| { | |
| "best_metric": 0.28254151344299316, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.16339869281045752, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006535947712418301, | |
| "grad_norm": 81.04505920410156, | |
| "learning_rate": 5e-05, | |
| "loss": 11.1064, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006535947712418301, | |
| "eval_loss": 10.93410873413086, | |
| "eval_runtime": 3.9389, | |
| "eval_samples_per_second": 12.694, | |
| "eval_steps_per_second": 3.3, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013071895424836602, | |
| "grad_norm": 84.43704986572266, | |
| "learning_rate": 0.0001, | |
| "loss": 10.7929, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0196078431372549, | |
| "grad_norm": 51.297943115234375, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 6.2038, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.026143790849673203, | |
| "grad_norm": 38.199363708496094, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 2.0512, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.032679738562091505, | |
| "grad_norm": 25.375030517578125, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 1.3986, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0392156862745098, | |
| "grad_norm": 25.622278213500977, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 1.3294, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0457516339869281, | |
| "grad_norm": 11.487774848937988, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 0.5629, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.05228758169934641, | |
| "grad_norm": 14.262380599975586, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.9633, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.058823529411764705, | |
| "grad_norm": 12.048569679260254, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.7031, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.06535947712418301, | |
| "grad_norm": 13.704314231872559, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.5484, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0718954248366013, | |
| "grad_norm": 9.657209396362305, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.4793, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0784313725490196, | |
| "grad_norm": 5.514215469360352, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.4715, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.08496732026143791, | |
| "grad_norm": 4.0377116203308105, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.422, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0915032679738562, | |
| "grad_norm": 7.226027965545654, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.4152, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.09803921568627451, | |
| "grad_norm": 5.052182674407959, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.4001, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.10457516339869281, | |
| "grad_norm": 2.393721103668213, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.3588, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.1111111111111111, | |
| "grad_norm": 5.823914051055908, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.4459, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.11764705882352941, | |
| "grad_norm": 3.734591245651245, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.3655, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.12418300653594772, | |
| "grad_norm": 4.15626859664917, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.4, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.13071895424836602, | |
| "grad_norm": 3.9641897678375244, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.4168, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.13725490196078433, | |
| "grad_norm": 3.6173903942108154, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.4026, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.1437908496732026, | |
| "grad_norm": 2.8172080516815186, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.361, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.1503267973856209, | |
| "grad_norm": 4.506333827972412, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.4224, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.1568627450980392, | |
| "grad_norm": 2.879072904586792, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.4037, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.16339869281045752, | |
| "grad_norm": 2.7367208003997803, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.4145, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.16339869281045752, | |
| "eval_loss": 0.28254151344299316, | |
| "eval_runtime": 4.0024, | |
| "eval_samples_per_second": 12.492, | |
| "eval_steps_per_second": 3.248, | |
| "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": 3.087239672233984e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |