| { | |
| "best_metric": 0.3440747857093811, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.03772161448509996, | |
| "eval_steps": 25, | |
| "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": 0.8223588466644287, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2964, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007544322897019992, | |
| "eval_loss": 0.7299715876579285, | |
| "eval_runtime": 20.4964, | |
| "eval_samples_per_second": 108.946, | |
| "eval_steps_per_second": 13.661, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0015088645794039985, | |
| "grad_norm": 1.088794231414795, | |
| "learning_rate": 4e-05, | |
| "loss": 0.4161, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.002263296869105998, | |
| "grad_norm": 1.4431239366531372, | |
| "learning_rate": 6e-05, | |
| "loss": 0.6274, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003017729158807997, | |
| "grad_norm": 1.3700398206710815, | |
| "learning_rate": 8e-05, | |
| "loss": 0.7206, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003772161448509996, | |
| "grad_norm": 1.6092513799667358, | |
| "learning_rate": 0.0001, | |
| "loss": 0.6625, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004526593738211996, | |
| "grad_norm": 1.4148694276809692, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 0.7251, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005281026027913994, | |
| "grad_norm": 1.8997093439102173, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 0.8545, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.006035458317615994, | |
| "grad_norm": 1.971493124961853, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 0.8497, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0067898906073179935, | |
| "grad_norm": 1.2389086484909058, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 0.58, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.007544322897019992, | |
| "grad_norm": 1.0392647981643677, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.4611, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.008298755186721992, | |
| "grad_norm": 1.0900479555130005, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 0.4568, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.009053187476423991, | |
| "grad_norm": 1.1517574787139893, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 0.5103, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00980761976612599, | |
| "grad_norm": 0.9526758193969727, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 0.4575, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.010562052055827989, | |
| "grad_norm": 0.9867358207702637, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.398, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.011316484345529988, | |
| "grad_norm": 0.8321422934532166, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 0.2724, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.012070916635231988, | |
| "grad_norm": 1.0108206272125244, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 0.4965, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.012825348924933987, | |
| "grad_norm": 1.017204761505127, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 0.4236, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.013579781214635987, | |
| "grad_norm": 0.899462878704071, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 0.3726, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.014334213504337986, | |
| "grad_norm": 0.8204650282859802, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 0.3617, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.015088645794039984, | |
| "grad_norm": 0.8329623937606812, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.3177, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.015843078083741986, | |
| "grad_norm": 0.9018030762672424, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 0.2997, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.016597510373443983, | |
| "grad_norm": 0.8355438709259033, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 0.3515, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01735194266314598, | |
| "grad_norm": 0.9412809610366821, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.4312, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.018106374952847983, | |
| "grad_norm": 0.73044753074646, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 0.2784, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01886080724254998, | |
| "grad_norm": 0.7530535459518433, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 0.2902, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01886080724254998, | |
| "eval_loss": 0.37233537435531616, | |
| "eval_runtime": 20.5074, | |
| "eval_samples_per_second": 108.887, | |
| "eval_steps_per_second": 13.654, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01961523953225198, | |
| "grad_norm": 0.7938961982727051, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 0.3513, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.02036967182195398, | |
| "grad_norm": 0.8030672669410706, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 0.2866, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.021124104111655977, | |
| "grad_norm": 0.8801215887069702, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 0.3616, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.02187853640135798, | |
| "grad_norm": 0.9829353094100952, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 0.3993, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.022632968691059976, | |
| "grad_norm": 0.8574352860450745, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 0.2965, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.023387400980761978, | |
| "grad_norm": 0.7809247970581055, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 0.3002, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.024141833270463976, | |
| "grad_norm": 0.7082892060279846, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.2101, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.024896265560165973, | |
| "grad_norm": 0.9846978187561035, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 0.3058, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.025650697849867975, | |
| "grad_norm": 0.7955850958824158, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 0.3272, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.026405130139569973, | |
| "grad_norm": 0.7140681743621826, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.204, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.027159562429271974, | |
| "grad_norm": 0.8312026262283325, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 0.3197, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.02791399471897397, | |
| "grad_norm": 0.8541383147239685, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 0.2884, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.028668427008675973, | |
| "grad_norm": 1.0792609453201294, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 0.4163, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.02942285929837797, | |
| "grad_norm": 0.9184907078742981, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 0.2996, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.03017729158807997, | |
| "grad_norm": 0.8710076808929443, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 0.3139, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03093172387778197, | |
| "grad_norm": 0.8901832103729248, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.2985, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.03168615616748397, | |
| "grad_norm": 1.0949760675430298, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 0.3072, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.03244058845718597, | |
| "grad_norm": 0.9372459650039673, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 0.3261, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.03319502074688797, | |
| "grad_norm": 1.1750974655151367, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 0.3653, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.033949453036589965, | |
| "grad_norm": 0.986308217048645, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 0.2915, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.03470388532629196, | |
| "grad_norm": 1.1063377857208252, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 0.355, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.03545831761599397, | |
| "grad_norm": 1.3662513494491577, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 0.4044, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.036212749905695965, | |
| "grad_norm": 1.5466667413711548, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 0.4211, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.03696718219539796, | |
| "grad_norm": 1.8994237184524536, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 0.3196, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.03772161448509996, | |
| "grad_norm": 3.1757965087890625, | |
| "learning_rate": 0.0, | |
| "loss": 0.5837, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03772161448509996, | |
| "eval_loss": 0.3440747857093811, | |
| "eval_runtime": 20.4759, | |
| "eval_samples_per_second": 109.055, | |
| "eval_steps_per_second": 13.675, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "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": 1999744829227008.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |