| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "eval_steps": 10, | |
| "global_step": 268, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.007462686567164179, | |
| "grad_norm": 3.073047161102295, | |
| "learning_rate": 0.0, | |
| "loss": 0.5576, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.014925373134328358, | |
| "grad_norm": 4.13862419128418, | |
| "learning_rate": 2.9411764705882356e-07, | |
| "loss": 0.6964, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.022388059701492536, | |
| "grad_norm": 4.69643497467041, | |
| "learning_rate": 5.882352941176471e-07, | |
| "loss": 0.8567, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.029850746268656716, | |
| "grad_norm": 4.596504211425781, | |
| "learning_rate": 8.823529411764707e-07, | |
| "loss": 0.8257, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03731343283582089, | |
| "grad_norm": 2.9434754848480225, | |
| "learning_rate": 1.1764705882352942e-06, | |
| "loss": 0.4799, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.04477611940298507, | |
| "grad_norm": 6.064290523529053, | |
| "learning_rate": 1.4705882352941177e-06, | |
| "loss": 1.0834, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.05223880597014925, | |
| "grad_norm": 3.5080268383026123, | |
| "learning_rate": 1.7647058823529414e-06, | |
| "loss": 0.6863, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.05970149253731343, | |
| "grad_norm": 3.5126824378967285, | |
| "learning_rate": 2.058823529411765e-06, | |
| "loss": 0.6823, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.06716417910447761, | |
| "grad_norm": 2.0096919536590576, | |
| "learning_rate": 2.3529411764705885e-06, | |
| "loss": 0.5064, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.07462686567164178, | |
| "grad_norm": 2.6150012016296387, | |
| "learning_rate": 2.647058823529412e-06, | |
| "loss": 0.9675, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07462686567164178, | |
| "eval_loss": 0.3130320906639099, | |
| "eval_runtime": 15.9567, | |
| "eval_samples_per_second": 10.717, | |
| "eval_steps_per_second": 1.379, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08208955223880597, | |
| "grad_norm": 2.244316577911377, | |
| "learning_rate": 2.9411764705882355e-06, | |
| "loss": 0.6905, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.08955223880597014, | |
| "grad_norm": 1.4434276819229126, | |
| "learning_rate": 3.2352941176470594e-06, | |
| "loss": 0.6089, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.09701492537313433, | |
| "grad_norm": 2.2414164543151855, | |
| "learning_rate": 3.529411764705883e-06, | |
| "loss": 0.4699, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.1044776119402985, | |
| "grad_norm": 2.0805301666259766, | |
| "learning_rate": 3.8235294117647055e-06, | |
| "loss": 0.6048, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.11194029850746269, | |
| "grad_norm": 2.441056251525879, | |
| "learning_rate": 4.11764705882353e-06, | |
| "loss": 0.6305, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.11940298507462686, | |
| "grad_norm": 2.762195110321045, | |
| "learning_rate": 4.411764705882353e-06, | |
| "loss": 0.7118, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.12686567164179105, | |
| "grad_norm": 2.0519938468933105, | |
| "learning_rate": 4.705882352941177e-06, | |
| "loss": 0.6276, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.13432835820895522, | |
| "grad_norm": 2.0802817344665527, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6074, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.1417910447761194, | |
| "grad_norm": 2.1733672618865967, | |
| "learning_rate": 5.294117647058824e-06, | |
| "loss": 0.6163, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.14925373134328357, | |
| "grad_norm": 2.3623249530792236, | |
| "learning_rate": 5.588235294117647e-06, | |
| "loss": 0.8673, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.14925373134328357, | |
| "eval_loss": 0.29671722650527954, | |
| "eval_runtime": 16.4113, | |
| "eval_samples_per_second": 10.42, | |
| "eval_steps_per_second": 1.341, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.15671641791044777, | |
| "grad_norm": 2.0744874477386475, | |
| "learning_rate": 5.882352941176471e-06, | |
| "loss": 0.7421, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.16417910447761194, | |
| "grad_norm": 1.4317227602005005, | |
| "learning_rate": 6.176470588235295e-06, | |
| "loss": 0.6758, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.17164179104477612, | |
| "grad_norm": 1.5149955749511719, | |
| "learning_rate": 6.470588235294119e-06, | |
| "loss": 0.7199, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.1791044776119403, | |
| "grad_norm": 1.4495139122009277, | |
| "learning_rate": 6.764705882352942e-06, | |
| "loss": 0.6544, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.1865671641791045, | |
| "grad_norm": 1.240043044090271, | |
| "learning_rate": 7.058823529411766e-06, | |
| "loss": 0.3998, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.19402985074626866, | |
| "grad_norm": 1.3463258743286133, | |
| "learning_rate": 7.352941176470589e-06, | |
| "loss": 0.6238, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.20149253731343283, | |
| "grad_norm": 1.5899564027786255, | |
| "learning_rate": 7.647058823529411e-06, | |
| "loss": 0.7535, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.208955223880597, | |
| "grad_norm": 0.9583171606063843, | |
| "learning_rate": 7.941176470588236e-06, | |
| "loss": 0.4474, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.21641791044776118, | |
| "grad_norm": 1.2705698013305664, | |
| "learning_rate": 8.23529411764706e-06, | |
| "loss": 0.6322, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.22388059701492538, | |
| "grad_norm": 1.2777875661849976, | |
| "learning_rate": 8.529411764705883e-06, | |
| "loss": 0.6081, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.22388059701492538, | |
| "eval_loss": 0.2805997133255005, | |
| "eval_runtime": 16.0973, | |
| "eval_samples_per_second": 10.623, | |
| "eval_steps_per_second": 1.367, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.23134328358208955, | |
| "grad_norm": 1.2508858442306519, | |
| "learning_rate": 8.823529411764707e-06, | |
| "loss": 0.4562, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.23880597014925373, | |
| "grad_norm": 1.1761791706085205, | |
| "learning_rate": 9.11764705882353e-06, | |
| "loss": 0.5464, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.2462686567164179, | |
| "grad_norm": 1.298427939414978, | |
| "learning_rate": 9.411764705882354e-06, | |
| "loss": 0.4709, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.2537313432835821, | |
| "grad_norm": 0.7913378477096558, | |
| "learning_rate": 9.705882352941177e-06, | |
| "loss": 0.2938, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.26119402985074625, | |
| "grad_norm": 1.0940293073654175, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4555, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.26865671641791045, | |
| "grad_norm": 1.1584433317184448, | |
| "learning_rate": 9.999939000729718e-06, | |
| "loss": 0.5991, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.27611940298507465, | |
| "grad_norm": 1.0347867012023926, | |
| "learning_rate": 9.99975600440723e-06, | |
| "loss": 0.6246, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.2835820895522388, | |
| "grad_norm": 1.4303066730499268, | |
| "learning_rate": 9.999451015497595e-06, | |
| "loss": 0.652, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.291044776119403, | |
| "grad_norm": 0.8853992819786072, | |
| "learning_rate": 9.999024041442455e-06, | |
| "loss": 0.5446, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.29850746268656714, | |
| "grad_norm": 0.7761288285255432, | |
| "learning_rate": 9.99847509265985e-06, | |
| "loss": 0.2384, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.29850746268656714, | |
| "eval_loss": 0.2706838846206665, | |
| "eval_runtime": 15.7024, | |
| "eval_samples_per_second": 10.89, | |
| "eval_steps_per_second": 1.401, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.30597014925373134, | |
| "grad_norm": 1.230162262916565, | |
| "learning_rate": 9.997804182543973e-06, | |
| "loss": 0.7637, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.31343283582089554, | |
| "grad_norm": 1.2055861949920654, | |
| "learning_rate": 9.997011327464832e-06, | |
| "loss": 0.6891, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.3208955223880597, | |
| "grad_norm": 1.5400534868240356, | |
| "learning_rate": 9.99609654676786e-06, | |
| "loss": 0.7425, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.3283582089552239, | |
| "grad_norm": 1.1577208042144775, | |
| "learning_rate": 9.99505986277344e-06, | |
| "loss": 0.5395, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.3358208955223881, | |
| "grad_norm": 1.050628423690796, | |
| "learning_rate": 9.993901300776358e-06, | |
| "loss": 0.4203, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.34328358208955223, | |
| "grad_norm": 1.0624663829803467, | |
| "learning_rate": 9.99262088904519e-06, | |
| "loss": 0.6665, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.35074626865671643, | |
| "grad_norm": 1.544499158859253, | |
| "learning_rate": 9.991218658821609e-06, | |
| "loss": 0.6507, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.3582089552238806, | |
| "grad_norm": 1.3652788400650024, | |
| "learning_rate": 9.989694644319618e-06, | |
| "loss": 0.8455, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.3656716417910448, | |
| "grad_norm": 1.29508376121521, | |
| "learning_rate": 9.988048882724732e-06, | |
| "loss": 0.5849, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.373134328358209, | |
| "grad_norm": 1.6214385032653809, | |
| "learning_rate": 9.98628141419305e-06, | |
| "loss": 0.5859, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.373134328358209, | |
| "eval_loss": 0.2677931785583496, | |
| "eval_runtime": 16.2049, | |
| "eval_samples_per_second": 10.552, | |
| "eval_steps_per_second": 1.358, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3805970149253731, | |
| "grad_norm": 0.8862821459770203, | |
| "learning_rate": 9.984392281850293e-06, | |
| "loss": 0.4504, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.3880597014925373, | |
| "grad_norm": 1.047014832496643, | |
| "learning_rate": 9.982381531790733e-06, | |
| "loss": 0.4514, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.39552238805970147, | |
| "grad_norm": 1.115302324295044, | |
| "learning_rate": 9.980249213076085e-06, | |
| "loss": 0.6673, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.40298507462686567, | |
| "grad_norm": 1.1105623245239258, | |
| "learning_rate": 9.977995377734307e-06, | |
| "loss": 0.4681, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.41044776119402987, | |
| "grad_norm": 0.9929081201553345, | |
| "learning_rate": 9.975620080758321e-06, | |
| "loss": 0.5058, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.417910447761194, | |
| "grad_norm": 1.0726927518844604, | |
| "learning_rate": 9.97312338010468e-06, | |
| "loss": 0.6072, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.4253731343283582, | |
| "grad_norm": 0.9720289707183838, | |
| "learning_rate": 9.970505336692153e-06, | |
| "loss": 0.5592, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.43283582089552236, | |
| "grad_norm": 1.327181100845337, | |
| "learning_rate": 9.967766014400233e-06, | |
| "loss": 0.5153, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.44029850746268656, | |
| "grad_norm": 1.0509099960327148, | |
| "learning_rate": 9.964905480067585e-06, | |
| "loss": 0.4982, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.44776119402985076, | |
| "grad_norm": 0.8376150727272034, | |
| "learning_rate": 9.961923803490412e-06, | |
| "loss": 0.488, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.44776119402985076, | |
| "eval_loss": 0.2636841833591461, | |
| "eval_runtime": 15.6643, | |
| "eval_samples_per_second": 10.917, | |
| "eval_steps_per_second": 1.404, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.4552238805970149, | |
| "grad_norm": 1.2392864227294922, | |
| "learning_rate": 9.958821057420752e-06, | |
| "loss": 0.4786, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.4626865671641791, | |
| "grad_norm": 1.0299177169799805, | |
| "learning_rate": 9.955597317564705e-06, | |
| "loss": 0.6627, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.4701492537313433, | |
| "grad_norm": 1.244341492652893, | |
| "learning_rate": 9.95225266258058e-06, | |
| "loss": 0.8958, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.47761194029850745, | |
| "grad_norm": 0.9261450171470642, | |
| "learning_rate": 9.948787174076982e-06, | |
| "loss": 0.4079, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.48507462686567165, | |
| "grad_norm": 0.7639384269714355, | |
| "learning_rate": 9.945200936610821e-06, | |
| "loss": 0.3676, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.4925373134328358, | |
| "grad_norm": 1.1056618690490723, | |
| "learning_rate": 9.941494037685244e-06, | |
| "loss": 0.6575, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 1.5201542377471924, | |
| "learning_rate": 9.9376665677475e-06, | |
| "loss": 0.5449, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.5074626865671642, | |
| "grad_norm": 0.904944121837616, | |
| "learning_rate": 9.933718620186745e-06, | |
| "loss": 0.4245, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.5149253731343284, | |
| "grad_norm": 0.9076265096664429, | |
| "learning_rate": 9.92965029133174e-06, | |
| "loss": 0.5433, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.5223880597014925, | |
| "grad_norm": 0.8957193493843079, | |
| "learning_rate": 9.925461680448528e-06, | |
| "loss": 0.3874, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.5223880597014925, | |
| "eval_loss": 0.2620687484741211, | |
| "eval_runtime": 16.11, | |
| "eval_samples_per_second": 10.615, | |
| "eval_steps_per_second": 1.366, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.5298507462686567, | |
| "grad_norm": 1.1844974756240845, | |
| "learning_rate": 9.921152889737985e-06, | |
| "loss": 0.7415, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.5373134328358209, | |
| "grad_norm": 1.1240217685699463, | |
| "learning_rate": 9.91672402433335e-06, | |
| "loss": 0.6783, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.5447761194029851, | |
| "grad_norm": 1.0070396661758423, | |
| "learning_rate": 9.912175192297648e-06, | |
| "loss": 0.3991, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.5522388059701493, | |
| "grad_norm": 0.8779905438423157, | |
| "learning_rate": 9.907506504621052e-06, | |
| "loss": 0.3972, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.5597014925373134, | |
| "grad_norm": 1.2013908624649048, | |
| "learning_rate": 9.902718075218176e-06, | |
| "loss": 0.59, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.5671641791044776, | |
| "grad_norm": 1.4874799251556396, | |
| "learning_rate": 9.897810020925301e-06, | |
| "loss": 0.6601, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.5746268656716418, | |
| "grad_norm": 1.2102411985397339, | |
| "learning_rate": 9.892782461497521e-06, | |
| "loss": 0.6659, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.582089552238806, | |
| "grad_norm": 1.09522545337677, | |
| "learning_rate": 9.887635519605816e-06, | |
| "loss": 0.6796, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.5895522388059702, | |
| "grad_norm": 1.020628809928894, | |
| "learning_rate": 9.882369320834068e-06, | |
| "loss": 0.6041, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.5970149253731343, | |
| "grad_norm": 1.0358238220214844, | |
| "learning_rate": 9.87698399367599e-06, | |
| "loss": 0.7233, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.5970149253731343, | |
| "eval_loss": 0.2595260739326477, | |
| "eval_runtime": 16.6446, | |
| "eval_samples_per_second": 10.274, | |
| "eval_steps_per_second": 1.322, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.6044776119402985, | |
| "grad_norm": 1.099974513053894, | |
| "learning_rate": 9.871479669531988e-06, | |
| "loss": 0.6985, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.6119402985074627, | |
| "grad_norm": 1.3373053073883057, | |
| "learning_rate": 9.865856482705973e-06, | |
| "loss": 0.6532, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.6194029850746269, | |
| "grad_norm": 0.9295642971992493, | |
| "learning_rate": 9.860114570402055e-06, | |
| "loss": 0.6586, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.6268656716417911, | |
| "grad_norm": 0.8639213442802429, | |
| "learning_rate": 9.854254072721222e-06, | |
| "loss": 0.3806, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.6343283582089553, | |
| "grad_norm": 1.1236610412597656, | |
| "learning_rate": 9.848275132657903e-06, | |
| "loss": 0.5605, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.6417910447761194, | |
| "grad_norm": 1.0268014669418335, | |
| "learning_rate": 9.842177896096495e-06, | |
| "loss": 0.6164, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.6492537313432836, | |
| "grad_norm": 1.311312198638916, | |
| "learning_rate": 9.835962511807786e-06, | |
| "loss": 0.6248, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.6567164179104478, | |
| "grad_norm": 1.103390097618103, | |
| "learning_rate": 9.829629131445342e-06, | |
| "loss": 0.5902, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.664179104477612, | |
| "grad_norm": 1.1991970539093018, | |
| "learning_rate": 9.823177909541795e-06, | |
| "loss": 0.7637, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.6716417910447762, | |
| "grad_norm": 1.0043079853057861, | |
| "learning_rate": 9.816609003505073e-06, | |
| "loss": 0.5539, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.6716417910447762, | |
| "eval_loss": 0.2582014799118042, | |
| "eval_runtime": 15.6475, | |
| "eval_samples_per_second": 10.928, | |
| "eval_steps_per_second": 1.406, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.6791044776119403, | |
| "grad_norm": 0.7138786315917969, | |
| "learning_rate": 9.80992257361457e-06, | |
| "loss": 0.3945, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.6865671641791045, | |
| "grad_norm": 1.0335519313812256, | |
| "learning_rate": 9.803118783017221e-06, | |
| "loss": 0.6189, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.6940298507462687, | |
| "grad_norm": 1.3408584594726562, | |
| "learning_rate": 9.796197797723532e-06, | |
| "loss": 0.7297, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.7014925373134329, | |
| "grad_norm": 1.0914255380630493, | |
| "learning_rate": 9.789159786603524e-06, | |
| "loss": 0.6801, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.7089552238805971, | |
| "grad_norm": 1.1385866403579712, | |
| "learning_rate": 9.782004921382612e-06, | |
| "loss": 0.6327, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.7164179104477612, | |
| "grad_norm": 0.8933367133140564, | |
| "learning_rate": 9.774733376637422e-06, | |
| "loss": 0.5923, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.7238805970149254, | |
| "grad_norm": 1.1315196752548218, | |
| "learning_rate": 9.767345329791523e-06, | |
| "loss": 0.6883, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.7313432835820896, | |
| "grad_norm": 0.9604437947273254, | |
| "learning_rate": 9.759840961111098e-06, | |
| "loss": 0.5106, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.7388059701492538, | |
| "grad_norm": 1.1591802835464478, | |
| "learning_rate": 9.752220453700556e-06, | |
| "loss": 0.6319, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.746268656716418, | |
| "grad_norm": 1.2259401082992554, | |
| "learning_rate": 9.744483993498052e-06, | |
| "loss": 0.4872, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.746268656716418, | |
| "eval_loss": 0.25687727332115173, | |
| "eval_runtime": 15.7529, | |
| "eval_samples_per_second": 10.855, | |
| "eval_steps_per_second": 1.397, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.753731343283582, | |
| "grad_norm": 0.6692157983779907, | |
| "learning_rate": 9.736631769270958e-06, | |
| "loss": 0.2946, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.7611940298507462, | |
| "grad_norm": 1.2447078227996826, | |
| "learning_rate": 9.728663972611253e-06, | |
| "loss": 0.6527, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.7686567164179104, | |
| "grad_norm": 1.0134166479110718, | |
| "learning_rate": 9.720580797930845e-06, | |
| "loss": 0.5679, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.7761194029850746, | |
| "grad_norm": 1.3856276273727417, | |
| "learning_rate": 9.712382442456845e-06, | |
| "loss": 0.7747, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.7835820895522388, | |
| "grad_norm": 1.1679767370224, | |
| "learning_rate": 9.704069106226728e-06, | |
| "loss": 0.6551, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.7910447761194029, | |
| "grad_norm": 1.041477918624878, | |
| "learning_rate": 9.695640992083472e-06, | |
| "loss": 0.6679, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.7985074626865671, | |
| "grad_norm": 1.5636087656021118, | |
| "learning_rate": 9.687098305670606e-06, | |
| "loss": 0.8609, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.8059701492537313, | |
| "grad_norm": 1.0191229581832886, | |
| "learning_rate": 9.67844125542718e-06, | |
| "loss": 0.516, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.8134328358208955, | |
| "grad_norm": 1.1325874328613281, | |
| "learning_rate": 9.669670052582695e-06, | |
| "loss": 0.7177, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.8208955223880597, | |
| "grad_norm": 0.9325621128082275, | |
| "learning_rate": 9.66078491115194e-06, | |
| "loss": 0.3969, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.8208955223880597, | |
| "eval_loss": 0.25576016306877136, | |
| "eval_runtime": 15.6749, | |
| "eval_samples_per_second": 10.909, | |
| "eval_steps_per_second": 1.404, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.8283582089552238, | |
| "grad_norm": 0.9852689504623413, | |
| "learning_rate": 9.651786047929772e-06, | |
| "loss": 0.4127, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.835820895522388, | |
| "grad_norm": 1.1226204633712769, | |
| "learning_rate": 9.642673682485831e-06, | |
| "loss": 0.7266, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.8432835820895522, | |
| "grad_norm": 1.1815338134765625, | |
| "learning_rate": 9.633448037159167e-06, | |
| "loss": 0.7233, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.8507462686567164, | |
| "grad_norm": 1.067295789718628, | |
| "learning_rate": 9.624109337052839e-06, | |
| "loss": 0.7226, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.8582089552238806, | |
| "grad_norm": 0.7038566470146179, | |
| "learning_rate": 9.614657810028402e-06, | |
| "loss": 0.352, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.8656716417910447, | |
| "grad_norm": 1.0434422492980957, | |
| "learning_rate": 9.605093686700356e-06, | |
| "loss": 0.7496, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.8731343283582089, | |
| "grad_norm": 0.6814462542533875, | |
| "learning_rate": 9.595417200430517e-06, | |
| "loss": 0.3977, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.8805970149253731, | |
| "grad_norm": 1.2506330013275146, | |
| "learning_rate": 9.585628587322329e-06, | |
| "loss": 0.5536, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.8880597014925373, | |
| "grad_norm": 2.40456485748291, | |
| "learning_rate": 9.575728086215093e-06, | |
| "loss": 0.8602, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.8955223880597015, | |
| "grad_norm": 0.9782617092132568, | |
| "learning_rate": 9.565715938678146e-06, | |
| "loss": 0.5878, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.8955223880597015, | |
| "eval_loss": 0.25602081418037415, | |
| "eval_runtime": 16.0769, | |
| "eval_samples_per_second": 10.636, | |
| "eval_steps_per_second": 1.368, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.9029850746268657, | |
| "grad_norm": 0.8370435833930969, | |
| "learning_rate": 9.555592389004967e-06, | |
| "loss": 0.6102, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.9104477611940298, | |
| "grad_norm": 1.0810141563415527, | |
| "learning_rate": 9.54535768420721e-06, | |
| "loss": 0.5595, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.917910447761194, | |
| "grad_norm": 1.0081559419631958, | |
| "learning_rate": 9.535012074008688e-06, | |
| "loss": 0.4607, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.9253731343283582, | |
| "grad_norm": 0.9018644690513611, | |
| "learning_rate": 9.524555810839267e-06, | |
| "loss": 0.4455, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.9328358208955224, | |
| "grad_norm": 0.6649499535560608, | |
| "learning_rate": 9.513989149828718e-06, | |
| "loss": 0.2407, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.9402985074626866, | |
| "grad_norm": 1.1930391788482666, | |
| "learning_rate": 9.503312348800486e-06, | |
| "loss": 0.6361, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.9477611940298507, | |
| "grad_norm": 0.9348613023757935, | |
| "learning_rate": 9.4925256682654e-06, | |
| "loss": 0.4939, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.9552238805970149, | |
| "grad_norm": 1.2714776992797852, | |
| "learning_rate": 9.481629371415315e-06, | |
| "loss": 0.6854, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.9626865671641791, | |
| "grad_norm": 1.0918177366256714, | |
| "learning_rate": 9.470623724116693e-06, | |
| "loss": 0.6523, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.9701492537313433, | |
| "grad_norm": 0.747653603553772, | |
| "learning_rate": 9.459508994904119e-06, | |
| "loss": 0.4212, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.9701492537313433, | |
| "eval_loss": 0.25406235456466675, | |
| "eval_runtime": 16.5104, | |
| "eval_samples_per_second": 10.357, | |
| "eval_steps_per_second": 1.332, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.9776119402985075, | |
| "grad_norm": 0.867660641670227, | |
| "learning_rate": 9.448285454973739e-06, | |
| "loss": 0.4303, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.9850746268656716, | |
| "grad_norm": 0.9838992357254028, | |
| "learning_rate": 9.43695337817665e-06, | |
| "loss": 0.6881, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.9925373134328358, | |
| "grad_norm": 1.149843454360962, | |
| "learning_rate": 9.42551304101222e-06, | |
| "loss": 0.6812, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.6692924499511719, | |
| "learning_rate": 9.413964722621339e-06, | |
| "loss": 0.3432, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 1.007462686567164, | |
| "grad_norm": 1.6719107627868652, | |
| "learning_rate": 9.4023087047796e-06, | |
| "loss": 0.5406, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.0149253731343284, | |
| "grad_norm": 0.7576178312301636, | |
| "learning_rate": 9.390545271890438e-06, | |
| "loss": 0.4529, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 1.0223880597014925, | |
| "grad_norm": 1.1865450143814087, | |
| "learning_rate": 9.378674710978185e-06, | |
| "loss": 0.4609, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 1.0298507462686568, | |
| "grad_norm": 1.0263293981552124, | |
| "learning_rate": 9.366697311681058e-06, | |
| "loss": 0.5971, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 1.037313432835821, | |
| "grad_norm": 0.838365912437439, | |
| "learning_rate": 9.354613366244108e-06, | |
| "loss": 0.4553, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 1.044776119402985, | |
| "grad_norm": 0.9639071822166443, | |
| "learning_rate": 9.342423169512072e-06, | |
| "loss": 0.5695, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.044776119402985, | |
| "eval_loss": 0.2554219663143158, | |
| "eval_runtime": 15.7211, | |
| "eval_samples_per_second": 10.877, | |
| "eval_steps_per_second": 1.399, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.0522388059701493, | |
| "grad_norm": 1.9610925912857056, | |
| "learning_rate": 9.330127018922195e-06, | |
| "loss": 0.4975, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 1.0597014925373134, | |
| "grad_norm": 0.6606642603874207, | |
| "learning_rate": 9.31772521449696e-06, | |
| "loss": 0.1836, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 1.0671641791044777, | |
| "grad_norm": 1.3162277936935425, | |
| "learning_rate": 9.305218058836778e-06, | |
| "loss": 0.6204, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 1.0746268656716418, | |
| "grad_norm": 1.4593067169189453, | |
| "learning_rate": 9.292605857112595e-06, | |
| "loss": 0.4129, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 1.0820895522388059, | |
| "grad_norm": 0.8607202172279358, | |
| "learning_rate": 9.279888917058453e-06, | |
| "loss": 0.4644, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.0895522388059702, | |
| "grad_norm": 1.15462064743042, | |
| "learning_rate": 9.267067548963975e-06, | |
| "loss": 0.4726, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 1.0970149253731343, | |
| "grad_norm": 2.365873336791992, | |
| "learning_rate": 9.254142065666802e-06, | |
| "loss": 0.716, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 1.1044776119402986, | |
| "grad_norm": 2.1044762134552, | |
| "learning_rate": 9.241112782544953e-06, | |
| "loss": 0.4993, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 1.1119402985074627, | |
| "grad_norm": 0.7202847003936768, | |
| "learning_rate": 9.22798001750913e-06, | |
| "loss": 0.2366, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 1.1194029850746268, | |
| "grad_norm": 0.93817538022995, | |
| "learning_rate": 9.214744090994973e-06, | |
| "loss": 0.4358, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.1194029850746268, | |
| "eval_loss": 0.2571178376674652, | |
| "eval_runtime": 16.0344, | |
| "eval_samples_per_second": 10.665, | |
| "eval_steps_per_second": 1.372, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.126865671641791, | |
| "grad_norm": 1.1024166345596313, | |
| "learning_rate": 9.201405325955222e-06, | |
| "loss": 0.4351, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 1.1343283582089552, | |
| "grad_norm": 0.8645644187927246, | |
| "learning_rate": 9.187964047851851e-06, | |
| "loss": 0.4179, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 1.1417910447761195, | |
| "grad_norm": 0.6371698975563049, | |
| "learning_rate": 9.174420584648123e-06, | |
| "loss": 0.1953, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 1.1492537313432836, | |
| "grad_norm": 1.643067717552185, | |
| "learning_rate": 9.160775266800583e-06, | |
| "loss": 0.4733, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 1.1567164179104479, | |
| "grad_norm": 0.9567477703094482, | |
| "learning_rate": 9.14702842725101e-06, | |
| "loss": 0.4015, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 1.164179104477612, | |
| "grad_norm": 0.8631231784820557, | |
| "learning_rate": 9.133180401418271e-06, | |
| "loss": 0.2983, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 1.171641791044776, | |
| "grad_norm": 0.6879262328147888, | |
| "learning_rate": 9.11923152719016e-06, | |
| "loss": 0.3474, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 1.1791044776119404, | |
| "grad_norm": 0.9094505906105042, | |
| "learning_rate": 9.10518214491513e-06, | |
| "loss": 0.5146, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 1.1865671641791045, | |
| "grad_norm": 0.7373756766319275, | |
| "learning_rate": 9.091032597394012e-06, | |
| "loss": 0.3366, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 1.1940298507462686, | |
| "grad_norm": 1.2869657278060913, | |
| "learning_rate": 9.076783229871636e-06, | |
| "loss": 0.6705, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.1940298507462686, | |
| "eval_loss": 0.2553011476993561, | |
| "eval_runtime": 15.7243, | |
| "eval_samples_per_second": 10.875, | |
| "eval_steps_per_second": 1.399, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.2014925373134329, | |
| "grad_norm": 1.151159405708313, | |
| "learning_rate": 9.062434390028407e-06, | |
| "loss": 0.5876, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 1.208955223880597, | |
| "grad_norm": 1.174561858177185, | |
| "learning_rate": 9.047986427971832e-06, | |
| "loss": 0.4806, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 1.2164179104477613, | |
| "grad_norm": 1.2193154096603394, | |
| "learning_rate": 9.033439696227966e-06, | |
| "loss": 0.5455, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 1.2238805970149254, | |
| "grad_norm": 1.2365609407424927, | |
| "learning_rate": 9.018794549732819e-06, | |
| "loss": 0.4742, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 1.2313432835820897, | |
| "grad_norm": 1.3054121732711792, | |
| "learning_rate": 9.00405134582369e-06, | |
| "loss": 0.5833, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 1.2388059701492538, | |
| "grad_norm": 0.5406851172447205, | |
| "learning_rate": 8.98921044423045e-06, | |
| "loss": 0.2561, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 1.2462686567164178, | |
| "grad_norm": 1.277519702911377, | |
| "learning_rate": 8.974272207066767e-06, | |
| "loss": 0.686, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 1.2537313432835822, | |
| "grad_norm": 0.9183409810066223, | |
| "learning_rate": 8.959236998821267e-06, | |
| "loss": 0.6249, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 1.2611940298507462, | |
| "grad_norm": 0.838150143623352, | |
| "learning_rate": 8.944105186348646e-06, | |
| "loss": 0.3115, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 1.2686567164179103, | |
| "grad_norm": 0.821236252784729, | |
| "learning_rate": 8.928877138860708e-06, | |
| "loss": 0.4498, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.2686567164179103, | |
| "eval_loss": 0.2549591362476349, | |
| "eval_runtime": 15.6822, | |
| "eval_samples_per_second": 10.904, | |
| "eval_steps_per_second": 1.403, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.2761194029850746, | |
| "grad_norm": 1.1852009296417236, | |
| "learning_rate": 8.913553227917366e-06, | |
| "loss": 0.5287, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 1.2835820895522387, | |
| "grad_norm": 0.8103587627410889, | |
| "learning_rate": 8.89813382741758e-06, | |
| "loss": 0.4295, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 1.291044776119403, | |
| "grad_norm": 0.7645599246025085, | |
| "learning_rate": 8.882619313590212e-06, | |
| "loss": 0.3835, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 1.2985074626865671, | |
| "grad_norm": 0.6826095581054688, | |
| "learning_rate": 8.86701006498488e-06, | |
| "loss": 0.2922, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 1.3059701492537314, | |
| "grad_norm": 0.7371439933776855, | |
| "learning_rate": 8.851306462462689e-06, | |
| "loss": 0.305, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.3134328358208955, | |
| "grad_norm": 1.2219048738479614, | |
| "learning_rate": 8.835508889186957e-06, | |
| "loss": 0.6685, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 1.3208955223880596, | |
| "grad_norm": 0.6370560526847839, | |
| "learning_rate": 8.819617730613863e-06, | |
| "loss": 0.2816, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 1.328358208955224, | |
| "grad_norm": 0.9550657272338867, | |
| "learning_rate": 8.803633374483036e-06, | |
| "loss": 0.433, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 1.335820895522388, | |
| "grad_norm": 0.9216323494911194, | |
| "learning_rate": 8.787556210808101e-06, | |
| "loss": 0.372, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 1.3432835820895521, | |
| "grad_norm": 0.8051882386207581, | |
| "learning_rate": 8.771386631867158e-06, | |
| "loss": 0.4607, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.3432835820895521, | |
| "eval_loss": 0.255341112613678, | |
| "eval_runtime": 15.7753, | |
| "eval_samples_per_second": 10.84, | |
| "eval_steps_per_second": 1.395, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.3507462686567164, | |
| "grad_norm": 1.3185007572174072, | |
| "learning_rate": 8.755125032193215e-06, | |
| "loss": 0.731, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 1.3582089552238805, | |
| "grad_norm": 0.8819650411605835, | |
| "learning_rate": 8.738771808564555e-06, | |
| "loss": 0.3844, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 1.3656716417910448, | |
| "grad_norm": 0.9434659481048584, | |
| "learning_rate": 8.722327359995064e-06, | |
| "loss": 0.4774, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 1.373134328358209, | |
| "grad_norm": 1.0129953622817993, | |
| "learning_rate": 8.705792087724485e-06, | |
| "loss": 0.6397, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 1.3805970149253732, | |
| "grad_norm": 0.8750033378601074, | |
| "learning_rate": 8.689166395208638e-06, | |
| "loss": 0.5263, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 1.3880597014925373, | |
| "grad_norm": 0.8555174469947815, | |
| "learning_rate": 8.672450688109563e-06, | |
| "loss": 0.4434, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 1.3955223880597014, | |
| "grad_norm": 1.1890219449996948, | |
| "learning_rate": 8.655645374285637e-06, | |
| "loss": 0.4444, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 1.4029850746268657, | |
| "grad_norm": 0.8571549654006958, | |
| "learning_rate": 8.638750863781614e-06, | |
| "loss": 0.2912, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 1.4104477611940298, | |
| "grad_norm": 0.8109440207481384, | |
| "learning_rate": 8.621767568818614e-06, | |
| "loss": 0.5321, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 1.417910447761194, | |
| "grad_norm": 0.5370824933052063, | |
| "learning_rate": 8.60469590378408e-06, | |
| "loss": 0.2494, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.417910447761194, | |
| "eval_loss": 0.2551746368408203, | |
| "eval_runtime": 16.3169, | |
| "eval_samples_per_second": 10.48, | |
| "eval_steps_per_second": 1.348, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.4253731343283582, | |
| "grad_norm": 0.9776721596717834, | |
| "learning_rate": 8.587536285221656e-06, | |
| "loss": 0.4893, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 1.4328358208955223, | |
| "grad_norm": 0.8991337418556213, | |
| "learning_rate": 8.570289131821025e-06, | |
| "loss": 0.4496, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 1.4402985074626866, | |
| "grad_norm": 0.8432929515838623, | |
| "learning_rate": 8.552954864407699e-06, | |
| "loss": 0.3647, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 1.4477611940298507, | |
| "grad_norm": 0.7621536254882812, | |
| "learning_rate": 8.535533905932739e-06, | |
| "loss": 0.3156, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 1.455223880597015, | |
| "grad_norm": 0.9852966070175171, | |
| "learning_rate": 8.518026681462448e-06, | |
| "loss": 0.3542, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 1.462686567164179, | |
| "grad_norm": 1.1621863842010498, | |
| "learning_rate": 8.500433618167993e-06, | |
| "loss": 0.6648, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 1.4701492537313432, | |
| "grad_norm": 0.845145583152771, | |
| "learning_rate": 8.482755145314987e-06, | |
| "loss": 0.2917, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 1.4776119402985075, | |
| "grad_norm": 0.8889628648757935, | |
| "learning_rate": 8.464991694253001e-06, | |
| "loss": 0.3615, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 1.4850746268656716, | |
| "grad_norm": 0.9698963165283203, | |
| "learning_rate": 8.44714369840506e-06, | |
| "loss": 0.5225, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 1.4925373134328357, | |
| "grad_norm": 0.7870234251022339, | |
| "learning_rate": 8.429211593257054e-06, | |
| "loss": 0.4429, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.4925373134328357, | |
| "eval_loss": 0.2533767521381378, | |
| "eval_runtime": 16.4295, | |
| "eval_samples_per_second": 10.408, | |
| "eval_steps_per_second": 1.339, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 0.8282889127731323, | |
| "learning_rate": 8.41119581634711e-06, | |
| "loss": 0.2888, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 1.5074626865671643, | |
| "grad_norm": 1.3417259454727173, | |
| "learning_rate": 8.393096807254932e-06, | |
| "loss": 0.8644, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 1.5149253731343284, | |
| "grad_norm": 0.7999916076660156, | |
| "learning_rate": 8.374915007591053e-06, | |
| "loss": 0.4493, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 1.5223880597014925, | |
| "grad_norm": 1.507180094718933, | |
| "learning_rate": 8.356650860986083e-06, | |
| "loss": 0.4486, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 1.5298507462686568, | |
| "grad_norm": 0.8137674927711487, | |
| "learning_rate": 8.338304813079866e-06, | |
| "loss": 0.4833, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 1.537313432835821, | |
| "grad_norm": 1.2336827516555786, | |
| "learning_rate": 8.319877311510614e-06, | |
| "loss": 0.6646, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 1.544776119402985, | |
| "grad_norm": 0.9395962953567505, | |
| "learning_rate": 8.301368805903988e-06, | |
| "loss": 0.455, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 1.5522388059701493, | |
| "grad_norm": 0.9407913684844971, | |
| "learning_rate": 8.282779747862122e-06, | |
| "loss": 0.6132, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 1.5597014925373134, | |
| "grad_norm": 0.7824919819831848, | |
| "learning_rate": 8.264110590952609e-06, | |
| "loss": 0.5489, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 1.5671641791044775, | |
| "grad_norm": 0.7193758487701416, | |
| "learning_rate": 8.245361790697425e-06, | |
| "loss": 0.4639, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.5671641791044775, | |
| "eval_loss": 0.2530945837497711, | |
| "eval_runtime": 16.071, | |
| "eval_samples_per_second": 10.64, | |
| "eval_steps_per_second": 1.369, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.5746268656716418, | |
| "grad_norm": 1.141431450843811, | |
| "learning_rate": 8.226533804561828e-06, | |
| "loss": 0.6021, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 1.582089552238806, | |
| "grad_norm": 0.8864127397537231, | |
| "learning_rate": 8.207627091943178e-06, | |
| "loss": 0.5709, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 1.5895522388059702, | |
| "grad_norm": 1.565999150276184, | |
| "learning_rate": 8.188642114159748e-06, | |
| "loss": 0.4649, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 1.5970149253731343, | |
| "grad_norm": 1.0003879070281982, | |
| "learning_rate": 8.169579334439453e-06, | |
| "loss": 0.5816, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 1.6044776119402986, | |
| "grad_norm": 1.0208603143692017, | |
| "learning_rate": 8.150439217908557e-06, | |
| "loss": 0.4815, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 1.6119402985074627, | |
| "grad_norm": 0.6908705830574036, | |
| "learning_rate": 8.131222231580313e-06, | |
| "loss": 0.3388, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 1.6194029850746268, | |
| "grad_norm": 1.2532159090042114, | |
| "learning_rate": 8.11192884434358e-06, | |
| "loss": 0.6774, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 1.626865671641791, | |
| "grad_norm": 0.8950490951538086, | |
| "learning_rate": 8.092559526951374e-06, | |
| "loss": 0.6011, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 1.6343283582089554, | |
| "grad_norm": 1.6891182661056519, | |
| "learning_rate": 8.073114752009388e-06, | |
| "loss": 0.5921, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 1.6417910447761193, | |
| "grad_norm": 1.0266426801681519, | |
| "learning_rate": 8.053594993964453e-06, | |
| "loss": 0.6355, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.6417910447761193, | |
| "eval_loss": 0.25234121084213257, | |
| "eval_runtime": 16.2031, | |
| "eval_samples_per_second": 10.554, | |
| "eval_steps_per_second": 1.358, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.6492537313432836, | |
| "grad_norm": 0.7774348258972168, | |
| "learning_rate": 8.034000729092967e-06, | |
| "loss": 0.4213, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 1.6567164179104479, | |
| "grad_norm": 0.9359886646270752, | |
| "learning_rate": 8.014332435489276e-06, | |
| "loss": 0.4473, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 1.664179104477612, | |
| "grad_norm": 0.8109466433525085, | |
| "learning_rate": 7.994590593054001e-06, | |
| "loss": 0.4733, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 1.671641791044776, | |
| "grad_norm": 0.7832448482513428, | |
| "learning_rate": 7.974775683482337e-06, | |
| "loss": 0.3198, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 1.6791044776119404, | |
| "grad_norm": 1.1789060831069946, | |
| "learning_rate": 7.954888190252292e-06, | |
| "loss": 0.5846, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 1.6865671641791045, | |
| "grad_norm": 0.9324489831924438, | |
| "learning_rate": 7.934928598612896e-06, | |
| "loss": 0.3998, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 1.6940298507462686, | |
| "grad_norm": 1.1701297760009766, | |
| "learning_rate": 7.914897395572362e-06, | |
| "loss": 0.6273, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 1.7014925373134329, | |
| "grad_norm": 0.9922040700912476, | |
| "learning_rate": 7.894795069886192e-06, | |
| "loss": 0.5599, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 1.7089552238805972, | |
| "grad_norm": 0.8753315806388855, | |
| "learning_rate": 7.874622112045269e-06, | |
| "loss": 0.4123, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 1.716417910447761, | |
| "grad_norm": 1.1100213527679443, | |
| "learning_rate": 7.854379014263877e-06, | |
| "loss": 0.3805, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.716417910447761, | |
| "eval_loss": 0.2517262399196625, | |
| "eval_runtime": 15.9604, | |
| "eval_samples_per_second": 10.714, | |
| "eval_steps_per_second": 1.378, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.7238805970149254, | |
| "grad_norm": 0.9963248372077942, | |
| "learning_rate": 7.83406627046769e-06, | |
| "loss": 0.2903, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 1.7313432835820897, | |
| "grad_norm": 0.7608401775360107, | |
| "learning_rate": 7.81368437628173e-06, | |
| "loss": 0.4172, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 1.7388059701492538, | |
| "grad_norm": 1.166113018989563, | |
| "learning_rate": 7.793233829018263e-06, | |
| "loss": 0.609, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 1.7462686567164178, | |
| "grad_norm": 0.7339043617248535, | |
| "learning_rate": 7.772715127664676e-06, | |
| "loss": 0.3509, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 1.7537313432835822, | |
| "grad_norm": 1.2148951292037964, | |
| "learning_rate": 7.752128772871292e-06, | |
| "loss": 0.4682, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 1.7611940298507462, | |
| "grad_norm": 2.158393383026123, | |
| "learning_rate": 7.731475266939159e-06, | |
| "loss": 0.4768, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 1.7686567164179103, | |
| "grad_norm": 1.624114990234375, | |
| "learning_rate": 7.710755113807793e-06, | |
| "loss": 0.5563, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 1.7761194029850746, | |
| "grad_norm": 0.6288245916366577, | |
| "learning_rate": 7.689968819042884e-06, | |
| "loss": 0.2496, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 1.783582089552239, | |
| "grad_norm": 0.6780006885528564, | |
| "learning_rate": 7.669116889823955e-06, | |
| "loss": 0.243, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 1.7910447761194028, | |
| "grad_norm": 1.302188515663147, | |
| "learning_rate": 7.648199834931994e-06, | |
| "loss": 0.5689, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.7910447761194028, | |
| "eval_loss": 0.25215157866477966, | |
| "eval_runtime": 16.1686, | |
| "eval_samples_per_second": 10.576, | |
| "eval_steps_per_second": 1.361, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.7985074626865671, | |
| "grad_norm": 0.9067533016204834, | |
| "learning_rate": 7.627218164737031e-06, | |
| "loss": 0.4587, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 1.8059701492537314, | |
| "grad_norm": 0.7963538765907288, | |
| "learning_rate": 7.6061723911857e-06, | |
| "loss": 0.4912, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 1.8134328358208955, | |
| "grad_norm": 0.8649603724479675, | |
| "learning_rate": 7.58506302778873e-06, | |
| "loss": 0.3812, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 1.8208955223880596, | |
| "grad_norm": 0.5839230418205261, | |
| "learning_rate": 7.563890589608427e-06, | |
| "loss": 0.341, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 1.828358208955224, | |
| "grad_norm": 0.8967713117599487, | |
| "learning_rate": 7.542655593246103e-06, | |
| "loss": 0.5506, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 1.835820895522388, | |
| "grad_norm": 1.0193324089050293, | |
| "learning_rate": 7.52135855682947e-06, | |
| "loss": 0.7101, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 1.8432835820895521, | |
| "grad_norm": 1.0445090532302856, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 0.4873, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 1.8507462686567164, | |
| "grad_norm": 1.0798559188842773, | |
| "learning_rate": 7.478580443900247e-06, | |
| "loss": 0.6465, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 1.8582089552238807, | |
| "grad_norm": 1.5234549045562744, | |
| "learning_rate": 7.457100411161128e-06, | |
| "loss": 0.6318, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 1.8656716417910446, | |
| "grad_norm": 1.1321910619735718, | |
| "learning_rate": 7.435560425889169e-06, | |
| "loss": 0.5929, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.8656716417910446, | |
| "eval_loss": 0.25326502323150635, | |
| "eval_runtime": 15.7124, | |
| "eval_samples_per_second": 10.883, | |
| "eval_steps_per_second": 1.4, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.873134328358209, | |
| "grad_norm": 0.8814710974693298, | |
| "learning_rate": 7.413961013653725e-06, | |
| "loss": 0.413, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 1.8805970149253732, | |
| "grad_norm": 0.782132625579834, | |
| "learning_rate": 7.392302701474151e-06, | |
| "loss": 0.4623, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 1.8880597014925373, | |
| "grad_norm": 1.0612297058105469, | |
| "learning_rate": 7.370586017806942e-06, | |
| "loss": 0.6307, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 1.8955223880597014, | |
| "grad_norm": 0.7790008783340454, | |
| "learning_rate": 7.34881149253284e-06, | |
| "loss": 0.4426, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 1.9029850746268657, | |
| "grad_norm": 0.8862120509147644, | |
| "learning_rate": 7.326979656943907e-06, | |
| "loss": 0.56, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 1.9104477611940298, | |
| "grad_norm": 0.6480329632759094, | |
| "learning_rate": 7.305091043730558e-06, | |
| "loss": 0.3719, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 1.917910447761194, | |
| "grad_norm": 1.0156606435775757, | |
| "learning_rate": 7.283146186968566e-06, | |
| "loss": 0.4542, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 1.9253731343283582, | |
| "grad_norm": 0.8710734248161316, | |
| "learning_rate": 7.261145622106033e-06, | |
| "loss": 0.4221, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 1.9328358208955225, | |
| "grad_norm": 0.9503659009933472, | |
| "learning_rate": 7.239089885950317e-06, | |
| "loss": 0.474, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 1.9402985074626866, | |
| "grad_norm": 0.9117936491966248, | |
| "learning_rate": 7.216979516654944e-06, | |
| "loss": 0.5434, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.9402985074626866, | |
| "eval_loss": 0.25116848945617676, | |
| "eval_runtime": 15.9835, | |
| "eval_samples_per_second": 10.699, | |
| "eval_steps_per_second": 1.376, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.9477611940298507, | |
| "grad_norm": 0.9242149591445923, | |
| "learning_rate": 7.194815053706471e-06, | |
| "loss": 0.4634, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 1.955223880597015, | |
| "grad_norm": 1.1205576658248901, | |
| "learning_rate": 7.172597037911323e-06, | |
| "loss": 0.5393, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 1.962686567164179, | |
| "grad_norm": 0.9420229196548462, | |
| "learning_rate": 7.1503260113826035e-06, | |
| "loss": 0.5668, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 1.9701492537313432, | |
| "grad_norm": 0.8083785772323608, | |
| "learning_rate": 7.128002517526856e-06, | |
| "loss": 0.3753, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 1.9776119402985075, | |
| "grad_norm": 0.8978068232536316, | |
| "learning_rate": 7.105627101030816e-06, | |
| "loss": 0.5198, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 1.9850746268656716, | |
| "grad_norm": 0.7519446611404419, | |
| "learning_rate": 7.083200307848116e-06, | |
| "loss": 0.3855, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 1.9925373134328357, | |
| "grad_norm": 0.9396398663520813, | |
| "learning_rate": 7.060722685185961e-06, | |
| "loss": 0.4073, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 1.6269404888153076, | |
| "learning_rate": 7.038194781491785e-06, | |
| "loss": 0.3679, | |
| "step": 268 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 670, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 1.0, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.204653518707753e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |