| { | |
| "best_metric": 0.10675784200429916, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-200", | |
| "epoch": 0.5089058524173028, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002544529262086514, | |
| "grad_norm": 2.0976202487945557, | |
| "learning_rate": 1.0017e-05, | |
| "loss": 0.4494, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002544529262086514, | |
| "eval_loss": 0.6885223388671875, | |
| "eval_runtime": 10.1676, | |
| "eval_samples_per_second": 16.326, | |
| "eval_steps_per_second": 4.131, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005089058524173028, | |
| "grad_norm": 2.4291188716888428, | |
| "learning_rate": 2.0034e-05, | |
| "loss": 0.4714, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007633587786259542, | |
| "grad_norm": 2.6177380084991455, | |
| "learning_rate": 3.0050999999999997e-05, | |
| "loss": 0.4572, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.010178117048346057, | |
| "grad_norm": 2.227078676223755, | |
| "learning_rate": 4.0068e-05, | |
| "loss": 0.3751, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01272264631043257, | |
| "grad_norm": 1.521238923072815, | |
| "learning_rate": 5.0085e-05, | |
| "loss": 0.3044, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.015267175572519083, | |
| "grad_norm": 1.3237571716308594, | |
| "learning_rate": 6.0101999999999995e-05, | |
| "loss": 0.2047, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.017811704834605598, | |
| "grad_norm": 1.6091803312301636, | |
| "learning_rate": 7.0119e-05, | |
| "loss": 0.1256, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.020356234096692113, | |
| "grad_norm": 1.4948714971542358, | |
| "learning_rate": 8.0136e-05, | |
| "loss": 0.1606, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.022900763358778626, | |
| "grad_norm": 1.0482193231582642, | |
| "learning_rate": 9.0153e-05, | |
| "loss": 0.1225, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02544529262086514, | |
| "grad_norm": 1.3892583847045898, | |
| "learning_rate": 0.00010017, | |
| "loss": 0.1892, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.027989821882951654, | |
| "grad_norm": 1.202789306640625, | |
| "learning_rate": 9.964278947368421e-05, | |
| "loss": 0.1744, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.030534351145038167, | |
| "grad_norm": 1.1245602369308472, | |
| "learning_rate": 9.911557894736841e-05, | |
| "loss": 0.0761, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03307888040712468, | |
| "grad_norm": 1.1420965194702148, | |
| "learning_rate": 9.858836842105263e-05, | |
| "loss": 0.0954, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.035623409669211195, | |
| "grad_norm": 0.8061597943305969, | |
| "learning_rate": 9.806115789473684e-05, | |
| "loss": 0.1012, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.03816793893129771, | |
| "grad_norm": 1.2784687280654907, | |
| "learning_rate": 9.753394736842106e-05, | |
| "loss": 0.1408, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04071246819338423, | |
| "grad_norm": 1.0279990434646606, | |
| "learning_rate": 9.700673684210526e-05, | |
| "loss": 0.1174, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.043256997455470736, | |
| "grad_norm": 1.0930790901184082, | |
| "learning_rate": 9.647952631578948e-05, | |
| "loss": 0.0984, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04580152671755725, | |
| "grad_norm": 0.4375361502170563, | |
| "learning_rate": 9.595231578947368e-05, | |
| "loss": 0.0476, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04834605597964377, | |
| "grad_norm": 0.5908359289169312, | |
| "learning_rate": 9.542510526315789e-05, | |
| "loss": 0.0612, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.05089058524173028, | |
| "grad_norm": 0.4914228916168213, | |
| "learning_rate": 9.48978947368421e-05, | |
| "loss": 0.0473, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05343511450381679, | |
| "grad_norm": 1.2252209186553955, | |
| "learning_rate": 9.437068421052632e-05, | |
| "loss": 0.1821, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05597964376590331, | |
| "grad_norm": 0.7145554423332214, | |
| "learning_rate": 9.384347368421052e-05, | |
| "loss": 0.0709, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.058524173027989825, | |
| "grad_norm": 0.2932605445384979, | |
| "learning_rate": 9.331626315789474e-05, | |
| "loss": 0.021, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.061068702290076333, | |
| "grad_norm": 0.628063440322876, | |
| "learning_rate": 9.278905263157894e-05, | |
| "loss": 0.0734, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06361323155216285, | |
| "grad_norm": 0.48500677943229675, | |
| "learning_rate": 9.226184210526316e-05, | |
| "loss": 0.0503, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06615776081424936, | |
| "grad_norm": 0.5622182488441467, | |
| "learning_rate": 9.173463157894736e-05, | |
| "loss": 0.0558, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.06870229007633588, | |
| "grad_norm": 0.5120857357978821, | |
| "learning_rate": 9.120742105263159e-05, | |
| "loss": 0.045, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.07124681933842239, | |
| "grad_norm": 0.12333207577466965, | |
| "learning_rate": 9.068021052631579e-05, | |
| "loss": 0.0056, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0737913486005089, | |
| "grad_norm": 0.8002417087554932, | |
| "learning_rate": 9.0153e-05, | |
| "loss": 0.1115, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.07633587786259542, | |
| "grad_norm": 3.1628360748291016, | |
| "learning_rate": 8.96257894736842e-05, | |
| "loss": 0.661, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07888040712468193, | |
| "grad_norm": 1.9972189664840698, | |
| "learning_rate": 8.909857894736842e-05, | |
| "loss": 0.3344, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.08142493638676845, | |
| "grad_norm": 1.6704767942428589, | |
| "learning_rate": 8.857136842105263e-05, | |
| "loss": 0.3315, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.08396946564885496, | |
| "grad_norm": 1.8845316171646118, | |
| "learning_rate": 8.804415789473684e-05, | |
| "loss": 0.3487, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.08651399491094147, | |
| "grad_norm": 2.4319205284118652, | |
| "learning_rate": 8.751694736842105e-05, | |
| "loss": 0.3297, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.089058524173028, | |
| "grad_norm": 2.7092981338500977, | |
| "learning_rate": 8.698973684210527e-05, | |
| "loss": 0.5175, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0916030534351145, | |
| "grad_norm": 1.65862238407135, | |
| "learning_rate": 8.646252631578948e-05, | |
| "loss": 0.3395, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.09414758269720101, | |
| "grad_norm": 1.9453610181808472, | |
| "learning_rate": 8.593531578947368e-05, | |
| "loss": 0.3279, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.09669211195928754, | |
| "grad_norm": 1.8823449611663818, | |
| "learning_rate": 8.54081052631579e-05, | |
| "loss": 0.3059, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.09923664122137404, | |
| "grad_norm": 1.427621603012085, | |
| "learning_rate": 8.48808947368421e-05, | |
| "loss": 0.2756, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.10178117048346055, | |
| "grad_norm": 1.9383624792099, | |
| "learning_rate": 8.435368421052631e-05, | |
| "loss": 0.3652, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.10432569974554708, | |
| "grad_norm": 0.5723309516906738, | |
| "learning_rate": 8.382647368421053e-05, | |
| "loss": 0.0681, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.10687022900763359, | |
| "grad_norm": 1.692962884902954, | |
| "learning_rate": 8.329926315789474e-05, | |
| "loss": 0.2737, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.10941475826972011, | |
| "grad_norm": 5.488102436065674, | |
| "learning_rate": 8.277205263157894e-05, | |
| "loss": 0.3806, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.11195928753180662, | |
| "grad_norm": 2.793001890182495, | |
| "learning_rate": 8.224484210526316e-05, | |
| "loss": 0.3236, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.11450381679389313, | |
| "grad_norm": 0.8564298152923584, | |
| "learning_rate": 8.171763157894736e-05, | |
| "loss": 0.0697, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.11704834605597965, | |
| "grad_norm": 1.465958595275879, | |
| "learning_rate": 8.119042105263158e-05, | |
| "loss": 0.1509, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.11959287531806616, | |
| "grad_norm": 1.0620710849761963, | |
| "learning_rate": 8.066321052631578e-05, | |
| "loss": 0.0998, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.12213740458015267, | |
| "grad_norm": 0.551638126373291, | |
| "learning_rate": 8.0136e-05, | |
| "loss": 0.0336, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.12468193384223919, | |
| "grad_norm": 1.185890555381775, | |
| "learning_rate": 7.960878947368421e-05, | |
| "loss": 0.0431, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.1272264631043257, | |
| "grad_norm": 0.4987131953239441, | |
| "learning_rate": 7.908157894736842e-05, | |
| "loss": 0.017, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1272264631043257, | |
| "eval_loss": 0.20289373397827148, | |
| "eval_runtime": 10.1481, | |
| "eval_samples_per_second": 16.358, | |
| "eval_steps_per_second": 4.139, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1297709923664122, | |
| "grad_norm": 1.5103840827941895, | |
| "learning_rate": 7.855436842105262e-05, | |
| "loss": 0.4364, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.13231552162849872, | |
| "grad_norm": 1.3223518133163452, | |
| "learning_rate": 7.802715789473684e-05, | |
| "loss": 0.3782, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.13486005089058525, | |
| "grad_norm": 1.2647677659988403, | |
| "learning_rate": 7.749994736842104e-05, | |
| "loss": 0.401, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.13740458015267176, | |
| "grad_norm": 0.7807660102844238, | |
| "learning_rate": 7.697273684210526e-05, | |
| "loss": 0.1596, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.13994910941475827, | |
| "grad_norm": 0.8354874849319458, | |
| "learning_rate": 7.644552631578947e-05, | |
| "loss": 0.165, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.14249363867684478, | |
| "grad_norm": 0.6091985702514648, | |
| "learning_rate": 7.591831578947369e-05, | |
| "loss": 0.0962, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.1450381679389313, | |
| "grad_norm": 0.7430208325386047, | |
| "learning_rate": 7.539110526315789e-05, | |
| "loss": 0.1676, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.1475826972010178, | |
| "grad_norm": 0.6381292343139648, | |
| "learning_rate": 7.48638947368421e-05, | |
| "loss": 0.1042, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.15012722646310434, | |
| "grad_norm": 0.8650558590888977, | |
| "learning_rate": 7.433668421052632e-05, | |
| "loss": 0.1513, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.15267175572519084, | |
| "grad_norm": 0.7318075895309448, | |
| "learning_rate": 7.380947368421052e-05, | |
| "loss": 0.1286, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.15521628498727735, | |
| "grad_norm": 0.5076261758804321, | |
| "learning_rate": 7.328226315789473e-05, | |
| "loss": 0.0677, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.15776081424936386, | |
| "grad_norm": 0.5992767214775085, | |
| "learning_rate": 7.275505263157895e-05, | |
| "loss": 0.0658, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.16030534351145037, | |
| "grad_norm": 1.0940337181091309, | |
| "learning_rate": 7.222784210526316e-05, | |
| "loss": 0.1328, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.1628498727735369, | |
| "grad_norm": 0.41800355911254883, | |
| "learning_rate": 7.170063157894737e-05, | |
| "loss": 0.0529, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.16539440203562342, | |
| "grad_norm": 0.410457968711853, | |
| "learning_rate": 7.117342105263158e-05, | |
| "loss": 0.0427, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.16793893129770993, | |
| "grad_norm": 0.928383469581604, | |
| "learning_rate": 7.064621052631578e-05, | |
| "loss": 0.0959, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.17048346055979643, | |
| "grad_norm": 0.39881715178489685, | |
| "learning_rate": 7.0119e-05, | |
| "loss": 0.0456, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.17302798982188294, | |
| "grad_norm": 0.6098618507385254, | |
| "learning_rate": 6.959178947368421e-05, | |
| "loss": 0.0535, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.17557251908396945, | |
| "grad_norm": 0.6409094333648682, | |
| "learning_rate": 6.906457894736843e-05, | |
| "loss": 0.0848, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.178117048346056, | |
| "grad_norm": 0.3413279950618744, | |
| "learning_rate": 6.853736842105263e-05, | |
| "loss": 0.0257, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.1806615776081425, | |
| "grad_norm": 0.41074299812316895, | |
| "learning_rate": 6.801015789473684e-05, | |
| "loss": 0.0237, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.183206106870229, | |
| "grad_norm": 0.6176720857620239, | |
| "learning_rate": 6.748294736842105e-05, | |
| "loss": 0.0628, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.18575063613231552, | |
| "grad_norm": 0.24736110866069794, | |
| "learning_rate": 6.695573684210526e-05, | |
| "loss": 0.0158, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.18829516539440203, | |
| "grad_norm": 0.8030320405960083, | |
| "learning_rate": 6.642852631578946e-05, | |
| "loss": 0.0547, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.19083969465648856, | |
| "grad_norm": 0.46492913365364075, | |
| "learning_rate": 6.590131578947369e-05, | |
| "loss": 0.0397, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.19338422391857507, | |
| "grad_norm": 0.570913553237915, | |
| "learning_rate": 6.537410526315789e-05, | |
| "loss": 0.0731, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.19592875318066158, | |
| "grad_norm": 0.8975678086280823, | |
| "learning_rate": 6.484689473684211e-05, | |
| "loss": 0.1668, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.1984732824427481, | |
| "grad_norm": 0.10023163259029388, | |
| "learning_rate": 6.431968421052631e-05, | |
| "loss": 0.0064, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.2010178117048346, | |
| "grad_norm": 1.0112429857254028, | |
| "learning_rate": 6.379247368421052e-05, | |
| "loss": 0.1961, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.2035623409669211, | |
| "grad_norm": 1.7674541473388672, | |
| "learning_rate": 6.326526315789474e-05, | |
| "loss": 0.4854, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.20610687022900764, | |
| "grad_norm": 2.2243638038635254, | |
| "learning_rate": 6.273805263157894e-05, | |
| "loss": 0.515, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.20865139949109415, | |
| "grad_norm": 1.8203999996185303, | |
| "learning_rate": 6.221084210526315e-05, | |
| "loss": 0.4717, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.21119592875318066, | |
| "grad_norm": 1.2786808013916016, | |
| "learning_rate": 6.168363157894737e-05, | |
| "loss": 0.2411, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.21374045801526717, | |
| "grad_norm": 1.3873907327651978, | |
| "learning_rate": 6.115642105263159e-05, | |
| "loss": 0.2586, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.21628498727735368, | |
| "grad_norm": 1.169811725616455, | |
| "learning_rate": 6.0629210526315787e-05, | |
| "loss": 0.2859, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.21882951653944022, | |
| "grad_norm": 1.7699614763259888, | |
| "learning_rate": 6.0101999999999995e-05, | |
| "loss": 0.3636, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.22137404580152673, | |
| "grad_norm": 1.0457572937011719, | |
| "learning_rate": 5.95747894736842e-05, | |
| "loss": 0.2371, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.22391857506361323, | |
| "grad_norm": 1.2649692296981812, | |
| "learning_rate": 5.904757894736841e-05, | |
| "loss": 0.2149, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.22646310432569974, | |
| "grad_norm": 0.8703845143318176, | |
| "learning_rate": 5.852036842105263e-05, | |
| "loss": 0.1582, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.22900763358778625, | |
| "grad_norm": 1.6556470394134521, | |
| "learning_rate": 5.799315789473684e-05, | |
| "loss": 0.2751, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.23155216284987276, | |
| "grad_norm": 1.0715538263320923, | |
| "learning_rate": 5.746594736842105e-05, | |
| "loss": 0.2189, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.2340966921119593, | |
| "grad_norm": 1.5337820053100586, | |
| "learning_rate": 5.693873684210526e-05, | |
| "loss": 0.3324, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.2366412213740458, | |
| "grad_norm": 0.6989188194274902, | |
| "learning_rate": 5.641152631578947e-05, | |
| "loss": 0.0784, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.23918575063613232, | |
| "grad_norm": 1.108068585395813, | |
| "learning_rate": 5.588431578947368e-05, | |
| "loss": 0.1732, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.24173027989821882, | |
| "grad_norm": 0.7206950783729553, | |
| "learning_rate": 5.5357105263157896e-05, | |
| "loss": 0.08, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.24427480916030533, | |
| "grad_norm": 1.3309029340744019, | |
| "learning_rate": 5.482989473684211e-05, | |
| "loss": 0.1309, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.24681933842239187, | |
| "grad_norm": 1.4102177619934082, | |
| "learning_rate": 5.430268421052632e-05, | |
| "loss": 0.1174, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.24936386768447838, | |
| "grad_norm": 0.6907632350921631, | |
| "learning_rate": 5.377547368421053e-05, | |
| "loss": 0.0753, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.25190839694656486, | |
| "grad_norm": 0.5914320945739746, | |
| "learning_rate": 5.3248263157894736e-05, | |
| "loss": 0.0487, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.2544529262086514, | |
| "grad_norm": 0.410552054643631, | |
| "learning_rate": 5.2721052631578944e-05, | |
| "loss": 0.028, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2544529262086514, | |
| "eval_loss": 0.1450011283159256, | |
| "eval_runtime": 10.1692, | |
| "eval_samples_per_second": 16.324, | |
| "eval_steps_per_second": 4.13, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.25699745547073793, | |
| "grad_norm": 0.9659016728401184, | |
| "learning_rate": 5.219384210526315e-05, | |
| "loss": 0.2955, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.2595419847328244, | |
| "grad_norm": 0.5893524885177612, | |
| "learning_rate": 5.1666631578947374e-05, | |
| "loss": 0.158, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.26208651399491095, | |
| "grad_norm": 0.561215877532959, | |
| "learning_rate": 5.113942105263158e-05, | |
| "loss": 0.1543, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.26463104325699743, | |
| "grad_norm": 0.5634675621986389, | |
| "learning_rate": 5.061221052631579e-05, | |
| "loss": 0.1578, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.26717557251908397, | |
| "grad_norm": 0.7371407747268677, | |
| "learning_rate": 5.0085e-05, | |
| "loss": 0.1396, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.2697201017811705, | |
| "grad_norm": 0.62689608335495, | |
| "learning_rate": 4.955778947368421e-05, | |
| "loss": 0.1542, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.272264631043257, | |
| "grad_norm": 0.5553103685379028, | |
| "learning_rate": 4.903057894736842e-05, | |
| "loss": 0.0909, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.2748091603053435, | |
| "grad_norm": 0.5198187828063965, | |
| "learning_rate": 4.850336842105263e-05, | |
| "loss": 0.0785, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.27735368956743, | |
| "grad_norm": 0.7179524898529053, | |
| "learning_rate": 4.797615789473684e-05, | |
| "loss": 0.1036, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.27989821882951654, | |
| "grad_norm": 0.44508594274520874, | |
| "learning_rate": 4.744894736842105e-05, | |
| "loss": 0.1104, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.2824427480916031, | |
| "grad_norm": 0.7336511015892029, | |
| "learning_rate": 4.692173684210526e-05, | |
| "loss": 0.1067, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.28498727735368956, | |
| "grad_norm": 0.9355735778808594, | |
| "learning_rate": 4.639452631578947e-05, | |
| "loss": 0.1675, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.2875318066157761, | |
| "grad_norm": 0.46843382716178894, | |
| "learning_rate": 4.586731578947368e-05, | |
| "loss": 0.0723, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.2900763358778626, | |
| "grad_norm": 0.5565648078918457, | |
| "learning_rate": 4.5340105263157894e-05, | |
| "loss": 0.0579, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.2926208651399491, | |
| "grad_norm": 0.35323649644851685, | |
| "learning_rate": 4.48128947368421e-05, | |
| "loss": 0.0532, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.2951653944020356, | |
| "grad_norm": 0.41509339213371277, | |
| "learning_rate": 4.428568421052632e-05, | |
| "loss": 0.0788, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.29770992366412213, | |
| "grad_norm": 0.4781738817691803, | |
| "learning_rate": 4.3758473684210525e-05, | |
| "loss": 0.0939, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.30025445292620867, | |
| "grad_norm": 0.5751485824584961, | |
| "learning_rate": 4.323126315789474e-05, | |
| "loss": 0.0883, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.30279898218829515, | |
| "grad_norm": 0.2596683204174042, | |
| "learning_rate": 4.270405263157895e-05, | |
| "loss": 0.0365, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.3053435114503817, | |
| "grad_norm": 0.572528600692749, | |
| "learning_rate": 4.217684210526316e-05, | |
| "loss": 0.0871, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.30788804071246817, | |
| "grad_norm": 0.5119253396987915, | |
| "learning_rate": 4.164963157894737e-05, | |
| "loss": 0.0973, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.3104325699745547, | |
| "grad_norm": 0.5054477453231812, | |
| "learning_rate": 4.112242105263158e-05, | |
| "loss": 0.0494, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.31297709923664124, | |
| "grad_norm": 0.3897090256214142, | |
| "learning_rate": 4.059521052631579e-05, | |
| "loss": 0.0333, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.3155216284987277, | |
| "grad_norm": 0.2573760747909546, | |
| "learning_rate": 4.0068e-05, | |
| "loss": 0.0229, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.31806615776081426, | |
| "grad_norm": 0.28332197666168213, | |
| "learning_rate": 3.954078947368421e-05, | |
| "loss": 0.0257, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.32061068702290074, | |
| "grad_norm": 0.446418434381485, | |
| "learning_rate": 3.901357894736842e-05, | |
| "loss": 0.0825, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.3231552162849873, | |
| "grad_norm": 0.29756420850753784, | |
| "learning_rate": 3.848636842105263e-05, | |
| "loss": 0.0242, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.3256997455470738, | |
| "grad_norm": 0.5935866236686707, | |
| "learning_rate": 3.795915789473684e-05, | |
| "loss": 0.0925, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.3282442748091603, | |
| "grad_norm": 0.2986157536506653, | |
| "learning_rate": 3.743194736842105e-05, | |
| "loss": 0.0154, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.33078880407124683, | |
| "grad_norm": 0.03564433753490448, | |
| "learning_rate": 3.690473684210526e-05, | |
| "loss": 0.0024, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.3333333333333333, | |
| "grad_norm": 0.021472949534654617, | |
| "learning_rate": 3.6377526315789475e-05, | |
| "loss": 0.0011, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.33587786259541985, | |
| "grad_norm": 1.2343424558639526, | |
| "learning_rate": 3.585031578947368e-05, | |
| "loss": 0.3226, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.3384223918575064, | |
| "grad_norm": 1.3323383331298828, | |
| "learning_rate": 3.532310526315789e-05, | |
| "loss": 0.2967, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.34096692111959287, | |
| "grad_norm": 1.58578360080719, | |
| "learning_rate": 3.4795894736842106e-05, | |
| "loss": 0.2687, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.3435114503816794, | |
| "grad_norm": 1.3783105611801147, | |
| "learning_rate": 3.4268684210526314e-05, | |
| "loss": 0.2798, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.3460559796437659, | |
| "grad_norm": 1.470922827720642, | |
| "learning_rate": 3.374147368421052e-05, | |
| "loss": 0.3177, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.3486005089058524, | |
| "grad_norm": 1.449453592300415, | |
| "learning_rate": 3.321426315789473e-05, | |
| "loss": 0.1875, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.3511450381679389, | |
| "grad_norm": 1.273271083831787, | |
| "learning_rate": 3.2687052631578946e-05, | |
| "loss": 0.2517, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.35368956743002544, | |
| "grad_norm": 1.2989132404327393, | |
| "learning_rate": 3.2159842105263154e-05, | |
| "loss": 0.1741, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.356234096692112, | |
| "grad_norm": 1.1349838972091675, | |
| "learning_rate": 3.163263157894737e-05, | |
| "loss": 0.2073, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.35877862595419846, | |
| "grad_norm": 1.2873899936676025, | |
| "learning_rate": 3.110542105263158e-05, | |
| "loss": 0.1692, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.361323155216285, | |
| "grad_norm": 1.297892689704895, | |
| "learning_rate": 3.057821052631579e-05, | |
| "loss": 0.1529, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.3638676844783715, | |
| "grad_norm": 1.0262969732284546, | |
| "learning_rate": 3.0050999999999997e-05, | |
| "loss": 0.1269, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.366412213740458, | |
| "grad_norm": 1.489499807357788, | |
| "learning_rate": 2.9523789473684206e-05, | |
| "loss": 0.2182, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.36895674300254455, | |
| "grad_norm": 2.6656413078308105, | |
| "learning_rate": 2.899657894736842e-05, | |
| "loss": 0.1811, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.37150127226463103, | |
| "grad_norm": 1.5800155401229858, | |
| "learning_rate": 2.846936842105263e-05, | |
| "loss": 0.1364, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.37404580152671757, | |
| "grad_norm": 0.6563022136688232, | |
| "learning_rate": 2.794215789473684e-05, | |
| "loss": 0.0965, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.37659033078880405, | |
| "grad_norm": 1.1012194156646729, | |
| "learning_rate": 2.7414947368421056e-05, | |
| "loss": 0.097, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.3791348600508906, | |
| "grad_norm": 1.3474540710449219, | |
| "learning_rate": 2.6887736842105264e-05, | |
| "loss": 0.1278, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.3816793893129771, | |
| "grad_norm": 1.2162439823150635, | |
| "learning_rate": 2.6360526315789472e-05, | |
| "loss": 0.1464, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.3816793893129771, | |
| "eval_loss": 0.1360974758863449, | |
| "eval_runtime": 10.1762, | |
| "eval_samples_per_second": 16.313, | |
| "eval_steps_per_second": 4.127, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.3842239185750636, | |
| "grad_norm": 0.6443613767623901, | |
| "learning_rate": 2.5833315789473687e-05, | |
| "loss": 0.2032, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.38676844783715014, | |
| "grad_norm": 0.7321302890777588, | |
| "learning_rate": 2.5306105263157895e-05, | |
| "loss": 0.1961, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.3893129770992366, | |
| "grad_norm": 0.7189200520515442, | |
| "learning_rate": 2.4778894736842104e-05, | |
| "loss": 0.1966, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.39185750636132316, | |
| "grad_norm": 0.6960674524307251, | |
| "learning_rate": 2.4251684210526315e-05, | |
| "loss": 0.2118, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.3944020356234097, | |
| "grad_norm": 0.7753060460090637, | |
| "learning_rate": 2.3724473684210524e-05, | |
| "loss": 0.2101, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.3969465648854962, | |
| "grad_norm": 0.5562716126441956, | |
| "learning_rate": 2.3197263157894735e-05, | |
| "loss": 0.1283, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.3994910941475827, | |
| "grad_norm": 0.37449532747268677, | |
| "learning_rate": 2.2670052631578947e-05, | |
| "loss": 0.1007, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.4020356234096692, | |
| "grad_norm": 0.5224964022636414, | |
| "learning_rate": 2.214284210526316e-05, | |
| "loss": 0.1294, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.40458015267175573, | |
| "grad_norm": 0.3669807016849518, | |
| "learning_rate": 2.161563157894737e-05, | |
| "loss": 0.0846, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.4071246819338422, | |
| "grad_norm": 0.5417796969413757, | |
| "learning_rate": 2.108842105263158e-05, | |
| "loss": 0.12, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.40966921119592875, | |
| "grad_norm": 0.506889820098877, | |
| "learning_rate": 2.056121052631579e-05, | |
| "loss": 0.0786, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.4122137404580153, | |
| "grad_norm": 0.49759092926979065, | |
| "learning_rate": 2.0034e-05, | |
| "loss": 0.093, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.41475826972010177, | |
| "grad_norm": 0.29034364223480225, | |
| "learning_rate": 1.950678947368421e-05, | |
| "loss": 0.0639, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.4173027989821883, | |
| "grad_norm": 0.6314502358436584, | |
| "learning_rate": 1.897957894736842e-05, | |
| "loss": 0.1211, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.4198473282442748, | |
| "grad_norm": 0.23841609060764313, | |
| "learning_rate": 1.845236842105263e-05, | |
| "loss": 0.0461, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.4223918575063613, | |
| "grad_norm": 0.35829946398735046, | |
| "learning_rate": 1.792515789473684e-05, | |
| "loss": 0.0773, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.42493638676844786, | |
| "grad_norm": 0.43481776118278503, | |
| "learning_rate": 1.7397947368421053e-05, | |
| "loss": 0.0921, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.42748091603053434, | |
| "grad_norm": 0.35226166248321533, | |
| "learning_rate": 1.687073684210526e-05, | |
| "loss": 0.0594, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.4300254452926209, | |
| "grad_norm": 0.5202860832214355, | |
| "learning_rate": 1.6343526315789473e-05, | |
| "loss": 0.0986, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.43256997455470736, | |
| "grad_norm": 0.23757660388946533, | |
| "learning_rate": 1.5816315789473685e-05, | |
| "loss": 0.032, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.4351145038167939, | |
| "grad_norm": 0.27789339423179626, | |
| "learning_rate": 1.5289105263157896e-05, | |
| "loss": 0.0438, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.43765903307888043, | |
| "grad_norm": 0.41914746165275574, | |
| "learning_rate": 1.4761894736842103e-05, | |
| "loss": 0.0462, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.4402035623409669, | |
| "grad_norm": 0.2738276720046997, | |
| "learning_rate": 1.4234684210526314e-05, | |
| "loss": 0.0293, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.44274809160305345, | |
| "grad_norm": 0.4610910713672638, | |
| "learning_rate": 1.3707473684210528e-05, | |
| "loss": 0.0522, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.44529262086513993, | |
| "grad_norm": 0.18284475803375244, | |
| "learning_rate": 1.3180263157894736e-05, | |
| "loss": 0.0267, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.44783715012722647, | |
| "grad_norm": 0.2613477110862732, | |
| "learning_rate": 1.2653052631578948e-05, | |
| "loss": 0.0191, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.45038167938931295, | |
| "grad_norm": 0.21745839715003967, | |
| "learning_rate": 1.2125842105263158e-05, | |
| "loss": 0.0267, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.4529262086513995, | |
| "grad_norm": 0.6353086829185486, | |
| "learning_rate": 1.1598631578947368e-05, | |
| "loss": 0.0828, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.455470737913486, | |
| "grad_norm": 1.0890721082687378, | |
| "learning_rate": 1.107142105263158e-05, | |
| "loss": 0.3399, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.4580152671755725, | |
| "grad_norm": 0.9117040038108826, | |
| "learning_rate": 1.054421052631579e-05, | |
| "loss": 0.2736, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.46055979643765904, | |
| "grad_norm": 1.2923952341079712, | |
| "learning_rate": 1.0017e-05, | |
| "loss": 0.267, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.4631043256997455, | |
| "grad_norm": 0.9573558568954468, | |
| "learning_rate": 9.48978947368421e-06, | |
| "loss": 0.2016, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.46564885496183206, | |
| "grad_norm": 0.787228524684906, | |
| "learning_rate": 8.96257894736842e-06, | |
| "loss": 0.1423, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.4681933842239186, | |
| "grad_norm": 1.1528656482696533, | |
| "learning_rate": 8.43536842105263e-06, | |
| "loss": 0.2141, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.4707379134860051, | |
| "grad_norm": 2.192894220352173, | |
| "learning_rate": 7.908157894736842e-06, | |
| "loss": 0.3117, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.4732824427480916, | |
| "grad_norm": 1.0140397548675537, | |
| "learning_rate": 7.380947368421051e-06, | |
| "loss": 0.1539, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.4758269720101781, | |
| "grad_norm": 1.4267032146453857, | |
| "learning_rate": 6.853736842105264e-06, | |
| "loss": 0.2976, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.47837150127226463, | |
| "grad_norm": 1.1065343618392944, | |
| "learning_rate": 6.326526315789474e-06, | |
| "loss": 0.2073, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.48091603053435117, | |
| "grad_norm": 1.1713448762893677, | |
| "learning_rate": 5.799315789473684e-06, | |
| "loss": 0.1977, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.48346055979643765, | |
| "grad_norm": 0.6917346119880676, | |
| "learning_rate": 5.272105263157895e-06, | |
| "loss": 0.0885, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.4860050890585242, | |
| "grad_norm": 1.0129892826080322, | |
| "learning_rate": 4.744894736842105e-06, | |
| "loss": 0.1472, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.48854961832061067, | |
| "grad_norm": 1.470230221748352, | |
| "learning_rate": 4.217684210526315e-06, | |
| "loss": 0.22, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.4910941475826972, | |
| "grad_norm": 0.406305730342865, | |
| "learning_rate": 3.6904736842105257e-06, | |
| "loss": 0.0418, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.49363867684478374, | |
| "grad_norm": 1.7621744871139526, | |
| "learning_rate": 3.163263157894737e-06, | |
| "loss": 0.2434, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.4961832061068702, | |
| "grad_norm": 1.2661513090133667, | |
| "learning_rate": 2.6360526315789473e-06, | |
| "loss": 0.1978, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.49872773536895676, | |
| "grad_norm": 1.6431432962417603, | |
| "learning_rate": 2.1088421052631577e-06, | |
| "loss": 0.2335, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.5012722646310432, | |
| "grad_norm": 1.3212987184524536, | |
| "learning_rate": 1.5816315789473685e-06, | |
| "loss": 0.0987, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.5038167938931297, | |
| "grad_norm": 0.8376440405845642, | |
| "learning_rate": 1.0544210526315788e-06, | |
| "loss": 0.0621, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.5063613231552163, | |
| "grad_norm": 0.5887414216995239, | |
| "learning_rate": 5.272105263157894e-07, | |
| "loss": 0.0602, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.5089058524173028, | |
| "grad_norm": 0.6141554117202759, | |
| "learning_rate": 0.0, | |
| "loss": 0.0582, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.5089058524173028, | |
| "eval_loss": 0.10675784200429916, | |
| "eval_runtime": 10.1526, | |
| "eval_samples_per_second": 16.35, | |
| "eval_steps_per_second": 4.137, | |
| "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": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.3676760973312e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |