| { | |
| "best_metric": 1.719061017036438, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.007064641469445425, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00028258565877781704, | |
| "grad_norm": 0.3366537094116211, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 1.8174, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00028258565877781704, | |
| "eval_loss": 1.7830026149749756, | |
| "eval_runtime": 594.3326, | |
| "eval_samples_per_second": 2.507, | |
| "eval_steps_per_second": 1.254, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005651713175556341, | |
| "grad_norm": 0.35943204164505005, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 1.8683, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0008477569763334511, | |
| "grad_norm": 0.3432379364967346, | |
| "learning_rate": 6e-06, | |
| "loss": 1.7749, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0011303426351112682, | |
| "grad_norm": 0.34676483273506165, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 1.7996, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.001412928293889085, | |
| "grad_norm": 0.3473469316959381, | |
| "learning_rate": 1e-05, | |
| "loss": 1.7699, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001412928293889085, | |
| "eval_loss": 1.7824054956436157, | |
| "eval_runtime": 592.766, | |
| "eval_samples_per_second": 2.514, | |
| "eval_steps_per_second": 1.257, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0016955139526669022, | |
| "grad_norm": 0.3355012536048889, | |
| "learning_rate": 1.2e-05, | |
| "loss": 1.7021, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.001978099611444719, | |
| "grad_norm": 0.3477957546710968, | |
| "learning_rate": 1.4e-05, | |
| "loss": 1.7825, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0022606852702225363, | |
| "grad_norm": 0.37028154730796814, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 1.7613, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.002543270929000353, | |
| "grad_norm": 0.3685254454612732, | |
| "learning_rate": 1.8e-05, | |
| "loss": 1.8725, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00282585658777817, | |
| "grad_norm": 0.3918016850948334, | |
| "learning_rate": 2e-05, | |
| "loss": 1.8196, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00282585658777817, | |
| "eval_loss": 1.7737009525299072, | |
| "eval_runtime": 594.6195, | |
| "eval_samples_per_second": 2.506, | |
| "eval_steps_per_second": 1.253, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0031084422465559873, | |
| "grad_norm": 0.41285502910614014, | |
| "learning_rate": 1.9781476007338058e-05, | |
| "loss": 1.7891, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0033910279053338045, | |
| "grad_norm": 0.40905317664146423, | |
| "learning_rate": 1.913545457642601e-05, | |
| "loss": 1.7408, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.003673613564111621, | |
| "grad_norm": 0.4296281933784485, | |
| "learning_rate": 1.8090169943749477e-05, | |
| "loss": 1.7049, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.003956199222889438, | |
| "grad_norm": 0.45140767097473145, | |
| "learning_rate": 1.6691306063588583e-05, | |
| "loss": 1.7752, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0042387848816672555, | |
| "grad_norm": 0.4051220118999481, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 1.6401, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0042387848816672555, | |
| "eval_loss": 1.749382495880127, | |
| "eval_runtime": 594.1003, | |
| "eval_samples_per_second": 2.508, | |
| "eval_steps_per_second": 1.254, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.004521370540445073, | |
| "grad_norm": 0.4922388195991516, | |
| "learning_rate": 1.3090169943749475e-05, | |
| "loss": 1.7663, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.00480395619922289, | |
| "grad_norm": 0.5050691962242126, | |
| "learning_rate": 1.1045284632676535e-05, | |
| "loss": 1.7657, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.005086541858000706, | |
| "grad_norm": 0.48165398836135864, | |
| "learning_rate": 8.954715367323468e-06, | |
| "loss": 1.7417, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.005369127516778523, | |
| "grad_norm": 0.5054903030395508, | |
| "learning_rate": 6.909830056250527e-06, | |
| "loss": 1.701, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.00565171317555634, | |
| "grad_norm": 0.5169705748558044, | |
| "learning_rate": 5.000000000000003e-06, | |
| "loss": 1.7885, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00565171317555634, | |
| "eval_loss": 1.7253152132034302, | |
| "eval_runtime": 594.1641, | |
| "eval_samples_per_second": 2.508, | |
| "eval_steps_per_second": 1.254, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0059342988343341575, | |
| "grad_norm": 0.5351309180259705, | |
| "learning_rate": 3.308693936411421e-06, | |
| "loss": 1.7862, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.006216884493111975, | |
| "grad_norm": 0.5683148503303528, | |
| "learning_rate": 1.9098300562505266e-06, | |
| "loss": 1.7741, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.006499470151889792, | |
| "grad_norm": 0.5412361025810242, | |
| "learning_rate": 8.645454235739903e-07, | |
| "loss": 1.7513, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.006782055810667609, | |
| "grad_norm": 0.5362508893013, | |
| "learning_rate": 2.1852399266194312e-07, | |
| "loss": 1.7641, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.007064641469445425, | |
| "grad_norm": 0.5213263630867004, | |
| "learning_rate": 0.0, | |
| "loss": 1.6887, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.007064641469445425, | |
| "eval_loss": 1.719061017036438, | |
| "eval_runtime": 594.2914, | |
| "eval_samples_per_second": 2.507, | |
| "eval_steps_per_second": 1.254, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "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": 1.5831027154944e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |