| { | |
| "best_metric": 3.3264994621276855, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.011518746760352474, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00023037493520704948, | |
| "grad_norm": 24.02033805847168, | |
| "learning_rate": 5e-05, | |
| "loss": 92.4645, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00023037493520704948, | |
| "eval_loss": 7.752479076385498, | |
| "eval_runtime": 1004.5497, | |
| "eval_samples_per_second": 29.111, | |
| "eval_steps_per_second": 3.639, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00046074987041409897, | |
| "grad_norm": 24.630556106567383, | |
| "learning_rate": 0.0001, | |
| "loss": 102.4691, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0006911248056211485, | |
| "grad_norm": 26.35936737060547, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 110.7519, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0009214997408281979, | |
| "grad_norm": 37.955142974853516, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 110.5107, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0011518746760352473, | |
| "grad_norm": 49.227054595947266, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 102.3134, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001382249611242297, | |
| "grad_norm": 58.47379684448242, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 97.825, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0016126245464493463, | |
| "grad_norm": 59.28702926635742, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 81.4675, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0018429994816563959, | |
| "grad_norm": 59.851619720458984, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 77.2976, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0020733744168634455, | |
| "grad_norm": 83.16780853271484, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 77.2945, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0023037493520704946, | |
| "grad_norm": 96.0419692993164, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 76.7964, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002534124287277544, | |
| "grad_norm": 77.29739379882812, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 71.0099, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.002764499222484594, | |
| "grad_norm": 93.4258041381836, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 71.9024, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.002994874157691643, | |
| "grad_norm": 82.28678131103516, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 67.3061, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0032252490928986926, | |
| "grad_norm": 113.76140594482422, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 65.2168, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.003455624028105742, | |
| "grad_norm": 89.61382293701172, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 65.1493, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0036859989633127917, | |
| "grad_norm": 60.73603439331055, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 60.6442, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.003916373898519841, | |
| "grad_norm": 53.58428192138672, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 61.5109, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.004146748833726891, | |
| "grad_norm": 47.94493865966797, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 59.7813, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00437712376893394, | |
| "grad_norm": 56.8787727355957, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 59.02, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.004607498704140989, | |
| "grad_norm": 58.95323944091797, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 63.1066, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004837873639348039, | |
| "grad_norm": 63.07703399658203, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 61.5307, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.005068248574555088, | |
| "grad_norm": 57.97236633300781, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 61.2133, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.005298623509762138, | |
| "grad_norm": 225.619140625, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 56.9318, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.005528998444969188, | |
| "grad_norm": 52.913509368896484, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 60.2307, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.005759373380176237, | |
| "grad_norm": 81.08842468261719, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 56.4839, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.005759373380176237, | |
| "eval_loss": 3.751025676727295, | |
| "eval_runtime": 1560.6937, | |
| "eval_samples_per_second": 18.737, | |
| "eval_steps_per_second": 2.343, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.005989748315383286, | |
| "grad_norm": 189.20632934570312, | |
| "learning_rate": 5e-05, | |
| "loss": 63.6113, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.006220123250590336, | |
| "grad_norm": 177.3588409423828, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 62.7124, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.006450498185797385, | |
| "grad_norm": 135.85980224609375, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 62.7468, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.006680873121004435, | |
| "grad_norm": 84.16732788085938, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 60.7165, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.006911248056211484, | |
| "grad_norm": 71.33744812011719, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 56.777, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0071416229914185335, | |
| "grad_norm": 72.3608169555664, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 59.9207, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0073719979266255835, | |
| "grad_norm": 66.34757232666016, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 52.6005, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.007602372861832633, | |
| "grad_norm": 71.25404357910156, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 57.5288, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.007832747797039682, | |
| "grad_norm": 68.51131439208984, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 53.9669, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.008063122732246731, | |
| "grad_norm": 65.51441955566406, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 55.8962, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.008293497667453782, | |
| "grad_norm": 60.33618927001953, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 50.4908, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.008523872602660831, | |
| "grad_norm": 77.44511413574219, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 55.3199, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.00875424753786788, | |
| "grad_norm": 54.78342056274414, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 53.1404, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.00898462247307493, | |
| "grad_norm": 83.0269775390625, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 52.3299, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.009214997408281978, | |
| "grad_norm": 87.23737335205078, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 52.0134, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.009445372343489028, | |
| "grad_norm": 75.3519515991211, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 53.1972, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.009675747278696079, | |
| "grad_norm": 61.294090270996094, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 48.7823, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.009906122213903128, | |
| "grad_norm": 63.34431076049805, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 53.6702, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.010136497149110177, | |
| "grad_norm": 44.3028678894043, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 55.0122, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.010366872084317226, | |
| "grad_norm": 49.571224212646484, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 55.7552, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.010597247019524275, | |
| "grad_norm": 43.006446838378906, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 55.4966, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.010827621954731326, | |
| "grad_norm": 47.070701599121094, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 55.856, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.011057996889938375, | |
| "grad_norm": 48.78907012939453, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 52.8863, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.011288371825145424, | |
| "grad_norm": 59.8986701965332, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 54.6934, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.011518746760352474, | |
| "grad_norm": 86.94013214111328, | |
| "learning_rate": 0.0, | |
| "loss": 55.1274, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.011518746760352474, | |
| "eval_loss": 3.3264994621276855, | |
| "eval_runtime": 1140.7657, | |
| "eval_samples_per_second": 25.635, | |
| "eval_steps_per_second": 3.205, | |
| "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": 5.262429617389568e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |