| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.8658008658008658, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004329004329004329, | |
| "grad_norm": 0.33439210057258606, | |
| "learning_rate": 1.001e-05, | |
| "loss": 0.7374, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004329004329004329, | |
| "eval_loss": NaN, | |
| "eval_runtime": 11.016, | |
| "eval_samples_per_second": 8.805, | |
| "eval_steps_per_second": 2.269, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008658008658008658, | |
| "grad_norm": 0.30539026856422424, | |
| "learning_rate": 2.002e-05, | |
| "loss": 0.7, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.012987012987012988, | |
| "grad_norm": 0.30680182576179504, | |
| "learning_rate": 3.0029999999999995e-05, | |
| "loss": 0.7228, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.017316017316017316, | |
| "grad_norm": 0.6637282371520996, | |
| "learning_rate": 4.004e-05, | |
| "loss": 0.6918, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.021645021645021644, | |
| "grad_norm": 0.33853232860565186, | |
| "learning_rate": 5.005e-05, | |
| "loss": 0.7408, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.025974025974025976, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.005999999999999e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.030303030303030304, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.006999999999998e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.03463203463203463, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.008e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03896103896103896, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.009e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.04329004329004329, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001001, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.047619047619047616, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.957315789473684e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.05194805194805195, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.904631578947367e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.05627705627705628, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.851947368421052e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.06060606060606061, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.799263157894736e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.06493506493506493, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.746578947368421e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.06926406926406926, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.693894736842104e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0735930735930736, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.641210526315789e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.07792207792207792, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.588526315789473e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.08225108225108226, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.535842105263157e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.08658008658008658, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.483157894736841e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09090909090909091, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.430473684210526e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.09523809523809523, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.37778947368421e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.09956709956709957, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.325105263157894e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.1038961038961039, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.272421052631578e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.10822510822510822, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.219736842105263e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.11255411255411256, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.167052631578946e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.11688311688311688, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.114368421052632e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.12121212121212122, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.061684210526315e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.12554112554112554, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.009e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.12987012987012986, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.956315789473683e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1341991341991342, | |
| "grad_norm": 0.5805222988128662, | |
| "learning_rate": 8.903631578947368e-05, | |
| "loss": 0.7943, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.13852813852813853, | |
| "grad_norm": 0.39428913593292236, | |
| "learning_rate": 8.850947368421052e-05, | |
| "loss": 0.7229, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.14285714285714285, | |
| "grad_norm": 0.6405807733535767, | |
| "learning_rate": 8.798263157894736e-05, | |
| "loss": 0.8673, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.1471861471861472, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.745578947368422e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.15151515151515152, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.692894736842105e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.15584415584415584, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.64021052631579e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.16017316017316016, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.587526315789473e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.1645021645021645, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.534842105263157e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.16883116883116883, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.482157894736842e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.17316017316017315, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.429473684210525e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1774891774891775, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.376789473684211e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.18181818181818182, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.324105263157894e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.18614718614718614, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.271421052631579e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.19047619047619047, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.218736842105262e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.19480519480519481, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.166052631578947e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.19913419913419914, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.113368421052631e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.20346320346320346, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.060684210526315e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.2077922077922078, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.008e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.21212121212121213, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.955315789473684e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.21645021645021645, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.902631578947368e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.21645021645021645, | |
| "eval_loss": NaN, | |
| "eval_runtime": 8.378, | |
| "eval_samples_per_second": 11.578, | |
| "eval_steps_per_second": 2.984, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.22077922077922077, | |
| "grad_norm": 0.34621065855026245, | |
| "learning_rate": 7.849947368421052e-05, | |
| "loss": 0.8347, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.22510822510822512, | |
| "grad_norm": 0.31127241253852844, | |
| "learning_rate": 7.797263157894736e-05, | |
| "loss": 0.7476, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.22943722943722944, | |
| "grad_norm": 0.3109810948371887, | |
| "learning_rate": 7.744578947368421e-05, | |
| "loss": 0.7386, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.23376623376623376, | |
| "grad_norm": 0.2887902855873108, | |
| "learning_rate": 7.691894736842104e-05, | |
| "loss": 0.6139, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.23809523809523808, | |
| "grad_norm": 0.327152818441391, | |
| "learning_rate": 7.63921052631579e-05, | |
| "loss": 0.7329, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.24242424242424243, | |
| "grad_norm": 0.3406467139720917, | |
| "learning_rate": 7.586526315789473e-05, | |
| "loss": 0.7201, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.24675324675324675, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.533842105263158e-05, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.2510822510822511, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.481157894736841e-05, | |
| "loss": 0.0, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.2554112554112554, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.428473684210526e-05, | |
| "loss": 0.0, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.2597402597402597, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.375789473684209e-05, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.26406926406926406, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.323105263157895e-05, | |
| "loss": 0.0, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.2683982683982684, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.270421052631578e-05, | |
| "loss": 0.0, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.2727272727272727, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.217736842105263e-05, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.27705627705627706, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.165052631578947e-05, | |
| "loss": 0.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.2813852813852814, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.11236842105263e-05, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.2857142857142857, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.059684210526315e-05, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.29004329004329005, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.006999999999998e-05, | |
| "loss": 0.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.2943722943722944, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.954315789473684e-05, | |
| "loss": 0.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.2987012987012987, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.901631578947368e-05, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.30303030303030304, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.848947368421052e-05, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.30735930735930733, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.796263157894737e-05, | |
| "loss": 0.0, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.3116883116883117, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.74357894736842e-05, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.31601731601731603, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.690894736842105e-05, | |
| "loss": 0.0, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.3203463203463203, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.638210526315788e-05, | |
| "loss": 0.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.3246753246753247, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.585526315789474e-05, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.329004329004329, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.532842105263157e-05, | |
| "loss": 0.0, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.3333333333333333, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.480157894736842e-05, | |
| "loss": 0.0, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.33766233766233766, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.427473684210526e-05, | |
| "loss": 0.0, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.341991341991342, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.37478947368421e-05, | |
| "loss": 0.0, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.3463203463203463, | |
| "grad_norm": 0.5967077612876892, | |
| "learning_rate": 6.322105263157894e-05, | |
| "loss": 1.5417, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.35064935064935066, | |
| "grad_norm": 0.481616735458374, | |
| "learning_rate": 6.269421052631577e-05, | |
| "loss": 0.7137, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.354978354978355, | |
| "grad_norm": 0.5399643778800964, | |
| "learning_rate": 6.216736842105263e-05, | |
| "loss": 0.7938, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.3593073593073593, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.164052631578947e-05, | |
| "loss": 0.0, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.36363636363636365, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.111368421052631e-05, | |
| "loss": 0.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.36796536796536794, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.058684210526315e-05, | |
| "loss": 0.0, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.3722943722943723, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.005999999999999e-05, | |
| "loss": 0.0, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.37662337662337664, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.953315789473684e-05, | |
| "loss": 0.0, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.38095238095238093, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.9006315789473676e-05, | |
| "loss": 0.0, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.3852813852813853, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.847947368421053e-05, | |
| "loss": 0.0, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.38961038961038963, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.795263157894737e-05, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.3939393939393939, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.742578947368421e-05, | |
| "loss": 0.0, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.39826839826839827, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.6898947368421046e-05, | |
| "loss": 0.0, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.4025974025974026, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.6372105263157886e-05, | |
| "loss": 0.0, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.4069264069264069, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.584526315789473e-05, | |
| "loss": 0.0, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.41125541125541126, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.531842105263158e-05, | |
| "loss": 0.0, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.4155844155844156, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.4791578947368424e-05, | |
| "loss": 0.0, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.4199134199134199, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.426473684210526e-05, | |
| "loss": 0.0, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.42424242424242425, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.37378947368421e-05, | |
| "loss": 0.0, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.42857142857142855, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.321105263157894e-05, | |
| "loss": 0.0, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.4329004329004329, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.268421052631578e-05, | |
| "loss": 0.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.4329004329004329, | |
| "eval_loss": NaN, | |
| "eval_runtime": 8.3775, | |
| "eval_samples_per_second": 11.579, | |
| "eval_steps_per_second": 2.984, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.43722943722943725, | |
| "grad_norm": 0.3175669014453888, | |
| "learning_rate": 5.2157368421052626e-05, | |
| "loss": 0.6472, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.44155844155844154, | |
| "grad_norm": 0.3083650767803192, | |
| "learning_rate": 5.163052631578947e-05, | |
| "loss": 0.7949, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.4458874458874459, | |
| "grad_norm": 0.2869618237018585, | |
| "learning_rate": 5.110368421052632e-05, | |
| "loss": 0.6991, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.45021645021645024, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.057684210526316e-05, | |
| "loss": 0.0, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.45454545454545453, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.005e-05, | |
| "loss": 0.0, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.4588744588744589, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.9523157894736836e-05, | |
| "loss": 0.0, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.46320346320346323, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.899631578947368e-05, | |
| "loss": 0.0, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.4675324675324675, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.846947368421052e-05, | |
| "loss": 0.0, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.47186147186147187, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.794263157894737e-05, | |
| "loss": 0.0, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.47619047619047616, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.7415789473684206e-05, | |
| "loss": 0.0, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.4805194805194805, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.688894736842105e-05, | |
| "loss": 0.0, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.48484848484848486, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.636210526315789e-05, | |
| "loss": 0.0, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.48917748917748916, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.583526315789473e-05, | |
| "loss": 0.0, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.4935064935064935, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.530842105263158e-05, | |
| "loss": 0.0, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.49783549783549785, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.4781578947368416e-05, | |
| "loss": 0.0, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.5021645021645021, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.425473684210526e-05, | |
| "loss": 0.0, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.5064935064935064, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.372789473684211e-05, | |
| "loss": 0.0, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.5108225108225108, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.320105263157895e-05, | |
| "loss": 0.0, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.5151515151515151, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.2674210526315786e-05, | |
| "loss": 0.0, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.5194805194805194, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.2147368421052626e-05, | |
| "loss": 0.0, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.5238095238095238, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.162052631578947e-05, | |
| "loss": 0.0, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.5281385281385281, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.109368421052631e-05, | |
| "loss": 0.0, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.5324675324675324, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.056684210526316e-05, | |
| "loss": 0.0, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.5367965367965368, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.004e-05, | |
| "loss": 0.0, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.5411255411255411, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.951315789473684e-05, | |
| "loss": 0.0, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.5454545454545454, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.898631578947368e-05, | |
| "loss": 0.0, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.5497835497835498, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.845947368421052e-05, | |
| "loss": 0.0, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.5541125541125541, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.7932631578947367e-05, | |
| "loss": 0.0, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.5584415584415584, | |
| "grad_norm": 0.5039573311805725, | |
| "learning_rate": 3.7405789473684206e-05, | |
| "loss": 0.7812, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.5627705627705628, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.6878947368421045e-05, | |
| "loss": 0.0, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.5670995670995671, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.635210526315789e-05, | |
| "loss": 0.0, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.582526315789474e-05, | |
| "loss": 0.0, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.5757575757575758, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.5298421052631576e-05, | |
| "loss": 0.0, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.5800865800865801, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.477157894736842e-05, | |
| "loss": 0.0, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.5844155844155844, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.424473684210526e-05, | |
| "loss": 0.0, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.5887445887445888, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.37178947368421e-05, | |
| "loss": 0.0, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.5930735930735931, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.319105263157894e-05, | |
| "loss": 0.0, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.5974025974025974, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.2664210526315786e-05, | |
| "loss": 0.0, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.6017316017316018, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.213736842105263e-05, | |
| "loss": 0.0, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.6060606060606061, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.161052631578947e-05, | |
| "loss": 0.0, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.6103896103896104, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.108368421052632e-05, | |
| "loss": 0.0, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.6147186147186147, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.0556842105263156e-05, | |
| "loss": 0.0, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.6190476190476191, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.0029999999999995e-05, | |
| "loss": 0.0, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.6233766233766234, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9503157894736838e-05, | |
| "loss": 0.0, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.6277056277056277, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8976315789473684e-05, | |
| "loss": 0.0, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.6320346320346321, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8449473684210523e-05, | |
| "loss": 0.0, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.6363636363636364, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7922631578947366e-05, | |
| "loss": 0.0, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.6406926406926406, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7395789473684212e-05, | |
| "loss": 0.0, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.645021645021645, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.686894736842105e-05, | |
| "loss": 0.0, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.6493506493506493, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.634210526315789e-05, | |
| "loss": 0.0, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.6493506493506493, | |
| "eval_loss": NaN, | |
| "eval_runtime": 8.5995, | |
| "eval_samples_per_second": 11.28, | |
| "eval_steps_per_second": 2.907, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.6536796536796536, | |
| "grad_norm": 0.3423425257205963, | |
| "learning_rate": 2.5815263157894736e-05, | |
| "loss": 0.6861, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.658008658008658, | |
| "grad_norm": 0.3168509304523468, | |
| "learning_rate": 2.528842105263158e-05, | |
| "loss": 0.7967, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.6623376623376623, | |
| "grad_norm": 0.29653236269950867, | |
| "learning_rate": 2.4761578947368418e-05, | |
| "loss": 0.7314, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 0.2796725034713745, | |
| "learning_rate": 2.423473684210526e-05, | |
| "loss": 0.6499, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.670995670995671, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3707894736842103e-05, | |
| "loss": 0.0, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.6753246753246753, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3181052631578946e-05, | |
| "loss": 0.0, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.6796536796536796, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.265421052631579e-05, | |
| "loss": 0.0, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.683982683982684, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.212736842105263e-05, | |
| "loss": 0.0, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.6883116883116883, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1600526315789474e-05, | |
| "loss": 0.0, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.6926406926406926, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1073684210526313e-05, | |
| "loss": 0.0, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.696969696969697, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0546842105263155e-05, | |
| "loss": 0.0, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.7012987012987013, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.002e-05, | |
| "loss": 0.0, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.7056277056277056, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.949315789473684e-05, | |
| "loss": 0.0, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.70995670995671, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8966315789473683e-05, | |
| "loss": 0.0, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.7142857142857143, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8439473684210522e-05, | |
| "loss": 0.0, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.7186147186147186, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.791263157894737e-05, | |
| "loss": 0.0, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.7229437229437229, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.738578947368421e-05, | |
| "loss": 0.0, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.7272727272727273, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.685894736842105e-05, | |
| "loss": 0.0, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.7316017316017316, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6332105263157893e-05, | |
| "loss": 0.0, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.7359307359307359, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5805263157894735e-05, | |
| "loss": 0.0, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.7402597402597403, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5278421052631578e-05, | |
| "loss": 0.0, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.7445887445887446, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4751578947368419e-05, | |
| "loss": 0.0, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.7489177489177489, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4224736842105262e-05, | |
| "loss": 0.0, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.7532467532467533, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3697894736842106e-05, | |
| "loss": 0.0, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.7575757575757576, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3171052631578945e-05, | |
| "loss": 0.0, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.7619047619047619, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.264421052631579e-05, | |
| "loss": 0.0, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.7662337662337663, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.211736842105263e-05, | |
| "loss": 0.0, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.7705627705627706, | |
| "grad_norm": 0.4464944899082184, | |
| "learning_rate": 1.1590526315789473e-05, | |
| "loss": 0.7245, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.7748917748917749, | |
| "grad_norm": 0.42561060190200806, | |
| "learning_rate": 1.1063684210526316e-05, | |
| "loss": 0.7586, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.7792207792207793, | |
| "grad_norm": 0.4319334626197815, | |
| "learning_rate": 1.0536842105263156e-05, | |
| "loss": 0.7706, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.7835497835497836, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.001e-05, | |
| "loss": 0.0, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.7878787878787878, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.483157894736842e-06, | |
| "loss": 0.0, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.7922077922077922, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.956315789473684e-06, | |
| "loss": 0.0, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.7965367965367965, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.429473684210525e-06, | |
| "loss": 0.0, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.8008658008658008, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.902631578947368e-06, | |
| "loss": 0.0, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.8051948051948052, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.3757894736842095e-06, | |
| "loss": 0.0, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.8095238095238095, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.848947368421053e-06, | |
| "loss": 0.0, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.8138528138528138, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.322105263157895e-06, | |
| "loss": 0.0, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.8181818181818182, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.7952631578947365e-06, | |
| "loss": 0.0, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.8225108225108225, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.268421052631578e-06, | |
| "loss": 0.0, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.8268398268398268, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.741578947368421e-06, | |
| "loss": 0.0, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.8311688311688312, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.2147368421052626e-06, | |
| "loss": 0.0, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.8354978354978355, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.6878947368421047e-06, | |
| "loss": 0.0, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.8398268398268398, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.1610526315789474e-06, | |
| "loss": 0.0, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.8441558441558441, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.634210526315789e-06, | |
| "loss": 0.0, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.8484848484848485, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1073684210526313e-06, | |
| "loss": 0.0, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.8528138528138528, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5805263157894737e-06, | |
| "loss": 0.0, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.8571428571428571, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0536842105263156e-06, | |
| "loss": 0.0, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.8614718614718615, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.268421052631578e-07, | |
| "loss": 0.0, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.8658008658008658, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.8658008658008658, | |
| "eval_loss": NaN, | |
| "eval_runtime": 8.7972, | |
| "eval_samples_per_second": 11.026, | |
| "eval_steps_per_second": 2.842, | |
| "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": 1.0444398149605786e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |