| { | |
| "best_metric": 0.33393481373786926, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.01778845084828675, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00071153803393147, | |
| "grad_norm": 4.15134859085083, | |
| "learning_rate": 5e-05, | |
| "loss": 3.1572, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00071153803393147, | |
| "eval_loss": 4.378438949584961, | |
| "eval_runtime": 3.4295, | |
| "eval_samples_per_second": 14.579, | |
| "eval_steps_per_second": 3.791, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00142307606786294, | |
| "grad_norm": 4.170166969299316, | |
| "learning_rate": 0.0001, | |
| "loss": 3.5344, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00213461410179441, | |
| "grad_norm": 3.9985992908477783, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 3.525, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00284615213572588, | |
| "grad_norm": 3.6105992794036865, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 2.8142, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00355769016965735, | |
| "grad_norm": 5.007969379425049, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 2.1902, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00426922820358882, | |
| "grad_norm": 3.7518584728240967, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 1.5608, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00498076623752029, | |
| "grad_norm": 3.1341824531555176, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.1253, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00569230427145176, | |
| "grad_norm": 2.485367774963379, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.8497, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00640384230538323, | |
| "grad_norm": 2.4227840900421143, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.6076, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0071153803393147, | |
| "grad_norm": 2.9558370113372803, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.4456, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00782691837324617, | |
| "grad_norm": 2.320117950439453, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.4223, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00853845640717764, | |
| "grad_norm": 2.1507346630096436, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.3642, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00924999444110911, | |
| "grad_norm": 3.829542875289917, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.9195, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.00996153247504058, | |
| "grad_norm": 2.7810795307159424, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.6957, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.01067307050897205, | |
| "grad_norm": 3.1059398651123047, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.543, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01138460854290352, | |
| "grad_norm": 2.7258763313293457, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.4601, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.01209614657683499, | |
| "grad_norm": 1.5909277200698853, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.3518, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.01280768461076646, | |
| "grad_norm": 0.9435157179832458, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.2869, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.01351922264469793, | |
| "grad_norm": 1.1259710788726807, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.2478, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0142307606786294, | |
| "grad_norm": 0.6966629028320312, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.1902, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01494229871256087, | |
| "grad_norm": 1.0074700117111206, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.1921, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.01565383674649234, | |
| "grad_norm": 0.9900541305541992, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.1861, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01636537478042381, | |
| "grad_norm": 0.6567324995994568, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.1719, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.01707691281435528, | |
| "grad_norm": 0.8026172518730164, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.1451, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01778845084828675, | |
| "grad_norm": 0.9177777767181396, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.1415, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01778845084828675, | |
| "eval_loss": 0.33393481373786926, | |
| "eval_runtime": 3.4972, | |
| "eval_samples_per_second": 14.297, | |
| "eval_steps_per_second": 3.717, | |
| "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": 2.984041808658432e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |