| { | |
| "best_metric": 2.8438894748687744, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.009954210631096954, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00039816842524387816, | |
| "grad_norm": 0.4925259053707123, | |
| "learning_rate": 2e-05, | |
| "loss": 12.0618, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00039816842524387816, | |
| "eval_loss": 2.9059953689575195, | |
| "eval_runtime": 39.4198, | |
| "eval_samples_per_second": 26.839, | |
| "eval_steps_per_second": 13.42, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007963368504877563, | |
| "grad_norm": 0.4671999216079712, | |
| "learning_rate": 4e-05, | |
| "loss": 11.7576, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0011945052757316346, | |
| "grad_norm": 0.47783833742141724, | |
| "learning_rate": 6e-05, | |
| "loss": 11.8741, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0015926737009755126, | |
| "grad_norm": 0.4054562747478485, | |
| "learning_rate": 8e-05, | |
| "loss": 12.0507, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.001990842126219391, | |
| "grad_norm": 0.4586869776248932, | |
| "learning_rate": 0.0001, | |
| "loss": 11.4486, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001990842126219391, | |
| "eval_loss": 2.9012277126312256, | |
| "eval_runtime": 39.2173, | |
| "eval_samples_per_second": 26.978, | |
| "eval_steps_per_second": 13.489, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002389010551463269, | |
| "grad_norm": 0.520916759967804, | |
| "learning_rate": 0.00012, | |
| "loss": 12.1643, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002787178976707147, | |
| "grad_norm": 0.4848686456680298, | |
| "learning_rate": 0.00014, | |
| "loss": 11.7552, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0031853474019510252, | |
| "grad_norm": 0.4438580274581909, | |
| "learning_rate": 0.00016, | |
| "loss": 11.6235, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0035835158271949035, | |
| "grad_norm": 0.4830387234687805, | |
| "learning_rate": 0.00018, | |
| "loss": 11.5816, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.003981684252438782, | |
| "grad_norm": 0.5963536500930786, | |
| "learning_rate": 0.0002, | |
| "loss": 12.3101, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.003981684252438782, | |
| "eval_loss": 2.8900258541107178, | |
| "eval_runtime": 39.3463, | |
| "eval_samples_per_second": 26.889, | |
| "eval_steps_per_second": 13.445, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00437985267768266, | |
| "grad_norm": 0.5164839625358582, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 10.7265, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.004778021102926538, | |
| "grad_norm": 0.6216098070144653, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 11.6547, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.005176189528170416, | |
| "grad_norm": 0.6192723512649536, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 11.7934, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.005574357953414294, | |
| "grad_norm": 0.5728830099105835, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 11.7896, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.005972526378658172, | |
| "grad_norm": 0.6537395119667053, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 11.9603, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.005972526378658172, | |
| "eval_loss": 2.8645522594451904, | |
| "eval_runtime": 39.2736, | |
| "eval_samples_per_second": 26.939, | |
| "eval_steps_per_second": 13.47, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0063706948039020505, | |
| "grad_norm": 0.6704771518707275, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 11.6669, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.006768863229145929, | |
| "grad_norm": 0.790111243724823, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 10.9923, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.007167031654389807, | |
| "grad_norm": 0.7258641719818115, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 11.2983, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.007565200079633685, | |
| "grad_norm": 0.7046627998352051, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 11.0444, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.007963368504877564, | |
| "grad_norm": 0.5883851647377014, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 10.8651, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.007963368504877564, | |
| "eval_loss": 2.847720146179199, | |
| "eval_runtime": 39.599, | |
| "eval_samples_per_second": 26.718, | |
| "eval_steps_per_second": 13.359, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.008361536930121441, | |
| "grad_norm": 0.6781258583068848, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 10.9849, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.00875970535536532, | |
| "grad_norm": 0.6742913722991943, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 11.2705, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.009157873780609197, | |
| "grad_norm": 0.7851435542106628, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 12.2947, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.009556042205853077, | |
| "grad_norm": 0.7483974695205688, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 11.2183, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.009954210631096954, | |
| "grad_norm": 0.7268701791763306, | |
| "learning_rate": 0.0, | |
| "loss": 10.7387, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.009954210631096954, | |
| "eval_loss": 2.8438894748687744, | |
| "eval_runtime": 39.4822, | |
| "eval_samples_per_second": 26.797, | |
| "eval_steps_per_second": 13.398, | |
| "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": 105052448489472.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |