| { | |
| "best_metric": 0.38303738832473755, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.01569612305760477, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006278449223041908, | |
| "grad_norm": 1.7238279581069946, | |
| "learning_rate": 2e-05, | |
| "loss": 7.385, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006278449223041908, | |
| "eval_loss": 2.143244743347168, | |
| "eval_runtime": 129.9707, | |
| "eval_samples_per_second": 5.163, | |
| "eval_steps_per_second": 2.585, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012556898446083817, | |
| "grad_norm": 2.936279773712158, | |
| "learning_rate": 4e-05, | |
| "loss": 10.7244, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0018835347669125726, | |
| "grad_norm": 2.1784932613372803, | |
| "learning_rate": 6e-05, | |
| "loss": 8.0292, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0025113796892167633, | |
| "grad_norm": 1.9787063598632812, | |
| "learning_rate": 8e-05, | |
| "loss": 6.6026, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0031392246115209545, | |
| "grad_norm": 3.616180896759033, | |
| "learning_rate": 0.0001, | |
| "loss": 10.2764, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0031392246115209545, | |
| "eval_loss": 2.0979456901550293, | |
| "eval_runtime": 127.4876, | |
| "eval_samples_per_second": 5.263, | |
| "eval_steps_per_second": 2.636, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.003767069533825145, | |
| "grad_norm": 4.404942512512207, | |
| "learning_rate": 0.00012, | |
| "loss": 8.2857, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004394914456129336, | |
| "grad_norm": 3.9975357055664062, | |
| "learning_rate": 0.00014, | |
| "loss": 10.9445, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.005022759378433527, | |
| "grad_norm": 5.789132118225098, | |
| "learning_rate": 0.00016, | |
| "loss": 8.4633, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.005650604300737718, | |
| "grad_norm": 3.1519086360931396, | |
| "learning_rate": 0.00018, | |
| "loss": 5.339, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006278449223041909, | |
| "grad_norm": 3.596461057662964, | |
| "learning_rate": 0.0002, | |
| "loss": 5.4954, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006278449223041909, | |
| "eval_loss": 1.227739691734314, | |
| "eval_runtime": 127.6723, | |
| "eval_samples_per_second": 5.256, | |
| "eval_steps_per_second": 2.632, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006906294145346099, | |
| "grad_norm": 4.8174285888671875, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 4.5564, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00753413906765029, | |
| "grad_norm": 6.006891250610352, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 4.5441, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00816198398995448, | |
| "grad_norm": 5.428179740905762, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 3.6617, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.008789828912258673, | |
| "grad_norm": 7.354944229125977, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 3.2464, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.009417673834562863, | |
| "grad_norm": 4.133303642272949, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.8796, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.009417673834562863, | |
| "eval_loss": 0.51548171043396, | |
| "eval_runtime": 127.4469, | |
| "eval_samples_per_second": 5.265, | |
| "eval_steps_per_second": 2.636, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.010045518756867053, | |
| "grad_norm": 5.053266525268555, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 2.2643, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.010673363679171245, | |
| "grad_norm": 6.078112602233887, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 1.8569, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.011301208601475436, | |
| "grad_norm": 3.603733539581299, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 1.3892, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.011929053523779626, | |
| "grad_norm": 5.492099761962891, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 1.8328, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.012556898446083818, | |
| "grad_norm": 4.075289249420166, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 1.5149, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.012556898446083818, | |
| "eval_loss": 0.40428486466407776, | |
| "eval_runtime": 128.1933, | |
| "eval_samples_per_second": 5.234, | |
| "eval_steps_per_second": 2.621, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.013184743368388008, | |
| "grad_norm": 5.27345085144043, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 1.737, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.013812588290692198, | |
| "grad_norm": 6.114956378936768, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 1.6646, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01444043321299639, | |
| "grad_norm": 4.758719444274902, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 1.194, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.01506827813530058, | |
| "grad_norm": 4.209386825561523, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 1.3629, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01569612305760477, | |
| "grad_norm": 2.46702241897583, | |
| "learning_rate": 0.0, | |
| "loss": 1.4752, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01569612305760477, | |
| "eval_loss": 0.38303738832473755, | |
| "eval_runtime": 127.4845, | |
| "eval_samples_per_second": 5.263, | |
| "eval_steps_per_second": 2.636, | |
| "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": 7915560763392000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |