| { | |
| "best_metric": 0.1061437726020813, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.6756756756756757, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.013513513513513514, | |
| "grad_norm": 12.717314720153809, | |
| "learning_rate": 5e-05, | |
| "loss": 8.4274, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013513513513513514, | |
| "eval_loss": 7.954690456390381, | |
| "eval_runtime": 14.7232, | |
| "eval_samples_per_second": 33.892, | |
| "eval_steps_per_second": 4.279, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02702702702702703, | |
| "grad_norm": 9.587789535522461, | |
| "learning_rate": 0.0001, | |
| "loss": 7.9128, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.04054054054054054, | |
| "grad_norm": 8.94620132446289, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 7.792, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.05405405405405406, | |
| "grad_norm": 7.296935558319092, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 6.2742, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06756756756756757, | |
| "grad_norm": 6.838016986846924, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 4.8382, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08108108108108109, | |
| "grad_norm": 6.258609771728516, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 3.4743, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0945945945945946, | |
| "grad_norm": 5.185582160949707, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.1705, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.10810810810810811, | |
| "grad_norm": 5.702025890350342, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.026, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.12162162162162163, | |
| "grad_norm": 4.799233913421631, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.6083, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.13513513513513514, | |
| "grad_norm": 3.8879895210266113, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.4726, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.14864864864864866, | |
| "grad_norm": 3.3153438568115234, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.139, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.16216216216216217, | |
| "grad_norm": 2.1994240283966064, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.6149, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.17567567567567569, | |
| "grad_norm": 1.7580081224441528, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.4744, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.1891891891891892, | |
| "grad_norm": 6.597604274749756, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.5315, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.20270270270270271, | |
| "grad_norm": 2.772972345352173, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.2898, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.21621621621621623, | |
| "grad_norm": 2.2589614391326904, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.2876, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.22972972972972974, | |
| "grad_norm": 3.2585842609405518, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.3712, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.24324324324324326, | |
| "grad_norm": 1.9761191606521606, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.3304, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.25675675675675674, | |
| "grad_norm": 2.4964427947998047, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.3233, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.2702702702702703, | |
| "grad_norm": 3.4830942153930664, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.2562, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.28378378378378377, | |
| "grad_norm": 1.4646419286727905, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.2734, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.2972972972972973, | |
| "grad_norm": 1.3460890054702759, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.2557, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.3108108108108108, | |
| "grad_norm": 2.1516573429107666, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.2221, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.32432432432432434, | |
| "grad_norm": 0.7785410284996033, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.1322, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.33783783783783783, | |
| "grad_norm": 1.2157323360443115, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.1936, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.33783783783783783, | |
| "eval_loss": 0.1367332488298416, | |
| "eval_runtime": 14.6829, | |
| "eval_samples_per_second": 33.985, | |
| "eval_steps_per_second": 4.291, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.35135135135135137, | |
| "grad_norm": 1.1153565645217896, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1049, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.36486486486486486, | |
| "grad_norm": 2.0206172466278076, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.2674, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.3783783783783784, | |
| "grad_norm": 1.362246036529541, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.1538, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.3918918918918919, | |
| "grad_norm": 2.0055975914001465, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.2147, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.40540540540540543, | |
| "grad_norm": 2.0882041454315186, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.2495, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4189189189189189, | |
| "grad_norm": 2.093991279602051, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.2051, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.43243243243243246, | |
| "grad_norm": 1.5407034158706665, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.2374, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.44594594594594594, | |
| "grad_norm": 1.5210086107254028, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.2486, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.4594594594594595, | |
| "grad_norm": 1.4573367834091187, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.2546, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.47297297297297297, | |
| "grad_norm": 1.430071473121643, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.2391, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.4864864864864865, | |
| "grad_norm": 1.4362925291061401, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.1405, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.9847790002822876, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.1705, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.5135135135135135, | |
| "grad_norm": 0.6195996403694153, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.1056, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.527027027027027, | |
| "grad_norm": 0.6867031455039978, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.102, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.5405405405405406, | |
| "grad_norm": 0.8032393455505371, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.1015, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5540540540540541, | |
| "grad_norm": 0.7433449029922485, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.0801, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.5675675675675675, | |
| "grad_norm": 0.8760620355606079, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.166, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.581081081081081, | |
| "grad_norm": 1.1115021705627441, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.2006, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.5945945945945946, | |
| "grad_norm": 1.569411277770996, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.2112, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.6081081081081081, | |
| "grad_norm": 1.140554666519165, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.1916, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.6216216216216216, | |
| "grad_norm": 1.0531151294708252, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.1669, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.6351351351351351, | |
| "grad_norm": 0.7130922079086304, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.1098, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.6486486486486487, | |
| "grad_norm": 1.31761634349823, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.1967, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.6621621621621622, | |
| "grad_norm": 0.7688131332397461, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.1144, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.6756756756756757, | |
| "grad_norm": 1.0444402694702148, | |
| "learning_rate": 0.0, | |
| "loss": 0.1457, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6756756756756757, | |
| "eval_loss": 0.1061437726020813, | |
| "eval_runtime": 14.6835, | |
| "eval_samples_per_second": 33.984, | |
| "eval_steps_per_second": 4.291, | |
| "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": 5.32019209568256e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |