| { |
| "best_metric": 1.6801203489303589, |
| "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": 1.681911587715149, |
| "learning_rate": 2e-05, |
| "loss": 1.7218, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.00013763677654669328, |
| "eval_loss": 2.2520158290863037, |
| "eval_runtime": 106.8393, |
| "eval_samples_per_second": 114.536, |
| "eval_steps_per_second": 14.321, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.00027527355309338655, |
| "grad_norm": 1.9964476823806763, |
| "learning_rate": 4e-05, |
| "loss": 1.878, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.00041291032964007983, |
| "grad_norm": 2.218065023422241, |
| "learning_rate": 6e-05, |
| "loss": 1.9068, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.0005505471061867731, |
| "grad_norm": 2.161393404006958, |
| "learning_rate": 8e-05, |
| "loss": 1.7922, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.0006881838827334664, |
| "grad_norm": 1.9325798749923706, |
| "learning_rate": 0.0001, |
| "loss": 1.7442, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.0008258206592801597, |
| "grad_norm": 3.0492777824401855, |
| "learning_rate": 9.987820251299122e-05, |
| "loss": 1.7041, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.0009634574358268529, |
| "grad_norm": 2.1566667556762695, |
| "learning_rate": 9.951340343707852e-05, |
| "loss": 1.7044, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.0011010942123735462, |
| "grad_norm": 2.4497389793395996, |
| "learning_rate": 9.890738003669029e-05, |
| "loss": 1.7599, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.0012387309889202395, |
| "grad_norm": 2.009220600128174, |
| "learning_rate": 9.806308479691595e-05, |
| "loss": 1.6069, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.0013763677654669328, |
| "grad_norm": 1.8601412773132324, |
| "learning_rate": 9.698463103929542e-05, |
| "loss": 1.6321, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.001514004542013626, |
| "grad_norm": 2.1711673736572266, |
| "learning_rate": 9.567727288213005e-05, |
| "loss": 1.6355, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.0016516413185603193, |
| "grad_norm": 1.869681715965271, |
| "learning_rate": 9.414737964294636e-05, |
| "loss": 1.6564, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.0017892780951070126, |
| "grad_norm": 1.8459086418151855, |
| "learning_rate": 9.24024048078213e-05, |
| "loss": 1.6571, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.0019269148716537059, |
| "grad_norm": 1.9504926204681396, |
| "learning_rate": 9.045084971874738e-05, |
| "loss": 1.5846, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.002064551648200399, |
| "grad_norm": 1.7249507904052734, |
| "learning_rate": 8.83022221559489e-05, |
| "loss": 1.4764, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.0022021884247470924, |
| "grad_norm": 1.8206087350845337, |
| "learning_rate": 8.596699001693255e-05, |
| "loss": 1.7208, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.0023398252012937857, |
| "grad_norm": 1.8255046606063843, |
| "learning_rate": 8.345653031794292e-05, |
| "loss": 1.6589, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.002477461977840479, |
| "grad_norm": 1.8157140016555786, |
| "learning_rate": 8.07830737662829e-05, |
| "loss": 1.5725, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.0026150987543871723, |
| "grad_norm": 1.8305015563964844, |
| "learning_rate": 7.795964517353735e-05, |
| "loss": 1.6672, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.0027527355309338655, |
| "grad_norm": 1.768606185913086, |
| "learning_rate": 7.500000000000001e-05, |
| "loss": 1.6213, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.002890372307480559, |
| "grad_norm": 1.811745285987854, |
| "learning_rate": 7.191855733945387e-05, |
| "loss": 1.6071, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.003028009084027252, |
| "grad_norm": 1.7457269430160522, |
| "learning_rate": 6.873032967079561e-05, |
| "loss": 1.5049, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.0031656458605739454, |
| "grad_norm": 1.6813018321990967, |
| "learning_rate": 6.545084971874738e-05, |
| "loss": 1.55, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.0033032826371206386, |
| "grad_norm": 1.7682090997695923, |
| "learning_rate": 6.209609477998338e-05, |
| "loss": 1.6086, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.003440919413667332, |
| "grad_norm": 1.8451300859451294, |
| "learning_rate": 5.868240888334653e-05, |
| "loss": 1.5775, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.003440919413667332, |
| "eval_loss": 1.70032799243927, |
| "eval_runtime": 106.8297, |
| "eval_samples_per_second": 114.547, |
| "eval_steps_per_second": 14.322, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.003578556190214025, |
| "grad_norm": 1.8355437517166138, |
| "learning_rate": 5.522642316338268e-05, |
| "loss": 1.579, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.0037161929667607185, |
| "grad_norm": 1.7906683683395386, |
| "learning_rate": 5.174497483512506e-05, |
| "loss": 1.4476, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.0038538297433074117, |
| "grad_norm": 1.82988703250885, |
| "learning_rate": 4.825502516487497e-05, |
| "loss": 1.5864, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.003991466519854105, |
| "grad_norm": 1.955890417098999, |
| "learning_rate": 4.477357683661734e-05, |
| "loss": 1.5891, |
| "step": 29 |
| }, |
| { |
| "epoch": 0.004129103296400798, |
| "grad_norm": 2.021894931793213, |
| "learning_rate": 4.131759111665349e-05, |
| "loss": 1.8077, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.0042667400729474916, |
| "grad_norm": 2.075988531112671, |
| "learning_rate": 3.790390522001662e-05, |
| "loss": 1.7214, |
| "step": 31 |
| }, |
| { |
| "epoch": 0.004404376849494185, |
| "grad_norm": 1.942689061164856, |
| "learning_rate": 3.4549150281252636e-05, |
| "loss": 1.7103, |
| "step": 32 |
| }, |
| { |
| "epoch": 0.004542013626040878, |
| "grad_norm": 2.155029058456421, |
| "learning_rate": 3.12696703292044e-05, |
| "loss": 1.7459, |
| "step": 33 |
| }, |
| { |
| "epoch": 0.004679650402587571, |
| "grad_norm": 1.9637714624404907, |
| "learning_rate": 2.8081442660546125e-05, |
| "loss": 1.6637, |
| "step": 34 |
| }, |
| { |
| "epoch": 0.004817287179134265, |
| "grad_norm": 1.9927000999450684, |
| "learning_rate": 2.500000000000001e-05, |
| "loss": 1.6629, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.004954923955680958, |
| "grad_norm": 2.146827459335327, |
| "learning_rate": 2.2040354826462668e-05, |
| "loss": 1.6425, |
| "step": 36 |
| }, |
| { |
| "epoch": 0.005092560732227651, |
| "grad_norm": 2.037449836730957, |
| "learning_rate": 1.9216926233717085e-05, |
| "loss": 1.8133, |
| "step": 37 |
| }, |
| { |
| "epoch": 0.0052301975087743445, |
| "grad_norm": 2.0150561332702637, |
| "learning_rate": 1.6543469682057106e-05, |
| "loss": 1.636, |
| "step": 38 |
| }, |
| { |
| "epoch": 0.005367834285321038, |
| "grad_norm": 2.134779691696167, |
| "learning_rate": 1.4033009983067452e-05, |
| "loss": 1.8358, |
| "step": 39 |
| }, |
| { |
| "epoch": 0.005505471061867731, |
| "grad_norm": 2.3213002681732178, |
| "learning_rate": 1.1697777844051105e-05, |
| "loss": 1.8923, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.005643107838414424, |
| "grad_norm": 2.3136813640594482, |
| "learning_rate": 9.549150281252633e-06, |
| "loss": 1.6691, |
| "step": 41 |
| }, |
| { |
| "epoch": 0.005780744614961118, |
| "grad_norm": 2.2391891479492188, |
| "learning_rate": 7.597595192178702e-06, |
| "loss": 1.7149, |
| "step": 42 |
| }, |
| { |
| "epoch": 0.005918381391507811, |
| "grad_norm": 2.2326366901397705, |
| "learning_rate": 5.852620357053651e-06, |
| "loss": 1.7424, |
| "step": 43 |
| }, |
| { |
| "epoch": 0.006056018168054504, |
| "grad_norm": 2.3350918292999268, |
| "learning_rate": 4.322727117869951e-06, |
| "loss": 1.9315, |
| "step": 44 |
| }, |
| { |
| "epoch": 0.0061936549446011974, |
| "grad_norm": 2.414999485015869, |
| "learning_rate": 3.0153689607045845e-06, |
| "loss": 1.8257, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.006331291721147891, |
| "grad_norm": 2.6851768493652344, |
| "learning_rate": 1.9369152030840556e-06, |
| "loss": 2.0204, |
| "step": 46 |
| }, |
| { |
| "epoch": 0.006468928497694584, |
| "grad_norm": 3.064577579498291, |
| "learning_rate": 1.0926199633097157e-06, |
| "loss": 2.0167, |
| "step": 47 |
| }, |
| { |
| "epoch": 0.006606565274241277, |
| "grad_norm": 3.4269301891326904, |
| "learning_rate": 4.865965629214819e-07, |
| "loss": 2.2436, |
| "step": 48 |
| }, |
| { |
| "epoch": 0.0067442020507879705, |
| "grad_norm": 3.9567739963531494, |
| "learning_rate": 1.2179748700879012e-07, |
| "loss": 2.3654, |
| "step": 49 |
| }, |
| { |
| "epoch": 0.006881838827334664, |
| "grad_norm": 7.154803276062012, |
| "learning_rate": 0.0, |
| "loss": 3.1455, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.006881838827334664, |
| "eval_loss": 1.6801203489303589, |
| "eval_runtime": 106.7627, |
| "eval_samples_per_second": 114.619, |
| "eval_steps_per_second": 14.331, |
| "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 |
| } |
|
|
