| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.019057702488088937, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006352567496029645, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 23.7178, | |
| "eval_samples_per_second": 125.771, | |
| "eval_steps_per_second": 41.952, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0019057702488088936, | |
| "grad_norm": 3.185934110661037e-05, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 138.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0038115404976177872, | |
| "grad_norm": 2.9136550438124686e-05, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 138.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005082053996823716, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 23.7611, | |
| "eval_samples_per_second": 125.542, | |
| "eval_steps_per_second": 41.875, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.005717310746426681, | |
| "grad_norm": 2.6557927412795834e-05, | |
| "learning_rate": 0.00027, | |
| "loss": 138.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0076230809952355745, | |
| "grad_norm": 2.7144717023475096e-05, | |
| "learning_rate": 0.00029265847744427303, | |
| "loss": 138.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.009528851244044468, | |
| "grad_norm": 2.6359681214671582e-05, | |
| "learning_rate": 0.00025606601717798207, | |
| "loss": 138.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.010164107993647432, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 23.7115, | |
| "eval_samples_per_second": 125.804, | |
| "eval_steps_per_second": 41.963, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.011434621492853361, | |
| "grad_norm": 3.279528027633205e-05, | |
| "learning_rate": 0.0001963525491562421, | |
| "loss": 138.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.013340391741662256, | |
| "grad_norm": 3.3322605304419994e-05, | |
| "learning_rate": 0.00012653483024396533, | |
| "loss": 138.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.015246161990471149, | |
| "grad_norm": 4.744883699459024e-05, | |
| "learning_rate": 6.183221215612904e-05, | |
| "loss": 138.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.015246161990471149, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 23.755, | |
| "eval_samples_per_second": 125.574, | |
| "eval_steps_per_second": 41.886, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.017151932239280042, | |
| "grad_norm": 3.736266808118671e-05, | |
| "learning_rate": 1.634902137174483e-05, | |
| "loss": 138.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.019057702488088937, | |
| "grad_norm": 4.924211316392757e-05, | |
| "learning_rate": 0.0, | |
| "loss": 138.0, | |
| "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": 9934126055424.0, | |
| "train_batch_size": 3, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |