| { | |
| "best_metric": 1.0824270248413086, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.07732456988208003, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003092982795283201, | |
| "grad_norm": 63.227630615234375, | |
| "learning_rate": 1e-05, | |
| "loss": 25.075, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003092982795283201, | |
| "eval_loss": 1.5490102767944336, | |
| "eval_runtime": 149.2754, | |
| "eval_samples_per_second": 3.651, | |
| "eval_steps_per_second": 1.829, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006185965590566402, | |
| "grad_norm": 66.90909576416016, | |
| "learning_rate": 2e-05, | |
| "loss": 23.6882, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.009278948385849604, | |
| "grad_norm": 63.644508361816406, | |
| "learning_rate": 3e-05, | |
| "loss": 23.8152, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.012371931181132804, | |
| "grad_norm": 66.12242126464844, | |
| "learning_rate": 4e-05, | |
| "loss": 24.5011, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.015464913976416006, | |
| "grad_norm": 37.521697998046875, | |
| "learning_rate": 5e-05, | |
| "loss": 20.4137, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01855789677169921, | |
| "grad_norm": 36.76587677001953, | |
| "learning_rate": 6e-05, | |
| "loss": 21.0439, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02165087956698241, | |
| "grad_norm": 35.1934928894043, | |
| "learning_rate": 7e-05, | |
| "loss": 19.4824, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02474386236226561, | |
| "grad_norm": 34.91908645629883, | |
| "learning_rate": 8e-05, | |
| "loss": 18.7023, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02783684515754881, | |
| "grad_norm": 37.3280143737793, | |
| "learning_rate": 9e-05, | |
| "loss": 19.6331, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03092982795283201, | |
| "grad_norm": 33.82084655761719, | |
| "learning_rate": 0.0001, | |
| "loss": 19.1644, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.034022810748115216, | |
| "grad_norm": 28.904260635375977, | |
| "learning_rate": 9.98458666866564e-05, | |
| "loss": 18.3894, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03711579354339842, | |
| "grad_norm": 33.33706283569336, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 19.5411, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.04020877633868162, | |
| "grad_norm": 28.71995735168457, | |
| "learning_rate": 9.861849601988383e-05, | |
| "loss": 17.7854, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.04330175913396482, | |
| "grad_norm": 24.508121490478516, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 17.7444, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.046394741929248015, | |
| "grad_norm": 25.298206329345703, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 17.419, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04948772472453122, | |
| "grad_norm": 26.203685760498047, | |
| "learning_rate": 9.45503262094184e-05, | |
| "loss": 17.0621, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.05258070751981442, | |
| "grad_norm": 28.71617889404297, | |
| "learning_rate": 9.263200821770461e-05, | |
| "loss": 19.3019, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.05567369031509762, | |
| "grad_norm": 24.17940902709961, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 17.6426, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.05876667311038082, | |
| "grad_norm": 25.524850845336914, | |
| "learning_rate": 8.802029828000156e-05, | |
| "loss": 17.6575, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.06185965590566402, | |
| "grad_norm": 30.970611572265625, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 18.1651, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06495263870094722, | |
| "grad_norm": 26.73845100402832, | |
| "learning_rate": 8.247240241650918e-05, | |
| "loss": 17.7731, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.06804562149623043, | |
| "grad_norm": 27.083934783935547, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 18.8107, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.07113860429151363, | |
| "grad_norm": 26.337148666381836, | |
| "learning_rate": 7.612492823579745e-05, | |
| "loss": 17.086, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.07423158708679684, | |
| "grad_norm": 24.6472225189209, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 19.3557, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.07732456988208003, | |
| "grad_norm": 24.704971313476562, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 17.915, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07732456988208003, | |
| "eval_loss": 1.0824270248413086, | |
| "eval_runtime": 150.1751, | |
| "eval_samples_per_second": 3.629, | |
| "eval_steps_per_second": 1.818, | |
| "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": 7.709054073411994e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |