| { | |
| "best_metric": 0.17505227029323578, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.7312614259597806, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.014625228519195612, | |
| "grad_norm": 5.831832408905029, | |
| "learning_rate": 5e-05, | |
| "loss": 10.4065, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.014625228519195612, | |
| "eval_loss": 10.162100791931152, | |
| "eval_runtime": 12.7337, | |
| "eval_samples_per_second": 36.203, | |
| "eval_steps_per_second": 4.555, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.029250457038391225, | |
| "grad_norm": 5.772745132446289, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3209, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.043875685557586835, | |
| "grad_norm": 5.314096927642822, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 10.0587, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.05850091407678245, | |
| "grad_norm": 5.838923454284668, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 8.9239, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.07312614259597806, | |
| "grad_norm": 5.815253257751465, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 7.5476, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08775137111517367, | |
| "grad_norm": 6.76201057434082, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 6.337, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.10237659963436929, | |
| "grad_norm": 7.72877311706543, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 4.9284, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.1170018281535649, | |
| "grad_norm": 6.701197624206543, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.4673, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.1316270566727605, | |
| "grad_norm": 6.677616596221924, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 3.0654, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.14625228519195613, | |
| "grad_norm": 5.724824905395508, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.0635, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.16087751371115175, | |
| "grad_norm": 4.8147501945495605, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.4939, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.17550274223034734, | |
| "grad_norm": 3.6128013134002686, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.9074, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.19012797074954296, | |
| "grad_norm": 4.377878189086914, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.7413, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.20475319926873858, | |
| "grad_norm": 2.699510335922241, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.4339, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.21937842778793418, | |
| "grad_norm": 3.3804996013641357, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.3749, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2340036563071298, | |
| "grad_norm": 4.033849716186523, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.3371, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.24862888482632542, | |
| "grad_norm": 2.868183135986328, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.2834, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.263254113345521, | |
| "grad_norm": 2.7503623962402344, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.3847, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.27787934186471663, | |
| "grad_norm": 3.617218494415283, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.4111, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.29250457038391225, | |
| "grad_norm": 3.1017227172851562, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.2372, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3071297989031079, | |
| "grad_norm": 2.2180283069610596, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.234, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.3217550274223035, | |
| "grad_norm": 1.6347497701644897, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.2487, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.33638025594149906, | |
| "grad_norm": 2.8232500553131104, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.1997, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.3510054844606947, | |
| "grad_norm": 2.066770076751709, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.1943, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.3656307129798903, | |
| "grad_norm": 1.40006422996521, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.2034, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3656307129798903, | |
| "eval_loss": 0.21981914341449738, | |
| "eval_runtime": 12.7149, | |
| "eval_samples_per_second": 36.257, | |
| "eval_steps_per_second": 4.562, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3802559414990859, | |
| "grad_norm": 2.550391912460327, | |
| "learning_rate": 5e-05, | |
| "loss": 0.2178, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.39488117001828155, | |
| "grad_norm": 2.0261378288269043, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.2351, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.40950639853747717, | |
| "grad_norm": 2.101436138153076, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.2448, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.42413162705667273, | |
| "grad_norm": 1.7612956762313843, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.1681, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.43875685557586835, | |
| "grad_norm": 1.6624386310577393, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.2175, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.453382084095064, | |
| "grad_norm": 1.192665457725525, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.2132, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.4680073126142596, | |
| "grad_norm": 1.0501598119735718, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.1571, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.4826325411334552, | |
| "grad_norm": 1.083679437637329, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.1835, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.49725776965265084, | |
| "grad_norm": 1.7676903009414673, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.2053, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.5118829981718465, | |
| "grad_norm": 1.9303137063980103, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.2096, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.526508226691042, | |
| "grad_norm": 0.9747893810272217, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.1409, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.5411334552102377, | |
| "grad_norm": 1.0830137729644775, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.1667, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.5557586837294333, | |
| "grad_norm": 1.4457792043685913, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.1385, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.5703839122486288, | |
| "grad_norm": 0.4956473708152771, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.105, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.5850091407678245, | |
| "grad_norm": 1.1572775840759277, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.1632, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5996343692870201, | |
| "grad_norm": 1.2062376737594604, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.2027, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.6142595978062158, | |
| "grad_norm": 0.7177852988243103, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.226, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.6288848263254113, | |
| "grad_norm": 0.8510001301765442, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.1587, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.643510054844607, | |
| "grad_norm": 1.0772465467453003, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.1439, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.6581352833638026, | |
| "grad_norm": 1.2371275424957275, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.1064, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.6727605118829981, | |
| "grad_norm": 0.785141110420227, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.156, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.6873857404021938, | |
| "grad_norm": 1.2632596492767334, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.1088, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.7020109689213894, | |
| "grad_norm": 1.0525493621826172, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.1652, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.716636197440585, | |
| "grad_norm": 0.9449817538261414, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.1478, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.7312614259597806, | |
| "grad_norm": 1.407353401184082, | |
| "learning_rate": 0.0, | |
| "loss": 0.1391, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.7312614259597806, | |
| "eval_loss": 0.17505227029323578, | |
| "eval_runtime": 12.7323, | |
| "eval_samples_per_second": 36.207, | |
| "eval_steps_per_second": 4.555, | |
| "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": 5.624057810649088e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |