| { | |
| "best_metric": 2.1492695808410645, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-20", | |
| "epoch": 0.007399186089530152, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003699593044765076, | |
| "grad_norm": 1.4009169340133667, | |
| "learning_rate": 2e-05, | |
| "loss": 10.4429, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003699593044765076, | |
| "eval_loss": 2.509531021118164, | |
| "eval_runtime": 104.6884, | |
| "eval_samples_per_second": 10.88, | |
| "eval_steps_per_second": 5.445, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007399186089530152, | |
| "grad_norm": 1.3309544324874878, | |
| "learning_rate": 4e-05, | |
| "loss": 9.6322, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0011098779134295228, | |
| "grad_norm": 1.5765141248703003, | |
| "learning_rate": 6e-05, | |
| "loss": 10.378, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0014798372179060304, | |
| "grad_norm": 1.1468253135681152, | |
| "learning_rate": 8e-05, | |
| "loss": 9.2956, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.001849796522382538, | |
| "grad_norm": 1.2961140871047974, | |
| "learning_rate": 0.0001, | |
| "loss": 9.8093, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001849796522382538, | |
| "eval_loss": 2.5007569789886475, | |
| "eval_runtime": 104.7232, | |
| "eval_samples_per_second": 10.876, | |
| "eval_steps_per_second": 5.443, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0022197558268590455, | |
| "grad_norm": 1.6239173412322998, | |
| "learning_rate": 0.00012, | |
| "loss": 9.2224, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002589715131335553, | |
| "grad_norm": 1.4490967988967896, | |
| "learning_rate": 0.00014, | |
| "loss": 9.5077, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0029596744358120607, | |
| "grad_norm": 1.7314764261245728, | |
| "learning_rate": 0.00016, | |
| "loss": 9.5829, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.003329633740288568, | |
| "grad_norm": 1.7692434787750244, | |
| "learning_rate": 0.00018, | |
| "loss": 9.8363, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.003699593044765076, | |
| "grad_norm": 2.1426827907562256, | |
| "learning_rate": 0.0002, | |
| "loss": 10.0488, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.003699593044765076, | |
| "eval_loss": 2.3780980110168457, | |
| "eval_runtime": 104.8377, | |
| "eval_samples_per_second": 10.864, | |
| "eval_steps_per_second": 5.437, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004069552349241583, | |
| "grad_norm": 1.9337842464447021, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 8.7787, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.004439511653718091, | |
| "grad_norm": 2.108654737472534, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 9.1597, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.004809470958194599, | |
| "grad_norm": 1.804977536201477, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 8.2654, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.005179430262671106, | |
| "grad_norm": 2.0446128845214844, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 9.4629, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.005549389567147614, | |
| "grad_norm": 1.792378306388855, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 8.666, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.005549389567147614, | |
| "eval_loss": 2.193725824356079, | |
| "eval_runtime": 107.7566, | |
| "eval_samples_per_second": 10.57, | |
| "eval_steps_per_second": 5.29, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0059193488716241215, | |
| "grad_norm": 2.1119868755340576, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 9.1084, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.006289308176100629, | |
| "grad_norm": 1.9483788013458252, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 8.5385, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.006659267480577136, | |
| "grad_norm": 1.958540439605713, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 8.3581, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.007029226785053644, | |
| "grad_norm": 2.1146419048309326, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 8.3837, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.007399186089530152, | |
| "grad_norm": 2.071730852127075, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 8.3191, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.007399186089530152, | |
| "eval_loss": 2.1492695808410645, | |
| "eval_runtime": 104.3323, | |
| "eval_samples_per_second": 10.917, | |
| "eval_steps_per_second": 5.463, | |
| "step": 20 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1835906755461120.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |