| { | |
| "best_metric": 1.2043055295944214, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.12876227265411236, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005150490906164494, | |
| "grad_norm": 1.6126657724380493, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 1.941, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005150490906164494, | |
| "eval_loss": 1.8850927352905273, | |
| "eval_runtime": 4.0033, | |
| "eval_samples_per_second": 12.49, | |
| "eval_steps_per_second": 3.247, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010300981812328988, | |
| "grad_norm": 1.6743135452270508, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 1.7523, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01545147271849348, | |
| "grad_norm": 1.6910467147827148, | |
| "learning_rate": 0.0001, | |
| "loss": 1.7829, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.020601963624657976, | |
| "grad_norm": 1.367571234703064, | |
| "learning_rate": 9.99571699711836e-05, | |
| "loss": 1.5894, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.02575245453082247, | |
| "grad_norm": 1.495391607284546, | |
| "learning_rate": 9.982876141412856e-05, | |
| "loss": 1.5111, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03090294543698696, | |
| "grad_norm": 1.160764455795288, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 1.4233, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03605343634315146, | |
| "grad_norm": 0.8878348469734192, | |
| "learning_rate": 9.931634888554937e-05, | |
| "loss": 1.348, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.04120392724931595, | |
| "grad_norm": 0.9640621542930603, | |
| "learning_rate": 9.893332032039701e-05, | |
| "loss": 1.3584, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.04635441815548044, | |
| "grad_norm": 0.9921740889549255, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 1.2667, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.05150490906164494, | |
| "grad_norm": 0.9959519505500793, | |
| "learning_rate": 9.791726278367022e-05, | |
| "loss": 1.1275, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05665539996780943, | |
| "grad_norm": 1.0067778825759888, | |
| "learning_rate": 9.728616793536588e-05, | |
| "loss": 1.0443, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.06180589087397392, | |
| "grad_norm": 1.338114857673645, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.0808, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.06695638178013842, | |
| "grad_norm": 1.3758338689804077, | |
| "learning_rate": 9.578385041664925e-05, | |
| "loss": 1.619, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.07210687268630292, | |
| "grad_norm": 0.9469649195671082, | |
| "learning_rate": 9.491548749301997e-05, | |
| "loss": 1.4238, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0772573635924674, | |
| "grad_norm": 0.6833482384681702, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.3451, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0824078544986319, | |
| "grad_norm": 0.8655621409416199, | |
| "learning_rate": 9.295261506157986e-05, | |
| "loss": 1.3856, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0875583454047964, | |
| "grad_norm": 0.7689515948295593, | |
| "learning_rate": 9.186184199300464e-05, | |
| "loss": 1.2611, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.09270883631096088, | |
| "grad_norm": 0.7660016417503357, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 1.236, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.09785932721712538, | |
| "grad_norm": 0.7246228456497192, | |
| "learning_rate": 8.947199994035401e-05, | |
| "loss": 1.1257, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.10300981812328988, | |
| "grad_norm": 0.791655421257019, | |
| "learning_rate": 8.817748015645558e-05, | |
| "loss": 1.1965, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.10816030902945437, | |
| "grad_norm": 0.8405879735946655, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.2137, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.11331079993561886, | |
| "grad_norm": 0.7571701407432556, | |
| "learning_rate": 8.540155934270471e-05, | |
| "loss": 1.0821, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.11846129084178336, | |
| "grad_norm": 0.9514710903167725, | |
| "learning_rate": 8.392544243589427e-05, | |
| "loss": 1.0548, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.12361178174794785, | |
| "grad_norm": 1.1480365991592407, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 1.0676, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.12876227265411236, | |
| "grad_norm": 1.1530849933624268, | |
| "learning_rate": 8.081093963579707e-05, | |
| "loss": 0.959, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.12876227265411236, | |
| "eval_loss": 1.2043055295944214, | |
| "eval_runtime": 4.0623, | |
| "eval_samples_per_second": 12.308, | |
| "eval_steps_per_second": 3.2, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "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": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |