| { | |
| "best_metric": 0.2061881422996521, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.2597402597402597, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01038961038961039, | |
| "grad_norm": 28.486879348754883, | |
| "learning_rate": 5e-05, | |
| "loss": 12.5804, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01038961038961039, | |
| "eval_loss": 12.917760848999023, | |
| "eval_runtime": 2.0615, | |
| "eval_samples_per_second": 24.254, | |
| "eval_steps_per_second": 6.306, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02077922077922078, | |
| "grad_norm": 27.35738754272461, | |
| "learning_rate": 0.0001, | |
| "loss": 12.6136, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03116883116883117, | |
| "grad_norm": 29.368932723999023, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 11.1211, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.04155844155844156, | |
| "grad_norm": 16.969623565673828, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 6.5609, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.05194805194805195, | |
| "grad_norm": 13.911603927612305, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 4.2736, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.06233766233766234, | |
| "grad_norm": 11.471969604492188, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 2.6157, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.07272727272727272, | |
| "grad_norm": 7.600925922393799, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.6604, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.08311688311688312, | |
| "grad_norm": 6.118250846862793, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.0122, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.09350649350649351, | |
| "grad_norm": 21.522790908813477, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.0105, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1038961038961039, | |
| "grad_norm": 6.143969535827637, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.6796, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.11428571428571428, | |
| "grad_norm": 2.42429256439209, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.6191, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.12467532467532468, | |
| "grad_norm": 2.489107847213745, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.6218, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.13506493506493505, | |
| "grad_norm": 0.9331566095352173, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.5814, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.14545454545454545, | |
| "grad_norm": 0.9218307137489319, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.5615, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.15584415584415584, | |
| "grad_norm": 1.182883858680725, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.5296, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.16623376623376623, | |
| "grad_norm": 1.2131173610687256, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.5056, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.17662337662337663, | |
| "grad_norm": 2.1901192665100098, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.4665, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.18701298701298702, | |
| "grad_norm": 2.1342835426330566, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.3724, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.1974025974025974, | |
| "grad_norm": 2.6826727390289307, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.3278, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.2077922077922078, | |
| "grad_norm": 3.3224539756774902, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.2767, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.21818181818181817, | |
| "grad_norm": 4.129552364349365, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.3239, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.22857142857142856, | |
| "grad_norm": 3.2705585956573486, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.2766, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.23896103896103896, | |
| "grad_norm": 3.935323476791382, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.2731, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.24935064935064935, | |
| "grad_norm": 3.1204378604888916, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.2364, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2597402597402597, | |
| "grad_norm": 2.0985143184661865, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.2235, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2597402597402597, | |
| "eval_loss": 0.2061881422996521, | |
| "eval_runtime": 2.0916, | |
| "eval_samples_per_second": 23.905, | |
| "eval_steps_per_second": 6.215, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "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": 8.1240447254528e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |