| { | |
| "best_metric": 1.4689046144485474, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 3.0285714285714285, | |
| "eval_steps": 50, | |
| "global_step": 53, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05714285714285714, | |
| "grad_norm": 6.932616233825684, | |
| "learning_rate": 1e-05, | |
| "loss": 2.647, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05714285714285714, | |
| "eval_loss": 3.8393256664276123, | |
| "eval_runtime": 0.5253, | |
| "eval_samples_per_second": 57.107, | |
| "eval_steps_per_second": 15.229, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.11428571428571428, | |
| "grad_norm": 17.747432708740234, | |
| "learning_rate": 2e-05, | |
| "loss": 3.1974, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.17142857142857143, | |
| "grad_norm": 50.56644058227539, | |
| "learning_rate": 3e-05, | |
| "loss": 5.3134, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.22857142857142856, | |
| "grad_norm": 39.969383239746094, | |
| "learning_rate": 4e-05, | |
| "loss": 5.3661, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.2857142857142857, | |
| "grad_norm": 2.693161964416504, | |
| "learning_rate": 5e-05, | |
| "loss": 2.3584, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.34285714285714286, | |
| "grad_norm": 3.9389383792877197, | |
| "learning_rate": 6e-05, | |
| "loss": 2.494, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 16.83061981201172, | |
| "learning_rate": 7e-05, | |
| "loss": 4.4394, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.45714285714285713, | |
| "grad_norm": 17.723873138427734, | |
| "learning_rate": 8e-05, | |
| "loss": 4.5342, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.5142857142857142, | |
| "grad_norm": 1.7711833715438843, | |
| "learning_rate": 9e-05, | |
| "loss": 2.152, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 2.3844153881073, | |
| "learning_rate": 0.0001, | |
| "loss": 2.1481, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.6285714285714286, | |
| "grad_norm": 5.348583698272705, | |
| "learning_rate": 9.986661418317759e-05, | |
| "loss": 2.2778, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.6857142857142857, | |
| "grad_norm": 11.029891967773438, | |
| "learning_rate": 9.946716840375551e-05, | |
| "loss": 3.0457, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.7428571428571429, | |
| "grad_norm": 1.6746666431427002, | |
| "learning_rate": 9.880379387779637e-05, | |
| "loss": 1.8864, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 2.1320276260375977, | |
| "learning_rate": 9.78800299954203e-05, | |
| "loss": 1.8959, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.8571428571428571, | |
| "grad_norm": 4.286759376525879, | |
| "learning_rate": 9.67008054366274e-05, | |
| "loss": 1.9878, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.9142857142857143, | |
| "grad_norm": 5.656648635864258, | |
| "learning_rate": 9.527241187465734e-05, | |
| "loss": 1.7362, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.9714285714285714, | |
| "grad_norm": 2.024832248687744, | |
| "learning_rate": 9.360247040719039e-05, | |
| "loss": 1.8654, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.0285714285714285, | |
| "grad_norm": 6.288355350494385, | |
| "learning_rate": 9.16998908944939e-05, | |
| "loss": 2.447, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.0857142857142856, | |
| "grad_norm": 1.7026642560958862, | |
| "learning_rate": 8.957482442146272e-05, | |
| "loss": 1.6209, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.1428571428571428, | |
| "grad_norm": 3.0923917293548584, | |
| "learning_rate": 8.72386091371891e-05, | |
| "loss": 1.6806, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 3.1564972400665283, | |
| "learning_rate": 8.47037097610317e-05, | |
| "loss": 0.9157, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.2571428571428571, | |
| "grad_norm": 3.0172536373138428, | |
| "learning_rate": 8.198365107794457e-05, | |
| "loss": 1.6018, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.3142857142857143, | |
| "grad_norm": 1.6614283323287964, | |
| "learning_rate": 7.909294577789766e-05, | |
| "loss": 1.4801, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.3714285714285714, | |
| "grad_norm": 2.370166301727295, | |
| "learning_rate": 7.604701702439651e-05, | |
| "loss": 1.2607, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.4285714285714286, | |
| "grad_norm": 3.243105888366699, | |
| "learning_rate": 7.286211616523193e-05, | |
| "loss": 0.8806, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.4857142857142858, | |
| "grad_norm": 4.326461315155029, | |
| "learning_rate": 6.95552360245078e-05, | |
| "loss": 1.4185, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.5428571428571427, | |
| "grad_norm": 1.7340881824493408, | |
| "learning_rate": 6.614402023857232e-05, | |
| "loss": 1.5775, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 2.532961130142212, | |
| "learning_rate": 6.264666911958404e-05, | |
| "loss": 0.929, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.657142857142857, | |
| "grad_norm": 3.551696300506592, | |
| "learning_rate": 5.908184254897182e-05, | |
| "loss": 1.0279, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.7142857142857144, | |
| "grad_norm": 2.457855224609375, | |
| "learning_rate": 5.546856041889373e-05, | |
| "loss": 1.4616, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.7714285714285714, | |
| "grad_norm": 1.8725690841674805, | |
| "learning_rate": 5.182610115288295e-05, | |
| "loss": 1.4615, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.8285714285714287, | |
| "grad_norm": 2.7832159996032715, | |
| "learning_rate": 4.817389884711705e-05, | |
| "loss": 1.3045, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.8857142857142857, | |
| "grad_norm": 3.263268232345581, | |
| "learning_rate": 4.4531439581106295e-05, | |
| "loss": 1.0625, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.9428571428571428, | |
| "grad_norm": 2.7395882606506348, | |
| "learning_rate": 4.0918157451028185e-05, | |
| "loss": 1.7622, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 4.847479820251465, | |
| "learning_rate": 3.735333088041596e-05, | |
| "loss": 1.075, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.057142857142857, | |
| "grad_norm": 1.2119523286819458, | |
| "learning_rate": 3.38559797614277e-05, | |
| "loss": 1.4441, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.1142857142857143, | |
| "grad_norm": 1.40659499168396, | |
| "learning_rate": 3.0444763975492208e-05, | |
| "loss": 1.1611, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.1714285714285713, | |
| "grad_norm": 2.3333632946014404, | |
| "learning_rate": 2.7137883834768073e-05, | |
| "loss": 1.0877, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.2285714285714286, | |
| "grad_norm": 2.755831718444824, | |
| "learning_rate": 2.3952982975603496e-05, | |
| "loss": 0.6574, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.2857142857142856, | |
| "grad_norm": 1.1510668992996216, | |
| "learning_rate": 2.090705422210237e-05, | |
| "loss": 1.4219, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.342857142857143, | |
| "grad_norm": 1.7422624826431274, | |
| "learning_rate": 1.801634892205545e-05, | |
| "loss": 1.1363, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "grad_norm": 2.6333487033843994, | |
| "learning_rate": 1.5296290238968303e-05, | |
| "loss": 0.6638, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.4571428571428573, | |
| "grad_norm": 4.440356731414795, | |
| "learning_rate": 1.2761390862810907e-05, | |
| "loss": 0.7639, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.5142857142857142, | |
| "grad_norm": 1.131514072418213, | |
| "learning_rate": 1.0425175578537299e-05, | |
| "loss": 1.3823, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.571428571428571, | |
| "grad_norm": 1.678874135017395, | |
| "learning_rate": 8.30010910550611e-06, | |
| "loss": 1.1248, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.6285714285714286, | |
| "grad_norm": 2.462118148803711, | |
| "learning_rate": 6.397529592809614e-06, | |
| "loss": 0.8621, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.685714285714286, | |
| "grad_norm": 3.6006405353546143, | |
| "learning_rate": 4.727588125342669e-06, | |
| "loss": 0.6778, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.742857142857143, | |
| "grad_norm": 1.086060881614685, | |
| "learning_rate": 3.299194563372604e-06, | |
| "loss": 1.3137, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "grad_norm": 1.4581565856933594, | |
| "learning_rate": 2.1199700045797077e-06, | |
| "loss": 1.1256, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.857142857142857, | |
| "grad_norm": 1.9829723834991455, | |
| "learning_rate": 1.196206122203647e-06, | |
| "loss": 1.006, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.857142857142857, | |
| "eval_loss": 1.4689046144485474, | |
| "eval_runtime": 0.5247, | |
| "eval_samples_per_second": 57.17, | |
| "eval_steps_per_second": 15.245, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.914285714285714, | |
| "grad_norm": 3.166837215423584, | |
| "learning_rate": 5.328315962444874e-07, | |
| "loss": 0.8571, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 2.9714285714285715, | |
| "grad_norm": 1.184228539466858, | |
| "learning_rate": 1.333858168224178e-07, | |
| "loss": 1.1258, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 3.0285714285714285, | |
| "grad_norm": 4.288901329040527, | |
| "learning_rate": 0.0, | |
| "loss": 1.5266, | |
| "step": 53 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 53, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "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": 3497938460344320.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |