| { | |
| "best_metric": 1.258978009223938, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.08130081300813008, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0032520325203252032, | |
| "grad_norm": 8.649699211120605, | |
| "learning_rate": 5e-05, | |
| "loss": 3.8328, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0032520325203252032, | |
| "eval_loss": 4.739724636077881, | |
| "eval_runtime": 1.0435, | |
| "eval_samples_per_second": 47.914, | |
| "eval_steps_per_second": 12.458, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0065040650406504065, | |
| "grad_norm": 9.0828857421875, | |
| "learning_rate": 0.0001, | |
| "loss": 3.8301, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00975609756097561, | |
| "grad_norm": 8.781737327575684, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 3.6125, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.013008130081300813, | |
| "grad_norm": 7.1591267585754395, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 2.7281, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.016260162601626018, | |
| "grad_norm": 6.628422737121582, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 2.4338, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01951219512195122, | |
| "grad_norm": 9.28081226348877, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 2.1153, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.022764227642276424, | |
| "grad_norm": 10.796428680419922, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 2.4577, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.026016260162601626, | |
| "grad_norm": 11.272285461425781, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 2.4268, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02926829268292683, | |
| "grad_norm": 6.810426235198975, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 2.1097, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.032520325203252036, | |
| "grad_norm": 4.808910369873047, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.8114, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03577235772357724, | |
| "grad_norm": 3.7050528526306152, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 1.7031, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03902439024390244, | |
| "grad_norm": 4.334346294403076, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 1.6524, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.04227642276422764, | |
| "grad_norm": 4.8794026374816895, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 1.9001, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.04552845528455285, | |
| "grad_norm": 6.016350269317627, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 2.0551, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.04878048780487805, | |
| "grad_norm": 4.182360649108887, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 1.9548, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05203252032520325, | |
| "grad_norm": 3.1308839321136475, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 1.6327, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.055284552845528454, | |
| "grad_norm": 2.6584155559539795, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.6004, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.05853658536585366, | |
| "grad_norm": 2.1619088649749756, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.6218, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.061788617886178863, | |
| "grad_norm": 2.1159422397613525, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 1.4287, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.06504065040650407, | |
| "grad_norm": 5.528226852416992, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.2984, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06829268292682927, | |
| "grad_norm": 3.2824182510375977, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 1.3323, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.07154471544715447, | |
| "grad_norm": 3.0928151607513428, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 1.19, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.07479674796747968, | |
| "grad_norm": 2.6824562549591064, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 1.2456, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.07804878048780488, | |
| "grad_norm": 2.8048856258392334, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 1.1748, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.08130081300813008, | |
| "grad_norm": 2.7431864738464355, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 1.1083, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08130081300813008, | |
| "eval_loss": 1.258978009223938, | |
| "eval_runtime": 0.5077, | |
| "eval_samples_per_second": 98.491, | |
| "eval_steps_per_second": 25.608, | |
| "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": 1.47650456322048e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |