| { | |
| "best_metric": 10.581374168395996, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.3404255319148936, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.013617021276595745, | |
| "grad_norm": 31.260223388671875, | |
| "learning_rate": 5e-05, | |
| "loss": 179.1719, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013617021276595745, | |
| "eval_loss": 11.210249900817871, | |
| "eval_runtime": 0.7004, | |
| "eval_samples_per_second": 71.388, | |
| "eval_steps_per_second": 18.561, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02723404255319149, | |
| "grad_norm": 38.27791213989258, | |
| "learning_rate": 0.0001, | |
| "loss": 179.33, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.04085106382978723, | |
| "grad_norm": 34.22037124633789, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 179.0171, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.05446808510638298, | |
| "grad_norm": 32.08433151245117, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 178.1888, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06808510638297872, | |
| "grad_norm": 30.398303985595703, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 177.8481, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08170212765957446, | |
| "grad_norm": 29.144142150878906, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 177.4651, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.09531914893617022, | |
| "grad_norm": 30.449281692504883, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 176.808, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.10893617021276596, | |
| "grad_norm": 29.39048957824707, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 176.475, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.1225531914893617, | |
| "grad_norm": 30.308015823364258, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 175.9786, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.13617021276595745, | |
| "grad_norm": 29.521896362304688, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 175.0975, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.1497872340425532, | |
| "grad_norm": 29.471303939819336, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 174.9922, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.16340425531914893, | |
| "grad_norm": 29.049652099609375, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 174.6531, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.17702127659574468, | |
| "grad_norm": 29.36743927001953, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 175.1359, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.19063829787234043, | |
| "grad_norm": 38.21333694458008, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 172.7683, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.20425531914893616, | |
| "grad_norm": 36.98329162597656, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 172.4297, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2178723404255319, | |
| "grad_norm": 33.906951904296875, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 172.1532, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.23148936170212767, | |
| "grad_norm": 32.73712921142578, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 172.097, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.2451063829787234, | |
| "grad_norm": 33.81500244140625, | |
| "learning_rate": 7.75e-05, | |
| "loss": 171.3027, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.25872340425531914, | |
| "grad_norm": 31.76679229736328, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 171.3058, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.2723404255319149, | |
| "grad_norm": 31.578975677490234, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 170.9581, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.28595744680851065, | |
| "grad_norm": 30.295276641845703, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 170.86, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.2995744680851064, | |
| "grad_norm": 31.39499855041504, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 170.3138, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.3131914893617021, | |
| "grad_norm": 29.06229019165039, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 170.4506, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.32680851063829786, | |
| "grad_norm": 30.135881423950195, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 169.6599, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.3404255319148936, | |
| "grad_norm": 30.49418830871582, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 171.7904, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3404255319148936, | |
| "eval_loss": 10.581374168395996, | |
| "eval_runtime": 0.353, | |
| "eval_samples_per_second": 141.661, | |
| "eval_steps_per_second": 36.832, | |
| "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": 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": 19055561932800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |