| { | |
| "best_metric": 1.0076379776000977, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.02781157656874674, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005562315313749349, | |
| "grad_norm": 0.1657542884349823, | |
| "learning_rate": 5e-05, | |
| "loss": 0.4995, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005562315313749349, | |
| "eval_loss": 1.4900273084640503, | |
| "eval_runtime": 138.2121, | |
| "eval_samples_per_second": 87.633, | |
| "eval_steps_per_second": 10.954, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0011124630627498697, | |
| "grad_norm": 0.2748042643070221, | |
| "learning_rate": 0.0001, | |
| "loss": 0.7094, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0016686945941248046, | |
| "grad_norm": 0.27427706122398376, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 0.7878, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0022249261254997394, | |
| "grad_norm": 0.1776735633611679, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.6785, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0027811576568746743, | |
| "grad_norm": 0.20435677468776703, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.7492, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.003337389188249609, | |
| "grad_norm": 0.2518686056137085, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.7544, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0038936207196245435, | |
| "grad_norm": 0.2997715175151825, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.0074, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.004449852250999479, | |
| "grad_norm": 0.40672293305397034, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.2292, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.005006083782374413, | |
| "grad_norm": 0.6158118844032288, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.3492, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0055623153137493485, | |
| "grad_norm": 0.8367748260498047, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.3936, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006118546845124283, | |
| "grad_norm": 0.7799615263938904, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.5371, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.006674778376499218, | |
| "grad_norm": 1.3306225538253784, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.7766, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.007231009907874153, | |
| "grad_norm": 0.28293538093566895, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.3871, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.007787241439249087, | |
| "grad_norm": 0.48717114329338074, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.6559, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.008343472970624021, | |
| "grad_norm": 0.5592238903045654, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.7763, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.008899704501998958, | |
| "grad_norm": 0.5054487586021423, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.721, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.009455936033373892, | |
| "grad_norm": 0.4145556390285492, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.7055, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.010012167564748826, | |
| "grad_norm": 0.36540091037750244, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.6979, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.010568399096123761, | |
| "grad_norm": 0.28136712312698364, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.7644, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.011124630627498697, | |
| "grad_norm": 0.2922019064426422, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.9497, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.011680862158873631, | |
| "grad_norm": 0.3472326695919037, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.17, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.012237093690248566, | |
| "grad_norm": 0.4307328462600708, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.295, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0127933252216235, | |
| "grad_norm": 0.6883488297462463, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.4575, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.013349556752998436, | |
| "grad_norm": 0.7492279410362244, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.3692, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01390578828437337, | |
| "grad_norm": 1.6095669269561768, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.9458, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01390578828437337, | |
| "eval_loss": 1.0297096967697144, | |
| "eval_runtime": 138.2794, | |
| "eval_samples_per_second": 87.591, | |
| "eval_steps_per_second": 10.949, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.014462019815748305, | |
| "grad_norm": 0.09419423341751099, | |
| "learning_rate": 5e-05, | |
| "loss": 0.4267, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.01501825134712324, | |
| "grad_norm": 0.1334831416606903, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.6666, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.015574482878498174, | |
| "grad_norm": 0.144070565700531, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.6366, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.01613071440987311, | |
| "grad_norm": 0.1303204894065857, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.633, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.016686945941248043, | |
| "grad_norm": 0.14772789180278778, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.732, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01724317747262298, | |
| "grad_norm": 0.1663038730621338, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.7748, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.017799409003997915, | |
| "grad_norm": 0.21385891735553741, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.008, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.01835564053537285, | |
| "grad_norm": 0.29136043787002563, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.1981, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.018911872066747784, | |
| "grad_norm": 0.358648419380188, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.2509, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.01946810359812272, | |
| "grad_norm": 0.40348002314567566, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.3403, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.020024335129497653, | |
| "grad_norm": 0.5576580762863159, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.385, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.020580566660872587, | |
| "grad_norm": 0.9451633095741272, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.5531, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.021136798192247522, | |
| "grad_norm": 0.10654843598604202, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.4292, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.021693029723622456, | |
| "grad_norm": 0.10906118899583817, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.5853, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.022249261254997394, | |
| "grad_norm": 0.1391826868057251, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.7037, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02280549278637233, | |
| "grad_norm": 0.13406039774417877, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.6435, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.023361724317747263, | |
| "grad_norm": 0.1331794112920761, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.6847, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.023917955849122197, | |
| "grad_norm": 0.1532629281282425, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.8577, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.024474187380497132, | |
| "grad_norm": 0.17151039838790894, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.8592, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.025030418911872066, | |
| "grad_norm": 0.24025927484035492, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.1217, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.025586650443247, | |
| "grad_norm": 0.2666977047920227, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.1314, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.026142881974621935, | |
| "grad_norm": 0.3222261369228363, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.2233, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.026699113505996873, | |
| "grad_norm": 0.42572563886642456, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.3975, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.027255345037371807, | |
| "grad_norm": 0.5978182554244995, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.3051, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.02781157656874674, | |
| "grad_norm": 1.0638318061828613, | |
| "learning_rate": 0.0, | |
| "loss": 1.7991, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02781157656874674, | |
| "eval_loss": 1.0076379776000977, | |
| "eval_runtime": 138.2815, | |
| "eval_samples_per_second": 87.589, | |
| "eval_steps_per_second": 10.949, | |
| "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": 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": 1.0608607728186163e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |