| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.2676928224861971, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005353856449723942, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 1.9197, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005353856449723942, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.205, | |
| "eval_samples_per_second": 11.891, | |
| "eval_steps_per_second": 11.891, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010707712899447884, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.016061569349171825, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.021415425798895767, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.02676928224861971, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03212313869834365, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03747699514806759, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.042830851597791535, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.04818470804751548, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00027, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.05353856449723942, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0003, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05889242094696336, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002999794957488703, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0642462773966873, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002999179886011389, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.06960013384641124, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002998154953722457, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.07495399029613518, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00029967204408281613, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.08030784674585913, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00029948767395100045, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.08566170319558307, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002992624353817517, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.09101555964530701, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002989963899530457, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.09636941609503095, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00029868961039904624, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.1017232725447549, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00029834218059022024, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.10707712899447884, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00029795419551040833, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.11243098544420278, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00029752576123085736, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.11778484189392673, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002970569948812214, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.12313869834365065, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002965480246175399, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.1284925547933746, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002959989895872009, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.13384641124309854, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002954100398908995, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.13384641124309854, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.2431, | |
| "eval_samples_per_second": 11.784, | |
| "eval_steps_per_second": 11.784, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.13920026769282248, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002947813365416023, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.14455412414254643, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002941130514205272, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.14990798059227037, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002934053672301536, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.1552618370419943, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00029265847744427303, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.16061569349171825, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00029187258625509513, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1659695499414422, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00029104790851742417, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.17132340639116614, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002901846696899191, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.17667726284089008, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00028928310577345606, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.18203111929061402, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002883434632466077, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.18738497574033797, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00028736599899825856, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.1927388321900619, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00028635098025737434, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.19809268863978585, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00028529868451994384, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.2034465450895098, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002842093994731145, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.20880040153923374, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00028308342291654174, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.21415425798895768, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00028192106268097334, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.21950811443868162, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00028072263654409154, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.22486197088840557, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002794884721436361, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.2302158273381295, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00027821890688783083, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.23556968378785345, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002769142878631403, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.2409235402375774, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00027557497173937923, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.2462773966873013, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000274201324672203, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.2516312531370253, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00027279372220300385, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.2569851095867492, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002713525491562421, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.26233896603647316, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00026987819953423867, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.2676928224861971, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00026837107640945905, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.2676928224861971, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.2459, | |
| "eval_samples_per_second": 11.776, | |
| "eval_steps_per_second": 11.776, | |
| "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": 7.42728611659776e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |