| { | |
| "best_metric": 11.9314546585083, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 3.1256830601092895, | |
| "eval_steps": 25, | |
| "global_step": 35, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08743169398907104, | |
| "grad_norm": 0.029055021703243256, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9276, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.08743169398907104, | |
| "eval_loss": 11.93380355834961, | |
| "eval_runtime": 0.1307, | |
| "eval_samples_per_second": 382.572, | |
| "eval_steps_per_second": 99.469, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.17486338797814208, | |
| "grad_norm": 0.03794427588582039, | |
| "learning_rate": 0.0001, | |
| "loss": 11.924, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.26229508196721313, | |
| "grad_norm": 0.03752344846725464, | |
| "learning_rate": 9.979623651578881e-05, | |
| "loss": 11.9252, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.34972677595628415, | |
| "grad_norm": 0.030064813792705536, | |
| "learning_rate": 9.91867913768218e-05, | |
| "loss": 11.926, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.4371584699453552, | |
| "grad_norm": 0.03259439393877983, | |
| "learning_rate": 9.81771838126524e-05, | |
| "loss": 11.9251, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.5245901639344263, | |
| "grad_norm": 0.02927307039499283, | |
| "learning_rate": 9.677655698572326e-05, | |
| "loss": 11.9235, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.6120218579234973, | |
| "grad_norm": 0.026567064225673676, | |
| "learning_rate": 9.499759518947156e-05, | |
| "loss": 11.9285, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.6994535519125683, | |
| "grad_norm": 0.03742191940546036, | |
| "learning_rate": 9.285640897740315e-05, | |
| "loss": 11.9271, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.7868852459016393, | |
| "grad_norm": 0.032700005918741226, | |
| "learning_rate": 9.037238926342544e-05, | |
| "loss": 11.9265, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.8743169398907104, | |
| "grad_norm": 0.0319342203438282, | |
| "learning_rate": 8.756803171472816e-05, | |
| "loss": 11.9229, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.9617486338797814, | |
| "grad_norm": 0.04569251462817192, | |
| "learning_rate": 8.446873302753784e-05, | |
| "loss": 11.9228, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.0710382513661203, | |
| "grad_norm": 0.058960121124982834, | |
| "learning_rate": 8.110256093070393e-05, | |
| "loss": 22.1082, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.1584699453551912, | |
| "grad_norm": 0.03168099746108055, | |
| "learning_rate": 7.75e-05, | |
| "loss": 11.1739, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.2459016393442623, | |
| "grad_norm": 0.04274030402302742, | |
| "learning_rate": 7.369367558508489e-05, | |
| "loss": 11.446, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": 0.03621490299701691, | |
| "learning_rate": 6.9718058349284e-05, | |
| "loss": 12.9078, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.4207650273224044, | |
| "grad_norm": 0.044496893882751465, | |
| "learning_rate": 6.560915209792424e-05, | |
| "loss": 11.5009, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.5081967213114753, | |
| "grad_norm": 0.03992842137813568, | |
| "learning_rate": 6.140416772229784e-05, | |
| "loss": 11.9468, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.5956284153005464, | |
| "grad_norm": 0.04237513989210129, | |
| "learning_rate": 5.714118621206842e-05, | |
| "loss": 12.1027, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.6830601092896176, | |
| "grad_norm": 0.04599763825535774, | |
| "learning_rate": 5.285881378793161e-05, | |
| "loss": 12.4252, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.7704918032786885, | |
| "grad_norm": 0.04472829028964043, | |
| "learning_rate": 4.859583227770218e-05, | |
| "loss": 11.0722, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.8579234972677594, | |
| "grad_norm": 0.04162151739001274, | |
| "learning_rate": 4.4390847902075774e-05, | |
| "loss": 12.3296, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.9453551912568305, | |
| "grad_norm": 0.05842168256640434, | |
| "learning_rate": 4.028194165071602e-05, | |
| "loss": 12.2021, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 2.0546448087431695, | |
| "grad_norm": 0.08463191241025925, | |
| "learning_rate": 3.630632441491512e-05, | |
| "loss": 22.1623, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.1420765027322406, | |
| "grad_norm": 0.04698154702782631, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 11.1355, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.2295081967213113, | |
| "grad_norm": 0.06285881251096725, | |
| "learning_rate": 2.889743906929609e-05, | |
| "loss": 11.2714, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.2295081967213113, | |
| "eval_loss": 11.9314546585083, | |
| "eval_runtime": 0.1362, | |
| "eval_samples_per_second": 367.084, | |
| "eval_steps_per_second": 95.442, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.3169398907103824, | |
| "grad_norm": 0.056846752762794495, | |
| "learning_rate": 2.5531266972462177e-05, | |
| "loss": 13.2342, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.4043715846994536, | |
| "grad_norm": 0.037951644510030746, | |
| "learning_rate": 2.2431968285271844e-05, | |
| "loss": 11.6904, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.4918032786885247, | |
| "grad_norm": 0.061074282974004745, | |
| "learning_rate": 1.9627610736574575e-05, | |
| "loss": 10.4965, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.579234972677596, | |
| "grad_norm": 0.04677893966436386, | |
| "learning_rate": 1.7143591022596845e-05, | |
| "loss": 12.9265, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "grad_norm": 0.05003131181001663, | |
| "learning_rate": 1.5002404810528451e-05, | |
| "loss": 12.5836, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.7540983606557377, | |
| "grad_norm": 0.052657756954431534, | |
| "learning_rate": 1.3223443014276737e-05, | |
| "loss": 10.8171, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.841530054644809, | |
| "grad_norm": 0.04703788459300995, | |
| "learning_rate": 1.1822816187347623e-05, | |
| "loss": 12.1961, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.92896174863388, | |
| "grad_norm": 0.05965609848499298, | |
| "learning_rate": 1.08132086231782e-05, | |
| "loss": 12.6582, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 3.0382513661202184, | |
| "grad_norm": 0.10015369951725006, | |
| "learning_rate": 1.0203763484211195e-05, | |
| "loss": 21.296, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 3.1256830601092895, | |
| "grad_norm": 0.04435504972934723, | |
| "learning_rate": 1e-05, | |
| "loss": 11.454, | |
| "step": 35 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 35, | |
| "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": 729745981440.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |