| { | |
| "best_metric": 2.4427363872528076, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.17825311942959002, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0071301247771836, | |
| "grad_norm": 1.5173163414001465, | |
| "learning_rate": 2e-05, | |
| "loss": 2.8537, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0071301247771836, | |
| "eval_loss": 3.90462064743042, | |
| "eval_runtime": 1.5866, | |
| "eval_samples_per_second": 148.747, | |
| "eval_steps_per_second": 18.908, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0142602495543672, | |
| "grad_norm": 1.3383238315582275, | |
| "learning_rate": 4e-05, | |
| "loss": 2.8749, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0213903743315508, | |
| "grad_norm": 1.6879465579986572, | |
| "learning_rate": 6e-05, | |
| "loss": 2.9998, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0285204991087344, | |
| "grad_norm": 1.7708063125610352, | |
| "learning_rate": 8e-05, | |
| "loss": 3.06, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.035650623885918005, | |
| "grad_norm": 1.486020803451538, | |
| "learning_rate": 0.0001, | |
| "loss": 2.9697, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0427807486631016, | |
| "grad_norm": 1.6805022954940796, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 2.8983, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.049910873440285206, | |
| "grad_norm": 1.4022825956344604, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 3.016, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0570409982174688, | |
| "grad_norm": 1.6186312437057495, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 2.8773, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.06417112299465241, | |
| "grad_norm": 1.357567310333252, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 2.9339, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.07130124777183601, | |
| "grad_norm": 1.825875997543335, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 3.0052, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0784313725490196, | |
| "grad_norm": 1.7561568021774292, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 2.8068, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0855614973262032, | |
| "grad_norm": 1.8440032005310059, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 3.0174, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.09269162210338681, | |
| "grad_norm": 1.3899633884429932, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 2.9899, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.09982174688057041, | |
| "grad_norm": 1.4993560314178467, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 2.8701, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.10695187165775401, | |
| "grad_norm": 1.4138418436050415, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 2.6803, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1140819964349376, | |
| "grad_norm": 1.846754789352417, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 2.9407, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.12121212121212122, | |
| "grad_norm": 1.996471881866455, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 3.2487, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.12834224598930483, | |
| "grad_norm": 2.1197140216827393, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 3.1799, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.1354723707664884, | |
| "grad_norm": 1.753442406654358, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 2.7721, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.14260249554367202, | |
| "grad_norm": 1.6010884046554565, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.5523, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1497326203208556, | |
| "grad_norm": 1.6448290348052979, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 2.9927, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.1568627450980392, | |
| "grad_norm": 1.990535020828247, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 2.6969, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.16399286987522282, | |
| "grad_norm": 1.4850422143936157, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 2.6551, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.1711229946524064, | |
| "grad_norm": 1.9399062395095825, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 3.0327, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.17825311942959002, | |
| "grad_norm": 2.076749086380005, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 3.104, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.17825311942959002, | |
| "eval_loss": 2.4427363872528076, | |
| "eval_runtime": 1.5836, | |
| "eval_samples_per_second": 149.028, | |
| "eval_steps_per_second": 18.944, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "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": 309022005657600.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |