| { | |
| "best_metric": 1.336300015449524, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 3.0654205607476634, | |
| "eval_steps": 25, | |
| "global_step": 41, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07476635514018691, | |
| "grad_norm": 1.0299956798553467, | |
| "learning_rate": 5e-05, | |
| "loss": 1.8481, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07476635514018691, | |
| "eval_loss": 1.9835611581802368, | |
| "eval_runtime": 5.7638, | |
| "eval_samples_per_second": 15.615, | |
| "eval_steps_per_second": 2.082, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.14953271028037382, | |
| "grad_norm": 1.4739512205123901, | |
| "learning_rate": 0.0001, | |
| "loss": 2.1583, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.22429906542056074, | |
| "grad_norm": 1.7936453819274902, | |
| "learning_rate": 9.983786540671051e-05, | |
| "loss": 2.1667, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.29906542056074764, | |
| "grad_norm": 0.6038073301315308, | |
| "learning_rate": 9.935251313189564e-05, | |
| "loss": 1.7027, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.37383177570093457, | |
| "grad_norm": 0.8746582865715027, | |
| "learning_rate": 9.85470908713026e-05, | |
| "loss": 1.7715, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.4485981308411215, | |
| "grad_norm": 1.1661409139633179, | |
| "learning_rate": 9.742682209735727e-05, | |
| "loss": 1.6901, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.5233644859813084, | |
| "grad_norm": 0.736312985420227, | |
| "learning_rate": 9.599897218294122e-05, | |
| "loss": 1.7535, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.5981308411214953, | |
| "grad_norm": 0.3984752893447876, | |
| "learning_rate": 9.42728012826605e-05, | |
| "loss": 1.5095, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.6728971962616822, | |
| "grad_norm": 1.0699872970581055, | |
| "learning_rate": 9.225950427718975e-05, | |
| "loss": 1.4176, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.7476635514018691, | |
| "grad_norm": 0.3961038887500763, | |
| "learning_rate": 8.997213817017507e-05, | |
| "loss": 1.7064, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.822429906542056, | |
| "grad_norm": 0.36805129051208496, | |
| "learning_rate": 8.742553740855506e-05, | |
| "loss": 1.4594, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.897196261682243, | |
| "grad_norm": 0.5991771221160889, | |
| "learning_rate": 8.463621767547998e-05, | |
| "loss": 1.4557, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.9719626168224299, | |
| "grad_norm": 0.7024437785148621, | |
| "learning_rate": 8.162226877976887e-05, | |
| "loss": 1.4328, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.0467289719626167, | |
| "grad_norm": 0.9319255352020264, | |
| "learning_rate": 7.840323733655778e-05, | |
| "loss": 2.7365, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.1214953271028036, | |
| "grad_norm": 0.6409429907798767, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.3024, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.1962616822429906, | |
| "grad_norm": 0.7907724380493164, | |
| "learning_rate": 7.143462807015271e-05, | |
| "loss": 1.2344, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.2710280373831775, | |
| "grad_norm": 0.46261414885520935, | |
| "learning_rate": 6.773024435212678e-05, | |
| "loss": 1.5109, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.3457943925233644, | |
| "grad_norm": 0.5007185339927673, | |
| "learning_rate": 6.391087319582264e-05, | |
| "loss": 1.4954, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.4205607476635513, | |
| "grad_norm": 0.7378676533699036, | |
| "learning_rate": 6.0001284688802226e-05, | |
| "loss": 1.1935, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.4953271028037383, | |
| "grad_norm": 0.39340218901634216, | |
| "learning_rate": 5.602683401276615e-05, | |
| "loss": 1.1742, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.5700934579439252, | |
| "grad_norm": 0.46088534593582153, | |
| "learning_rate": 5.201329700547076e-05, | |
| "loss": 1.738, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.644859813084112, | |
| "grad_norm": 0.5656598210334778, | |
| "learning_rate": 4.798670299452926e-05, | |
| "loss": 1.2124, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.719626168224299, | |
| "grad_norm": 0.20644834637641907, | |
| "learning_rate": 4.397316598723385e-05, | |
| "loss": 0.4425, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.794392523364486, | |
| "grad_norm": 0.46902337670326233, | |
| "learning_rate": 3.9998715311197785e-05, | |
| "loss": 2.6494, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.8691588785046729, | |
| "grad_norm": 0.5184024572372437, | |
| "learning_rate": 3.608912680417737e-05, | |
| "loss": 1.2957, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.8691588785046729, | |
| "eval_loss": 1.336300015449524, | |
| "eval_runtime": 5.7765, | |
| "eval_samples_per_second": 15.58, | |
| "eval_steps_per_second": 2.077, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.9439252336448598, | |
| "grad_norm": 0.7272557616233826, | |
| "learning_rate": 3.226975564787322e-05, | |
| "loss": 1.2889, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.0186915887850465, | |
| "grad_norm": 0.5690138936042786, | |
| "learning_rate": 2.8565371929847284e-05, | |
| "loss": 2.5088, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.0934579439252334, | |
| "grad_norm": 0.3526255488395691, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.2991, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.1682242990654204, | |
| "grad_norm": 0.47234588861465454, | |
| "learning_rate": 2.1596762663442218e-05, | |
| "loss": 1.1887, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.2429906542056073, | |
| "grad_norm": 0.384577214717865, | |
| "learning_rate": 1.837773122023114e-05, | |
| "loss": 0.7942, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.317757009345794, | |
| "grad_norm": 0.3493711054325104, | |
| "learning_rate": 1.536378232452003e-05, | |
| "loss": 2.081, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.392523364485981, | |
| "grad_norm": 0.4692765176296234, | |
| "learning_rate": 1.257446259144494e-05, | |
| "loss": 1.1978, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.467289719626168, | |
| "grad_norm": 0.31681570410728455, | |
| "learning_rate": 1.0027861829824952e-05, | |
| "loss": 0.9036, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.542056074766355, | |
| "grad_norm": 0.36259856820106506, | |
| "learning_rate": 7.740495722810271e-06, | |
| "loss": 1.9976, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.616822429906542, | |
| "grad_norm": 0.384077787399292, | |
| "learning_rate": 5.727198717339511e-06, | |
| "loss": 1.332, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.691588785046729, | |
| "grad_norm": 0.27743789553642273, | |
| "learning_rate": 4.001027817058789e-06, | |
| "loss": 0.7633, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.7663551401869158, | |
| "grad_norm": 0.32165083289146423, | |
| "learning_rate": 2.573177902642726e-06, | |
| "loss": 2.0513, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.8411214953271027, | |
| "grad_norm": 0.39092400670051575, | |
| "learning_rate": 1.4529091286973995e-06, | |
| "loss": 1.1744, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.9158878504672896, | |
| "grad_norm": 0.47860899567604065, | |
| "learning_rate": 6.474868681043578e-07, | |
| "loss": 1.1507, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.9906542056074765, | |
| "grad_norm": 1.0024253129959106, | |
| "learning_rate": 1.6213459328950352e-07, | |
| "loss": 1.9473, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 3.0654205607476634, | |
| "grad_norm": 0.37559443712234497, | |
| "learning_rate": 0.0, | |
| "loss": 1.7136, | |
| "step": 41 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 41, | |
| "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": 8.614183290158449e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |