| { | |
| "best_metric": 4.626386642456055, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.034381983840467596, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0013752793536187038, | |
| "grad_norm": 47.247737884521484, | |
| "learning_rate": 5e-05, | |
| "loss": 90.7898, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013752793536187038, | |
| "eval_loss": 6.071027755737305, | |
| "eval_runtime": 2.9009, | |
| "eval_samples_per_second": 17.236, | |
| "eval_steps_per_second": 4.481, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0027505587072374077, | |
| "grad_norm": 50.189151763916016, | |
| "learning_rate": 0.0001, | |
| "loss": 94.6107, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0041258380608561115, | |
| "grad_norm": 45.00249099731445, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 93.878, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005501117414474815, | |
| "grad_norm": 31.018747329711914, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 87.0647, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006876396768093519, | |
| "grad_norm": 25.834840774536133, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 85.2583, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.008251676121712223, | |
| "grad_norm": 23.79578971862793, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 82.2246, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.009626955475330927, | |
| "grad_norm": 24.951824188232422, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 79.9058, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.01100223482894963, | |
| "grad_norm": 14.284527778625488, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 79.1301, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.012377514182568335, | |
| "grad_norm": 49.100196838378906, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 78.4692, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.013752793536187038, | |
| "grad_norm": 85.69519805908203, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 78.4167, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.015128072889805742, | |
| "grad_norm": 82.62657165527344, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 80.1901, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.016503352243424446, | |
| "grad_norm": 35.43754196166992, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 81.3278, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01787863159704315, | |
| "grad_norm": 30.274520874023438, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 76.5465, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.019253910950661854, | |
| "grad_norm": 24.64078140258789, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 72.6522, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.020629190304280558, | |
| "grad_norm": 24.059825897216797, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 72.8096, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02200446965789926, | |
| "grad_norm": 14.653773307800293, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 73.2995, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.023379749011517965, | |
| "grad_norm": 8.644264221191406, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 74.0428, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.02475502836513667, | |
| "grad_norm": 31.19290542602539, | |
| "learning_rate": 7.75e-05, | |
| "loss": 74.5504, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.026130307718755373, | |
| "grad_norm": 24.381179809570312, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 75.5478, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.027505587072374077, | |
| "grad_norm": 40.15234375, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 76.11, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02888086642599278, | |
| "grad_norm": 24.75045394897461, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 75.888, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.030256145779611485, | |
| "grad_norm": 11.645346641540527, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 76.7001, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.03163142513323019, | |
| "grad_norm": 18.211610794067383, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 78.1607, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.03300670448684889, | |
| "grad_norm": 22.749834060668945, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 78.6751, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.034381983840467596, | |
| "grad_norm": 14.634866714477539, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 80.3792, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.034381983840467596, | |
| "eval_loss": 4.626386642456055, | |
| "eval_runtime": 2.9216, | |
| "eval_samples_per_second": 17.114, | |
| "eval_steps_per_second": 4.45, | |
| "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": 2.629552387915776e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |