| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.0196174595389897, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00039234919077979404, | |
| "grad_norm": 0.7801864743232727, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 1.1076, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00039234919077979404, | |
| "eval_loss": 2.6347837448120117, | |
| "eval_runtime": 5.3964, | |
| "eval_samples_per_second": 9.265, | |
| "eval_steps_per_second": 1.297, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007846983815595881, | |
| "grad_norm": 0.4603287875652313, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 1.7697, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0011770475723393821, | |
| "grad_norm": 0.5424301028251648, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 2.1838, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0015693967631191762, | |
| "grad_norm": 0.5732556581497192, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 2.1462, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00196174595389897, | |
| "grad_norm": 0.5106447339057922, | |
| "learning_rate": 0.00015, | |
| "loss": 2.5732, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0023540951446787643, | |
| "grad_norm": 0.4012216329574585, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 2.3035, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0027464443354585583, | |
| "grad_norm": 0.4464437961578369, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 2.5018, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0031387935262383523, | |
| "grad_norm": 0.49094539880752563, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 2.4145, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.003531142717018146, | |
| "grad_norm": 0.5340158939361572, | |
| "learning_rate": 0.00027, | |
| "loss": 2.5605, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00392349190779794, | |
| "grad_norm": 0.469400018453598, | |
| "learning_rate": 0.0003, | |
| "loss": 2.5807, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0043158410985777345, | |
| "grad_norm": 0.40649205446243286, | |
| "learning_rate": 0.0002999794957488703, | |
| "loss": 2.3967, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0047081902893575285, | |
| "grad_norm": 0.43658336997032166, | |
| "learning_rate": 0.0002999179886011389, | |
| "loss": 2.3976, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0051005394801373225, | |
| "grad_norm": 0.5445865392684937, | |
| "learning_rate": 0.0002998154953722457, | |
| "loss": 2.3869, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.005492888670917117, | |
| "grad_norm": 0.4407218098640442, | |
| "learning_rate": 0.00029967204408281613, | |
| "loss": 2.1568, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.005885237861696911, | |
| "grad_norm": 0.3098980188369751, | |
| "learning_rate": 0.00029948767395100045, | |
| "loss": 2.1049, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.006277587052476705, | |
| "grad_norm": 0.38185837864875793, | |
| "learning_rate": 0.0002992624353817517, | |
| "loss": 2.2054, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.006669936243256498, | |
| "grad_norm": 0.3709363043308258, | |
| "learning_rate": 0.0002989963899530457, | |
| "loss": 2.1322, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.007062285434036292, | |
| "grad_norm": 0.3822822570800781, | |
| "learning_rate": 0.00029868961039904624, | |
| "loss": 2.2528, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.007454634624816086, | |
| "grad_norm": 0.40470457077026367, | |
| "learning_rate": 0.00029834218059022024, | |
| "loss": 2.1562, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.00784698381559588, | |
| "grad_norm": 0.46746203303337097, | |
| "learning_rate": 0.00029795419551040833, | |
| "loss": 2.2253, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.008239333006375674, | |
| "grad_norm": 0.5920839905738831, | |
| "learning_rate": 0.00029752576123085736, | |
| "loss": 2.2653, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.008631682197155469, | |
| "grad_norm": 0.4972122609615326, | |
| "learning_rate": 0.0002970569948812214, | |
| "loss": 2.174, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.009024031387935262, | |
| "grad_norm": 0.31875213980674744, | |
| "learning_rate": 0.0002965480246175399, | |
| "loss": 2.094, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.009416380578715057, | |
| "grad_norm": 0.49916020035743713, | |
| "learning_rate": 0.0002959989895872009, | |
| "loss": 2.0421, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.00980872976949485, | |
| "grad_norm": 0.35592731833457947, | |
| "learning_rate": 0.0002954100398908995, | |
| "loss": 2.0896, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.00980872976949485, | |
| "eval_loss": 1.9814097881317139, | |
| "eval_runtime": 4.9578, | |
| "eval_samples_per_second": 10.085, | |
| "eval_steps_per_second": 1.412, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.010201078960274645, | |
| "grad_norm": 0.5454434156417847, | |
| "learning_rate": 0.0002947813365416023, | |
| "loss": 2.0981, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.010593428151054438, | |
| "grad_norm": 0.41645103693008423, | |
| "learning_rate": 0.0002941130514205272, | |
| "loss": 2.006, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.010985777341834233, | |
| "grad_norm": 0.539344847202301, | |
| "learning_rate": 0.0002934053672301536, | |
| "loss": 1.9416, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.011378126532614026, | |
| "grad_norm": 0.408270001411438, | |
| "learning_rate": 0.00029265847744427303, | |
| "loss": 2.0615, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.011770475723393821, | |
| "grad_norm": 0.4333832263946533, | |
| "learning_rate": 0.00029187258625509513, | |
| "loss": 2.0464, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.012162824914173614, | |
| "grad_norm": 0.3659256398677826, | |
| "learning_rate": 0.00029104790851742417, | |
| "loss": 1.9172, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.01255517410495341, | |
| "grad_norm": 0.45351165533065796, | |
| "learning_rate": 0.0002901846696899191, | |
| "loss": 1.9599, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.012947523295733203, | |
| "grad_norm": 0.4614894688129425, | |
| "learning_rate": 0.00028928310577345606, | |
| "loss": 1.9147, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.013339872486512996, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002883434632466077, | |
| "loss": 1.9759, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.01373222167729279, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00028736599899825856, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.014124570868072584, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00028635098025737434, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.014516920058852379, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00028529868451994384, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.014909269249632172, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002842093994731145, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.015301618440411967, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00028308342291654174, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.01569396763119176, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00028192106268097334, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.016086316821971553, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00028072263654409154, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.016478666012751348, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002794884721436361, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.016871015203531143, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00027821890688783083, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.017263364394310938, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002769142878631403, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.01765571358509073, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00027557497173937923, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.018048062775870524, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000274201324672203, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.01844041196665032, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00027279372220300385, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.018832761157430114, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002713525491562421, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.019225110348209905, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00026987819953423867, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0196174595389897, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00026837107640945905, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0196174595389897, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.7136, | |
| "eval_samples_per_second": 10.608, | |
| "eval_steps_per_second": 1.485, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.877552082065818e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |