| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 6.589743589743589, | |
| "eval_steps": 5, | |
| "global_step": 133, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05128205128205128, | |
| "grad_norm": 30.696048736572266, | |
| "learning_rate": 2e-07, | |
| "loss": 2.6145, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05128205128205128, | |
| "eval_loss": 2.721662998199463, | |
| "eval_runtime": 0.1874, | |
| "eval_samples_per_second": 165.427, | |
| "eval_steps_per_second": 26.682, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.10256410256410256, | |
| "grad_norm": 31.234418869018555, | |
| "learning_rate": 4e-07, | |
| "loss": 2.839, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.15384615384615385, | |
| "grad_norm": 26.09066390991211, | |
| "learning_rate": 6e-07, | |
| "loss": 2.804, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.20512820512820512, | |
| "grad_norm": 25.11672019958496, | |
| "learning_rate": 8e-07, | |
| "loss": 2.7178, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.2564102564102564, | |
| "grad_norm": 25.194042205810547, | |
| "learning_rate": 1e-06, | |
| "loss": 2.7668, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.2564102564102564, | |
| "eval_loss": 2.701810359954834, | |
| "eval_runtime": 0.1865, | |
| "eval_samples_per_second": 166.189, | |
| "eval_steps_per_second": 26.805, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.3076923076923077, | |
| "grad_norm": 31.70111656188965, | |
| "learning_rate": 1.2e-06, | |
| "loss": 2.5639, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.358974358974359, | |
| "grad_norm": 25.10308837890625, | |
| "learning_rate": 1.4e-06, | |
| "loss": 2.6011, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.41025641025641024, | |
| "grad_norm": 25.298452377319336, | |
| "learning_rate": 1.6e-06, | |
| "loss": 2.6779, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.46153846153846156, | |
| "grad_norm": 22.12431526184082, | |
| "learning_rate": 1.8e-06, | |
| "loss": 2.5438, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.5128205128205128, | |
| "grad_norm": 17.181961059570312, | |
| "learning_rate": 2e-06, | |
| "loss": 2.6304, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.5128205128205128, | |
| "eval_loss": 2.5064780712127686, | |
| "eval_runtime": 0.1877, | |
| "eval_samples_per_second": 165.144, | |
| "eval_steps_per_second": 26.636, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.5641025641025641, | |
| "grad_norm": 15.064467430114746, | |
| "learning_rate": 1.9998476951563913e-06, | |
| "loss": 2.6119, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.6153846153846154, | |
| "grad_norm": 15.15453815460205, | |
| "learning_rate": 1.9993908270190957e-06, | |
| "loss": 2.5618, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 14.976338386535645, | |
| "learning_rate": 1.998629534754574e-06, | |
| "loss": 2.5799, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.717948717948718, | |
| "grad_norm": 16.855302810668945, | |
| "learning_rate": 1.997564050259824e-06, | |
| "loss": 2.4803, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.7692307692307693, | |
| "grad_norm": 14.893013954162598, | |
| "learning_rate": 1.9961946980917456e-06, | |
| "loss": 2.3635, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.7692307692307693, | |
| "eval_loss": 2.3580050468444824, | |
| "eval_runtime": 0.1876, | |
| "eval_samples_per_second": 165.285, | |
| "eval_steps_per_second": 26.659, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.8205128205128205, | |
| "grad_norm": 12.848993301391602, | |
| "learning_rate": 1.994521895368273e-06, | |
| "loss": 2.4411, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.8717948717948718, | |
| "grad_norm": 15.440024375915527, | |
| "learning_rate": 1.992546151641322e-06, | |
| "loss": 2.4781, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.9230769230769231, | |
| "grad_norm": 13.695003509521484, | |
| "learning_rate": 1.99026806874157e-06, | |
| "loss": 2.4198, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.9743589743589743, | |
| "grad_norm": 13.504029273986816, | |
| "learning_rate": 1.9876883405951377e-06, | |
| "loss": 2.4088, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.0256410256410255, | |
| "grad_norm": 16.270732879638672, | |
| "learning_rate": 1.984807753012208e-06, | |
| "loss": 2.4553, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.0256410256410255, | |
| "eval_loss": 2.281332015991211, | |
| "eval_runtime": 0.1875, | |
| "eval_samples_per_second": 165.302, | |
| "eval_steps_per_second": 26.662, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.0384615384615385, | |
| "grad_norm": 13.558752059936523, | |
| "learning_rate": 1.981627183447664e-06, | |
| "loss": 2.3328, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.0897435897435896, | |
| "grad_norm": 13.454627990722656, | |
| "learning_rate": 1.9781476007338054e-06, | |
| "loss": 2.3366, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.141025641025641, | |
| "grad_norm": 14.2904052734375, | |
| "learning_rate": 1.9743700647852355e-06, | |
| "loss": 2.174, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.1923076923076923, | |
| "grad_norm": 13.595693588256836, | |
| "learning_rate": 1.9702957262759963e-06, | |
| "loss": 2.2358, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.2435897435897436, | |
| "grad_norm": 12.418634414672852, | |
| "learning_rate": 1.965925826289068e-06, | |
| "loss": 2.2344, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.2435897435897436, | |
| "eval_loss": 2.233912467956543, | |
| "eval_runtime": 0.1904, | |
| "eval_samples_per_second": 162.822, | |
| "eval_steps_per_second": 26.262, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.294871794871795, | |
| "grad_norm": 15.914401054382324, | |
| "learning_rate": 1.9612616959383188e-06, | |
| "loss": 2.259, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.3461538461538463, | |
| "grad_norm": 12.605673789978027, | |
| "learning_rate": 1.9563047559630356e-06, | |
| "loss": 2.0799, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.3974358974358974, | |
| "grad_norm": 13.526497840881348, | |
| "learning_rate": 1.9510565162951534e-06, | |
| "loss": 2.1993, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.4487179487179487, | |
| "grad_norm": 12.563177108764648, | |
| "learning_rate": 1.945518575599317e-06, | |
| "loss": 2.2513, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 12.170258522033691, | |
| "learning_rate": 1.9396926207859082e-06, | |
| "loss": 2.4562, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "eval_loss": 2.2017483711242676, | |
| "eval_runtime": 0.1881, | |
| "eval_samples_per_second": 164.78, | |
| "eval_steps_per_second": 26.577, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.5512820512820513, | |
| "grad_norm": 13.118155479431152, | |
| "learning_rate": 1.9335804264972015e-06, | |
| "loss": 2.1825, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.6025641025641026, | |
| "grad_norm": 13.182004928588867, | |
| "learning_rate": 1.9271838545667875e-06, | |
| "loss": 2.2352, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.6538461538461537, | |
| "grad_norm": 14.191438674926758, | |
| "learning_rate": 1.9205048534524403e-06, | |
| "loss": 2.2883, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.7051282051282053, | |
| "grad_norm": 13.125994682312012, | |
| "learning_rate": 1.9135454576426007e-06, | |
| "loss": 2.204, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.7564102564102564, | |
| "grad_norm": 13.099204063415527, | |
| "learning_rate": 1.9063077870366499e-06, | |
| "loss": 2.0943, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.7564102564102564, | |
| "eval_loss": 2.1725800037384033, | |
| "eval_runtime": 0.1875, | |
| "eval_samples_per_second": 165.319, | |
| "eval_steps_per_second": 26.664, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.8076923076923077, | |
| "grad_norm": 12.349153518676758, | |
| "learning_rate": 1.8987940462991669e-06, | |
| "loss": 2.2073, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.858974358974359, | |
| "grad_norm": 12.74866008758545, | |
| "learning_rate": 1.8910065241883678e-06, | |
| "loss": 2.2062, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.9102564102564101, | |
| "grad_norm": 10.330320358276367, | |
| "learning_rate": 1.8829475928589268e-06, | |
| "loss": 2.0004, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.9615384615384617, | |
| "grad_norm": 13.375683784484863, | |
| "learning_rate": 1.8746197071393956e-06, | |
| "loss": 1.9728, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.0128205128205128, | |
| "grad_norm": 13.092984199523926, | |
| "learning_rate": 1.8660254037844386e-06, | |
| "loss": 2.0695, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.0128205128205128, | |
| "eval_loss": 2.1425397396087646, | |
| "eval_runtime": 0.1884, | |
| "eval_samples_per_second": 164.566, | |
| "eval_steps_per_second": 26.543, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.0256410256410255, | |
| "grad_norm": 12.576122283935547, | |
| "learning_rate": 1.8571673007021123e-06, | |
| "loss": 2.0414, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.076923076923077, | |
| "grad_norm": 13.123306274414062, | |
| "learning_rate": 1.8480480961564257e-06, | |
| "loss": 2.1836, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.128205128205128, | |
| "grad_norm": 11.772199630737305, | |
| "learning_rate": 1.838670567945424e-06, | |
| "loss": 2.0555, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.1794871794871793, | |
| "grad_norm": 12.407557487487793, | |
| "learning_rate": 1.8290375725550415e-06, | |
| "loss": 1.9841, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.230769230769231, | |
| "grad_norm": 10.64401626586914, | |
| "learning_rate": 1.8191520442889917e-06, | |
| "loss": 1.8616, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.230769230769231, | |
| "eval_loss": 2.117149591445923, | |
| "eval_runtime": 0.1871, | |
| "eval_samples_per_second": 165.686, | |
| "eval_steps_per_second": 26.724, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.282051282051282, | |
| "grad_norm": 11.632575035095215, | |
| "learning_rate": 1.8090169943749474e-06, | |
| "loss": 1.9493, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.3333333333333335, | |
| "grad_norm": 13.22929573059082, | |
| "learning_rate": 1.7986355100472927e-06, | |
| "loss": 1.9483, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.3846153846153846, | |
| "grad_norm": 13.824577331542969, | |
| "learning_rate": 1.7880107536067217e-06, | |
| "loss": 2.0555, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.435897435897436, | |
| "grad_norm": 10.910252571105957, | |
| "learning_rate": 1.7771459614569707e-06, | |
| "loss": 2.1374, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.4871794871794872, | |
| "grad_norm": 13.26654052734375, | |
| "learning_rate": 1.766044443118978e-06, | |
| "loss": 2.0498, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.4871794871794872, | |
| "eval_loss": 2.1040406227111816, | |
| "eval_runtime": 0.1886, | |
| "eval_samples_per_second": 164.403, | |
| "eval_steps_per_second": 26.517, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.5384615384615383, | |
| "grad_norm": 11.703288078308105, | |
| "learning_rate": 1.7547095802227721e-06, | |
| "loss": 1.9002, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 2.58974358974359, | |
| "grad_norm": 13.835978507995605, | |
| "learning_rate": 1.743144825477394e-06, | |
| "loss": 1.988, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 2.641025641025641, | |
| "grad_norm": 14.295548439025879, | |
| "learning_rate": 1.7313537016191704e-06, | |
| "loss": 2.0443, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 2.6923076923076925, | |
| "grad_norm": 11.679184913635254, | |
| "learning_rate": 1.719339800338651e-06, | |
| "loss": 1.9208, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 2.7435897435897436, | |
| "grad_norm": 15.062151908874512, | |
| "learning_rate": 1.7071067811865474e-06, | |
| "loss": 1.9028, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.7435897435897436, | |
| "eval_loss": 2.098405361175537, | |
| "eval_runtime": 0.186, | |
| "eval_samples_per_second": 166.69, | |
| "eval_steps_per_second": 26.886, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.7948717948717947, | |
| "grad_norm": 14.257363319396973, | |
| "learning_rate": 1.6946583704589972e-06, | |
| "loss": 1.9604, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 2.8461538461538463, | |
| "grad_norm": 12.327591896057129, | |
| "learning_rate": 1.6819983600624985e-06, | |
| "loss": 1.9919, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 2.8974358974358974, | |
| "grad_norm": 14.447932243347168, | |
| "learning_rate": 1.669130606358858e-06, | |
| "loss": 1.9196, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 2.948717948717949, | |
| "grad_norm": 12.253332138061523, | |
| "learning_rate": 1.6560590289905071e-06, | |
| "loss": 1.8955, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 14.021129608154297, | |
| "learning_rate": 1.6427876096865393e-06, | |
| "loss": 1.9057, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 2.084063768386841, | |
| "eval_runtime": 0.1878, | |
| "eval_samples_per_second": 165.031, | |
| "eval_steps_per_second": 26.618, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 3.0128205128205128, | |
| "grad_norm": 12.585602760314941, | |
| "learning_rate": 1.6293203910498375e-06, | |
| "loss": 1.9736, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 3.064102564102564, | |
| "grad_norm": 12.412880897521973, | |
| "learning_rate": 1.615661475325658e-06, | |
| "loss": 1.906, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 3.1153846153846154, | |
| "grad_norm": 12.772639274597168, | |
| "learning_rate": 1.6018150231520484e-06, | |
| "loss": 1.8674, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 3.1666666666666665, | |
| "grad_norm": 9.931306838989258, | |
| "learning_rate": 1.587785252292473e-06, | |
| "loss": 1.8862, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 3.217948717948718, | |
| "grad_norm": 13.5899658203125, | |
| "learning_rate": 1.573576436351046e-06, | |
| "loss": 1.7464, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 3.217948717948718, | |
| "eval_loss": 2.078381061553955, | |
| "eval_runtime": 0.1867, | |
| "eval_samples_per_second": 166.085, | |
| "eval_steps_per_second": 26.788, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 3.269230769230769, | |
| "grad_norm": 11.722041130065918, | |
| "learning_rate": 1.5591929034707466e-06, | |
| "loss": 1.8595, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 3.3205128205128207, | |
| "grad_norm": 12.511164665222168, | |
| "learning_rate": 1.544639035015027e-06, | |
| "loss": 1.8445, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 3.371794871794872, | |
| "grad_norm": 15.670218467712402, | |
| "learning_rate": 1.5299192642332049e-06, | |
| "loss": 1.8044, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 3.423076923076923, | |
| "grad_norm": 12.341389656066895, | |
| "learning_rate": 1.5150380749100543e-06, | |
| "loss": 1.811, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 3.4743589743589745, | |
| "grad_norm": 13.361737251281738, | |
| "learning_rate": 1.5e-06, | |
| "loss": 1.8284, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 3.4743589743589745, | |
| "eval_loss": 2.078845500946045, | |
| "eval_runtime": 0.1879, | |
| "eval_samples_per_second": 164.946, | |
| "eval_steps_per_second": 26.604, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 3.5256410256410255, | |
| "grad_norm": 14.585214614868164, | |
| "learning_rate": 1.4848096202463372e-06, | |
| "loss": 1.7391, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 3.5769230769230766, | |
| "grad_norm": 11.4587984085083, | |
| "learning_rate": 1.4694715627858908e-06, | |
| "loss": 1.8459, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 3.628205128205128, | |
| "grad_norm": 14.638727188110352, | |
| "learning_rate": 1.4539904997395467e-06, | |
| "loss": 1.814, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 3.6794871794871797, | |
| "grad_norm": 15.081775665283203, | |
| "learning_rate": 1.4383711467890773e-06, | |
| "loss": 1.9079, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 3.730769230769231, | |
| "grad_norm": 12.757416725158691, | |
| "learning_rate": 1.4226182617406994e-06, | |
| "loss": 1.8866, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 3.730769230769231, | |
| "eval_loss": 2.0760610103607178, | |
| "eval_runtime": 0.1867, | |
| "eval_samples_per_second": 166.063, | |
| "eval_steps_per_second": 26.784, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 3.782051282051282, | |
| "grad_norm": 14.678832054138184, | |
| "learning_rate": 1.4067366430758004e-06, | |
| "loss": 1.7503, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 3.8333333333333335, | |
| "grad_norm": 15.981603622436523, | |
| "learning_rate": 1.3907311284892735e-06, | |
| "loss": 1.7984, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 3.8846153846153846, | |
| "grad_norm": 14.856511116027832, | |
| "learning_rate": 1.374606593415912e-06, | |
| "loss": 1.7843, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 3.935897435897436, | |
| "grad_norm": 14.275514602661133, | |
| "learning_rate": 1.3583679495453e-06, | |
| "loss": 1.7888, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 3.9871794871794872, | |
| "grad_norm": 12.734882354736328, | |
| "learning_rate": 1.3420201433256689e-06, | |
| "loss": 1.8927, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.9871794871794872, | |
| "eval_loss": 2.067340135574341, | |
| "eval_runtime": 0.1861, | |
| "eval_samples_per_second": 166.583, | |
| "eval_steps_per_second": 26.868, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 4.038461538461538, | |
| "grad_norm": 14.663799285888672, | |
| "learning_rate": 1.3255681544571566e-06, | |
| "loss": 1.7531, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 4.051282051282051, | |
| "grad_norm": 12.570903778076172, | |
| "learning_rate": 1.3090169943749473e-06, | |
| "loss": 1.7588, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 4.102564102564102, | |
| "grad_norm": 11.108199119567871, | |
| "learning_rate": 1.2923717047227368e-06, | |
| "loss": 1.6173, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 4.153846153846154, | |
| "grad_norm": 14.328954696655273, | |
| "learning_rate": 1.275637355816999e-06, | |
| "loss": 1.7411, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 4.205128205128205, | |
| "grad_norm": 14.140481948852539, | |
| "learning_rate": 1.2588190451025207e-06, | |
| "loss": 1.5778, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 4.205128205128205, | |
| "eval_loss": 2.0778791904449463, | |
| "eval_runtime": 0.1891, | |
| "eval_samples_per_second": 163.917, | |
| "eval_steps_per_second": 26.438, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 4.256410256410256, | |
| "grad_norm": 13.933786392211914, | |
| "learning_rate": 1.2419218955996676e-06, | |
| "loss": 1.5578, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 4.3076923076923075, | |
| "grad_norm": 16.1457462310791, | |
| "learning_rate": 1.2249510543438651e-06, | |
| "loss": 1.6873, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 4.358974358974359, | |
| "grad_norm": 16.26984977722168, | |
| "learning_rate": 1.207911690817759e-06, | |
| "loss": 1.6605, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 4.410256410256411, | |
| "grad_norm": 19.391223907470703, | |
| "learning_rate": 1.1908089953765447e-06, | |
| "loss": 1.6272, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 4.461538461538462, | |
| "grad_norm": 19.38517951965332, | |
| "learning_rate": 1.1736481776669305e-06, | |
| "loss": 1.7274, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 4.461538461538462, | |
| "eval_loss": 2.0934271812438965, | |
| "eval_runtime": 0.1874, | |
| "eval_samples_per_second": 165.396, | |
| "eval_steps_per_second": 26.677, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 4.512820512820513, | |
| "grad_norm": 16.367389678955078, | |
| "learning_rate": 1.156434465040231e-06, | |
| "loss": 1.8406, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 4.564102564102564, | |
| "grad_norm": 18.22227668762207, | |
| "learning_rate": 1.1391731009600653e-06, | |
| "loss": 1.7469, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 4.615384615384615, | |
| "grad_norm": 14.44421100616455, | |
| "learning_rate": 1.1218693434051474e-06, | |
| "loss": 1.5867, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 4.666666666666667, | |
| "grad_norm": 13.295368194580078, | |
| "learning_rate": 1.1045284632676535e-06, | |
| "loss": 1.7081, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 4.717948717948718, | |
| "grad_norm": 15.499272346496582, | |
| "learning_rate": 1.0871557427476583e-06, | |
| "loss": 1.7431, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 4.717948717948718, | |
| "eval_loss": 2.065159559249878, | |
| "eval_runtime": 0.1863, | |
| "eval_samples_per_second": 166.408, | |
| "eval_steps_per_second": 26.84, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 4.769230769230769, | |
| "grad_norm": 15.949275016784668, | |
| "learning_rate": 1.069756473744125e-06, | |
| "loss": 1.6641, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 4.82051282051282, | |
| "grad_norm": 13.781301498413086, | |
| "learning_rate": 1.052335956242944e-06, | |
| "loss": 1.5421, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 4.871794871794872, | |
| "grad_norm": 16.268604278564453, | |
| "learning_rate": 1.034899496702501e-06, | |
| "loss": 1.7906, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 4.923076923076923, | |
| "grad_norm": 12.881053924560547, | |
| "learning_rate": 1.0174524064372837e-06, | |
| "loss": 1.7359, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 4.9743589743589745, | |
| "grad_norm": 15.596150398254395, | |
| "learning_rate": 1e-06, | |
| "loss": 1.8728, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 4.9743589743589745, | |
| "eval_loss": 2.0617754459381104, | |
| "eval_runtime": 0.1875, | |
| "eval_samples_per_second": 165.345, | |
| "eval_steps_per_second": 26.668, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 5.0256410256410255, | |
| "grad_norm": 16.61153221130371, | |
| "learning_rate": 9.825475935627165e-07, | |
| "loss": 1.6729, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 5.038461538461538, | |
| "grad_norm": 13.130430221557617, | |
| "learning_rate": 9.651005032974993e-07, | |
| "loss": 1.6707, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 5.089743589743589, | |
| "grad_norm": 14.977300643920898, | |
| "learning_rate": 9.476640437570561e-07, | |
| "loss": 1.5516, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 5.141025641025641, | |
| "grad_norm": 17.314029693603516, | |
| "learning_rate": 9.302435262558747e-07, | |
| "loss": 1.6449, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 5.1923076923076925, | |
| "grad_norm": 15.75112247467041, | |
| "learning_rate": 9.128442572523417e-07, | |
| "loss": 1.5729, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 5.1923076923076925, | |
| "eval_loss": 2.083660125732422, | |
| "eval_runtime": 0.187, | |
| "eval_samples_per_second": 165.747, | |
| "eval_steps_per_second": 26.733, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 5.243589743589744, | |
| "grad_norm": 19.511394500732422, | |
| "learning_rate": 8.954715367323466e-07, | |
| "loss": 1.5756, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 5.294871794871795, | |
| "grad_norm": 16.741764068603516, | |
| "learning_rate": 8.781306565948526e-07, | |
| "loss": 1.6627, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 5.346153846153846, | |
| "grad_norm": 16.6429443359375, | |
| "learning_rate": 8.608268990399348e-07, | |
| "loss": 1.6097, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 5.397435897435898, | |
| "grad_norm": 22.457843780517578, | |
| "learning_rate": 8.435655349597689e-07, | |
| "loss": 1.6192, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 5.448717948717949, | |
| "grad_norm": 13.546624183654785, | |
| "learning_rate": 8.263518223330696e-07, | |
| "loss": 1.4631, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 5.448717948717949, | |
| "eval_loss": 2.087294816970825, | |
| "eval_runtime": 0.1887, | |
| "eval_samples_per_second": 164.276, | |
| "eval_steps_per_second": 26.496, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 5.5, | |
| "grad_norm": 16.943618774414062, | |
| "learning_rate": 8.091910046234551e-07, | |
| "loss": 1.5529, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 5.551282051282051, | |
| "grad_norm": 17.719892501831055, | |
| "learning_rate": 7.920883091822408e-07, | |
| "loss": 1.7165, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 5.602564102564102, | |
| "grad_norm": 14.0659818649292, | |
| "learning_rate": 7.750489456561351e-07, | |
| "loss": 1.5024, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 5.653846153846154, | |
| "grad_norm": 17.86212921142578, | |
| "learning_rate": 7.580781044003324e-07, | |
| "loss": 1.5745, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 5.705128205128205, | |
| "grad_norm": 17.252527236938477, | |
| "learning_rate": 7.411809548974791e-07, | |
| "loss": 1.4758, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 5.705128205128205, | |
| "eval_loss": 2.074392557144165, | |
| "eval_runtime": 0.1875, | |
| "eval_samples_per_second": 165.36, | |
| "eval_steps_per_second": 26.671, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 5.756410256410256, | |
| "grad_norm": 18.326730728149414, | |
| "learning_rate": 7.243626441830009e-07, | |
| "loss": 1.5874, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 5.8076923076923075, | |
| "grad_norm": 14.133539199829102, | |
| "learning_rate": 7.076282952772633e-07, | |
| "loss": 1.4556, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 5.858974358974359, | |
| "grad_norm": 16.187454223632812, | |
| "learning_rate": 6.909830056250526e-07, | |
| "loss": 1.5353, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 5.910256410256411, | |
| "grad_norm": 18.15951919555664, | |
| "learning_rate": 6.744318455428435e-07, | |
| "loss": 1.6346, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 5.961538461538462, | |
| "grad_norm": 14.860916137695312, | |
| "learning_rate": 6.579798566743313e-07, | |
| "loss": 1.5289, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 5.961538461538462, | |
| "eval_loss": 2.0899431705474854, | |
| "eval_runtime": 0.1896, | |
| "eval_samples_per_second": 163.49, | |
| "eval_steps_per_second": 26.369, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 6.012820512820513, | |
| "grad_norm": 23.091646194458008, | |
| "learning_rate": 6.416320504546997e-07, | |
| "loss": 1.6633, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 6.0256410256410255, | |
| "grad_norm": 19.409482955932617, | |
| "learning_rate": 6.253934065840879e-07, | |
| "loss": 1.6998, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 6.076923076923077, | |
| "grad_norm": 15.723928451538086, | |
| "learning_rate": 6.092688715107263e-07, | |
| "loss": 1.5407, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 6.128205128205128, | |
| "grad_norm": 17.410001754760742, | |
| "learning_rate": 5.932633569241999e-07, | |
| "loss": 1.4682, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 6.17948717948718, | |
| "grad_norm": 15.949166297912598, | |
| "learning_rate": 5.773817382593007e-07, | |
| "loss": 1.515, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 6.17948717948718, | |
| "eval_loss": 2.091871500015259, | |
| "eval_runtime": 0.1884, | |
| "eval_samples_per_second": 164.579, | |
| "eval_steps_per_second": 26.545, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 6.230769230769231, | |
| "grad_norm": 19.262935638427734, | |
| "learning_rate": 5.616288532109224e-07, | |
| "loss": 1.4557, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 6.282051282051282, | |
| "grad_norm": 18.071447372436523, | |
| "learning_rate": 5.460095002604532e-07, | |
| "loss": 1.4763, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 6.333333333333333, | |
| "grad_norm": 14.22094440460205, | |
| "learning_rate": 5.305284372141095e-07, | |
| "loss": 1.3375, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 6.384615384615385, | |
| "grad_norm": 19.112789154052734, | |
| "learning_rate": 5.15190379753663e-07, | |
| "loss": 1.5896, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 6.435897435897436, | |
| "grad_norm": 19.069456100463867, | |
| "learning_rate": 5.000000000000002e-07, | |
| "loss": 1.5757, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 6.435897435897436, | |
| "eval_loss": 2.0978188514709473, | |
| "eval_runtime": 0.1888, | |
| "eval_samples_per_second": 164.22, | |
| "eval_steps_per_second": 26.487, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 6.487179487179487, | |
| "grad_norm": 16.8870792388916, | |
| "learning_rate": 4.849619250899458e-07, | |
| "loss": 1.4204, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 6.538461538461538, | |
| "grad_norm": 20.033496856689453, | |
| "learning_rate": 4.700807357667952e-07, | |
| "loss": 1.6698, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 6.589743589743589, | |
| "grad_norm": 18.386215209960938, | |
| "learning_rate": 4.5536096498497287e-07, | |
| "loss": 1.4692, | |
| "step": 133 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 190, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 19, | |
| "total_flos": 1.733580238744453e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |