| { | |
| "best_metric": 1.4563179016113281, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.021482277121374866, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0008592910848549946, | |
| "grad_norm": 0.1244405135512352, | |
| "learning_rate": 2e-05, | |
| "loss": 1.5391, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008592910848549946, | |
| "eval_loss": 1.5906188488006592, | |
| "eval_runtime": 44.0456, | |
| "eval_samples_per_second": 11.125, | |
| "eval_steps_per_second": 5.562, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0017185821697099893, | |
| "grad_norm": 0.14478178322315216, | |
| "learning_rate": 4e-05, | |
| "loss": 1.5235, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0025778732545649837, | |
| "grad_norm": 0.1352323442697525, | |
| "learning_rate": 6e-05, | |
| "loss": 1.5502, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0034371643394199786, | |
| "grad_norm": 0.1392003744840622, | |
| "learning_rate": 8e-05, | |
| "loss": 1.6646, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.004296455424274973, | |
| "grad_norm": 0.1406022608280182, | |
| "learning_rate": 0.0001, | |
| "loss": 1.6298, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004296455424274973, | |
| "eval_loss": 1.5890916585922241, | |
| "eval_runtime": 43.3931, | |
| "eval_samples_per_second": 11.292, | |
| "eval_steps_per_second": 5.646, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0051557465091299675, | |
| "grad_norm": 0.14741098880767822, | |
| "learning_rate": 0.00012, | |
| "loss": 1.6771, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.006015037593984963, | |
| "grad_norm": 0.14259102940559387, | |
| "learning_rate": 0.00014, | |
| "loss": 1.4313, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.006874328678839957, | |
| "grad_norm": 0.15861880779266357, | |
| "learning_rate": 0.00016, | |
| "loss": 1.5912, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.007733619763694952, | |
| "grad_norm": 0.14995227754116058, | |
| "learning_rate": 0.00018, | |
| "loss": 1.5259, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.008592910848549946, | |
| "grad_norm": 0.16810151934623718, | |
| "learning_rate": 0.0002, | |
| "loss": 1.5864, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.008592910848549946, | |
| "eval_loss": 1.5573710203170776, | |
| "eval_runtime": 43.4122, | |
| "eval_samples_per_second": 11.287, | |
| "eval_steps_per_second": 5.644, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00945220193340494, | |
| "grad_norm": 0.17970110476016998, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 1.5495, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.010311493018259935, | |
| "grad_norm": 0.17453698813915253, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 1.5553, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01117078410311493, | |
| "grad_norm": 0.18503691256046295, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 1.5771, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.012030075187969926, | |
| "grad_norm": 0.16835591197013855, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 1.3748, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.01288936627282492, | |
| "grad_norm": 0.1760474592447281, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.5093, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01288936627282492, | |
| "eval_loss": 1.4957950115203857, | |
| "eval_runtime": 43.272, | |
| "eval_samples_per_second": 11.324, | |
| "eval_steps_per_second": 5.662, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.013748657357679914, | |
| "grad_norm": 0.1684129536151886, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.4227, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.014607948442534909, | |
| "grad_norm": 0.18524901568889618, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 1.6153, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.015467239527389903, | |
| "grad_norm": 0.1905449479818344, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 1.4586, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0163265306122449, | |
| "grad_norm": 0.19282594323158264, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 1.4929, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.017185821697099892, | |
| "grad_norm": 0.20464837551116943, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 1.4875, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.017185821697099892, | |
| "eval_loss": 1.4633499383926392, | |
| "eval_runtime": 43.3147, | |
| "eval_samples_per_second": 11.313, | |
| "eval_steps_per_second": 5.656, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01804511278195489, | |
| "grad_norm": 0.18878105282783508, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 1.3512, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.01890440386680988, | |
| "grad_norm": 0.1834011822938919, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 1.4658, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.019763694951664877, | |
| "grad_norm": 0.19138497114181519, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 1.4699, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.02062298603651987, | |
| "grad_norm": 0.21401111781597137, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 1.4216, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.021482277121374866, | |
| "grad_norm": 0.20592810213565826, | |
| "learning_rate": 0.0, | |
| "loss": 1.4432, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.021482277121374866, | |
| "eval_loss": 1.4563179016113281, | |
| "eval_runtime": 43.2353, | |
| "eval_samples_per_second": 11.333, | |
| "eval_steps_per_second": 5.667, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1278959891251200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |