| { | |
| "best_metric": 0.9007372856140137, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.328654004954583, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.026424442609413706, | |
| "grad_norm": 1.2801134586334229, | |
| "learning_rate": 5e-05, | |
| "loss": 1.4454, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.026424442609413706, | |
| "eval_loss": 1.7167054414749146, | |
| "eval_runtime": 14.545, | |
| "eval_samples_per_second": 35.063, | |
| "eval_steps_per_second": 4.4, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05284888521882741, | |
| "grad_norm": 1.4502079486846924, | |
| "learning_rate": 0.0001, | |
| "loss": 1.5445, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.07927332782824112, | |
| "grad_norm": 1.228658676147461, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.4853, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.10569777043765483, | |
| "grad_norm": 0.6352747678756714, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.28, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.13212221304706853, | |
| "grad_norm": 0.9758851528167725, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.2696, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.15854665565648224, | |
| "grad_norm": 0.7691611647605896, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.2215, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.18497109826589594, | |
| "grad_norm": 0.6990065574645996, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.185, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.21139554087530965, | |
| "grad_norm": 0.6230758428573608, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.196, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.23781998348472336, | |
| "grad_norm": 0.6842356324195862, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.1017, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.26424442609413706, | |
| "grad_norm": 0.4312884211540222, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.0258, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2906688687035508, | |
| "grad_norm": 0.66916424036026, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.0451, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.3170933113129645, | |
| "grad_norm": 0.44833680987358093, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.0256, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.3435177539223782, | |
| "grad_norm": 0.4610114097595215, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.9961, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.3699421965317919, | |
| "grad_norm": 0.4431484341621399, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.9747, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.3963666391412056, | |
| "grad_norm": 0.3800238370895386, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.9763, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.4227910817506193, | |
| "grad_norm": 0.5571978092193604, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.9513, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.44921552436003304, | |
| "grad_norm": 0.5053445100784302, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.9914, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.4756399669694467, | |
| "grad_norm": 0.6664589047431946, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.9101, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.5020644095788604, | |
| "grad_norm": 0.40090277791023254, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.949, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.5284888521882741, | |
| "grad_norm": 0.3949279189109802, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.979, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.5549132947976878, | |
| "grad_norm": 0.542736828327179, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.9684, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.5813377374071016, | |
| "grad_norm": 0.36220383644104004, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.9402, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.6077621800165153, | |
| "grad_norm": 0.4769664406776428, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.9322, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.634186622625929, | |
| "grad_norm": 0.5257561206817627, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.9413, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.6606110652353427, | |
| "grad_norm": 0.26396870613098145, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.9221, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.6606110652353427, | |
| "eval_loss": 0.9185070395469666, | |
| "eval_runtime": 14.5245, | |
| "eval_samples_per_second": 35.113, | |
| "eval_steps_per_second": 4.406, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.6870355078447564, | |
| "grad_norm": 0.4967907667160034, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9383, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.7134599504541701, | |
| "grad_norm": 0.3578830063343048, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.906, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.7398843930635838, | |
| "grad_norm": 0.40701600909233093, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.9408, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.7663088356729976, | |
| "grad_norm": 0.4491502046585083, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.9597, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.7927332782824112, | |
| "grad_norm": 0.2592903673648834, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.9551, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.8191577208918249, | |
| "grad_norm": 0.1899711787700653, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.9402, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.8455821635012386, | |
| "grad_norm": 0.33069103956222534, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.9352, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.8720066061106524, | |
| "grad_norm": 0.4107014834880829, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.9186, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.8984310487200661, | |
| "grad_norm": 0.3768468201160431, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.9166, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.9248554913294798, | |
| "grad_norm": 0.1930578052997589, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.8981, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.9512799339388934, | |
| "grad_norm": 0.2350042760372162, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.8844, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.9777043765483072, | |
| "grad_norm": 0.6842407584190369, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.8483, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.0115606936416186, | |
| "grad_norm": 0.49989911913871765, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.4444, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.0379851362510322, | |
| "grad_norm": 0.23442403972148895, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.8976, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.064409578860446, | |
| "grad_norm": 0.2569376230239868, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.9354, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.0908340214698595, | |
| "grad_norm": 0.31655338406562805, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.9327, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.1172584640792733, | |
| "grad_norm": 0.27351218461990356, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.9258, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.143682906688687, | |
| "grad_norm": 0.3348250389099121, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.9264, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.1701073492981007, | |
| "grad_norm": 0.303664892911911, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.8842, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.1965317919075145, | |
| "grad_norm": 0.44823157787323, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.9372, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.2229562345169283, | |
| "grad_norm": 0.31823575496673584, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.9131, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.2493806771263418, | |
| "grad_norm": 0.2725352942943573, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.7334, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.2758051197357556, | |
| "grad_norm": 0.12976203858852386, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.0483, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.3022295623451692, | |
| "grad_norm": 0.139130100607872, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.9324, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.328654004954583, | |
| "grad_norm": 0.1179971992969513, | |
| "learning_rate": 0.0, | |
| "loss": 0.9317, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.328654004954583, | |
| "eval_loss": 0.9007372856140137, | |
| "eval_runtime": 22.3252, | |
| "eval_samples_per_second": 22.844, | |
| "eval_steps_per_second": 2.867, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 1.0518209551663104e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |