| { | |
| "best_metric": 0.44243600964546204, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.0695187165775402, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0213903743315508, | |
| "grad_norm": 22.107988357543945, | |
| "learning_rate": 5e-05, | |
| "loss": 11.3772, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0213903743315508, | |
| "eval_loss": 11.360074043273926, | |
| "eval_runtime": 13.037, | |
| "eval_samples_per_second": 24.162, | |
| "eval_steps_per_second": 3.068, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0427807486631016, | |
| "grad_norm": 25.125825881958008, | |
| "learning_rate": 0.0001, | |
| "loss": 11.6658, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.06417112299465241, | |
| "grad_norm": 20.297456741333008, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 10.6422, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0855614973262032, | |
| "grad_norm": 18.9375, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 9.3747, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.10695187165775401, | |
| "grad_norm": 20.752914428710938, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 7.9148, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.12834224598930483, | |
| "grad_norm": 14.726287841796875, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 6.15, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.1497326203208556, | |
| "grad_norm": 15.424025535583496, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 5.2052, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.1711229946524064, | |
| "grad_norm": 19.312702178955078, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 4.4023, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.1925133689839572, | |
| "grad_norm": 18.59730339050293, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 3.3221, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.21390374331550802, | |
| "grad_norm": 12.209615707397461, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.8044, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.23529411764705882, | |
| "grad_norm": 14.418610572814941, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 2.292, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.25668449197860965, | |
| "grad_norm": 12.645349502563477, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.4891, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.27807486631016043, | |
| "grad_norm": 6.159994125366211, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.967, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.2994652406417112, | |
| "grad_norm": 11.86545181274414, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.8284, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.32085561497326204, | |
| "grad_norm": 20.72309684753418, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.8923, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.3422459893048128, | |
| "grad_norm": 18.53023910522461, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.6848, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.36363636363636365, | |
| "grad_norm": 7.3748860359191895, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.6042, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.3850267379679144, | |
| "grad_norm": 5.71441650390625, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.5293, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.40641711229946526, | |
| "grad_norm": 13.76638412475586, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.6376, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.42780748663101603, | |
| "grad_norm": 16.7197208404541, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.6221, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.44919786096256686, | |
| "grad_norm": 11.481889724731445, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.7481, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.47058823529411764, | |
| "grad_norm": 17.15256118774414, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.8192, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.4919786096256685, | |
| "grad_norm": 3.653644323348999, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.4961, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.5133689839572193, | |
| "grad_norm": 4.527404308319092, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.4964, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.5347593582887701, | |
| "grad_norm": 2.5339252948760986, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.5008, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5347593582887701, | |
| "eval_loss": 0.6032811403274536, | |
| "eval_runtime": 13.0102, | |
| "eval_samples_per_second": 24.212, | |
| "eval_steps_per_second": 3.075, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5561497326203209, | |
| "grad_norm": 2.761204481124878, | |
| "learning_rate": 5e-05, | |
| "loss": 0.4991, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.5775401069518716, | |
| "grad_norm": 2.248439073562622, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.4998, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.5989304812834224, | |
| "grad_norm": 8.887104034423828, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.6861, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.6203208556149733, | |
| "grad_norm": 12.968907356262207, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.9096, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.6417112299465241, | |
| "grad_norm": 11.061800956726074, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.806, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.6631016042780749, | |
| "grad_norm": 5.628628730773926, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.5288, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.6844919786096256, | |
| "grad_norm": 4.9715166091918945, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.4373, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.7058823529411765, | |
| "grad_norm": 4.011041164398193, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.4285, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.7272727272727273, | |
| "grad_norm": 3.736095666885376, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.4914, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.7486631016042781, | |
| "grad_norm": 6.084108352661133, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.6763, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.7700534759358288, | |
| "grad_norm": 1.327826738357544, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.437, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.7914438502673797, | |
| "grad_norm": 2.1312787532806396, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.4217, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.8128342245989305, | |
| "grad_norm": 4.005236625671387, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.4557, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.8342245989304813, | |
| "grad_norm": 1.245957612991333, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.4159, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.8556149732620321, | |
| "grad_norm": 4.751588821411133, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.5018, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.8770053475935828, | |
| "grad_norm": 6.285404682159424, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.519, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.8983957219251337, | |
| "grad_norm": 5.302483558654785, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.5138, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.9197860962566845, | |
| "grad_norm": 2.5284996032714844, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.4295, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.9411764705882353, | |
| "grad_norm": 7.028666019439697, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.4705, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.9625668449197861, | |
| "grad_norm": 4.487104892730713, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.4287, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.983957219251337, | |
| "grad_norm": 2.946838140487671, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.4318, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.0053475935828877, | |
| "grad_norm": 2.243734836578369, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.5529, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.0267379679144386, | |
| "grad_norm": 2.9415969848632812, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.4532, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.0481283422459893, | |
| "grad_norm": 1.878656029701233, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.4325, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.0695187165775402, | |
| "grad_norm": 2.0214691162109375, | |
| "learning_rate": 0.0, | |
| "loss": 0.3916, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.0695187165775402, | |
| "eval_loss": 0.44243600964546204, | |
| "eval_runtime": 12.9999, | |
| "eval_samples_per_second": 24.231, | |
| "eval_steps_per_second": 3.077, | |
| "step": 50 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.229252309123072e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |