| { | |
| "best_metric": 1.0614150762557983, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.15464913976416006, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "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 | |
| }, | |
| { | |
| "epoch": 0.08041755267736324, | |
| "grad_norm": 24.245737075805664, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 17.5508, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.08351053547264643, | |
| "grad_norm": 23.731287002563477, | |
| "learning_rate": 6.167226819279528e-05, | |
| "loss": 16.6255, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.08660351826792964, | |
| "grad_norm": 25.361608505249023, | |
| "learning_rate": 5.782172325201155e-05, | |
| "loss": 17.3047, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.08969650106321284, | |
| "grad_norm": 25.7116756439209, | |
| "learning_rate": 5.392295478639225e-05, | |
| "loss": 18.7329, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.09278948385849603, | |
| "grad_norm": 22.363431930541992, | |
| "learning_rate": 5e-05, | |
| "loss": 16.206, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09588246665377924, | |
| "grad_norm": 25.386978149414062, | |
| "learning_rate": 4.607704521360776e-05, | |
| "loss": 18.509, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.09897544944906243, | |
| "grad_norm": 23.575090408325195, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 16.8986, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.10206843224434564, | |
| "grad_norm": 24.97161102294922, | |
| "learning_rate": 3.832773180720475e-05, | |
| "loss": 18.4959, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.10516141503962884, | |
| "grad_norm": 22.639801025390625, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 16.6215, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.10825439783491204, | |
| "grad_norm": 21.792438507080078, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 16.5128, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.11134738063019524, | |
| "grad_norm": 23.47806167602539, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 16.1797, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.11444036342547845, | |
| "grad_norm": 20.9477596282959, | |
| "learning_rate": 2.3875071764202563e-05, | |
| "loss": 14.7101, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.11753334622076164, | |
| "grad_norm": 23.272993087768555, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 17.4994, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.12062632901604485, | |
| "grad_norm": 24.445510864257812, | |
| "learning_rate": 1.7527597583490822e-05, | |
| "loss": 18.4799, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.12371931181132804, | |
| "grad_norm": 21.996252059936523, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 16.2203, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.12681229460661125, | |
| "grad_norm": 24.246135711669922, | |
| "learning_rate": 1.1979701719998453e-05, | |
| "loss": 17.0163, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.12990527740189445, | |
| "grad_norm": 26.47881507873535, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 17.7896, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.13299826019717764, | |
| "grad_norm": 22.64656639099121, | |
| "learning_rate": 7.367991782295391e-06, | |
| "loss": 16.8853, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.13609124299246086, | |
| "grad_norm": 23.412134170532227, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 16.9634, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.13918422578774406, | |
| "grad_norm": 23.991744995117188, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 16.9744, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.14227720858302725, | |
| "grad_norm": 22.722434997558594, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 17.6464, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.14537019137831045, | |
| "grad_norm": 25.069778442382812, | |
| "learning_rate": 1.3815039801161721e-06, | |
| "loss": 17.4536, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.14846317417359367, | |
| "grad_norm": 24.66384506225586, | |
| "learning_rate": 6.15582970243117e-07, | |
| "loss": 17.223, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.15155615696887687, | |
| "grad_norm": 25.479217529296875, | |
| "learning_rate": 1.5413331334360182e-07, | |
| "loss": 17.2031, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.15464913976416006, | |
| "grad_norm": 22.113872528076172, | |
| "learning_rate": 0.0, | |
| "loss": 19.1739, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.15464913976416006, | |
| "eval_loss": 1.0614150762557983, | |
| "eval_runtime": 150.2967, | |
| "eval_samples_per_second": 3.626, | |
| "eval_steps_per_second": 1.816, | |
| "step": 50 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.5435789463506125e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |