| { | |
| "best_metric": 0.7650135159492493, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 3.058275058275058, | |
| "eval_steps": 25, | |
| "global_step": 41, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07459207459207459, | |
| "grad_norm": 49.79338073730469, | |
| "learning_rate": 5e-05, | |
| "loss": 31.079, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07459207459207459, | |
| "eval_loss": 1.1030958890914917, | |
| "eval_runtime": 4.3497, | |
| "eval_samples_per_second": 11.495, | |
| "eval_steps_per_second": 2.989, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.14918414918414918, | |
| "grad_norm": 61.619346618652344, | |
| "learning_rate": 0.0001, | |
| "loss": 35.8237, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.22377622377622378, | |
| "grad_norm": 44.663516998291016, | |
| "learning_rate": 9.985407886603945e-05, | |
| "loss": 35.1631, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.29836829836829837, | |
| "grad_norm": 28.899295806884766, | |
| "learning_rate": 9.941726181870608e-05, | |
| "loss": 29.8061, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.372960372960373, | |
| "grad_norm": 25.077674865722656, | |
| "learning_rate": 9.869238178417235e-05, | |
| "loss": 28.4287, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.44755244755244755, | |
| "grad_norm": 21.780200958251953, | |
| "learning_rate": 9.768413988762156e-05, | |
| "loss": 29.4979, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.5221445221445221, | |
| "grad_norm": 16.97848129272461, | |
| "learning_rate": 9.639907496464709e-05, | |
| "loss": 27.768, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.5967365967365967, | |
| "grad_norm": 14.971733093261719, | |
| "learning_rate": 9.484552115439445e-05, | |
| "loss": 27.3351, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.6713286713286714, | |
| "grad_norm": 14.10373592376709, | |
| "learning_rate": 9.303355384947076e-05, | |
| "loss": 27.1077, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.745920745920746, | |
| "grad_norm": 15.110809326171875, | |
| "learning_rate": 9.097492435315756e-05, | |
| "loss": 25.9653, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.8205128205128205, | |
| "grad_norm": 12.38207721710205, | |
| "learning_rate": 8.868298366769954e-05, | |
| "loss": 26.2124, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.8951048951048951, | |
| "grad_norm": 12.963375091552734, | |
| "learning_rate": 8.617259590793198e-05, | |
| "loss": 26.3925, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.9696969696969697, | |
| "grad_norm": 17.126346588134766, | |
| "learning_rate": 8.346004190179198e-05, | |
| "loss": 27.4152, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.0442890442890442, | |
| "grad_norm": 11.388605117797852, | |
| "learning_rate": 8.056291360290201e-05, | |
| "loss": 24.0213, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.118881118881119, | |
| "grad_norm": 13.905165672302246, | |
| "learning_rate": 7.75e-05, | |
| "loss": 24.7093, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.1934731934731935, | |
| "grad_norm": 14.038837432861328, | |
| "learning_rate": 7.429116526313744e-05, | |
| "loss": 23.8335, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.2680652680652682, | |
| "grad_norm": 14.542243957519531, | |
| "learning_rate": 7.095721991691411e-05, | |
| "loss": 23.6019, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.3426573426573427, | |
| "grad_norm": 11.928253173828125, | |
| "learning_rate": 6.751978587624037e-05, | |
| "loss": 23.773, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.4172494172494172, | |
| "grad_norm": 13.130093574523926, | |
| "learning_rate": 6.400115621992201e-05, | |
| "loss": 23.8141, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.491841491841492, | |
| "grad_norm": 15.3530855178833, | |
| "learning_rate": 6.042415061148954e-05, | |
| "loss": 23.2327, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.5664335664335665, | |
| "grad_norm": 10.706517219543457, | |
| "learning_rate": 5.681196730492368e-05, | |
| "loss": 23.0154, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.641025641025641, | |
| "grad_norm": 12.62425708770752, | |
| "learning_rate": 5.318803269507634e-05, | |
| "loss": 22.7153, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.7156177156177157, | |
| "grad_norm": 15.199002265930176, | |
| "learning_rate": 4.9575849388510473e-05, | |
| "loss": 23.8232, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.7902097902097902, | |
| "grad_norm": 10.122224807739258, | |
| "learning_rate": 4.599884378007802e-05, | |
| "loss": 21.8521, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.8648018648018647, | |
| "grad_norm": 12.264386177062988, | |
| "learning_rate": 4.248021412375963e-05, | |
| "loss": 23.36, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.8648018648018647, | |
| "eval_loss": 0.7650135159492493, | |
| "eval_runtime": 4.3787, | |
| "eval_samples_per_second": 11.419, | |
| "eval_steps_per_second": 2.969, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.9393939393939394, | |
| "grad_norm": 13.958155632019043, | |
| "learning_rate": 3.904278008308589e-05, | |
| "loss": 23.0799, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.013986013986014, | |
| "grad_norm": 13.080740928649902, | |
| "learning_rate": 3.570883473686256e-05, | |
| "loss": 22.7616, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.0885780885780885, | |
| "grad_norm": 9.918713569641113, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 22.2095, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.163170163170163, | |
| "grad_norm": 12.069844245910645, | |
| "learning_rate": 2.9437086397097995e-05, | |
| "loss": 21.0234, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.237762237762238, | |
| "grad_norm": 14.520157814025879, | |
| "learning_rate": 2.6539958098208027e-05, | |
| "loss": 21.4936, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.312354312354312, | |
| "grad_norm": 9.91746711730957, | |
| "learning_rate": 2.3827404092068032e-05, | |
| "loss": 20.1627, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.386946386946387, | |
| "grad_norm": 11.826277732849121, | |
| "learning_rate": 2.1317016332300447e-05, | |
| "loss": 21.355, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.4615384615384617, | |
| "grad_norm": 13.523852348327637, | |
| "learning_rate": 1.902507564684246e-05, | |
| "loss": 20.8342, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.5361305361305364, | |
| "grad_norm": 11.003284454345703, | |
| "learning_rate": 1.6966446150529244e-05, | |
| "loss": 20.2875, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.6107226107226107, | |
| "grad_norm": 11.648452758789062, | |
| "learning_rate": 1.515447884560556e-05, | |
| "loss": 21.3661, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.6853146853146854, | |
| "grad_norm": 13.226274490356445, | |
| "learning_rate": 1.3600925035352913e-05, | |
| "loss": 20.4063, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.7599067599067597, | |
| "grad_norm": 12.421295166015625, | |
| "learning_rate": 1.2315860112378455e-05, | |
| "loss": 20.5653, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.8344988344988344, | |
| "grad_norm": 11.139906883239746, | |
| "learning_rate": 1.130761821582766e-05, | |
| "loss": 21.522, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.909090909090909, | |
| "grad_norm": 12.317776679992676, | |
| "learning_rate": 1.0582738181293923e-05, | |
| "loss": 21.0642, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.983682983682984, | |
| "grad_norm": 13.74180793762207, | |
| "learning_rate": 1.0145921133960554e-05, | |
| "loss": 20.5685, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 3.058275058275058, | |
| "grad_norm": 10.381887435913086, | |
| "learning_rate": 1e-05, | |
| "loss": 21.0001, | |
| "step": 41 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 41, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "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": 4.63958278020268e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |