| { | |
| "best_metric": 1.6789900064468384, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.006881838827334664, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00013763677654669328, | |
| "grad_norm": 1.6983609199523926, | |
| "learning_rate": 2e-05, | |
| "loss": 1.7218, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00013763677654669328, | |
| "eval_loss": 2.2520158290863037, | |
| "eval_runtime": 107.4134, | |
| "eval_samples_per_second": 113.924, | |
| "eval_steps_per_second": 14.244, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00027527355309338655, | |
| "grad_norm": 1.9989323616027832, | |
| "learning_rate": 4e-05, | |
| "loss": 1.878, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00041291032964007983, | |
| "grad_norm": 2.2018532752990723, | |
| "learning_rate": 6e-05, | |
| "loss": 1.9075, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0005505471061867731, | |
| "grad_norm": 2.1392979621887207, | |
| "learning_rate": 8e-05, | |
| "loss": 1.7916, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0006881838827334664, | |
| "grad_norm": 1.908968210220337, | |
| "learning_rate": 0.0001, | |
| "loss": 1.7452, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0008258206592801597, | |
| "grad_norm": 3.3882720470428467, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 1.7066, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0009634574358268529, | |
| "grad_norm": 2.1865386962890625, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 1.7084, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0011010942123735462, | |
| "grad_norm": 2.4881649017333984, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 1.7654, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0012387309889202395, | |
| "grad_norm": 2.024473190307617, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 1.6083, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0013763677654669328, | |
| "grad_norm": 1.8449368476867676, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 1.6326, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.001514004542013626, | |
| "grad_norm": 2.1751227378845215, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 1.6355, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0016516413185603193, | |
| "grad_norm": 1.8992284536361694, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 1.6579, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0017892780951070126, | |
| "grad_norm": 1.79997980594635, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 1.6576, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0019269148716537059, | |
| "grad_norm": 1.9317549467086792, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 1.5869, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.002064551648200399, | |
| "grad_norm": 1.7598886489868164, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 1.4784, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0022021884247470924, | |
| "grad_norm": 1.7964980602264404, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 1.7223, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0023398252012937857, | |
| "grad_norm": 1.791191816329956, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 1.6612, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.002477461977840479, | |
| "grad_norm": 1.8247939348220825, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 1.5746, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0026150987543871723, | |
| "grad_norm": 1.8562343120574951, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 1.6678, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0027527355309338655, | |
| "grad_norm": 1.7591829299926758, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.6254, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.002890372307480559, | |
| "grad_norm": 1.7937219142913818, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 1.6089, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.003028009084027252, | |
| "grad_norm": 1.7370078563690186, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 1.5068, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0031656458605739454, | |
| "grad_norm": 1.6745147705078125, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 1.5484, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0033032826371206386, | |
| "grad_norm": 1.7756022214889526, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 1.6105, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.003440919413667332, | |
| "grad_norm": 1.7923301458358765, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 1.5792, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.003440919413667332, | |
| "eval_loss": 1.700939655303955, | |
| "eval_runtime": 107.4877, | |
| "eval_samples_per_second": 113.846, | |
| "eval_steps_per_second": 14.234, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.003578556190214025, | |
| "grad_norm": 1.8309403657913208, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 1.5803, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0037161929667607185, | |
| "grad_norm": 1.8094103336334229, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 1.4502, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0038538297433074117, | |
| "grad_norm": 1.837483286857605, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 1.587, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.003991466519854105, | |
| "grad_norm": 1.9412227869033813, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 1.5866, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.004129103296400798, | |
| "grad_norm": 2.0173988342285156, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 1.8093, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0042667400729474916, | |
| "grad_norm": 2.0680758953094482, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 1.7212, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.004404376849494185, | |
| "grad_norm": 1.93842351436615, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 1.7122, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.004542013626040878, | |
| "grad_norm": 2.129516124725342, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 1.7436, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.004679650402587571, | |
| "grad_norm": 1.9408643245697021, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 1.6622, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.004817287179134265, | |
| "grad_norm": 1.9809863567352295, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.6646, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.004954923955680958, | |
| "grad_norm": 2.126344919204712, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 1.6433, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.005092560732227651, | |
| "grad_norm": 2.0364034175872803, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 1.8124, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0052301975087743445, | |
| "grad_norm": 2.0222976207733154, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 1.637, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.005367834285321038, | |
| "grad_norm": 2.119856834411621, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 1.8401, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.005505471061867731, | |
| "grad_norm": 2.2993125915527344, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 1.8964, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.005643107838414424, | |
| "grad_norm": 2.2917792797088623, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 1.6729, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.005780744614961118, | |
| "grad_norm": 2.2233023643493652, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 1.7126, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.005918381391507811, | |
| "grad_norm": 2.236922025680542, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 1.7439, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.006056018168054504, | |
| "grad_norm": 2.325484275817871, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 1.9329, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0061936549446011974, | |
| "grad_norm": 2.3953254222869873, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 1.8257, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.006331291721147891, | |
| "grad_norm": 2.677058219909668, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 2.0218, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.006468928497694584, | |
| "grad_norm": 2.981875419616699, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 2.0141, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.006606565274241277, | |
| "grad_norm": 3.397183895111084, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 2.2502, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0067442020507879705, | |
| "grad_norm": 3.8943850994110107, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 2.3663, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.006881838827334664, | |
| "grad_norm": 7.032155990600586, | |
| "learning_rate": 0.0, | |
| "loss": 3.1411, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.006881838827334664, | |
| "eval_loss": 1.6789900064468384, | |
| "eval_runtime": 107.4686, | |
| "eval_samples_per_second": 113.866, | |
| "eval_steps_per_second": 14.237, | |
| "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": 1941781210988544.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |