{ "best_metric": 0.5360515117645264, "best_model_checkpoint": "miner_id_24/checkpoint-25", "epoch": 0.121765601217656, "eval_steps": 25, "global_step": 25, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.004870624048706241, "grad_norm": 16.72881507873535, "learning_rate": 5e-05, "loss": 8.3921, "step": 1 }, { "epoch": 0.004870624048706241, "eval_loss": 9.057514190673828, "eval_runtime": 71.7813, "eval_samples_per_second": 19.267, "eval_steps_per_second": 2.41, "step": 1 }, { "epoch": 0.009741248097412482, "grad_norm": 15.822189331054688, "learning_rate": 0.0001, "loss": 7.9704, "step": 2 }, { "epoch": 0.014611872146118721, "grad_norm": 13.3932523727417, "learning_rate": 9.989294616193017e-05, "loss": 6.5688, "step": 3 }, { "epoch": 0.019482496194824964, "grad_norm": 13.645103454589844, "learning_rate": 9.957224306869053e-05, "loss": 4.353, "step": 4 }, { "epoch": 0.0243531202435312, "grad_norm": 7.153406143188477, "learning_rate": 9.903926402016153e-05, "loss": 2.6478, "step": 5 }, { "epoch": 0.029223744292237442, "grad_norm": 6.654831409454346, "learning_rate": 9.829629131445342e-05, "loss": 1.8828, "step": 6 }, { "epoch": 0.03409436834094368, "grad_norm": 4.364143371582031, "learning_rate": 9.73465064747553e-05, "loss": 1.5108, "step": 7 }, { "epoch": 0.03896499238964993, "grad_norm": 3.8312578201293945, "learning_rate": 9.619397662556435e-05, "loss": 1.2444, "step": 8 }, { "epoch": 0.043835616438356165, "grad_norm": 3.3526787757873535, "learning_rate": 9.484363707663442e-05, "loss": 1.0499, "step": 9 }, { "epoch": 0.0487062404870624, "grad_norm": 3.6641740798950195, "learning_rate": 9.330127018922194e-05, "loss": 1.259, "step": 10 }, { "epoch": 0.05357686453576865, "grad_norm": 4.9439697265625, "learning_rate": 9.157348061512727e-05, "loss": 1.2799, "step": 11 }, { "epoch": 0.058447488584474884, "grad_norm": 6.172881126403809, "learning_rate": 8.966766701456177e-05, "loss": 1.2713, "step": 12 }, { "epoch": 0.06331811263318113, "grad_norm": 4.652101039886475, "learning_rate": 8.759199037394887e-05, "loss": 1.0875, "step": 13 }, { "epoch": 0.06818873668188737, "grad_norm": 3.588376760482788, "learning_rate": 8.535533905932738e-05, "loss": 0.8818, "step": 14 }, { "epoch": 0.0730593607305936, "grad_norm": 3.3157095909118652, "learning_rate": 8.296729075500344e-05, "loss": 0.8273, "step": 15 }, { "epoch": 0.07792998477929985, "grad_norm": 3.7570765018463135, "learning_rate": 8.043807145043604e-05, "loss": 0.8661, "step": 16 }, { "epoch": 0.08280060882800609, "grad_norm": 2.7482430934906006, "learning_rate": 7.777851165098012e-05, "loss": 0.6994, "step": 17 }, { "epoch": 0.08767123287671233, "grad_norm": 2.6488161087036133, "learning_rate": 7.500000000000001e-05, "loss": 0.6133, "step": 18 }, { "epoch": 0.09254185692541857, "grad_norm": 3.297456741333008, "learning_rate": 7.211443451095007e-05, "loss": 0.6869, "step": 19 }, { "epoch": 0.0974124809741248, "grad_norm": 2.9892847537994385, "learning_rate": 6.91341716182545e-05, "loss": 0.5922, "step": 20 }, { "epoch": 0.10228310502283106, "grad_norm": 3.2806317806243896, "learning_rate": 6.607197326515808e-05, "loss": 0.7227, "step": 21 }, { "epoch": 0.1071537290715373, "grad_norm": 3.8307526111602783, "learning_rate": 6.294095225512603e-05, "loss": 0.6735, "step": 22 }, { "epoch": 0.11202435312024353, "grad_norm": 2.4038965702056885, "learning_rate": 5.9754516100806423e-05, "loss": 0.4627, "step": 23 }, { "epoch": 0.11689497716894977, "grad_norm": 3.308608293533325, "learning_rate": 5.6526309611002594e-05, "loss": 0.702, "step": 24 }, { "epoch": 0.121765601217656, "grad_norm": 3.786376953125, "learning_rate": 5.327015646150716e-05, "loss": 0.6389, "step": 25 }, { "epoch": 0.121765601217656, "eval_loss": 0.5360515117645264, "eval_runtime": 71.4632, "eval_samples_per_second": 19.353, "eval_steps_per_second": 2.421, "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": 3.317763172739318e+17, "train_batch_size": 2, "trial_name": null, "trial_params": null }