| { | |
| "best_metric": 11.915081977844238, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.1145475372279496, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004581901489117984, | |
| "grad_norm": 0.07413589209318161, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9187, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004581901489117984, | |
| "eval_loss": 11.921486854553223, | |
| "eval_runtime": 2.8885, | |
| "eval_samples_per_second": 508.918, | |
| "eval_steps_per_second": 63.701, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009163802978235968, | |
| "grad_norm": 0.07265150547027588, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9227, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.013745704467353952, | |
| "grad_norm": 0.07466991245746613, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 11.9223, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.018327605956471937, | |
| "grad_norm": 0.07356178760528564, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 11.9243, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.022909507445589918, | |
| "grad_norm": 0.07974877208471298, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 11.9218, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.027491408934707903, | |
| "grad_norm": 0.07175926119089127, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 11.9258, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.032073310423825885, | |
| "grad_norm": 0.07525207847356796, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 11.9239, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.03665521191294387, | |
| "grad_norm": 0.08125446736812592, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 11.9184, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.041237113402061855, | |
| "grad_norm": 0.08757330477237701, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 11.9226, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.045819014891179836, | |
| "grad_norm": 0.07028602063655853, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 11.9194, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.050400916380297825, | |
| "grad_norm": 0.09795945137739182, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 11.9188, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.054982817869415807, | |
| "grad_norm": 0.12250470370054245, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 11.9179, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.05956471935853379, | |
| "grad_norm": 0.11524302512407303, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 11.9195, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.06414662084765177, | |
| "grad_norm": 0.0978427454829216, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 11.9243, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.06872852233676977, | |
| "grad_norm": 0.09556348621845245, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 11.9233, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07331042382588775, | |
| "grad_norm": 0.09863463044166565, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 11.921, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.07789232531500573, | |
| "grad_norm": 0.09590347856283188, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 11.9177, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.08247422680412371, | |
| "grad_norm": 0.09834495186805725, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 11.9223, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.08705612829324169, | |
| "grad_norm": 0.1007021963596344, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 11.9227, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.09163802978235967, | |
| "grad_norm": 0.10571432113647461, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 11.9195, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09621993127147767, | |
| "grad_norm": 0.10596074163913727, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 11.9229, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.10080183276059565, | |
| "grad_norm": 0.10513018071651459, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 11.9179, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.10538373424971363, | |
| "grad_norm": 0.10683262348175049, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 11.9218, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.10996563573883161, | |
| "grad_norm": 0.13230830430984497, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 11.9149, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.1145475372279496, | |
| "grad_norm": 0.17609983682632446, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 11.9121, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1145475372279496, | |
| "eval_loss": 11.915081977844238, | |
| "eval_runtime": 2.8867, | |
| "eval_samples_per_second": 509.229, | |
| "eval_steps_per_second": 63.74, | |
| "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": 521247129600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |