| { | |
| "best_metric": 4.630157470703125, | |
| "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": 1.3573954105377197, | |
| "learning_rate": 5e-05, | |
| "loss": 5.4569, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013752793536187038, | |
| "eval_loss": 5.800675868988037, | |
| "eval_runtime": 4.4274, | |
| "eval_samples_per_second": 11.293, | |
| "eval_steps_per_second": 2.936, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0027505587072374077, | |
| "grad_norm": 1.1038050651550293, | |
| "learning_rate": 0.0001, | |
| "loss": 5.5196, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0041258380608561115, | |
| "grad_norm": 1.128781795501709, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 5.537, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005501117414474815, | |
| "grad_norm": 1.1495604515075684, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 5.4791, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006876396768093519, | |
| "grad_norm": 1.0771335363388062, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 5.3432, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.008251676121712223, | |
| "grad_norm": 1.124253511428833, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 5.2646, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.009626955475330927, | |
| "grad_norm": 0.999345600605011, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 5.0927, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.01100223482894963, | |
| "grad_norm": 1.0835942029953003, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 5.1607, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.012377514182568335, | |
| "grad_norm": 0.7795541882514954, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 5.0415, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.013752793536187038, | |
| "grad_norm": 1.2778282165527344, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 5.1147, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.015128072889805742, | |
| "grad_norm": 1.7453047037124634, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 5.1534, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.016503352243424446, | |
| "grad_norm": 1.9628040790557861, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 5.2754, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01787863159704315, | |
| "grad_norm": 2.570558547973633, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 5.0466, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.019253910950661854, | |
| "grad_norm": 1.3346421718597412, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 4.4947, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.020629190304280558, | |
| "grad_norm": 2.2572271823883057, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 4.45, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02200446965789926, | |
| "grad_norm": 1.0499677658081055, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 4.5362, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.023379749011517965, | |
| "grad_norm": 2.3192594051361084, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 4.553, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.02475502836513667, | |
| "grad_norm": 1.927417516708374, | |
| "learning_rate": 7.75e-05, | |
| "loss": 4.5915, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.026130307718755373, | |
| "grad_norm": 0.3943534195423126, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 4.6225, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.027505587072374077, | |
| "grad_norm": 1.8378969430923462, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 4.7635, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02888086642599278, | |
| "grad_norm": 1.5817768573760986, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 4.7496, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.030256145779611485, | |
| "grad_norm": 0.7282426953315735, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 4.7856, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.03163142513323019, | |
| "grad_norm": 1.0822144746780396, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 4.8682, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.03300670448684889, | |
| "grad_norm": 0.6497578620910645, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 5.0268, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.034381983840467596, | |
| "grad_norm": 1.9047386646270752, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 5.3267, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.034381983840467596, | |
| "eval_loss": 4.630157470703125, | |
| "eval_runtime": 4.4751, | |
| "eval_samples_per_second": 11.173, | |
| "eval_steps_per_second": 2.905, | |
| "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": 1.327074698592256e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |