| { | |
| "best_metric": 0.04139801859855652, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.4561717352415027, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.028622540250447227, | |
| "grad_norm": 219.70053100585938, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9516, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.028622540250447227, | |
| "eval_loss": 1.238963007926941, | |
| "eval_runtime": 6.9134, | |
| "eval_samples_per_second": 33.992, | |
| "eval_steps_per_second": 4.339, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.057245080500894455, | |
| "grad_norm": 234.6845703125, | |
| "learning_rate": 0.0001, | |
| "loss": 1.0405, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.08586762075134168, | |
| "grad_norm": 71.39820098876953, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 0.4477, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.11449016100178891, | |
| "grad_norm": 28.74665069580078, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.2055, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.14311270125223613, | |
| "grad_norm": 72.32389831542969, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.194, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.17173524150268335, | |
| "grad_norm": 12.614567756652832, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.1527, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.2003577817531306, | |
| "grad_norm": 12.43664264678955, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.1547, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.22898032200357782, | |
| "grad_norm": 11.506562232971191, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.1529, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.25760286225402507, | |
| "grad_norm": 8.407600402832031, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.1031, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.28622540250447226, | |
| "grad_norm": 10.93082046508789, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.105, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3148479427549195, | |
| "grad_norm": 7.173758029937744, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.1007, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.3434704830053667, | |
| "grad_norm": 6.843894004821777, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.0901, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.37209302325581395, | |
| "grad_norm": 5.500521659851074, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.0981, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.4007155635062612, | |
| "grad_norm": 10.176575660705566, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.1116, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.4293381037567084, | |
| "grad_norm": 8.115479469299316, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.116, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.45796064400715564, | |
| "grad_norm": 15.09660530090332, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.1463, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.4865831842576029, | |
| "grad_norm": 9.49724292755127, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.1267, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.5152057245080501, | |
| "grad_norm": 6.2978196144104, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.0648, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.5438282647584973, | |
| "grad_norm": 5.191648006439209, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.0844, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.5724508050089445, | |
| "grad_norm": 7.677884101867676, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0882, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.6010733452593918, | |
| "grad_norm": 6.417791843414307, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.0859, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.629695885509839, | |
| "grad_norm": 6.256846904754639, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.086, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.6583184257602862, | |
| "grad_norm": 6.789362907409668, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.0929, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.6869409660107334, | |
| "grad_norm": 6.729310989379883, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.0937, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.7155635062611807, | |
| "grad_norm": 6.641665935516357, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.0872, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.7155635062611807, | |
| "eval_loss": 0.0668637827038765, | |
| "eval_runtime": 6.9097, | |
| "eval_samples_per_second": 34.01, | |
| "eval_steps_per_second": 4.342, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.7441860465116279, | |
| "grad_norm": 6.980295658111572, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0684, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.7728085867620751, | |
| "grad_norm": 8.31533145904541, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.0578, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.8014311270125224, | |
| "grad_norm": 4.423112869262695, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.0607, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.8300536672629696, | |
| "grad_norm": 6.696436405181885, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.0686, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.8586762075134168, | |
| "grad_norm": 6.26486873626709, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.0516, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.8872987477638641, | |
| "grad_norm": 6.031646251678467, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.0539, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.9159212880143113, | |
| "grad_norm": 7.471781253814697, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0529, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.9445438282647585, | |
| "grad_norm": 4.425765514373779, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.0518, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.9731663685152058, | |
| "grad_norm": 6.656881332397461, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.052, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.0268336314847943, | |
| "grad_norm": 11.75803279876709, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.0384, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.0554561717352415, | |
| "grad_norm": 7.5000786781311035, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.0322, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.0840787119856887, | |
| "grad_norm": 12.667994499206543, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.0492, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.112701252236136, | |
| "grad_norm": 9.831031799316406, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0388, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.141323792486583, | |
| "grad_norm": 9.961572647094727, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.0306, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.1699463327370303, | |
| "grad_norm": 7.772109031677246, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.0553, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.1985688729874777, | |
| "grad_norm": 7.32382345199585, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.0418, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.227191413237925, | |
| "grad_norm": 16.050722122192383, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.0489, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.255813953488372, | |
| "grad_norm": 8.445350646972656, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.0344, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.2844364937388193, | |
| "grad_norm": 5.381591320037842, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0279, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.3130590339892665, | |
| "grad_norm": 5.421046733856201, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.0472, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.341681574239714, | |
| "grad_norm": 9.946616172790527, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.0377, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.3703041144901609, | |
| "grad_norm": 10.54006290435791, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.0489, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.3989266547406083, | |
| "grad_norm": 7.798122406005859, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.0341, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.4275491949910555, | |
| "grad_norm": 7.607766628265381, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.0504, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.4561717352415027, | |
| "grad_norm": 8.484859466552734, | |
| "learning_rate": 0.0, | |
| "loss": 0.0358, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.4561717352415027, | |
| "eval_loss": 0.04139801859855652, | |
| "eval_runtime": 6.9109, | |
| "eval_samples_per_second": 34.004, | |
| "eval_steps_per_second": 4.341, | |
| "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": 5.658021338284032e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |