| { | |
| "best_metric": 1.4314173460006714, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.8097165991902834, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.016194331983805668, | |
| "grad_norm": 1.2264509201049805, | |
| "learning_rate": 2e-05, | |
| "loss": 2.5021, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.016194331983805668, | |
| "eval_loss": 2.0643351078033447, | |
| "eval_runtime": 1.4014, | |
| "eval_samples_per_second": 296.142, | |
| "eval_steps_per_second": 9.277, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.032388663967611336, | |
| "grad_norm": 1.6805273294448853, | |
| "learning_rate": 4e-05, | |
| "loss": 2.5745, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.048582995951417005, | |
| "grad_norm": 1.7652519941329956, | |
| "learning_rate": 6e-05, | |
| "loss": 2.5328, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.06477732793522267, | |
| "grad_norm": 1.5449025630950928, | |
| "learning_rate": 8e-05, | |
| "loss": 2.3659, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.08097165991902834, | |
| "grad_norm": 1.6735774278640747, | |
| "learning_rate": 0.0001, | |
| "loss": 2.1857, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.09716599190283401, | |
| "grad_norm": 1.6963685750961304, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 1.8412, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.11336032388663968, | |
| "grad_norm": 2.557154417037964, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 0.9034, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.12955465587044535, | |
| "grad_norm": 1.9427818059921265, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 0.602, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.145748987854251, | |
| "grad_norm": 2.8637917041778564, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 0.466, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.16194331983805668, | |
| "grad_norm": 2.685127019882202, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.579, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.17813765182186234, | |
| "grad_norm": 8.085659980773926, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 2.1929, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.19433198380566802, | |
| "grad_norm": 9.449539184570312, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 2.2207, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.21052631578947367, | |
| "grad_norm": 10.27923583984375, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 2.9688, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.22672064777327935, | |
| "grad_norm": 6.787315368652344, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 2.915, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.242914979757085, | |
| "grad_norm": 3.513465166091919, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 2.5693, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2591093117408907, | |
| "grad_norm": 1.9367728233337402, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 2.3619, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.27530364372469635, | |
| "grad_norm": 1.4051806926727295, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 2.1111, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.291497975708502, | |
| "grad_norm": 1.225314736366272, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 1.9262, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.3076923076923077, | |
| "grad_norm": 1.328678846359253, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 1.6366, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.32388663967611336, | |
| "grad_norm": 1.8155649900436401, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.8547, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.340080971659919, | |
| "grad_norm": 1.852184772491455, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 0.4935, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.3562753036437247, | |
| "grad_norm": 2.91139554977417, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 0.4462, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.3724696356275304, | |
| "grad_norm": 1.7215583324432373, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 1.3439, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.38866396761133604, | |
| "grad_norm": 1.5459332466125488, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 1.6769, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.4048582995951417, | |
| "grad_norm": 1.4038276672363281, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 1.4309, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.4048582995951417, | |
| "eval_loss": 1.5288701057434082, | |
| "eval_runtime": 1.4075, | |
| "eval_samples_per_second": 294.854, | |
| "eval_steps_per_second": 9.236, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.42105263157894735, | |
| "grad_norm": 1.0969359874725342, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 2.3448, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.43724696356275305, | |
| "grad_norm": 1.16632878780365, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 2.3496, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.4534412955465587, | |
| "grad_norm": 1.0668652057647705, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 2.1761, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.46963562753036436, | |
| "grad_norm": 0.9689870476722717, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 2.109, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.48582995951417, | |
| "grad_norm": 0.9078288674354553, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 1.8696, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5020242914979757, | |
| "grad_norm": 1.026144027709961, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 1.6314, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.5182186234817814, | |
| "grad_norm": 1.445268154144287, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.8089, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.5344129554655871, | |
| "grad_norm": 1.7678817510604858, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 0.4337, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.5506072874493927, | |
| "grad_norm": 2.1613621711730957, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 0.3891, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.5668016194331984, | |
| "grad_norm": 2.175659656524658, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.3807, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.582995951417004, | |
| "grad_norm": 1.0014805793762207, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 1.6756, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.5991902834008097, | |
| "grad_norm": 0.9872593879699707, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 1.3493, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.6153846153846154, | |
| "grad_norm": 0.8853523135185242, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 2.1145, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.631578947368421, | |
| "grad_norm": 0.8329710960388184, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 2.3212, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.6477732793522267, | |
| "grad_norm": 0.774543285369873, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 2.265, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.6639676113360324, | |
| "grad_norm": 0.7718155980110168, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 2.1585, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.680161943319838, | |
| "grad_norm": 0.758331298828125, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 1.9219, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.6963562753036437, | |
| "grad_norm": 0.8226709365844727, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 1.8131, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.7125506072874493, | |
| "grad_norm": 0.9785775542259216, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 0.8923, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.728744939271255, | |
| "grad_norm": 1.1432104110717773, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 0.6488, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.7449392712550608, | |
| "grad_norm": 1.4502125978469849, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 0.3185, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.7611336032388664, | |
| "grad_norm": 1.425331950187683, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 0.2999, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.7773279352226721, | |
| "grad_norm": 0.8650718927383423, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 1.3693, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.7935222672064778, | |
| "grad_norm": 0.8605427145957947, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 1.4871, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.8097165991902834, | |
| "grad_norm": 0.8215957283973694, | |
| "learning_rate": 0.0, | |
| "loss": 1.3633, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.8097165991902834, | |
| "eval_loss": 1.4314173460006714, | |
| "eval_runtime": 1.4157, | |
| "eval_samples_per_second": 293.137, | |
| "eval_steps_per_second": 9.183, | |
| "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": 5, | |
| "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": 1.409481984442368e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |