| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.01687550099143568, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 8.437750495717842e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.004e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 8.437750495717842e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 971.3872, | |
| "eval_samples_per_second": 5.137, | |
| "eval_steps_per_second": 1.285, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00016875500991435683, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.008e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00025313251487153526, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.012e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00033751001982871366, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.016e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00042188752478589206, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.02e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0005062650297430705, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.024e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0005906425347002489, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.028e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0006750200396574273, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.032e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0007593975446146058, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.036000000000001e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0008437750495717841, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001004, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0009281525545289626, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.987157894736842e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.001012530059486141, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.934315789473684e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0010969075644433194, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.881473684210525e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0011812850694004977, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.828631578947369e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0012656625743576763, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.77578947368421e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0013500400793148546, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.722947368421052e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.001434417584272033, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.670105263157895e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0015187950892292116, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.617263157894737e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00160317259418639, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.564421052631579e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0016875500991435683, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.511578947368421e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0017719276041007468, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.458736842105264e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0018563051090579252, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.405894736842106e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0019406826140151035, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.353052631578947e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.002025060118972282, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.300210526315789e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.00210943762392946, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.247368421052631e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0021938151288866388, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.194526315789473e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0022781926338438173, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.141684210526316e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0023625701388009955, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.088842105263158e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.002446947643758174, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.036000000000001e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0025313251487153526, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.983157894736843e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0026157026536725307, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.930315789473684e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0027000801586297093, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.877473684210526e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.002784457663586888, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.824631578947368e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.002868835168544066, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.771789473684211e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0029532126735012446, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.718947368421053e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.003037590178458423, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.666105263157895e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0031219676834156013, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.613263157894737e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.00320634518837278, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.560421052631578e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0032907226933299584, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.50757894736842e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0033751001982871365, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.454736842105263e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.003459477703244315, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.401894736842106e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0035438552082014936, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.349052631578948e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0036282327131586718, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.29621052631579e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0037126102181158503, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.243368421052632e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.003796987723073029, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.190526315789474e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.003881365228030207, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.137684210526315e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.003965742732987386, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.084842105263157e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.004050120237944564, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.032e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.004134497742901743, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.979157894736842e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.00421887524785892, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.926315789473684e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.00421887524785892, | |
| "eval_loss": NaN, | |
| "eval_runtime": 970.4964, | |
| "eval_samples_per_second": 5.142, | |
| "eval_steps_per_second": 1.286, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.004303252752816099, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.873473684210526e-05, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.0043876302577732776, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.820631578947369e-05, | |
| "loss": 0.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.004472007762730456, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.76778947368421e-05, | |
| "loss": 0.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.004556385267687635, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.714947368421052e-05, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.004640762772644813, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.662105263157896e-05, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.004725140277601991, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.609263157894737e-05, | |
| "loss": 0.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.0048095177825591695, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.556421052631579e-05, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.004893895287516348, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.503578947368421e-05, | |
| "loss": 0.0, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.004978272792473527, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.450736842105263e-05, | |
| "loss": 0.0, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.005062650297430705, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.397894736842105e-05, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.005147027802387884, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.345052631578948e-05, | |
| "loss": 0.0, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.0052314053073450615, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.29221052631579e-05, | |
| "loss": 0.0, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.00531578281230224, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.239368421052631e-05, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.005400160317259419, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.186526315789474e-05, | |
| "loss": 0.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.005484537822216597, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.133684210526316e-05, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.005568915327173776, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.080842105263158e-05, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.005653292832130954, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.028e-05, | |
| "loss": 0.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.005737670337088132, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.975157894736843e-05, | |
| "loss": 0.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.0058220478420453105, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.922315789473685e-05, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.005906425347002489, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.869473684210527e-05, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.005990802851959668, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.816631578947368e-05, | |
| "loss": 0.0, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.006075180356916846, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.76378947368421e-05, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.006159557861874025, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.710947368421052e-05, | |
| "loss": 0.0, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.0062439353668312025, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.658105263157894e-05, | |
| "loss": 0.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.006328312871788381, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.605263157894737e-05, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.00641269037674556, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.55242105263158e-05, | |
| "loss": 0.0, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.006497067881702738, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.499578947368422e-05, | |
| "loss": 0.0, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.006581445386659917, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.446736842105264e-05, | |
| "loss": 0.0, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.0066658228916170945, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.393894736842105e-05, | |
| "loss": 0.0, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.006750200396574273, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.341052631578947e-05, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.006834577901531452, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.288210526315789e-05, | |
| "loss": 0.0, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.00691895540648863, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.235368421052632e-05, | |
| "loss": 0.0, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.007003332911445809, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.182526315789474e-05, | |
| "loss": 0.0, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.007087710416402987, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.129684210526316e-05, | |
| "loss": 0.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.007172087921360165, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.076842105263158e-05, | |
| "loss": 0.0, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.0072564654263173435, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.024e-05, | |
| "loss": 0.0, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.007340842931274522, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.971157894736842e-05, | |
| "loss": 0.0, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.007425220436231701, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.9183157894736835e-05, | |
| "loss": 0.0, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.007509597941188879, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.8654736842105267e-05, | |
| "loss": 0.0, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.007593975446146058, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.8126315789473684e-05, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.0076783529511032355, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.759789473684211e-05, | |
| "loss": 0.0, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.007762730456060414, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.706947368421053e-05, | |
| "loss": 0.0, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.007847107961017593, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.6541052631578945e-05, | |
| "loss": 0.0, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.007931485465974771, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.601263157894736e-05, | |
| "loss": 0.0, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.00801586297093195, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.5484210526315794e-05, | |
| "loss": 0.0, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.008100240475889128, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.495578947368421e-05, | |
| "loss": 0.0, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.008184617980846307, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.442736842105264e-05, | |
| "loss": 0.0, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.008268995485803485, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.3898947368421055e-05, | |
| "loss": 0.0, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.008353372990760664, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.337052631578947e-05, | |
| "loss": 0.0, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.00843775049571784, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.284210526315789e-05, | |
| "loss": 0.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.00843775049571784, | |
| "eval_loss": NaN, | |
| "eval_runtime": 970.5833, | |
| "eval_samples_per_second": 5.141, | |
| "eval_steps_per_second": 1.286, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.00852212800067502, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.231368421052631e-05, | |
| "loss": 0.0, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.008606505505632198, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.178526315789474e-05, | |
| "loss": 0.0, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.008690883010589377, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.1256842105263165e-05, | |
| "loss": 0.0, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.008775260515546555, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.072842105263158e-05, | |
| "loss": 0.0, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.008859638020503734, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.02e-05, | |
| "loss": 0.0, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.008944015525460912, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.967157894736842e-05, | |
| "loss": 0.0, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.00902839303041809, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.914315789473684e-05, | |
| "loss": 0.0, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.00911277053537527, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.861473684210526e-05, | |
| "loss": 0.0, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.009197148040332448, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.8086315789473686e-05, | |
| "loss": 0.0, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.009281525545289626, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.7557894736842104e-05, | |
| "loss": 0.0, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.009365903050246805, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.702947368421053e-05, | |
| "loss": 0.0, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.009450280555203982, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.6501052631578946e-05, | |
| "loss": 0.0, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.00953465806016116, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.5972631578947364e-05, | |
| "loss": 0.0, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.009619035565118339, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.544421052631579e-05, | |
| "loss": 0.0, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.009703413070075518, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.4915789473684213e-05, | |
| "loss": 0.0, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.009787790575032696, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.438736842105263e-05, | |
| "loss": 0.0, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.009872168079989875, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.3858947368421056e-05, | |
| "loss": 0.0, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.009956545584947053, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.3330526315789474e-05, | |
| "loss": 0.0, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.010040923089904232, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.280210526315789e-05, | |
| "loss": 0.0, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.01012530059486141, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.2273684210526317e-05, | |
| "loss": 0.0, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.010209678099818589, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.174526315789474e-05, | |
| "loss": 0.0, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.010294055604775768, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.121684210526316e-05, | |
| "loss": 0.0, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.010378433109732944, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.068842105263158e-05, | |
| "loss": 0.0, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.010462810614690123, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.016e-05, | |
| "loss": 0.0, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.010547188119647301, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.963157894736842e-05, | |
| "loss": 0.0, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.01063156562460448, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.9103157894736844e-05, | |
| "loss": 0.0, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.010715943129561659, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.857473684210526e-05, | |
| "loss": 0.0, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.010800320634518837, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.804631578947369e-05, | |
| "loss": 0.0, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.010884698139476016, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.7517894736842105e-05, | |
| "loss": 0.0, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.010969075644433194, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.698947368421052e-05, | |
| "loss": 0.0, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.011053453149390373, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.646105263157895e-05, | |
| "loss": 0.0, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.011137830654347551, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.593263157894737e-05, | |
| "loss": 0.0, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.01122220815930473, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.540421052631579e-05, | |
| "loss": 0.0, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.011306585664261909, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.4875789473684215e-05, | |
| "loss": 0.0, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.011390963169219085, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.434736842105263e-05, | |
| "loss": 0.0, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.011475340674176264, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.381894736842105e-05, | |
| "loss": 0.0, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.011559718179133443, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.329052631578947e-05, | |
| "loss": 0.0, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.011644095684090621, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.27621052631579e-05, | |
| "loss": 0.0, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.0117284731890478, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.223368421052632e-05, | |
| "loss": 0.0, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.011812850694004978, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.1705263157894736e-05, | |
| "loss": 0.0, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.011897228198962157, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.117684210526316e-05, | |
| "loss": 0.0, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.011981605703919335, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.064842105263158e-05, | |
| "loss": 0.0, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.012065983208876514, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.012e-05, | |
| "loss": 0.0, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.012150360713833692, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9591578947368418e-05, | |
| "loss": 0.0, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.012234738218790871, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9063157894736842e-05, | |
| "loss": 0.0, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.01231911572374805, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8534736842105264e-05, | |
| "loss": 0.0, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.012403493228705226, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.800631578947368e-05, | |
| "loss": 0.0, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.012487870733662405, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7477894736842106e-05, | |
| "loss": 0.0, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.012572248238619584, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6949473684210527e-05, | |
| "loss": 0.0, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.012656625743576762, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6421052631578945e-05, | |
| "loss": 0.0, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.012656625743576762, | |
| "eval_loss": NaN, | |
| "eval_runtime": 970.289, | |
| "eval_samples_per_second": 5.143, | |
| "eval_steps_per_second": 1.286, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.01274100324853394, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.589263157894737e-05, | |
| "loss": 0.0, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.01282538075349112, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.536421052631579e-05, | |
| "loss": 0.0, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.012909758258448298, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.483578947368421e-05, | |
| "loss": 0.0, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.012994135763405476, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.430736842105263e-05, | |
| "loss": 0.0, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.013078513268362655, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3778947368421052e-05, | |
| "loss": 0.0, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.013162890773319834, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3250526315789473e-05, | |
| "loss": 0.0, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.013247268278277012, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2722105263157894e-05, | |
| "loss": 0.0, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.013331645783234189, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2193684210526316e-05, | |
| "loss": 0.0, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.013416023288191367, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1665263157894737e-05, | |
| "loss": 0.0, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.013500400793148546, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1136842105263158e-05, | |
| "loss": 0.0, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.013584778298105725, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.060842105263158e-05, | |
| "loss": 0.0, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.013669155803062903, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.008e-05, | |
| "loss": 0.0, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.013753533308020082, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9551578947368422e-05, | |
| "loss": 0.0, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.01383791081297726, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9023157894736843e-05, | |
| "loss": 0.0, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.013922288317934439, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.849473684210526e-05, | |
| "loss": 0.0, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.014006665822891617, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7966315789473686e-05, | |
| "loss": 0.0, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.014091043327848796, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7437894736842107e-05, | |
| "loss": 0.0, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.014175420832805975, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6909473684210525e-05, | |
| "loss": 0.0, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.014259798337763153, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.638105263157895e-05, | |
| "loss": 0.0, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.01434417584272033, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5852631578947368e-05, | |
| "loss": 0.0, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.014428553347677509, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.532421052631579e-05, | |
| "loss": 0.0, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.014512930852634687, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4795789473684209e-05, | |
| "loss": 0.0, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.014597308357591866, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4267368421052632e-05, | |
| "loss": 0.0, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.014681685862549044, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3738947368421053e-05, | |
| "loss": 0.0, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.014766063367506223, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3210526315789473e-05, | |
| "loss": 0.0, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.014850440872463401, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2682105263157896e-05, | |
| "loss": 0.0, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.01493481837742058, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2153684210526315e-05, | |
| "loss": 0.0, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.015019195882377758, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1625263157894737e-05, | |
| "loss": 0.0, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.015103573387334937, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1096842105263158e-05, | |
| "loss": 0.0, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.015187950892292116, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0568421052631579e-05, | |
| "loss": 0.0, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.015272328397249294, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.004e-05, | |
| "loss": 0.0, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.015356705902206471, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.511578947368422e-06, | |
| "loss": 0.0, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.01544108340716365, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.983157894736843e-06, | |
| "loss": 0.0, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.015525460912120828, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.454736842105263e-06, | |
| "loss": 0.0, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.015609838417078007, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.926315789473684e-06, | |
| "loss": 0.0, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.015694215922035185, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.397894736842104e-06, | |
| "loss": 0.0, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.015778593426992366, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.8694736842105265e-06, | |
| "loss": 0.0, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.015862970931949542, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.341052631578948e-06, | |
| "loss": 0.0, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.01594734843690672, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.812631578947368e-06, | |
| "loss": 0.0, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.0160317259418639, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.2842105263157896e-06, | |
| "loss": 0.0, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.016116103446821076, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.755789473684211e-06, | |
| "loss": 0.0, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.016200480951778257, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.227368421052631e-06, | |
| "loss": 0.0, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.016284858456735433, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.698947368421052e-06, | |
| "loss": 0.0, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.016369235961692614, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.170526315789474e-06, | |
| "loss": 0.0, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.01645361346664979, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6421052631578948e-06, | |
| "loss": 0.0, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.01653799097160697, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1136842105263157e-06, | |
| "loss": 0.0, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.016622368476564148, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.585263157894737e-06, | |
| "loss": 0.0, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.016706745981521328, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0568421052631578e-06, | |
| "loss": 0.0, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.016791123486478505, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.284210526315789e-07, | |
| "loss": 0.0, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.01687550099143568, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.01687550099143568, | |
| "eval_loss": NaN, | |
| "eval_runtime": 970.3531, | |
| "eval_samples_per_second": 5.142, | |
| "eval_steps_per_second": 1.286, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 3 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.4059815544710758e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |