| { | |
| "best_metric": 0.6592954993247986, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.9501187648456056, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03800475059382423, | |
| "grad_norm": 0.29411759972572327, | |
| "learning_rate": 5e-05, | |
| "loss": 0.8144, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03800475059382423, | |
| "eval_loss": 1.0114444494247437, | |
| "eval_runtime": 3.593, | |
| "eval_samples_per_second": 13.916, | |
| "eval_steps_per_second": 3.618, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07600950118764846, | |
| "grad_norm": 0.43555742502212524, | |
| "learning_rate": 0.0001, | |
| "loss": 0.7299, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.11401425178147269, | |
| "grad_norm": 0.530921995639801, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 0.7875, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.15201900237529692, | |
| "grad_norm": 0.44882693886756897, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 0.6892, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.19002375296912113, | |
| "grad_norm": 0.5552424192428589, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 0.8262, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.22802850356294538, | |
| "grad_norm": 0.6508234739303589, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 0.8837, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.2660332541567696, | |
| "grad_norm": 0.21037250757217407, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 0.693, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.30403800475059384, | |
| "grad_norm": 0.2537347078323364, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.4355, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.342042755344418, | |
| "grad_norm": 0.3227172791957855, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.4278, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.38004750593824227, | |
| "grad_norm": 0.3554595410823822, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.5003, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.4180522565320665, | |
| "grad_norm": 0.3022133409976959, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.5099, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.45605700712589076, | |
| "grad_norm": 0.31370723247528076, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.5727, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.49406175771971494, | |
| "grad_norm": 0.4634961187839508, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.78, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.5320665083135392, | |
| "grad_norm": 0.21107812225818634, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.5925, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5700712589073634, | |
| "grad_norm": 0.20424596965312958, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.5511, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.6080760095011877, | |
| "grad_norm": 0.20124682784080505, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.4627, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.6460807600950119, | |
| "grad_norm": 0.19492486119270325, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.475, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.684085510688836, | |
| "grad_norm": 0.22841496765613556, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.5942, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.7220902612826603, | |
| "grad_norm": 0.27940472960472107, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.5875, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.7600950118764845, | |
| "grad_norm": 0.19323502480983734, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.7253, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7980997624703088, | |
| "grad_norm": 0.14682111144065857, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.4848, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.836104513064133, | |
| "grad_norm": 0.18906645476818085, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.6015, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.8741092636579573, | |
| "grad_norm": 0.18058668076992035, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.4769, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.9121140142517815, | |
| "grad_norm": 0.1932019293308258, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.4867, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.9501187648456056, | |
| "grad_norm": 0.24099431931972504, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.6925, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.9501187648456056, | |
| "eval_loss": 0.6592954993247986, | |
| "eval_runtime": 3.2051, | |
| "eval_samples_per_second": 15.6, | |
| "eval_steps_per_second": 4.056, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.812028905324544e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |