| { | |
| "best_metric": 1.467692255973816, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.6650041562759768, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.013300083125519535, | |
| "grad_norm": 0.30807769298553467, | |
| "learning_rate": 5e-05, | |
| "loss": 1.5989, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013300083125519535, | |
| "eval_loss": 1.8170369863510132, | |
| "eval_runtime": 4.4482, | |
| "eval_samples_per_second": 113.979, | |
| "eval_steps_per_second": 14.388, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02660016625103907, | |
| "grad_norm": 0.33670011162757874, | |
| "learning_rate": 0.0001, | |
| "loss": 1.6635, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0399002493765586, | |
| "grad_norm": 0.35574978590011597, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.639, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.05320033250207814, | |
| "grad_norm": 0.43438073992729187, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.7603, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06650041562759768, | |
| "grad_norm": 0.4591783583164215, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.7698, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0798004987531172, | |
| "grad_norm": 0.3775702118873596, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.6717, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.09310058187863675, | |
| "grad_norm": 0.40178415179252625, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.6908, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.10640066500415628, | |
| "grad_norm": 0.39939138293266296, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.6511, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.11970074812967581, | |
| "grad_norm": 0.4064088761806488, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.6223, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.13300083125519535, | |
| "grad_norm": 0.42422300577163696, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.6776, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.14630091438071488, | |
| "grad_norm": 0.4172786474227905, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.6897, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.1596009975062344, | |
| "grad_norm": 0.4498286247253418, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.7711, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.17290108063175394, | |
| "grad_norm": 0.2242169827222824, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.5764, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.1862011637572735, | |
| "grad_norm": 0.220079705119133, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.4311, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.19950124688279303, | |
| "grad_norm": 0.2502831816673279, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.5599, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.21280133000831256, | |
| "grad_norm": 0.27619630098342896, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.5565, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.22610141313383209, | |
| "grad_norm": 0.2701985239982605, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.5664, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.23940149625935161, | |
| "grad_norm": 0.24903272092342377, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.596, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.25270157938487114, | |
| "grad_norm": 0.2547197937965393, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.4784, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.2660016625103907, | |
| "grad_norm": 0.22915960848331451, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.4753, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2793017456359102, | |
| "grad_norm": 0.2612093985080719, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.5629, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.29260182876142976, | |
| "grad_norm": 0.26348868012428284, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.412, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.3059019118869493, | |
| "grad_norm": 0.28813788294792175, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.5054, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.3192019950124688, | |
| "grad_norm": 0.31999000906944275, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.5242, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.3325020781379884, | |
| "grad_norm": 0.4172128736972809, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.499, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3325020781379884, | |
| "eval_loss": 1.4860926866531372, | |
| "eval_runtime": 4.4333, | |
| "eval_samples_per_second": 114.363, | |
| "eval_steps_per_second": 14.436, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3458021612635079, | |
| "grad_norm": 0.18647287786006927, | |
| "learning_rate": 5e-05, | |
| "loss": 1.4277, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.35910224438902744, | |
| "grad_norm": 0.20698946714401245, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.4413, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.372402327514547, | |
| "grad_norm": 0.20511312782764435, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.4307, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.3857024106400665, | |
| "grad_norm": 0.2180362045764923, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.4408, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.39900249376558605, | |
| "grad_norm": 0.21642690896987915, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.4654, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.41230257689110555, | |
| "grad_norm": 0.21712642908096313, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.4509, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.4256026600166251, | |
| "grad_norm": 0.22278568148612976, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.4888, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.4389027431421446, | |
| "grad_norm": 0.2208184450864792, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.3575, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.45220282626766417, | |
| "grad_norm": 0.23661835491657257, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.4795, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.46550290939318373, | |
| "grad_norm": 0.25014418363571167, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.48, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.47880299251870323, | |
| "grad_norm": 0.26492103934288025, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.4518, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.4921030756442228, | |
| "grad_norm": 0.33129605650901794, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.5776, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.5054031587697423, | |
| "grad_norm": 0.22219394147396088, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.5443, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.5187032418952618, | |
| "grad_norm": 0.21399854123592377, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.4885, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.5320033250207814, | |
| "grad_norm": 0.20631512999534607, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.3427, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.545303408146301, | |
| "grad_norm": 0.21566346287727356, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.459, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.5586034912718204, | |
| "grad_norm": 0.20011813938617706, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.4605, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.57190357439734, | |
| "grad_norm": 0.21354447305202484, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.4537, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.5852036575228595, | |
| "grad_norm": 0.20864373445510864, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.3382, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.5985037406483791, | |
| "grad_norm": 0.20621033012866974, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.3996, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.6118038237738986, | |
| "grad_norm": 0.24815712869167328, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.4625, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.6251039068994181, | |
| "grad_norm": 0.2448890209197998, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.4835, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.6384039900249376, | |
| "grad_norm": 0.26246240735054016, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.4203, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.6517040731504572, | |
| "grad_norm": 0.30303773283958435, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.5443, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.6650041562759768, | |
| "grad_norm": 0.4216666519641876, | |
| "learning_rate": 0.0, | |
| "loss": 1.5894, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6650041562759768, | |
| "eval_loss": 1.467692255973816, | |
| "eval_runtime": 4.4285, | |
| "eval_samples_per_second": 114.486, | |
| "eval_steps_per_second": 14.452, | |
| "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": 8.33416392081408e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |