| { | |
| "best_metric": 2.1376192569732666, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.024792363951902815, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0009916945580761127, | |
| "grad_norm": 1.8227845430374146, | |
| "learning_rate": 5e-05, | |
| "loss": 2.9259, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009916945580761127, | |
| "eval_loss": 2.9540276527404785, | |
| "eval_runtime": 1.1246, | |
| "eval_samples_per_second": 44.46, | |
| "eval_steps_per_second": 11.56, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0019833891161522253, | |
| "grad_norm": 1.9859800338745117, | |
| "learning_rate": 0.0001, | |
| "loss": 2.8428, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0029750836742283376, | |
| "grad_norm": 1.788472294807434, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 2.7766, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003966778232304451, | |
| "grad_norm": 1.7515558004379272, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 2.5321, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0049584727903805624, | |
| "grad_norm": 1.6862818002700806, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 2.405, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.005950167348456675, | |
| "grad_norm": 1.08989417552948, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 2.3068, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.006941861906532788, | |
| "grad_norm": 1.0072200298309326, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 2.2333, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.007933556464608901, | |
| "grad_norm": 0.9319274425506592, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 2.1966, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.008925251022685012, | |
| "grad_norm": 0.9776121377944946, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 2.1115, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.009916945580761125, | |
| "grad_norm": 1.1010252237319946, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 2.3014, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.010908640138837238, | |
| "grad_norm": 0.9887837767601013, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 2.1886, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.01190033469691335, | |
| "grad_norm": 1.0444656610488892, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 2.172, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.012892029254989463, | |
| "grad_norm": 0.9816225171089172, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 2.2176, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.013883723813065576, | |
| "grad_norm": 0.8053462505340576, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 2.1568, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.014875418371141688, | |
| "grad_norm": 0.7338224053382874, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 2.1749, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.015867112929217803, | |
| "grad_norm": 0.7205262184143066, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 2.2502, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.016858807487293914, | |
| "grad_norm": 0.7129595279693604, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 2.0921, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.017850502045370024, | |
| "grad_norm": 0.6924590468406677, | |
| "learning_rate": 7.75e-05, | |
| "loss": 2.1471, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.01884219660344614, | |
| "grad_norm": 0.6652086973190308, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 2.0456, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.01983389116152225, | |
| "grad_norm": 0.6703733205795288, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 2.1318, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.020825585719598364, | |
| "grad_norm": 0.6245272159576416, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 2.1297, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.021817280277674475, | |
| "grad_norm": 0.653343915939331, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 2.1109, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.02280897483575059, | |
| "grad_norm": 0.6606502532958984, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 2.1653, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0238006693938267, | |
| "grad_norm": 0.6672307848930359, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 2.1121, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.024792363951902815, | |
| "grad_norm": 0.6210116744041443, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 2.049, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.024792363951902815, | |
| "eval_loss": 2.1376192569732666, | |
| "eval_runtime": 1.1245, | |
| "eval_samples_per_second": 44.466, | |
| "eval_steps_per_second": 11.561, | |
| "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": 3.91521434075136e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |