| { | |
| "best_metric": 0.01978439837694168, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 2.223433242506812, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.043596730245231606, | |
| "grad_norm": 14.609258651733398, | |
| "learning_rate": 5e-05, | |
| "loss": 10.9229, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.043596730245231606, | |
| "eval_loss": 11.462030410766602, | |
| "eval_runtime": 4.8176, | |
| "eval_samples_per_second": 32.174, | |
| "eval_steps_per_second": 4.151, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.08719346049046321, | |
| "grad_norm": 14.825850486755371, | |
| "learning_rate": 0.0001, | |
| "loss": 11.3637, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.1307901907356948, | |
| "grad_norm": 14.313569068908691, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 10.5762, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.17438692098092642, | |
| "grad_norm": 20.055015563964844, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 7.006, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.21798365122615804, | |
| "grad_norm": 17.558155059814453, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 3.4836, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.2615803814713896, | |
| "grad_norm": 10.12147045135498, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.2241, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.30517711171662126, | |
| "grad_norm": 6.290586471557617, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.8574, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.34877384196185285, | |
| "grad_norm": 5.365172386169434, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.5709, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.3923705722070845, | |
| "grad_norm": 2.534698486328125, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.2367, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.4359673024523161, | |
| "grad_norm": 5.189870357513428, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.2049, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.47956403269754766, | |
| "grad_norm": 2.6924498081207275, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.1444, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.5231607629427792, | |
| "grad_norm": 8.41533374786377, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.3991, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.5667574931880109, | |
| "grad_norm": 4.177337169647217, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.2151, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.6103542234332425, | |
| "grad_norm": 1.2241578102111816, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.1315, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.6539509536784741, | |
| "grad_norm": 1.8561956882476807, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.1008, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.6975476839237057, | |
| "grad_norm": 2.9710350036621094, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.1297, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.7411444141689373, | |
| "grad_norm": 4.106350421905518, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.1502, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.784741144414169, | |
| "grad_norm": 3.2620880603790283, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.1297, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.8283378746594006, | |
| "grad_norm": 2.53080415725708, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.0639, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.8719346049046321, | |
| "grad_norm": 1.1116608381271362, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0986, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.9155313351498637, | |
| "grad_norm": 1.287713646888733, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.0489, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.9591280653950953, | |
| "grad_norm": 2.044447183609009, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.1412, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.0245231607629428, | |
| "grad_norm": 5.4860334396362305, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.1393, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.0681198910081744, | |
| "grad_norm": 0.41240328550338745, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.0429, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.111716621253406, | |
| "grad_norm": 2.7775936126708984, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.0645, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.111716621253406, | |
| "eval_loss": 0.08786293864250183, | |
| "eval_runtime": 4.8027, | |
| "eval_samples_per_second": 32.274, | |
| "eval_steps_per_second": 4.164, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.1553133514986376, | |
| "grad_norm": 2.960618734359741, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0719, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.1989100817438691, | |
| "grad_norm": 3.1005544662475586, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.0936, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.2425068119891007, | |
| "grad_norm": 0.5020301938056946, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.0441, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.2861035422343323, | |
| "grad_norm": 0.7082467675209045, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.0199, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.3297002724795641, | |
| "grad_norm": 1.5583200454711914, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.0518, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.3732970027247957, | |
| "grad_norm": 1.1485878229141235, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.0447, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.4168937329700273, | |
| "grad_norm": 2.684978723526001, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0235, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.4604904632152589, | |
| "grad_norm": 1.4292771816253662, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.0502, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.5040871934604905, | |
| "grad_norm": 1.1590442657470703, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.0307, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.547683923705722, | |
| "grad_norm": 0.2641136348247528, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.0102, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.5912806539509536, | |
| "grad_norm": 0.37619253993034363, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.0247, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.6348773841961854, | |
| "grad_norm": 0.25651946663856506, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.0083, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.6784741144414168, | |
| "grad_norm": 0.3186868727207184, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0105, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.7220708446866486, | |
| "grad_norm": 0.41207724809646606, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.0213, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.76566757493188, | |
| "grad_norm": 0.31666725873947144, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.0038, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.8092643051771118, | |
| "grad_norm": 0.5484305620193481, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.0148, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.8528610354223434, | |
| "grad_norm": 0.44189968705177307, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.0101, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.896457765667575, | |
| "grad_norm": 0.6846371293067932, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.017, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.9400544959128065, | |
| "grad_norm": 0.29374387860298157, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.011, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.005449591280654, | |
| "grad_norm": 0.2908608913421631, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.0082, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.0490463215258856, | |
| "grad_norm": 0.12878499925136566, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.007, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.092643051771117, | |
| "grad_norm": 0.14788788557052612, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.0041, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.136239782016349, | |
| "grad_norm": 0.35576820373535156, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.0119, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.1798365122615806, | |
| "grad_norm": 0.337051659822464, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.0099, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.223433242506812, | |
| "grad_norm": 0.5203828811645508, | |
| "learning_rate": 0.0, | |
| "loss": 0.0171, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.223433242506812, | |
| "eval_loss": 0.01978439837694168, | |
| "eval_runtime": 4.8057, | |
| "eval_samples_per_second": 32.253, | |
| "eval_steps_per_second": 4.162, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 5.968083617316864e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |