime": 108.0404, |
| "eval_samples_per_second": 873.793, |
| "eval_steps_per_second": 6.831, |
| "step": 27000 |
| }, |
| { |
| "epoch": 1.0, |
| "step": 29562, |
| "total_flos": 4.126336903687864e+17, |
| "train_loss": 8.319568829916784, |
| "train_runtime": 13641.1405, |
| "train_samples_per_second": 277.383, |
| "train_steps_per_second": 2.167 |
| } |
| ], |
| "logging_steps": 3000, |
| "max_steps": 29562, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 3000, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 4.126336903687864e+17, |
| "train_batch_size": 128, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
