| { | |
| "best_metric": 1.6733660697937012, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.03772161448509996, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007544322897019992, | |
| "grad_norm": 28.675323486328125, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 8.4345, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007544322897019992, | |
| "eval_loss": 2.208278179168701, | |
| "eval_runtime": 221.7168, | |
| "eval_samples_per_second": 10.071, | |
| "eval_steps_per_second": 5.038, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0015088645794039985, | |
| "grad_norm": 29.8911190032959, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 7.8978, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.002263296869105998, | |
| "grad_norm": 25.677209854125977, | |
| "learning_rate": 1e-05, | |
| "loss": 8.1437, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003017729158807997, | |
| "grad_norm": 29.33332061767578, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 8.1284, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003772161448509996, | |
| "grad_norm": 22.953279495239258, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 7.5246, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004526593738211996, | |
| "grad_norm": 24.480426788330078, | |
| "learning_rate": 2e-05, | |
| "loss": 7.4452, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005281026027913994, | |
| "grad_norm": 18.336746215820312, | |
| "learning_rate": 2.3333333333333336e-05, | |
| "loss": 6.855, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.006035458317615994, | |
| "grad_norm": 14.812328338623047, | |
| "learning_rate": 2.6666666666666667e-05, | |
| "loss": 6.3316, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0067898906073179935, | |
| "grad_norm": 14.74028205871582, | |
| "learning_rate": 3e-05, | |
| "loss": 6.8076, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.007544322897019992, | |
| "grad_norm": 15.624900817871094, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 6.6817, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.008298755186721992, | |
| "grad_norm": 13.134078025817871, | |
| "learning_rate": 3.6666666666666666e-05, | |
| "loss": 6.5695, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.009053187476423991, | |
| "grad_norm": 11.790728569030762, | |
| "learning_rate": 4e-05, | |
| "loss": 6.0311, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00980761976612599, | |
| "grad_norm": 13.062444686889648, | |
| "learning_rate": 4.3333333333333334e-05, | |
| "loss": 6.5594, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.010562052055827989, | |
| "grad_norm": 11.395371437072754, | |
| "learning_rate": 4.666666666666667e-05, | |
| "loss": 6.4936, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.011316484345529988, | |
| "grad_norm": 13.467660903930664, | |
| "learning_rate": 5e-05, | |
| "loss": 6.3229, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.012070916635231988, | |
| "grad_norm": 12.771601676940918, | |
| "learning_rate": 5.333333333333333e-05, | |
| "loss": 6.7069, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.012825348924933987, | |
| "grad_norm": 13.968463897705078, | |
| "learning_rate": 5.666666666666667e-05, | |
| "loss": 6.5837, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.013579781214635987, | |
| "grad_norm": 12.743508338928223, | |
| "learning_rate": 6e-05, | |
| "loss": 6.6322, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.014334213504337986, | |
| "grad_norm": 10.325510025024414, | |
| "learning_rate": 6.333333333333333e-05, | |
| "loss": 6.4495, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.015088645794039984, | |
| "grad_norm": 10.890840530395508, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 6.0026, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.015843078083741986, | |
| "grad_norm": 10.725335121154785, | |
| "learning_rate": 7e-05, | |
| "loss": 6.0757, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.016597510373443983, | |
| "grad_norm": 12.592613220214844, | |
| "learning_rate": 7.333333333333333e-05, | |
| "loss": 5.9807, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01735194266314598, | |
| "grad_norm": 11.364941596984863, | |
| "learning_rate": 7.666666666666667e-05, | |
| "loss": 5.5821, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.018106374952847983, | |
| "grad_norm": 12.720358848571777, | |
| "learning_rate": 8e-05, | |
| "loss": 5.9976, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01886080724254998, | |
| "grad_norm": 13.64416790008545, | |
| "learning_rate": 8.333333333333334e-05, | |
| "loss": 6.1231, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01961523953225198, | |
| "grad_norm": 11.732402801513672, | |
| "learning_rate": 8.666666666666667e-05, | |
| "loss": 5.9014, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.02036967182195398, | |
| "grad_norm": 11.253823280334473, | |
| "learning_rate": 9e-05, | |
| "loss": 6.1194, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.021124104111655977, | |
| "grad_norm": 12.609724998474121, | |
| "learning_rate": 9.333333333333334e-05, | |
| "loss": 6.3912, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.02187853640135798, | |
| "grad_norm": 17.590932846069336, | |
| "learning_rate": 9.666666666666667e-05, | |
| "loss": 6.2529, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.022632968691059976, | |
| "grad_norm": 11.86485767364502, | |
| "learning_rate": 0.0001, | |
| "loss": 6.0362, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.023387400980761978, | |
| "grad_norm": 11.341562271118164, | |
| "learning_rate": 9.999146252290264e-05, | |
| "loss": 5.7276, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.024141833270463976, | |
| "grad_norm": 12.26652717590332, | |
| "learning_rate": 9.996585300715116e-05, | |
| "loss": 5.598, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.024896265560165973, | |
| "grad_norm": 11.066813468933105, | |
| "learning_rate": 9.99231801983717e-05, | |
| "loss": 6.3367, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.025650697849867975, | |
| "grad_norm": 13.498788833618164, | |
| "learning_rate": 9.986345866928941e-05, | |
| "loss": 5.407, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.026405130139569973, | |
| "grad_norm": 9.877449035644531, | |
| "learning_rate": 9.978670881475172e-05, | |
| "loss": 5.6733, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.027159562429271974, | |
| "grad_norm": 10.806673049926758, | |
| "learning_rate": 9.96929568447637e-05, | |
| "loss": 5.4878, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.02791399471897397, | |
| "grad_norm": 9.050161361694336, | |
| "learning_rate": 9.958223477553714e-05, | |
| "loss": 5.2645, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.028668427008675973, | |
| "grad_norm": 11.107382774353027, | |
| "learning_rate": 9.94545804185573e-05, | |
| "loss": 5.0922, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.02942285929837797, | |
| "grad_norm": 11.42280101776123, | |
| "learning_rate": 9.931003736767013e-05, | |
| "loss": 6.2962, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.03017729158807997, | |
| "grad_norm": 11.97855281829834, | |
| "learning_rate": 9.91486549841951e-05, | |
| "loss": 5.7078, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03093172387778197, | |
| "grad_norm": 12.64185905456543, | |
| "learning_rate": 9.89704883800683e-05, | |
| "loss": 5.2872, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.03168615616748397, | |
| "grad_norm": 10.183547973632812, | |
| "learning_rate": 9.877559839902184e-05, | |
| "loss": 5.02, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.03244058845718597, | |
| "grad_norm": 9.924983978271484, | |
| "learning_rate": 9.85640515958057e-05, | |
| "loss": 4.922, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.03319502074688797, | |
| "grad_norm": 10.258749961853027, | |
| "learning_rate": 9.833592021345937e-05, | |
| "loss": 5.0618, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.033949453036589965, | |
| "grad_norm": 11.61485481262207, | |
| "learning_rate": 9.809128215864097e-05, | |
| "loss": 4.4817, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.03470388532629196, | |
| "grad_norm": 11.918696403503418, | |
| "learning_rate": 9.783022097502204e-05, | |
| "loss": 4.2096, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.03545831761599397, | |
| "grad_norm": 13.742955207824707, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 3.9376, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.036212749905695965, | |
| "grad_norm": 12.087013244628906, | |
| "learning_rate": 9.725919140804099e-05, | |
| "loss": 3.4829, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.03696718219539796, | |
| "grad_norm": 9.929948806762695, | |
| "learning_rate": 9.694941803075283e-05, | |
| "loss": 1.3657, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.03772161448509996, | |
| "grad_norm": 14.584424018859863, | |
| "learning_rate": 9.662361147021779e-05, | |
| "loss": 2.7382, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03772161448509996, | |
| "eval_loss": 1.6733660697937012, | |
| "eval_runtime": 223.1506, | |
| "eval_samples_per_second": 10.007, | |
| "eval_steps_per_second": 5.006, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.190764995162931e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |