| { | |
| "best_metric": 1.02402925491333, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.15429122468659595, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003085824493731919, | |
| "grad_norm": 404.16534423828125, | |
| "learning_rate": 5e-05, | |
| "loss": 3.101, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003085824493731919, | |
| "eval_loss": 4.791520595550537, | |
| "eval_runtime": 142.6105, | |
| "eval_samples_per_second": 15.307, | |
| "eval_steps_per_second": 1.914, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006171648987463838, | |
| "grad_norm": 461.33148193359375, | |
| "learning_rate": 0.0001, | |
| "loss": 3.7056, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.009257473481195757, | |
| "grad_norm": 332.9734191894531, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 2.7524, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.012343297974927676, | |
| "grad_norm": 317.5028381347656, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.5412, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.015429122468659595, | |
| "grad_norm": 301.2236633300781, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.4091, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.018514946962391515, | |
| "grad_norm": 172.79122924804688, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.3246, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.021600771456123432, | |
| "grad_norm": 364.7156066894531, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.2849, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.024686595949855353, | |
| "grad_norm": 176.93199157714844, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.7689, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02777242044358727, | |
| "grad_norm": 222.73155212402344, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.9251, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03085824493731919, | |
| "grad_norm": 158.37278747558594, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.6428, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03394406943105111, | |
| "grad_norm": 219.42369079589844, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.6383, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03702989392478303, | |
| "grad_norm": 207.2635955810547, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.5722, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.040115718418514947, | |
| "grad_norm": 256.03277587890625, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.8305, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.043201542912246864, | |
| "grad_norm": 213.34117126464844, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.5297, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.04628736740597879, | |
| "grad_norm": 305.8034973144531, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.5751, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.049373191899710706, | |
| "grad_norm": 356.3681640625, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.4967, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.05245901639344262, | |
| "grad_norm": 149.27049255371094, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.1311, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.05554484088717454, | |
| "grad_norm": 98.71231079101562, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.2267, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.05863066538090646, | |
| "grad_norm": 123.04528045654297, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.44, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.06171648987463838, | |
| "grad_norm": 98.89627838134766, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.2261, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06480231436837029, | |
| "grad_norm": 124.62467956542969, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.27, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.06788813886210222, | |
| "grad_norm": 131.42848205566406, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.3113, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.07097396335583414, | |
| "grad_norm": 142.43338012695312, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.4003, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.07405978784956606, | |
| "grad_norm": 149.421875, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.3319, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.07714561234329798, | |
| "grad_norm": 113.16695404052734, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.0517, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07714561234329798, | |
| "eval_loss": 1.3193860054016113, | |
| "eval_runtime": 142.6088, | |
| "eval_samples_per_second": 15.308, | |
| "eval_steps_per_second": 1.914, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08023143683702989, | |
| "grad_norm": 213.13775634765625, | |
| "learning_rate": 5e-05, | |
| "loss": 1.3893, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.08331726133076181, | |
| "grad_norm": 184.24436950683594, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.4026, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.08640308582449373, | |
| "grad_norm": 140.5086212158203, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.2069, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.08948891031822565, | |
| "grad_norm": 88.218994140625, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.1404, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.09257473481195758, | |
| "grad_norm": 96.05084228515625, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.1807, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0956605593056895, | |
| "grad_norm": 174.5589599609375, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.3129, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.09874638379942141, | |
| "grad_norm": 183.8505096435547, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.3968, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.10183220829315333, | |
| "grad_norm": 127.412353515625, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.2247, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.10491803278688525, | |
| "grad_norm": 91.00982666015625, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.1556, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.10800385728061716, | |
| "grad_norm": 114.41508483886719, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.1534, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.11108968177434908, | |
| "grad_norm": 130.89572143554688, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.1666, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.114175506268081, | |
| "grad_norm": 133.42132568359375, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.8188, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.11726133076181292, | |
| "grad_norm": 95.00689697265625, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.9134, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.12034715525554485, | |
| "grad_norm": 94.86679077148438, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.1303, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.12343297974927676, | |
| "grad_norm": 98.16373443603516, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.1006, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.12651880424300868, | |
| "grad_norm": 99.14767456054688, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.1203, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.12960462873674058, | |
| "grad_norm": 101.3357162475586, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.1717, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.13269045323047252, | |
| "grad_norm": 86.6534652709961, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.0954, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.13577627772420445, | |
| "grad_norm": 94.54973602294922, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.1935, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.13886210221793635, | |
| "grad_norm": 114.60092163085938, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.1784, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.14194792671166828, | |
| "grad_norm": 92.37266540527344, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.9896, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.14503375120540019, | |
| "grad_norm": 109.13663482666016, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.9855, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.14811957569913212, | |
| "grad_norm": 108.86652374267578, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.1733, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.15120540019286402, | |
| "grad_norm": 98.48587036132812, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.0276, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.15429122468659595, | |
| "grad_norm": 126.57118225097656, | |
| "learning_rate": 0.0, | |
| "loss": 0.9324, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.15429122468659595, | |
| "eval_loss": 1.02402925491333, | |
| "eval_runtime": 142.6345, | |
| "eval_samples_per_second": 15.305, | |
| "eval_steps_per_second": 1.914, | |
| "step": 50 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.658027780734976e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |