| { | |
| "best_metric": 0.5398735404014587, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.7575757575757576, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.030303030303030304, | |
| "grad_norm": 42.65187454223633, | |
| "learning_rate": 5e-05, | |
| "loss": 40.5917, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.030303030303030304, | |
| "eval_loss": 3.099010944366455, | |
| "eval_runtime": 1.7169, | |
| "eval_samples_per_second": 29.122, | |
| "eval_steps_per_second": 7.572, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.06060606060606061, | |
| "grad_norm": 40.510066986083984, | |
| "learning_rate": 0.0001, | |
| "loss": 42.2134, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.09090909090909091, | |
| "grad_norm": 35.972103118896484, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 42.4964, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.12121212121212122, | |
| "grad_norm": 32.96562576293945, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 39.1957, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.15151515151515152, | |
| "grad_norm": 26.64986801147461, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 34.6822, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.18181818181818182, | |
| "grad_norm": 28.514524459838867, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 31.089, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.21212121212121213, | |
| "grad_norm": 30.795284271240234, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 29.8746, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.24242424242424243, | |
| "grad_norm": 26.673248291015625, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 33.1275, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.2727272727272727, | |
| "grad_norm": 17.892269134521484, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 20.5216, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.30303030303030304, | |
| "grad_norm": 18.253292083740234, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 19.7817, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3333333333333333, | |
| "grad_norm": 18.005361557006836, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 18.1535, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.36363636363636365, | |
| "grad_norm": 17.88747787475586, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 16.7335, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.3939393939393939, | |
| "grad_norm": 14.878911972045898, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 15.589, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.42424242424242425, | |
| "grad_norm": 22.06363868713379, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 14.918, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.45454545454545453, | |
| "grad_norm": 24.978647232055664, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 14.4283, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.48484848484848486, | |
| "grad_norm": 21.225818634033203, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 15.9054, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.5151515151515151, | |
| "grad_norm": 10.050722122192383, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 10.8822, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.5454545454545454, | |
| "grad_norm": 10.84476089477539, | |
| "learning_rate": 7.75e-05, | |
| "loss": 10.6607, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.5757575757575758, | |
| "grad_norm": 9.327929496765137, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 10.7404, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.6060606060606061, | |
| "grad_norm": 8.07457160949707, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 9.6303, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.6363636363636364, | |
| "grad_norm": 10.68208122253418, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 9.915, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 9.476519584655762, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 9.0757, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.696969696969697, | |
| "grad_norm": 10.420138359069824, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 8.6263, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.7272727272727273, | |
| "grad_norm": 15.338788032531738, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 9.5048, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.7575757575757576, | |
| "grad_norm": 11.519371032714844, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 7.3465, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.7575757575757576, | |
| "eval_loss": 0.5398735404014587, | |
| "eval_runtime": 1.7452, | |
| "eval_samples_per_second": 28.65, | |
| "eval_steps_per_second": 7.449, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 2.629578157719552e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |