| { | |
| "best_metric": 10.373350143432617, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.7272727272727273, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02909090909090909, | |
| "grad_norm": 0.04542732611298561, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3755, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02909090909090909, | |
| "eval_loss": 10.378427505493164, | |
| "eval_runtime": 0.2157, | |
| "eval_samples_per_second": 1075.713, | |
| "eval_steps_per_second": 134.464, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05818181818181818, | |
| "grad_norm": 0.044699184596538544, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3757, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.08727272727272728, | |
| "grad_norm": 0.04836718365550041, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 10.3797, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.11636363636363636, | |
| "grad_norm": 0.04853840544819832, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 10.3785, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.14545454545454545, | |
| "grad_norm": 0.04985123127698898, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 10.3808, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.17454545454545456, | |
| "grad_norm": 0.05220064893364906, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 10.3776, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.20363636363636364, | |
| "grad_norm": 0.054472118616104126, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 10.3783, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.23272727272727273, | |
| "grad_norm": 0.06365810334682465, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 10.3777, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.26181818181818184, | |
| "grad_norm": 0.0501365028321743, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 10.3754, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.2909090909090909, | |
| "grad_norm": 0.048848334699869156, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 10.3747, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.04923773556947708, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 10.3744, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.3490909090909091, | |
| "grad_norm": 0.04974054545164108, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 10.3749, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.3781818181818182, | |
| "grad_norm": 0.05604294314980507, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 10.3741, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.4072727272727273, | |
| "grad_norm": 0.05577346310019493, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 10.3788, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.43636363636363634, | |
| "grad_norm": 0.06580042093992233, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 10.3744, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.46545454545454545, | |
| "grad_norm": 0.06522443145513535, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 10.3795, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.49454545454545457, | |
| "grad_norm": 0.08119519799947739, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 10.3759, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.5236363636363637, | |
| "grad_norm": 0.056983832269907, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 10.3713, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.5527272727272727, | |
| "grad_norm": 0.052240677177906036, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 10.3741, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.5818181818181818, | |
| "grad_norm": 0.06199200823903084, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 10.3755, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.610909090909091, | |
| "grad_norm": 0.06343241035938263, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 10.3748, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.07450269907712936, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 10.374, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.6690909090909091, | |
| "grad_norm": 0.0749194473028183, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 10.3728, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.6981818181818182, | |
| "grad_norm": 0.08099077641963959, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 10.373, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.7272727272727273, | |
| "grad_norm": 0.08432656526565552, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 10.3731, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.7272727272727273, | |
| "eval_loss": 10.373350143432617, | |
| "eval_runtime": 0.212, | |
| "eval_samples_per_second": 1094.239, | |
| "eval_steps_per_second": 136.78, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 21384029798400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |