| { | |
| "best_metric": 2.7820396423339844, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-20", | |
| "epoch": 0.013395847287340924, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006697923643670462, | |
| "grad_norm": 55.58503723144531, | |
| "learning_rate": 2e-05, | |
| "loss": 17.2692, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006697923643670462, | |
| "eval_loss": 4.885843276977539, | |
| "eval_runtime": 127.0272, | |
| "eval_samples_per_second": 4.952, | |
| "eval_steps_per_second": 2.48, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013395847287340924, | |
| "grad_norm": 53.867401123046875, | |
| "learning_rate": 4e-05, | |
| "loss": 24.7375, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0020093770931011385, | |
| "grad_norm": 93.12490844726562, | |
| "learning_rate": 6e-05, | |
| "loss": 20.3105, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0026791694574681848, | |
| "grad_norm": 39.96519088745117, | |
| "learning_rate": 8e-05, | |
| "loss": 15.8861, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003348961821835231, | |
| "grad_norm": 53.5129508972168, | |
| "learning_rate": 0.0001, | |
| "loss": 17.3642, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.003348961821835231, | |
| "eval_loss": 4.032679557800293, | |
| "eval_runtime": 126.4259, | |
| "eval_samples_per_second": 4.975, | |
| "eval_steps_per_second": 2.492, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004018754186202277, | |
| "grad_norm": 54.64722442626953, | |
| "learning_rate": 0.00012, | |
| "loss": 17.1145, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004688546550569324, | |
| "grad_norm": 47.83176803588867, | |
| "learning_rate": 0.00014, | |
| "loss": 16.429, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0053583389149363695, | |
| "grad_norm": 34.30319595336914, | |
| "learning_rate": 0.00016, | |
| "loss": 11.9642, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.006028131279303416, | |
| "grad_norm": 43.736900329589844, | |
| "learning_rate": 0.00018, | |
| "loss": 14.0488, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006697923643670462, | |
| "grad_norm": 34.1674690246582, | |
| "learning_rate": 0.0002, | |
| "loss": 12.288, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006697923643670462, | |
| "eval_loss": 3.0784964561462402, | |
| "eval_runtime": 125.8228, | |
| "eval_samples_per_second": 4.999, | |
| "eval_steps_per_second": 2.504, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007367716008037508, | |
| "grad_norm": 49.211883544921875, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 14.7968, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.008037508372404554, | |
| "grad_norm": 30.02019500732422, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 10.412, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.008707300736771601, | |
| "grad_norm": 34.77397537231445, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 11.8404, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.009377093101138647, | |
| "grad_norm": 37.78995895385742, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 11.643, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.010046885465505693, | |
| "grad_norm": 37.61135482788086, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 11.3571, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.010046885465505693, | |
| "eval_loss": 2.9143412113189697, | |
| "eval_runtime": 124.2648, | |
| "eval_samples_per_second": 5.062, | |
| "eval_steps_per_second": 2.535, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.010716677829872739, | |
| "grad_norm": 30.211618423461914, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 10.1207, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.011386470194239785, | |
| "grad_norm": 32.74803161621094, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 11.6455, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.012056262558606833, | |
| "grad_norm": 42.23529815673828, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 12.6393, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.012726054922973878, | |
| "grad_norm": 47.026275634765625, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 11.7427, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.013395847287340924, | |
| "grad_norm": 44.214298248291016, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 11.9615, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.013395847287340924, | |
| "eval_loss": 2.7820396423339844, | |
| "eval_runtime": 124.547, | |
| "eval_samples_per_second": 5.05, | |
| "eval_steps_per_second": 2.529, | |
| "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": 3505339571896320.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |