| { | |
| "best_metric": 1.6785205602645874, | |
| "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": 1.701811671257019, | |
| "learning_rate": 2e-05, | |
| "loss": 1.7218, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00013763677654669328, | |
| "eval_loss": 2.2520158290863037, | |
| "eval_runtime": 106.9133, | |
| "eval_samples_per_second": 114.457, | |
| "eval_steps_per_second": 14.311, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00027527355309338655, | |
| "grad_norm": 1.9986348152160645, | |
| "learning_rate": 4e-05, | |
| "loss": 1.878, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00041291032964007983, | |
| "grad_norm": 2.2074553966522217, | |
| "learning_rate": 6e-05, | |
| "loss": 1.9073, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0005505471061867731, | |
| "grad_norm": 2.140049457550049, | |
| "learning_rate": 8e-05, | |
| "loss": 1.7929, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0006881838827334664, | |
| "grad_norm": 1.929785132408142, | |
| "learning_rate": 0.0001, | |
| "loss": 1.7427, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0008258206592801597, | |
| "grad_norm": 3.609555244445801, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 1.7067, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0009634574358268529, | |
| "grad_norm": 2.2431936264038086, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 1.708, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0011010942123735462, | |
| "grad_norm": 2.487065315246582, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 1.764, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0012387309889202395, | |
| "grad_norm": 2.030827283859253, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 1.6104, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0013763677654669328, | |
| "grad_norm": 1.8583109378814697, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 1.6329, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.001514004542013626, | |
| "grad_norm": 2.221379518508911, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 1.6367, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0016516413185603193, | |
| "grad_norm": 1.913684368133545, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 1.6586, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0017892780951070126, | |
| "grad_norm": 1.8143997192382812, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 1.6583, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0019269148716537059, | |
| "grad_norm": 1.9706239700317383, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 1.5833, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.002064551648200399, | |
| "grad_norm": 1.7588917016983032, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 1.4789, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0022021884247470924, | |
| "grad_norm": 1.8227847814559937, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 1.7236, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0023398252012937857, | |
| "grad_norm": 1.8207757472991943, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 1.6635, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.002477461977840479, | |
| "grad_norm": 1.821920394897461, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 1.5714, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0026150987543871723, | |
| "grad_norm": 1.8597149848937988, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 1.6667, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0027527355309338655, | |
| "grad_norm": 1.7658398151397705, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.6241, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.002890372307480559, | |
| "grad_norm": 1.7973589897155762, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 1.6108, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.003028009084027252, | |
| "grad_norm": 1.7474368810653687, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 1.5065, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0031656458605739454, | |
| "grad_norm": 1.6852911710739136, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 1.5501, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0033032826371206386, | |
| "grad_norm": 1.768506646156311, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 1.6089, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.003440919413667332, | |
| "grad_norm": 1.7844042778015137, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 1.58, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.003440919413667332, | |
| "eval_loss": 1.699485421180725, | |
| "eval_runtime": 106.8659, | |
| "eval_samples_per_second": 114.508, | |
| "eval_steps_per_second": 14.317, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.003578556190214025, | |
| "grad_norm": 1.8210140466690063, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 1.5769, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0037161929667607185, | |
| "grad_norm": 1.803637981414795, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 1.4474, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0038538297433074117, | |
| "grad_norm": 1.8251798152923584, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 1.5875, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.003991466519854105, | |
| "grad_norm": 1.932847499847412, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 1.5869, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.004129103296400798, | |
| "grad_norm": 2.0150198936462402, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 1.8076, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0042667400729474916, | |
| "grad_norm": 2.0604617595672607, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 1.7204, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.004404376849494185, | |
| "grad_norm": 1.9407871961593628, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 1.7125, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.004542013626040878, | |
| "grad_norm": 2.1350440979003906, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 1.7457, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.004679650402587571, | |
| "grad_norm": 1.9392979145050049, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 1.6631, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.004817287179134265, | |
| "grad_norm": 1.967930555343628, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.6614, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.004954923955680958, | |
| "grad_norm": 2.1190671920776367, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 1.6438, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.005092560732227651, | |
| "grad_norm": 2.027472496032715, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 1.8127, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0052301975087743445, | |
| "grad_norm": 1.9992049932479858, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 1.6343, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.005367834285321038, | |
| "grad_norm": 2.1239211559295654, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 1.8371, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.005505471061867731, | |
| "grad_norm": 2.310203790664673, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 1.8977, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.005643107838414424, | |
| "grad_norm": 2.299560070037842, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 1.6689, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.005780744614961118, | |
| "grad_norm": 2.2246201038360596, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 1.7129, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.005918381391507811, | |
| "grad_norm": 2.226691484451294, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 1.7453, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.006056018168054504, | |
| "grad_norm": 2.3118553161621094, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 1.9296, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0061936549446011974, | |
| "grad_norm": 2.4144370555877686, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 1.8286, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.006331291721147891, | |
| "grad_norm": 2.6773507595062256, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 2.0211, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.006468928497694584, | |
| "grad_norm": 3.043905019760132, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 2.0154, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.006606565274241277, | |
| "grad_norm": 3.406757116317749, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 2.2506, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0067442020507879705, | |
| "grad_norm": 3.9268417358398438, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 2.3643, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.006881838827334664, | |
| "grad_norm": 7.131216526031494, | |
| "learning_rate": 0.0, | |
| "loss": 3.1503, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.006881838827334664, | |
| "eval_loss": 1.6785205602645874, | |
| "eval_runtime": 106.9957, | |
| "eval_samples_per_second": 114.369, | |
| "eval_steps_per_second": 14.3, | |
| "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 | |
| } | |