| { | |
| "best_metric": 0.6571388244628906, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.004227436060029592, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001690974424011837, | |
| "grad_norm": 0.44534990191459656, | |
| "learning_rate": 2e-05, | |
| "loss": 0.8361, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001690974424011837, | |
| "eval_loss": 0.7383658289909363, | |
| "eval_runtime": 289.8598, | |
| "eval_samples_per_second": 8.59, | |
| "eval_steps_per_second": 4.295, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003381948848023674, | |
| "grad_norm": 0.39999261498451233, | |
| "learning_rate": 4e-05, | |
| "loss": 0.674, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.000507292327203551, | |
| "grad_norm": 0.4477081000804901, | |
| "learning_rate": 6e-05, | |
| "loss": 0.8428, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006763897696047348, | |
| "grad_norm": 0.45397526025772095, | |
| "learning_rate": 8e-05, | |
| "loss": 0.8515, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0008454872120059184, | |
| "grad_norm": 0.5277665853500366, | |
| "learning_rate": 0.0001, | |
| "loss": 0.6478, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0008454872120059184, | |
| "eval_loss": 0.7303531765937805, | |
| "eval_runtime": 290.2226, | |
| "eval_samples_per_second": 8.58, | |
| "eval_steps_per_second": 4.29, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001014584654407102, | |
| "grad_norm": 0.4257364869117737, | |
| "learning_rate": 0.00012, | |
| "loss": 0.7801, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0011836820968082857, | |
| "grad_norm": 0.444397896528244, | |
| "learning_rate": 0.00014, | |
| "loss": 0.7304, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0013527795392094695, | |
| "grad_norm": 0.4189773201942444, | |
| "learning_rate": 0.00016, | |
| "loss": 0.6306, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0015218769816106531, | |
| "grad_norm": 0.45941877365112305, | |
| "learning_rate": 0.00018, | |
| "loss": 0.7581, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0016909744240118367, | |
| "grad_norm": 0.43248504400253296, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6054, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0016909744240118367, | |
| "eval_loss": 0.6886987686157227, | |
| "eval_runtime": 294.1514, | |
| "eval_samples_per_second": 8.465, | |
| "eval_steps_per_second": 4.233, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0018600718664130206, | |
| "grad_norm": 0.45267313718795776, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 0.7075, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.002029169308814204, | |
| "grad_norm": 0.44445890188217163, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 0.7202, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.002198266751215388, | |
| "grad_norm": 0.4871218502521515, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 0.6876, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0023673641936165714, | |
| "grad_norm": 0.4805002212524414, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 0.698, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0025364616360177552, | |
| "grad_norm": 0.5254651308059692, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.6566, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0025364616360177552, | |
| "eval_loss": 0.6768798828125, | |
| "eval_runtime": 296.3003, | |
| "eval_samples_per_second": 8.404, | |
| "eval_steps_per_second": 4.202, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.002705559078418939, | |
| "grad_norm": 0.5989558100700378, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.6743, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0028746565208201224, | |
| "grad_norm": 0.5035123229026794, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 0.8069, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0030437539632213063, | |
| "grad_norm": 0.5071959495544434, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 0.6762, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00321285140562249, | |
| "grad_norm": 0.4506031572818756, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 0.5849, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0033819488480236735, | |
| "grad_norm": 0.4659384787082672, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.6887, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0033819488480236735, | |
| "eval_loss": 0.6605696082115173, | |
| "eval_runtime": 295.6071, | |
| "eval_samples_per_second": 8.423, | |
| "eval_steps_per_second": 4.212, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0035510462904248573, | |
| "grad_norm": 0.47143518924713135, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 0.7764, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.003720143732826041, | |
| "grad_norm": 0.47666624188423157, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 0.595, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0038892411752272245, | |
| "grad_norm": 0.44477328658103943, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 0.6747, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.004058338617628408, | |
| "grad_norm": 0.40303224325180054, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 0.4601, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.004227436060029592, | |
| "grad_norm": 0.5073460936546326, | |
| "learning_rate": 0.0, | |
| "loss": 0.6363, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004227436060029592, | |
| "eval_loss": 0.6571388244628906, | |
| "eval_runtime": 292.1469, | |
| "eval_samples_per_second": 8.523, | |
| "eval_steps_per_second": 4.262, | |
| "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": 440738910830592.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |