| { | |
| "best_metric": 6.912809371948242, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.3322314049586776, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.026446280991735537, | |
| "grad_norm": 0.6606590151786804, | |
| "learning_rate": 5e-05, | |
| "loss": 6.9198, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.026446280991735537, | |
| "eval_loss": 6.939949989318848, | |
| "eval_runtime": 0.2079, | |
| "eval_samples_per_second": 1226.53, | |
| "eval_steps_per_second": 153.917, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05289256198347107, | |
| "grad_norm": 0.6681128144264221, | |
| "learning_rate": 0.0001, | |
| "loss": 6.9171, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.07933884297520662, | |
| "grad_norm": 0.27679502964019775, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 6.9456, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.10578512396694215, | |
| "grad_norm": 0.2745823264122009, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 6.9391, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.1322314049586777, | |
| "grad_norm": 0.219028040766716, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 6.9458, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.15867768595041323, | |
| "grad_norm": 0.25739091634750366, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 6.9417, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.18512396694214875, | |
| "grad_norm": 0.3217504918575287, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 6.9345, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.2115702479338843, | |
| "grad_norm": 0.3200313448905945, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 6.9359, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.23801652892561984, | |
| "grad_norm": 0.3203120231628418, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 6.9336, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.2644628099173554, | |
| "grad_norm": 0.6145105361938477, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 6.9088, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2909090909090909, | |
| "grad_norm": 0.6703035235404968, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 6.901, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.31735537190082647, | |
| "grad_norm": 0.26121264696121216, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 6.9301, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.343801652892562, | |
| "grad_norm": 0.27104130387306213, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 6.9334, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.3702479338842975, | |
| "grad_norm": 0.2263699471950531, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 6.9346, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.39669421487603307, | |
| "grad_norm": 0.24379611015319824, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 6.9342, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.4231404958677686, | |
| "grad_norm": 0.29605957865715027, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 6.9266, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.44958677685950416, | |
| "grad_norm": 0.3095487952232361, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 6.9225, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.47603305785123967, | |
| "grad_norm": 0.3249109089374542, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 6.9311, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.5024793388429752, | |
| "grad_norm": 0.4838687777519226, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 6.9051, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.5289256198347108, | |
| "grad_norm": 0.6721590757369995, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 6.8906, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.5553719008264463, | |
| "grad_norm": 0.31941476464271545, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 6.9157, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.5818181818181818, | |
| "grad_norm": 0.24956785142421722, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 6.9243, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.6082644628099173, | |
| "grad_norm": 0.2541434168815613, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 6.9263, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.6347107438016529, | |
| "grad_norm": 0.251471608877182, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 6.9317, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.6611570247933884, | |
| "grad_norm": 0.2736002206802368, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 6.9218, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.6611570247933884, | |
| "eval_loss": 6.9197845458984375, | |
| "eval_runtime": 0.2085, | |
| "eval_samples_per_second": 1223.197, | |
| "eval_steps_per_second": 153.499, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.687603305785124, | |
| "grad_norm": 0.3520897328853607, | |
| "learning_rate": 5e-05, | |
| "loss": 6.9146, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.7140495867768595, | |
| "grad_norm": 0.36051222681999207, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 6.9212, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.740495867768595, | |
| "grad_norm": 0.36609479784965515, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 6.9077, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.7669421487603306, | |
| "grad_norm": 0.6825762391090393, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 6.8783, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.7933884297520661, | |
| "grad_norm": 0.4839974641799927, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 6.8943, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.8198347107438017, | |
| "grad_norm": 0.28504496812820435, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 6.9179, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.8462809917355372, | |
| "grad_norm": 0.3000105619430542, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 6.9187, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.8727272727272727, | |
| "grad_norm": 0.20943278074264526, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 6.9359, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.8991735537190083, | |
| "grad_norm": 0.26605117321014404, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 6.9216, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.9256198347107438, | |
| "grad_norm": 0.31303733587265015, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 6.914, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.9520661157024793, | |
| "grad_norm": 0.32604312896728516, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 6.9163, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.9785123966942149, | |
| "grad_norm": 0.32598012685775757, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 6.9243, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.0148760330578512, | |
| "grad_norm": 0.7397525906562805, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 10.6965, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.0413223140495869, | |
| "grad_norm": 0.6702333688735962, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 6.953, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.0677685950413223, | |
| "grad_norm": 0.3199296295642853, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 7.0705, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.094214876033058, | |
| "grad_norm": 0.28222858905792236, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 7.0668, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.1206611570247933, | |
| "grad_norm": 0.18209977447986603, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 5.656, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.147107438016529, | |
| "grad_norm": 0.2604251801967621, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 7.9056, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.1735537190082646, | |
| "grad_norm": 0.289387971162796, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 6.8854, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 0.34119921922683716, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 7.1047, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.2264462809917356, | |
| "grad_norm": 0.3346429765224457, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 6.8513, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.252892561983471, | |
| "grad_norm": 0.32595688104629517, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 6.1413, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.2793388429752066, | |
| "grad_norm": 0.746822714805603, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 7.5015, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.3057851239669422, | |
| "grad_norm": 0.416890412569046, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 6.8391, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.3322314049586776, | |
| "grad_norm": 0.2753528952598572, | |
| "learning_rate": 0.0, | |
| "loss": 7.1526, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.3322314049586776, | |
| "eval_loss": 6.912809371948242, | |
| "eval_runtime": 0.2069, | |
| "eval_samples_per_second": 1232.763, | |
| "eval_steps_per_second": 154.7, | |
| "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": 5705957376000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |