| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.27816411682892905, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005563282336578581, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005563282336578581, | |
| "eval_loss": NaN, | |
| "eval_runtime": 7.9966, | |
| "eval_samples_per_second": 6.253, | |
| "eval_steps_per_second": 0.875, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.011126564673157162, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.016689847009735744, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.022253129346314324, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.027816411682892908, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03337969401947149, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03894297635605007, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.04450625869262865, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.05006954102920723, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00027, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.055632823365785816, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0003, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.061196105702364396, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002999794957488703, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.06675938803894298, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002999179886011389, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.07232267037552156, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002998154953722457, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.07788595271210014, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00029967204408281613, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.08344923504867872, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00029948767395100045, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0890125173852573, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002992624353817517, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.09457579972183588, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002989963899530457, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.10013908205841446, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00029868961039904624, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.10570236439499305, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00029834218059022024, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.11126564673157163, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00029795419551040833, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1168289290681502, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00029752576123085736, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.12239221140472879, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002970569948812214, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.12795549374130738, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002965480246175399, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.13351877607788595, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002959989895872009, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.13908205841446453, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002954100398908995, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.13908205841446453, | |
| "eval_loss": NaN, | |
| "eval_runtime": 7.5653, | |
| "eval_samples_per_second": 6.609, | |
| "eval_steps_per_second": 0.925, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.14464534075104313, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002947813365416023, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.1502086230876217, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002941130514205272, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.15577190542420027, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002934053672301536, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.16133518776077885, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00029265847744427303, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.16689847009735745, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00029187258625509513, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.17246175243393602, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00029104790851742417, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.1780250347705146, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002901846696899191, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.1835883171070932, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00028928310577345606, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.18915159944367177, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002883434632466077, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.19471488178025034, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00028736599899825856, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.20027816411682892, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00028635098025737434, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.20584144645340752, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00028529868451994384, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.2114047287899861, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002842093994731145, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.21696801112656466, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00028308342291654174, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.22253129346314326, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00028192106268097334, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.22809457579972184, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00028072263654409154, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.2336578581363004, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002794884721436361, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.23922114047287898, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00027821890688783083, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.24478442280945759, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002769142878631403, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.25034770514603616, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00027557497173937923, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.25591098748261476, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000274201324672203, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.2614742698191933, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00027279372220300385, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.2670375521557719, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002713525491562421, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.2726008344923505, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00026987819953423867, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.27816411682892905, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00026837107640945905, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.27816411682892905, | |
| "eval_loss": NaN, | |
| "eval_runtime": 7.566, | |
| "eval_samples_per_second": 6.608, | |
| "eval_steps_per_second": 0.925, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 1.4910702964074086e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |