| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 42, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.37735849056603776, |
| "grad_norm": 0.6055235266685486, |
| "learning_rate": 0.0001955572805786141, |
| "loss": 1.4222, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.7547169811320755, |
| "grad_norm": 0.6678768992424011, |
| "learning_rate": 0.000178183148246803, |
| "loss": 1.2074, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.0754716981132075, |
| "grad_norm": 0.7173440456390381, |
| "learning_rate": 0.00015000000000000001, |
| "loss": 1.0679, |
| "step": 15 |
| }, |
| { |
| "epoch": 1.4528301886792452, |
| "grad_norm": 0.5845156908035278, |
| "learning_rate": 0.00011490422661761744, |
| "loss": 0.8821, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.830188679245283, |
| "grad_norm": 0.6559388637542725, |
| "learning_rate": 7.774790660436858e-05, |
| "loss": 0.9135, |
| "step": 25 |
| }, |
| { |
| "epoch": 2.150943396226415, |
| "grad_norm": 0.6896112561225891, |
| "learning_rate": 4.3667994193637796e-05, |
| "loss": 0.8115, |
| "step": 30 |
| }, |
| { |
| "epoch": 2.5283018867924527, |
| "grad_norm": 0.9695717096328735, |
| "learning_rate": 1.7376122568400532e-05, |
| "loss": 0.7526, |
| "step": 35 |
| }, |
| { |
| "epoch": 2.9056603773584904, |
| "grad_norm": 0.6637054681777954, |
| "learning_rate": 2.5072087818176382e-06, |
| "loss": 0.7661, |
| "step": 40 |
| }, |
| { |
| "epoch": 3.0, |
| "step": 42, |
| "total_flos": 2.674932293881037e+16, |
| "train_loss": 0.972808321317037, |
| "train_runtime": 285.5422, |
| "train_samples_per_second": 2.206, |
| "train_steps_per_second": 0.147 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 42, |
| "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": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2.674932293881037e+16, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
