| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.1718213058419244, | |
| "eval_steps": 9, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001718213058419244, | |
| "grad_norm": 16.851408004760742, | |
| "learning_rate": 1e-05, | |
| "loss": 16.6484, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001718213058419244, | |
| "eval_loss": 16.627044677734375, | |
| "eval_runtime": 9.9282, | |
| "eval_samples_per_second": 49.354, | |
| "eval_steps_per_second": 6.245, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003436426116838488, | |
| "grad_norm": 16.717243194580078, | |
| "learning_rate": 2e-05, | |
| "loss": 16.3156, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.005154639175257732, | |
| "grad_norm": 16.413101196289062, | |
| "learning_rate": 3e-05, | |
| "loss": 16.6699, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006872852233676976, | |
| "grad_norm": 16.836313247680664, | |
| "learning_rate": 4e-05, | |
| "loss": 16.6116, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00859106529209622, | |
| "grad_norm": 16.442672729492188, | |
| "learning_rate": 5e-05, | |
| "loss": 16.358, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.010309278350515464, | |
| "grad_norm": 14.661097526550293, | |
| "learning_rate": 6e-05, | |
| "loss": 15.7403, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.012027491408934709, | |
| "grad_norm": 15.021746635437012, | |
| "learning_rate": 7e-05, | |
| "loss": 16.1866, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.013745704467353952, | |
| "grad_norm": 13.62826919555664, | |
| "learning_rate": 8e-05, | |
| "loss": 15.7283, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.015463917525773196, | |
| "grad_norm": 12.390254974365234, | |
| "learning_rate": 9e-05, | |
| "loss": 15.0803, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.015463917525773196, | |
| "eval_loss": 14.207258224487305, | |
| "eval_runtime": 8.7119, | |
| "eval_samples_per_second": 56.245, | |
| "eval_steps_per_second": 7.117, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01718213058419244, | |
| "grad_norm": 11.050700187683105, | |
| "learning_rate": 0.0001, | |
| "loss": 14.3405, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.018900343642611683, | |
| "grad_norm": 10.292141914367676, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 13.1701, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.020618556701030927, | |
| "grad_norm": 12.430923461914062, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 13.263, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.022336769759450172, | |
| "grad_norm": 11.984938621520996, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 12.0077, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.024054982817869417, | |
| "grad_norm": 13.232406616210938, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 12.0673, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.02577319587628866, | |
| "grad_norm": 12.7660493850708, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 10.8489, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.027491408934707903, | |
| "grad_norm": 13.3019437789917, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 10.213, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.029209621993127148, | |
| "grad_norm": 13.64773178100586, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 9.3943, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.030927835051546393, | |
| "grad_norm": 14.809378623962402, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 8.7002, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.030927835051546393, | |
| "eval_loss": 8.073286056518555, | |
| "eval_runtime": 8.6987, | |
| "eval_samples_per_second": 56.33, | |
| "eval_steps_per_second": 7.128, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.03264604810996564, | |
| "grad_norm": 15.218389511108398, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 7.7854, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.03436426116838488, | |
| "grad_norm": 13.829675674438477, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 7.2369, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03608247422680412, | |
| "grad_norm": 12.88297176361084, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 5.9757, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.037800687285223365, | |
| "grad_norm": 10.21223258972168, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 5.9149, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.03951890034364261, | |
| "grad_norm": 9.509270668029785, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 5.1372, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.041237113402061855, | |
| "grad_norm": 9.279484748840332, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 4.7909, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0429553264604811, | |
| "grad_norm": 8.418981552124023, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 4.4278, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.044673539518900345, | |
| "grad_norm": 7.834316253662109, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 4.2375, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.04639175257731959, | |
| "grad_norm": 4.54257869720459, | |
| "learning_rate": 9.145187862775209e-05, | |
| "loss": 3.4823, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.04639175257731959, | |
| "eval_loss": 3.497758388519287, | |
| "eval_runtime": 8.7435, | |
| "eval_samples_per_second": 56.042, | |
| "eval_steps_per_second": 7.091, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.048109965635738834, | |
| "grad_norm": 3.5246834754943848, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 3.2534, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.04982817869415808, | |
| "grad_norm": 2.8932206630706787, | |
| "learning_rate": 8.940053768033609e-05, | |
| "loss": 3.0302, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.05154639175257732, | |
| "grad_norm": 4.531274795532227, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 3.1251, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05326460481099656, | |
| "grad_norm": 3.05279803276062, | |
| "learning_rate": 8.715724127386972e-05, | |
| "loss": 2.8615, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.054982817869415807, | |
| "grad_norm": 4.427277088165283, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 2.807, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.05670103092783505, | |
| "grad_norm": 3.3197824954986572, | |
| "learning_rate": 8.473291852294987e-05, | |
| "loss": 2.6673, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.058419243986254296, | |
| "grad_norm": 3.382016897201538, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 2.5111, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.06013745704467354, | |
| "grad_norm": 3.760643482208252, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 2.4273, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.061855670103092786, | |
| "grad_norm": 4.035512924194336, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 2.3342, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.061855670103092786, | |
| "eval_loss": 2.2023770809173584, | |
| "eval_runtime": 8.6946, | |
| "eval_samples_per_second": 56.357, | |
| "eval_steps_per_second": 7.131, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.06357388316151202, | |
| "grad_norm": 3.8396847248077393, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 2.1292, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.06529209621993128, | |
| "grad_norm": 4.242040157318115, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 1.988, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.06701030927835051, | |
| "grad_norm": 5.146888256072998, | |
| "learning_rate": 7.649596321166024e-05, | |
| "loss": 1.9038, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.06872852233676977, | |
| "grad_norm": 3.964784622192383, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.6303, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.070446735395189, | |
| "grad_norm": 3.849836826324463, | |
| "learning_rate": 7.347357813929454e-05, | |
| "loss": 1.4865, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.07216494845360824, | |
| "grad_norm": 3.7047228813171387, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 1.3345, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.07388316151202749, | |
| "grad_norm": 3.9774022102355957, | |
| "learning_rate": 7.033683215379002e-05, | |
| "loss": 1.2022, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.07560137457044673, | |
| "grad_norm": 3.579848527908325, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 1.0866, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.07731958762886598, | |
| "grad_norm": 4.896625518798828, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 0.9897, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.07731958762886598, | |
| "eval_loss": 0.9358645081520081, | |
| "eval_runtime": 8.7052, | |
| "eval_samples_per_second": 56.288, | |
| "eval_steps_per_second": 7.122, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.07903780068728522, | |
| "grad_norm": 3.324166774749756, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.8361, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.08075601374570447, | |
| "grad_norm": 2.9657347202301025, | |
| "learning_rate": 6.378186779084995e-05, | |
| "loss": 0.7752, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.08247422680412371, | |
| "grad_norm": 7.9927659034729, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 0.9171, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.08419243986254296, | |
| "grad_norm": 2.4020230770111084, | |
| "learning_rate": 6.0395584540887963e-05, | |
| "loss": 0.5936, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0859106529209622, | |
| "grad_norm": 2.2517313957214355, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 0.526, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08762886597938144, | |
| "grad_norm": 1.9767582416534424, | |
| "learning_rate": 5.695865504800327e-05, | |
| "loss": 0.4614, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.08934707903780069, | |
| "grad_norm": 1.8230546712875366, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 0.4171, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.09106529209621993, | |
| "grad_norm": 1.681349515914917, | |
| "learning_rate": 5.348782368720626e-05, | |
| "loss": 0.3586, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.09278350515463918, | |
| "grad_norm": 1.5400270223617554, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 0.3335, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.09278350515463918, | |
| "eval_loss": 0.33134225010871887, | |
| "eval_runtime": 8.7597, | |
| "eval_samples_per_second": 55.938, | |
| "eval_steps_per_second": 7.078, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.09450171821305842, | |
| "grad_norm": 1.304337501525879, | |
| "learning_rate": 5e-05, | |
| "loss": 0.2771, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.09621993127147767, | |
| "grad_norm": 1.19948148727417, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 0.2577, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.0979381443298969, | |
| "grad_norm": 2.155170440673828, | |
| "learning_rate": 4.6512176312793736e-05, | |
| "loss": 0.2378, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.09965635738831616, | |
| "grad_norm": 0.991316020488739, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 0.2219, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.1013745704467354, | |
| "grad_norm": 0.8723356127738953, | |
| "learning_rate": 4.3041344951996746e-05, | |
| "loss": 0.1829, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.10309278350515463, | |
| "grad_norm": 0.7809861898422241, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 0.1648, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.10481099656357389, | |
| "grad_norm": 4.812243938446045, | |
| "learning_rate": 3.960441545911204e-05, | |
| "loss": 0.5258, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.10652920962199312, | |
| "grad_norm": 0.6602714657783508, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 0.1331, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.10824742268041238, | |
| "grad_norm": 0.6083123087882996, | |
| "learning_rate": 3.6218132209150045e-05, | |
| "loss": 0.1235, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.10824742268041238, | |
| "eval_loss": 0.1572849601507187, | |
| "eval_runtime": 8.7062, | |
| "eval_samples_per_second": 56.282, | |
| "eval_steps_per_second": 7.121, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.10996563573883161, | |
| "grad_norm": 0.5714665055274963, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.1153, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.11168384879725086, | |
| "grad_norm": 0.5366259813308716, | |
| "learning_rate": 3.289899283371657e-05, | |
| "loss": 0.1106, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.1134020618556701, | |
| "grad_norm": 2.607645273208618, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 0.1287, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.11512027491408934, | |
| "grad_norm": 0.46359169483184814, | |
| "learning_rate": 2.9663167846209998e-05, | |
| "loss": 0.0965, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.11683848797250859, | |
| "grad_norm": 0.4538125693798065, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 0.0943, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.11855670103092783, | |
| "grad_norm": 0.4187633991241455, | |
| "learning_rate": 2.6526421860705473e-05, | |
| "loss": 0.0864, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.12027491408934708, | |
| "grad_norm": 0.6285544633865356, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.1119, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.12199312714776632, | |
| "grad_norm": 2.7116782665252686, | |
| "learning_rate": 2.350403678833976e-05, | |
| "loss": 0.1012, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.12371134020618557, | |
| "grad_norm": 0.34447985887527466, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 0.0739, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.12371134020618557, | |
| "eval_loss": 0.10849026590585709, | |
| "eval_runtime": 8.7182, | |
| "eval_samples_per_second": 56.204, | |
| "eval_steps_per_second": 7.112, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.1254295532646048, | |
| "grad_norm": 0.3649945557117462, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 0.0748, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.12714776632302405, | |
| "grad_norm": 0.3274010419845581, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 0.0695, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.12886597938144329, | |
| "grad_norm": 0.3254413902759552, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 0.0677, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.13058419243986255, | |
| "grad_norm": 3.348130702972412, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 0.1091, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.1323024054982818, | |
| "grad_norm": 6.107163906097412, | |
| "learning_rate": 1.526708147705013e-05, | |
| "loss": 0.5306, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.13402061855670103, | |
| "grad_norm": 0.3043591380119324, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 0.0641, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.13573883161512026, | |
| "grad_norm": 0.302204430103302, | |
| "learning_rate": 1.2842758726130283e-05, | |
| "loss": 0.0642, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.13745704467353953, | |
| "grad_norm": 0.28447940945625305, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 0.0613, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.13917525773195877, | |
| "grad_norm": 0.27646705508232117, | |
| "learning_rate": 1.0599462319663905e-05, | |
| "loss": 0.0605, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.13917525773195877, | |
| "eval_loss": 0.09266447275876999, | |
| "eval_runtime": 8.7152, | |
| "eval_samples_per_second": 56.224, | |
| "eval_steps_per_second": 7.114, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.140893470790378, | |
| "grad_norm": 0.8577637672424316, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.0687, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.14261168384879724, | |
| "grad_norm": 0.28629401326179504, | |
| "learning_rate": 8.548121372247918e-06, | |
| "loss": 0.0606, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.14432989690721648, | |
| "grad_norm": 0.4762267768383026, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 0.0751, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.14604810996563575, | |
| "grad_norm": 0.2938355803489685, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.0586, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.14776632302405499, | |
| "grad_norm": 0.28194454312324524, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 0.0568, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.14948453608247422, | |
| "grad_norm": 0.28809523582458496, | |
| "learning_rate": 5.060297685041659e-06, | |
| "loss": 0.0584, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.15120274914089346, | |
| "grad_norm": 0.25631386041641235, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 0.0542, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.15292096219931273, | |
| "grad_norm": 0.3819483518600464, | |
| "learning_rate": 3.6408072716606346e-06, | |
| "loss": 0.0594, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.15463917525773196, | |
| "grad_norm": 0.467550665140152, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 0.0749, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.15463917525773196, | |
| "eval_loss": 0.08718819171190262, | |
| "eval_runtime": 8.6945, | |
| "eval_samples_per_second": 56.358, | |
| "eval_steps_per_second": 7.131, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.1563573883161512, | |
| "grad_norm": 0.3134761154651642, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 0.0602, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.15807560137457044, | |
| "grad_norm": 0.268108069896698, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 0.0575, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.15979381443298968, | |
| "grad_norm": 0.2512245774269104, | |
| "learning_rate": 1.4852136862001764e-06, | |
| "loss": 0.0544, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.16151202749140894, | |
| "grad_norm": 2.219799280166626, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 0.0984, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.16323024054982818, | |
| "grad_norm": 0.2962862253189087, | |
| "learning_rate": 7.596123493895991e-07, | |
| "loss": 0.0569, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.16494845360824742, | |
| "grad_norm": 0.2534407079219818, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 0.0563, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.16666666666666666, | |
| "grad_norm": 0.30495700240135193, | |
| "learning_rate": 2.7390523158633554e-07, | |
| "loss": 0.0575, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.16838487972508592, | |
| "grad_norm": 0.5423720479011536, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 0.0793, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.17010309278350516, | |
| "grad_norm": 0.25193852186203003, | |
| "learning_rate": 3.04586490452119e-08, | |
| "loss": 0.055, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.17010309278350516, | |
| "eval_loss": 0.08638428151607513, | |
| "eval_runtime": 8.6961, | |
| "eval_samples_per_second": 56.347, | |
| "eval_steps_per_second": 7.13, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.1718213058419244, | |
| "grad_norm": 0.30860844254493713, | |
| "learning_rate": 0.0, | |
| "loss": 0.0568, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2665681652809728.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |