| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00252881798832529, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 8.429393294417634e-05, | |
| "eval_loss": 2.416701078414917, | |
| "eval_runtime": 262.9194, | |
| "eval_samples_per_second": 18.998, | |
| "eval_steps_per_second": 9.501, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00025288179883252904, | |
| "grad_norm": 0.5816600918769836, | |
| "learning_rate": 3e-05, | |
| "loss": 2.3099, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0005057635976650581, | |
| "grad_norm": 0.665079653263092, | |
| "learning_rate": 6e-05, | |
| "loss": 2.3403, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0006743514635534107, | |
| "eval_loss": 2.2723031044006348, | |
| "eval_runtime": 261.6831, | |
| "eval_samples_per_second": 19.088, | |
| "eval_steps_per_second": 9.546, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0007586453964975871, | |
| "grad_norm": 0.6872488856315613, | |
| "learning_rate": 9e-05, | |
| "loss": 2.2119, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0010115271953301161, | |
| "grad_norm": 0.8066004514694214, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 2.1951, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.001264408994162645, | |
| "grad_norm": 0.9734544157981873, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.997, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0013487029271068215, | |
| "eval_loss": 1.712154507637024, | |
| "eval_runtime": 261.3622, | |
| "eval_samples_per_second": 19.111, | |
| "eval_steps_per_second": 9.558, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0015172907929951742, | |
| "grad_norm": 0.838837742805481, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 1.6336, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0017701725918277031, | |
| "grad_norm": 0.9744684100151062, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 1.5937, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0020230543906602323, | |
| "grad_norm": 0.7924067378044128, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 1.5408, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0020230543906602323, | |
| "eval_loss": 1.5494054555892944, | |
| "eval_runtime": 261.4684, | |
| "eval_samples_per_second": 19.104, | |
| "eval_steps_per_second": 9.554, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0022759361894927614, | |
| "grad_norm": 0.6777858734130859, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 1.6079, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.00252881798832529, | |
| "grad_norm": 0.565368115901947, | |
| "learning_rate": 0.0, | |
| "loss": 1.2456, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.048558039990272e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |