| { | |
| "best_metric": 2.626811981201172, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.09017132551848513, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0036068530207394047, | |
| "grad_norm": 0.9312214851379395, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 11.1103, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0036068530207394047, | |
| "eval_loss": 2.680246353149414, | |
| "eval_runtime": 12.0869, | |
| "eval_samples_per_second": 9.68, | |
| "eval_steps_per_second": 4.881, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007213706041478809, | |
| "grad_norm": 0.920833170413971, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 10.8111, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.010820559062218215, | |
| "grad_norm": 0.9480271339416504, | |
| "learning_rate": 6e-06, | |
| "loss": 10.6508, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.014427412082957619, | |
| "grad_norm": 0.9571245312690735, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 10.7966, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.018034265103697024, | |
| "grad_norm": 0.9208737015724182, | |
| "learning_rate": 1e-05, | |
| "loss": 10.9468, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.018034265103697024, | |
| "eval_loss": 2.6797571182250977, | |
| "eval_runtime": 12.0851, | |
| "eval_samples_per_second": 9.681, | |
| "eval_steps_per_second": 4.882, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02164111812443643, | |
| "grad_norm": 0.9306275844573975, | |
| "learning_rate": 1.2e-05, | |
| "loss": 10.6401, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.025247971145175834, | |
| "grad_norm": 0.9370696544647217, | |
| "learning_rate": 1.4e-05, | |
| "loss": 10.6417, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.028854824165915238, | |
| "grad_norm": 1.055396318435669, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 10.7145, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.032461677186654644, | |
| "grad_norm": 1.0336787700653076, | |
| "learning_rate": 1.8e-05, | |
| "loss": 10.7719, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03606853020739405, | |
| "grad_norm": 1.0623098611831665, | |
| "learning_rate": 2e-05, | |
| "loss": 10.8959, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03606853020739405, | |
| "eval_loss": 2.6718361377716064, | |
| "eval_runtime": 12.0963, | |
| "eval_samples_per_second": 9.672, | |
| "eval_steps_per_second": 4.878, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03967538322813345, | |
| "grad_norm": 1.1591328382492065, | |
| "learning_rate": 1.9781476007338058e-05, | |
| "loss": 10.7372, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.04328223624887286, | |
| "grad_norm": 1.1925017833709717, | |
| "learning_rate": 1.913545457642601e-05, | |
| "loss": 10.6267, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.046889089269612265, | |
| "grad_norm": 1.2597171068191528, | |
| "learning_rate": 1.8090169943749477e-05, | |
| "loss": 10.8772, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.05049594229035167, | |
| "grad_norm": 1.3097079992294312, | |
| "learning_rate": 1.6691306063588583e-05, | |
| "loss": 10.6183, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.05410279531109107, | |
| "grad_norm": 1.390768051147461, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 10.5317, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05410279531109107, | |
| "eval_loss": 2.6502935886383057, | |
| "eval_runtime": 12.1513, | |
| "eval_samples_per_second": 9.629, | |
| "eval_steps_per_second": 4.855, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.057709648331830475, | |
| "grad_norm": 1.3049812316894531, | |
| "learning_rate": 1.3090169943749475e-05, | |
| "loss": 10.6775, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.061316501352569885, | |
| "grad_norm": 1.3082205057144165, | |
| "learning_rate": 1.1045284632676535e-05, | |
| "loss": 10.4822, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.06492335437330929, | |
| "grad_norm": 1.460840106010437, | |
| "learning_rate": 8.954715367323468e-06, | |
| "loss": 10.7828, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.06853020739404869, | |
| "grad_norm": 1.2913298606872559, | |
| "learning_rate": 6.909830056250527e-06, | |
| "loss": 10.4023, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0721370604147881, | |
| "grad_norm": 1.4784389734268188, | |
| "learning_rate": 5.000000000000003e-06, | |
| "loss": 10.6093, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0721370604147881, | |
| "eval_loss": 2.63152813911438, | |
| "eval_runtime": 12.0811, | |
| "eval_samples_per_second": 9.685, | |
| "eval_steps_per_second": 4.884, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0757439134355275, | |
| "grad_norm": 1.4882969856262207, | |
| "learning_rate": 3.308693936411421e-06, | |
| "loss": 10.718, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0793507664562669, | |
| "grad_norm": 1.4357144832611084, | |
| "learning_rate": 1.9098300562505266e-06, | |
| "loss": 10.5072, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0829576194770063, | |
| "grad_norm": 1.4908266067504883, | |
| "learning_rate": 8.645454235739903e-07, | |
| "loss": 10.5149, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.08656447249774572, | |
| "grad_norm": 1.411119818687439, | |
| "learning_rate": 2.1852399266194312e-07, | |
| "loss": 10.5278, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.09017132551848513, | |
| "grad_norm": 1.4688230752944946, | |
| "learning_rate": 0.0, | |
| "loss": 10.4999, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.09017132551848513, | |
| "eval_loss": 2.626811981201172, | |
| "eval_runtime": 12.1576, | |
| "eval_samples_per_second": 9.624, | |
| "eval_steps_per_second": 4.853, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7994716371025920.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |