| { | |
| "best_metric": 2.6525354385375977, | |
| "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": 12.477754592895508, | |
| "learning_rate": 5e-05, | |
| "loss": 36.282, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07476635514018691, | |
| "eval_loss": 3.060811758041382, | |
| "eval_runtime": 0.2235, | |
| "eval_samples_per_second": 402.634, | |
| "eval_steps_per_second": 53.685, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.14953271028037382, | |
| "grad_norm": 20.176923751831055, | |
| "learning_rate": 0.0001, | |
| "loss": 42.7203, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.22429906542056074, | |
| "grad_norm": 58.305416107177734, | |
| "learning_rate": 9.983786540671051e-05, | |
| "loss": 55.9882, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.29906542056074764, | |
| "grad_norm": 43.69650650024414, | |
| "learning_rate": 9.935251313189564e-05, | |
| "loss": 46.6822, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.37383177570093457, | |
| "grad_norm": 11.199535369873047, | |
| "learning_rate": 9.85470908713026e-05, | |
| "loss": 39.1852, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.4485981308411215, | |
| "grad_norm": 38.89397430419922, | |
| "learning_rate": 9.742682209735727e-05, | |
| "loss": 49.5955, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.5233644859813084, | |
| "grad_norm": 61.32236862182617, | |
| "learning_rate": 9.599897218294122e-05, | |
| "loss": 53.197, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.5981308411214953, | |
| "grad_norm": 12.756400108337402, | |
| "learning_rate": 9.42728012826605e-05, | |
| "loss": 37.8893, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.6728971962616822, | |
| "grad_norm": 21.473352432250977, | |
| "learning_rate": 9.225950427718975e-05, | |
| "loss": 44.1805, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.7476635514018691, | |
| "grad_norm": 56.127567291259766, | |
| "learning_rate": 8.997213817017507e-05, | |
| "loss": 51.3801, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.822429906542056, | |
| "grad_norm": 14.02192211151123, | |
| "learning_rate": 8.742553740855506e-05, | |
| "loss": 37.1142, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.897196261682243, | |
| "grad_norm": 17.666357040405273, | |
| "learning_rate": 8.463621767547998e-05, | |
| "loss": 41.9052, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.9719626168224299, | |
| "grad_norm": 46.62154769897461, | |
| "learning_rate": 8.162226877976887e-05, | |
| "loss": 54.8154, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.0467289719626167, | |
| "grad_norm": 17.347009658813477, | |
| "learning_rate": 7.840323733655778e-05, | |
| "loss": 38.5423, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.1214953271028036, | |
| "grad_norm": 15.314298629760742, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 38.654, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.1962616822429906, | |
| "grad_norm": 18.701488494873047, | |
| "learning_rate": 7.143462807015271e-05, | |
| "loss": 43.01, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.2710280373831775, | |
| "grad_norm": 38.01932907104492, | |
| "learning_rate": 6.773024435212678e-05, | |
| "loss": 47.2544, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.3457943925233644, | |
| "grad_norm": 12.378190994262695, | |
| "learning_rate": 6.391087319582264e-05, | |
| "loss": 37.0581, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.4205607476635513, | |
| "grad_norm": 15.580528259277344, | |
| "learning_rate": 6.0001284688802226e-05, | |
| "loss": 43.4861, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.4953271028037383, | |
| "grad_norm": 45.35871124267578, | |
| "learning_rate": 5.602683401276615e-05, | |
| "loss": 48.2524, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.5700934579439252, | |
| "grad_norm": 10.084379196166992, | |
| "learning_rate": 5.201329700547076e-05, | |
| "loss": 35.6121, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.644859813084112, | |
| "grad_norm": 14.362281799316406, | |
| "learning_rate": 4.798670299452926e-05, | |
| "loss": 40.7834, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.719626168224299, | |
| "grad_norm": 35.394142150878906, | |
| "learning_rate": 4.397316598723385e-05, | |
| "loss": 47.5074, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.794392523364486, | |
| "grad_norm": 28.203998565673828, | |
| "learning_rate": 3.9998715311197785e-05, | |
| "loss": 40.5831, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.8691588785046729, | |
| "grad_norm": 12.237970352172852, | |
| "learning_rate": 3.608912680417737e-05, | |
| "loss": 38.2899, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.8691588785046729, | |
| "eval_loss": 2.6525354385375977, | |
| "eval_runtime": 0.2206, | |
| "eval_samples_per_second": 408.063, | |
| "eval_steps_per_second": 54.408, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.9439252336448598, | |
| "grad_norm": 24.12892723083496, | |
| "learning_rate": 3.226975564787322e-05, | |
| "loss": 45.5854, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.0186915887850465, | |
| "grad_norm": 37.78959655761719, | |
| "learning_rate": 2.8565371929847284e-05, | |
| "loss": 44.6516, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.0934579439252334, | |
| "grad_norm": 8.680986404418945, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 35.3207, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.1682242990654204, | |
| "grad_norm": 15.282751083374023, | |
| "learning_rate": 2.1596762663442218e-05, | |
| "loss": 40.6217, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.2429906542056073, | |
| "grad_norm": 46.95691680908203, | |
| "learning_rate": 1.837773122023114e-05, | |
| "loss": 48.1315, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.317757009345794, | |
| "grad_norm": 8.166537284851074, | |
| "learning_rate": 1.536378232452003e-05, | |
| "loss": 34.1442, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.392523364485981, | |
| "grad_norm": 12.032683372497559, | |
| "learning_rate": 1.257446259144494e-05, | |
| "loss": 38.6735, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.467289719626168, | |
| "grad_norm": 26.102218627929688, | |
| "learning_rate": 1.0027861829824952e-05, | |
| "loss": 46.4967, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.542056074766355, | |
| "grad_norm": 23.399124145507812, | |
| "learning_rate": 7.740495722810271e-06, | |
| "loss": 39.0796, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.616822429906542, | |
| "grad_norm": 10.58754825592041, | |
| "learning_rate": 5.727198717339511e-06, | |
| "loss": 38.4049, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.691588785046729, | |
| "grad_norm": 20.302406311035156, | |
| "learning_rate": 4.001027817058789e-06, | |
| "loss": 43.2738, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.7663551401869158, | |
| "grad_norm": 41.23537063598633, | |
| "learning_rate": 2.573177902642726e-06, | |
| "loss": 46.7631, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.8411214953271027, | |
| "grad_norm": 9.360715866088867, | |
| "learning_rate": 1.4529091286973995e-06, | |
| "loss": 37.2748, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.9158878504672896, | |
| "grad_norm": 15.773098945617676, | |
| "learning_rate": 6.474868681043578e-07, | |
| "loss": 41.8172, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.9906542056074765, | |
| "grad_norm": 44.15718078613281, | |
| "learning_rate": 1.6213459328950352e-07, | |
| "loss": 47.5584, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 3.0654205607476634, | |
| "grad_norm": 11.734289169311523, | |
| "learning_rate": 0.0, | |
| "loss": 35.6847, | |
| "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": 5827368409104384.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |