| { | |
| "best_metric": 0.7155137062072754, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 3.1870967741935483, | |
| "eval_steps": 25, | |
| "global_step": 29, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.1032258064516129, | |
| "grad_norm": 32.42584228515625, | |
| "learning_rate": 5e-05, | |
| "loss": 9.994, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.1032258064516129, | |
| "eval_loss": 10.080071449279785, | |
| "eval_runtime": 1.4018, | |
| "eval_samples_per_second": 46.368, | |
| "eval_steps_per_second": 6.42, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.2064516129032258, | |
| "grad_norm": 31.778467178344727, | |
| "learning_rate": 0.0001, | |
| "loss": 10.2471, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.3096774193548387, | |
| "grad_norm": 28.872024536132812, | |
| "learning_rate": 9.966191788709716e-05, | |
| "loss": 8.9676, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.4129032258064516, | |
| "grad_norm": 24.91484832763672, | |
| "learning_rate": 9.865224352899119e-05, | |
| "loss": 5.6914, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.5161290322580645, | |
| "grad_norm": 19.651994705200195, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 3.4858, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.6193548387096774, | |
| "grad_norm": 12.760610580444336, | |
| "learning_rate": 9.468163201617062e-05, | |
| "loss": 2.0323, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.7225806451612903, | |
| "grad_norm": 8.97213363647461, | |
| "learning_rate": 9.177439057064683e-05, | |
| "loss": 1.2647, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.8258064516129032, | |
| "grad_norm": 7.663300514221191, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 1.0998, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.9290322580645162, | |
| "grad_norm": 4.413909912109375, | |
| "learning_rate": 8.43120818934367e-05, | |
| "loss": 0.8302, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 1.096774193548387, | |
| "grad_norm": 7.911396503448486, | |
| "learning_rate": 7.985792958513931e-05, | |
| "loss": 1.5907, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 1.8574804067611694, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.8178, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.303225806451613, | |
| "grad_norm": 2.2993381023406982, | |
| "learning_rate": 6.980398830195785e-05, | |
| "loss": 0.7621, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.4064516129032258, | |
| "grad_norm": 1.3951315879821777, | |
| "learning_rate": 6.434016163555452e-05, | |
| "loss": 0.8151, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.5096774193548388, | |
| "grad_norm": 1.6730773448944092, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 0.7631, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.6129032258064515, | |
| "grad_norm": 2.9503276348114014, | |
| "learning_rate": 5.290724144552379e-05, | |
| "loss": 0.831, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.7161290322580647, | |
| "grad_norm": 2.8496549129486084, | |
| "learning_rate": 4.709275855447621e-05, | |
| "loss": 0.7962, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.8193548387096774, | |
| "grad_norm": 2.765697479248047, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 0.7946, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.9225806451612903, | |
| "grad_norm": 2.062514066696167, | |
| "learning_rate": 3.5659838364445505e-05, | |
| "loss": 0.7552, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 2.0903225806451613, | |
| "grad_norm": 5.532806396484375, | |
| "learning_rate": 3.019601169804216e-05, | |
| "loss": 1.3519, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 2.193548387096774, | |
| "grad_norm": 1.1353923082351685, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.7581, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.296774193548387, | |
| "grad_norm": 1.3633109331130981, | |
| "learning_rate": 2.0142070414860704e-05, | |
| "loss": 0.7257, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "grad_norm": 3.0388028621673584, | |
| "learning_rate": 1.5687918106563326e-05, | |
| "loss": 0.8124, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 2.5032258064516126, | |
| "grad_norm": 1.115830421447754, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 0.7593, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.606451612903226, | |
| "grad_norm": 3.475860118865967, | |
| "learning_rate": 8.225609429353187e-06, | |
| "loss": 0.8125, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.709677419354839, | |
| "grad_norm": 1.7441613674163818, | |
| "learning_rate": 5.318367983829392e-06, | |
| "loss": 0.787, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.709677419354839, | |
| "eval_loss": 0.7155137062072754, | |
| "eval_runtime": 1.3781, | |
| "eval_samples_per_second": 47.165, | |
| "eval_steps_per_second": 6.531, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.8129032258064517, | |
| "grad_norm": 1.4053550958633423, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 0.8174, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.9161290322580644, | |
| "grad_norm": 2.1084353923797607, | |
| "learning_rate": 1.3477564710088098e-06, | |
| "loss": 0.7691, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 3.0838709677419356, | |
| "grad_norm": 5.000555515289307, | |
| "learning_rate": 3.380821129028489e-07, | |
| "loss": 1.2892, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 3.1870967741935483, | |
| "grad_norm": 2.501575469970703, | |
| "learning_rate": 0.0, | |
| "loss": 0.8028, | |
| "step": 29 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 29, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "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": 4.541648635271578e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |