| { | |
| "best_metric": 0.32584547996520996, | |
| "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": 7.0867180824279785, | |
| "learning_rate": 2e-05, | |
| "loss": 4.3627, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00028258565877781704, | |
| "eval_loss": 1.1540579795837402, | |
| "eval_runtime": 455.9223, | |
| "eval_samples_per_second": 3.268, | |
| "eval_steps_per_second": 1.634, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005651713175556341, | |
| "grad_norm": 8.107670783996582, | |
| "learning_rate": 4e-05, | |
| "loss": 5.0805, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0008477569763334511, | |
| "grad_norm": 7.456545352935791, | |
| "learning_rate": 6e-05, | |
| "loss": 4.7013, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0011303426351112682, | |
| "grad_norm": 7.036722183227539, | |
| "learning_rate": 8e-05, | |
| "loss": 4.5868, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.001412928293889085, | |
| "grad_norm": 6.056708335876465, | |
| "learning_rate": 0.0001, | |
| "loss": 4.2471, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001412928293889085, | |
| "eval_loss": 0.8982149958610535, | |
| "eval_runtime": 454.5076, | |
| "eval_samples_per_second": 3.278, | |
| "eval_steps_per_second": 1.639, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0016955139526669022, | |
| "grad_norm": 5.632623195648193, | |
| "learning_rate": 0.00012, | |
| "loss": 3.4771, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.001978099611444719, | |
| "grad_norm": 6.000317096710205, | |
| "learning_rate": 0.00014, | |
| "loss": 3.3221, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0022606852702225363, | |
| "grad_norm": 6.009365081787109, | |
| "learning_rate": 0.00016, | |
| "loss": 2.7419, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.002543270929000353, | |
| "grad_norm": 5.749902248382568, | |
| "learning_rate": 0.00018, | |
| "loss": 2.565, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00282585658777817, | |
| "grad_norm": 7.822487831115723, | |
| "learning_rate": 0.0002, | |
| "loss": 1.7873, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00282585658777817, | |
| "eval_loss": 0.435401976108551, | |
| "eval_runtime": 453.0574, | |
| "eval_samples_per_second": 3.289, | |
| "eval_steps_per_second": 1.644, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0031084422465559873, | |
| "grad_norm": 8.154427528381348, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 1.7293, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0033910279053338045, | |
| "grad_norm": 3.9936041831970215, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 1.5691, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.003673613564111621, | |
| "grad_norm": 3.17008376121521, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 1.4452, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.003956199222889438, | |
| "grad_norm": 2.970133066177368, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 1.5994, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0042387848816672555, | |
| "grad_norm": 3.0812292098999023, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.6177, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0042387848816672555, | |
| "eval_loss": 0.3540613651275635, | |
| "eval_runtime": 451.6427, | |
| "eval_samples_per_second": 3.299, | |
| "eval_steps_per_second": 1.65, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.004521370540445073, | |
| "grad_norm": 3.2199628353118896, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.3606, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.00480395619922289, | |
| "grad_norm": 2.6285812854766846, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 1.748, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.005086541858000706, | |
| "grad_norm": 2.7720754146575928, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 1.7257, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.005369127516778523, | |
| "grad_norm": 2.474501132965088, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 1.3987, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.00565171317555634, | |
| "grad_norm": 2.400693893432617, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 1.4751, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00565171317555634, | |
| "eval_loss": 0.3312912583351135, | |
| "eval_runtime": 450.7561, | |
| "eval_samples_per_second": 3.306, | |
| "eval_steps_per_second": 1.653, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0059342988343341575, | |
| "grad_norm": 2.3116421699523926, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 1.3819, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.006216884493111975, | |
| "grad_norm": 2.419229507446289, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 1.3341, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.006499470151889792, | |
| "grad_norm": 2.5362722873687744, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 1.368, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.006782055810667609, | |
| "grad_norm": 2.0525970458984375, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 1.037, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.007064641469445425, | |
| "grad_norm": 2.673909902572632, | |
| "learning_rate": 0.0, | |
| "loss": 1.3617, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.007064641469445425, | |
| "eval_loss": 0.32584547996520996, | |
| "eval_runtime": 449.8115, | |
| "eval_samples_per_second": 3.312, | |
| "eval_steps_per_second": 1.656, | |
| "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": 8763358996070400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |