| { | |
| "best_metric": 0.5620399713516235, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.9900497512437811, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03980099502487562, | |
| "grad_norm": 0.13307230174541473, | |
| "learning_rate": 5e-05, | |
| "loss": 0.7752, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03980099502487562, | |
| "eval_loss": 0.7566336393356323, | |
| "eval_runtime": 5.0659, | |
| "eval_samples_per_second": 33.558, | |
| "eval_steps_per_second": 4.343, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07960199004975124, | |
| "grad_norm": 0.1349344104528427, | |
| "learning_rate": 0.0001, | |
| "loss": 0.756, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.11940298507462686, | |
| "grad_norm": 0.13909032940864563, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 0.7531, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.15920398009950248, | |
| "grad_norm": 0.14223748445510864, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.7397, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.19900497512437812, | |
| "grad_norm": 0.19557783007621765, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.7403, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.23880597014925373, | |
| "grad_norm": 0.12540394067764282, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.6391, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.27860696517412936, | |
| "grad_norm": 0.12868504226207733, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.6688, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.31840796019900497, | |
| "grad_norm": 0.14338752627372742, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.6822, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.3582089552238806, | |
| "grad_norm": 0.1410781592130661, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.6879, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.39800995024875624, | |
| "grad_norm": 0.10805737972259521, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.6344, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.43781094527363185, | |
| "grad_norm": 0.11142578721046448, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.6047, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.47761194029850745, | |
| "grad_norm": 0.09217383712530136, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.6048, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.5174129353233831, | |
| "grad_norm": 0.06935001164674759, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.62, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.5572139303482587, | |
| "grad_norm": 0.07017137110233307, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.6364, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5970149253731343, | |
| "grad_norm": 0.07594887167215347, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.6402, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.6368159203980099, | |
| "grad_norm": 0.07854108512401581, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.6215, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.6766169154228856, | |
| "grad_norm": 0.07627039402723312, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.5876, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.7164179104477612, | |
| "grad_norm": 0.09767764806747437, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.5739, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.7562189054726368, | |
| "grad_norm": 0.0784846842288971, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.5987, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.7960199004975125, | |
| "grad_norm": 0.0701882392168045, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.6514, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.835820895522388, | |
| "grad_norm": 0.07107464969158173, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.6176, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.8756218905472637, | |
| "grad_norm": 0.0965135395526886, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.5857, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.9154228855721394, | |
| "grad_norm": 0.08715957403182983, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.5829, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.9552238805970149, | |
| "grad_norm": 0.07449861615896225, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.5732, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.9950248756218906, | |
| "grad_norm": 0.07877979427576065, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.5357, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.9950248756218906, | |
| "eval_loss": 0.5807715058326721, | |
| "eval_runtime": 11.1585, | |
| "eval_samples_per_second": 15.235, | |
| "eval_steps_per_second": 1.972, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.0348258706467661, | |
| "grad_norm": 0.22895914316177368, | |
| "learning_rate": 5e-05, | |
| "loss": 1.1264, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.0746268656716418, | |
| "grad_norm": 0.14677956700325012, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.5921, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.1144278606965174, | |
| "grad_norm": 0.11105823516845703, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.5877, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.154228855721393, | |
| "grad_norm": 0.1271418184041977, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.5577, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.1940298507462686, | |
| "grad_norm": 0.1278061419725418, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.5555, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.2338308457711442, | |
| "grad_norm": 0.14156891405582428, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.5235, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.2736318407960199, | |
| "grad_norm": 0.11495278775691986, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.5603, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.3134328358208955, | |
| "grad_norm": 0.11897273361682892, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.5988, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.3532338308457712, | |
| "grad_norm": 0.12612038850784302, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.5884, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.3930348258706466, | |
| "grad_norm": 0.11991294473409653, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.5569, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.4328358208955223, | |
| "grad_norm": 0.1252669394016266, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.5409, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.472636815920398, | |
| "grad_norm": 0.1387309730052948, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.5438, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.5124378109452736, | |
| "grad_norm": 0.1291898936033249, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.5205, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.5522388059701493, | |
| "grad_norm": 0.12257789820432663, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.5969, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.5920398009950247, | |
| "grad_norm": 0.12527777254581451, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.56, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.6318407960199006, | |
| "grad_norm": 0.12541717290878296, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.5398, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.671641791044776, | |
| "grad_norm": 0.12988954782485962, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.5432, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.7114427860696517, | |
| "grad_norm": 0.13142308592796326, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.553, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.7512437810945274, | |
| "grad_norm": 0.1271471232175827, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.4937, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.7910447761194028, | |
| "grad_norm": 0.11726174503564835, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.6301, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.8308457711442787, | |
| "grad_norm": 0.12278467416763306, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.5612, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.8706467661691542, | |
| "grad_norm": 0.12573637068271637, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.5555, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.9104477611940298, | |
| "grad_norm": 0.12766633927822113, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.5573, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.9502487562189055, | |
| "grad_norm": 0.14149890840053558, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.5547, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.9900497512437811, | |
| "grad_norm": 0.14994728565216064, | |
| "learning_rate": 0.0, | |
| "loss": 0.4937, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.9900497512437811, | |
| "eval_loss": 0.5620399713516235, | |
| "eval_runtime": 11.1558, | |
| "eval_samples_per_second": 15.239, | |
| "eval_steps_per_second": 1.972, | |
| "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": 5.259156315439104e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |