| { | |
| "best_metric": 0.704805850982666, | |
| "best_model_checkpoint": "final_models/glue_models/structroberta_s2_50ep//finetune/mnli-mm/checkpoint-12600", | |
| "epoch": 3.596059113300493, | |
| "global_step": 14600, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "eval_accuracy": 0.47517505288124084, | |
| "eval_loss": 1.0218451023101807, | |
| "eval_runtime": 13.3834, | |
| "eval_samples_per_second": 469.539, | |
| "eval_steps_per_second": 58.73, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_accuracy": 0.5058879852294922, | |
| "eval_loss": 0.9849981069564819, | |
| "eval_runtime": 13.3966, | |
| "eval_samples_per_second": 469.075, | |
| "eval_steps_per_second": 58.672, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.938423645320197e-05, | |
| "loss": 1.0369, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_accuracy": 0.5035009384155273, | |
| "eval_loss": 0.977361261844635, | |
| "eval_runtime": 13.3479, | |
| "eval_samples_per_second": 470.784, | |
| "eval_steps_per_second": 58.886, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_accuracy": 0.5544239282608032, | |
| "eval_loss": 0.9257498383522034, | |
| "eval_runtime": 13.332, | |
| "eval_samples_per_second": 471.347, | |
| "eval_steps_per_second": 58.956, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 4.876847290640394e-05, | |
| "loss": 0.9552, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_accuracy": 0.5798854231834412, | |
| "eval_loss": 0.8948496580123901, | |
| "eval_runtime": 13.3129, | |
| "eval_samples_per_second": 472.022, | |
| "eval_steps_per_second": 59.04, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_accuracy": 0.5932527184486389, | |
| "eval_loss": 0.8739783763885498, | |
| "eval_runtime": 13.3024, | |
| "eval_samples_per_second": 472.396, | |
| "eval_steps_per_second": 59.087, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_accuracy": 0.5992997884750366, | |
| "eval_loss": 0.8715024590492249, | |
| "eval_runtime": 13.3455, | |
| "eval_samples_per_second": 470.872, | |
| "eval_steps_per_second": 58.896, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 4.8152709359605915e-05, | |
| "loss": 0.9196, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_accuracy": 0.6125079393386841, | |
| "eval_loss": 0.8552348613739014, | |
| "eval_runtime": 13.3292, | |
| "eval_samples_per_second": 471.446, | |
| "eval_steps_per_second": 58.968, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_accuracy": 0.6031190156936646, | |
| "eval_loss": 0.850425660610199, | |
| "eval_runtime": 13.3264, | |
| "eval_samples_per_second": 471.546, | |
| "eval_steps_per_second": 58.981, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 4.753694581280788e-05, | |
| "loss": 0.8826, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_accuracy": 0.6261935234069824, | |
| "eval_loss": 0.831270158290863, | |
| "eval_runtime": 13.3443, | |
| "eval_samples_per_second": 470.914, | |
| "eval_steps_per_second": 58.902, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_accuracy": 0.6239656209945679, | |
| "eval_loss": 0.8242226243019104, | |
| "eval_runtime": 13.3277, | |
| "eval_samples_per_second": 471.498, | |
| "eval_steps_per_second": 58.975, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_accuracy": 0.6328771710395813, | |
| "eval_loss": 0.811508059501648, | |
| "eval_runtime": 13.3485, | |
| "eval_samples_per_second": 470.764, | |
| "eval_steps_per_second": 58.883, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 4.6921182266009855e-05, | |
| "loss": 0.8583, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_accuracy": 0.6341502070426941, | |
| "eval_loss": 0.812808632850647, | |
| "eval_runtime": 13.2942, | |
| "eval_samples_per_second": 472.686, | |
| "eval_steps_per_second": 59.123, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_accuracy": 0.6338319778442383, | |
| "eval_loss": 0.8130684494972229, | |
| "eval_runtime": 13.3877, | |
| "eval_samples_per_second": 469.385, | |
| "eval_steps_per_second": 58.711, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 4.630541871921182e-05, | |
| "loss": 0.844, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_accuracy": 0.6233291029930115, | |
| "eval_loss": 0.8244798183441162, | |
| "eval_runtime": 13.2608, | |
| "eval_samples_per_second": 473.877, | |
| "eval_steps_per_second": 59.272, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_accuracy": 0.6532463431358337, | |
| "eval_loss": 0.7844635844230652, | |
| "eval_runtime": 13.2963, | |
| "eval_samples_per_second": 472.614, | |
| "eval_steps_per_second": 59.114, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_accuracy": 0.6473583579063416, | |
| "eval_loss": 0.8013091683387756, | |
| "eval_runtime": 13.2787, | |
| "eval_samples_per_second": 473.239, | |
| "eval_steps_per_second": 59.192, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 4.5689655172413794e-05, | |
| "loss": 0.8253, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "eval_accuracy": 0.6537237167358398, | |
| "eval_loss": 0.7885627150535583, | |
| "eval_runtime": 13.2853, | |
| "eval_samples_per_second": 473.003, | |
| "eval_steps_per_second": 59.163, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "eval_accuracy": 0.657224714756012, | |
| "eval_loss": 0.7786855101585388, | |
| "eval_runtime": 13.2824, | |
| "eval_samples_per_second": 473.108, | |
| "eval_steps_per_second": 59.176, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 4.507389162561577e-05, | |
| "loss": 0.8155, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_accuracy": 0.6702737212181091, | |
| "eval_loss": 0.7679744362831116, | |
| "eval_runtime": 13.3377, | |
| "eval_samples_per_second": 471.146, | |
| "eval_steps_per_second": 58.931, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "eval_accuracy": 0.6697962880134583, | |
| "eval_loss": 0.7682982087135315, | |
| "eval_runtime": 13.2938, | |
| "eval_samples_per_second": 472.703, | |
| "eval_steps_per_second": 59.125, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "eval_accuracy": 0.6580203771591187, | |
| "eval_loss": 0.7912976145744324, | |
| "eval_runtime": 13.3163, | |
| "eval_samples_per_second": 471.902, | |
| "eval_steps_per_second": 59.025, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 4.4458128078817734e-05, | |
| "loss": 0.7535, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "eval_accuracy": 0.66343092918396, | |
| "eval_loss": 0.7666918039321899, | |
| "eval_runtime": 13.3587, | |
| "eval_samples_per_second": 470.404, | |
| "eval_steps_per_second": 58.838, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "eval_accuracy": 0.6731381416320801, | |
| "eval_loss": 0.758724570274353, | |
| "eval_runtime": 13.3698, | |
| "eval_samples_per_second": 470.016, | |
| "eval_steps_per_second": 58.789, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 4.384236453201971e-05, | |
| "loss": 0.7414, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "eval_accuracy": 0.6814131140708923, | |
| "eval_loss": 0.7651153802871704, | |
| "eval_runtime": 13.3862, | |
| "eval_samples_per_second": 469.437, | |
| "eval_steps_per_second": 58.717, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "eval_accuracy": 0.676957368850708, | |
| "eval_loss": 0.7536196112632751, | |
| "eval_runtime": 13.3955, | |
| "eval_samples_per_second": 469.111, | |
| "eval_steps_per_second": 58.676, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "eval_accuracy": 0.6669318675994873, | |
| "eval_loss": 0.7888858318328857, | |
| "eval_runtime": 13.397, | |
| "eval_samples_per_second": 469.06, | |
| "eval_steps_per_second": 58.67, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 4.3226600985221674e-05, | |
| "loss": 0.7301, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "eval_accuracy": 0.6752068996429443, | |
| "eval_loss": 0.7618388533592224, | |
| "eval_runtime": 13.4029, | |
| "eval_samples_per_second": 468.852, | |
| "eval_steps_per_second": 58.644, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "eval_accuracy": 0.6767982244491577, | |
| "eval_loss": 0.7687408328056335, | |
| "eval_runtime": 13.3939, | |
| "eval_samples_per_second": 469.17, | |
| "eval_steps_per_second": 58.684, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 4.261083743842365e-05, | |
| "loss": 0.7268, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "eval_accuracy": 0.6807765960693359, | |
| "eval_loss": 0.736904501914978, | |
| "eval_runtime": 13.3486, | |
| "eval_samples_per_second": 470.762, | |
| "eval_steps_per_second": 58.883, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "eval_accuracy": 0.684118390083313, | |
| "eval_loss": 0.7463005185127258, | |
| "eval_runtime": 13.3702, | |
| "eval_samples_per_second": 469.999, | |
| "eval_steps_per_second": 58.787, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "eval_accuracy": 0.6817314028739929, | |
| "eval_loss": 0.7449538707733154, | |
| "eval_runtime": 13.3959, | |
| "eval_samples_per_second": 469.098, | |
| "eval_steps_per_second": 58.675, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 4.199507389162562e-05, | |
| "loss": 0.7356, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "eval_accuracy": 0.6713876724243164, | |
| "eval_loss": 0.7528935670852661, | |
| "eval_runtime": 13.3896, | |
| "eval_samples_per_second": 469.319, | |
| "eval_steps_per_second": 58.702, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "eval_accuracy": 0.6662953495979309, | |
| "eval_loss": 0.7754761576652527, | |
| "eval_runtime": 13.4001, | |
| "eval_samples_per_second": 468.953, | |
| "eval_steps_per_second": 58.656, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 4.1379310344827587e-05, | |
| "loss": 0.7266, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "eval_accuracy": 0.6858688592910767, | |
| "eval_loss": 0.7322450280189514, | |
| "eval_runtime": 13.3919, | |
| "eval_samples_per_second": 469.241, | |
| "eval_steps_per_second": 58.692, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "eval_accuracy": 0.6847549080848694, | |
| "eval_loss": 0.7321462035179138, | |
| "eval_runtime": 13.3912, | |
| "eval_samples_per_second": 469.265, | |
| "eval_steps_per_second": 58.695, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "eval_accuracy": 0.684118390083313, | |
| "eval_loss": 0.7431775331497192, | |
| "eval_runtime": 13.297, | |
| "eval_samples_per_second": 472.587, | |
| "eval_steps_per_second": 59.111, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 4.076354679802955e-05, | |
| "loss": 0.727, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "eval_accuracy": 0.6823679208755493, | |
| "eval_loss": 0.7466910481452942, | |
| "eval_runtime": 13.2854, | |
| "eval_samples_per_second": 473.001, | |
| "eval_steps_per_second": 59.163, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "eval_accuracy": 0.6952577829360962, | |
| "eval_loss": 0.7211511731147766, | |
| "eval_runtime": 13.2945, | |
| "eval_samples_per_second": 472.678, | |
| "eval_steps_per_second": 59.122, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 4.014778325123153e-05, | |
| "loss": 0.7198, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "eval_accuracy": 0.6871419548988342, | |
| "eval_loss": 0.7214533686637878, | |
| "eval_runtime": 13.2721, | |
| "eval_samples_per_second": 473.473, | |
| "eval_steps_per_second": 59.222, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "eval_accuracy": 0.6879376173019409, | |
| "eval_loss": 0.7568030953407288, | |
| "eval_runtime": 13.3149, | |
| "eval_samples_per_second": 471.952, | |
| "eval_steps_per_second": 59.032, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "eval_accuracy": 0.6838001012802124, | |
| "eval_loss": 0.7772753238677979, | |
| "eval_runtime": 13.2999, | |
| "eval_samples_per_second": 472.486, | |
| "eval_steps_per_second": 59.098, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 3.95320197044335e-05, | |
| "loss": 0.6354, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "eval_accuracy": 0.6828452944755554, | |
| "eval_loss": 0.780381441116333, | |
| "eval_runtime": 13.3032, | |
| "eval_samples_per_second": 472.368, | |
| "eval_steps_per_second": 59.084, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "eval_accuracy": 0.6904837489128113, | |
| "eval_loss": 0.7529885172843933, | |
| "eval_runtime": 13.3496, | |
| "eval_samples_per_second": 470.727, | |
| "eval_steps_per_second": 58.878, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 3.891625615763547e-05, | |
| "loss": 0.6095, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "eval_accuracy": 0.682208776473999, | |
| "eval_loss": 0.7504951357841492, | |
| "eval_runtime": 13.3411, | |
| "eval_samples_per_second": 471.026, | |
| "eval_steps_per_second": 58.916, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "eval_accuracy": 0.6930299401283264, | |
| "eval_loss": 0.7513622641563416, | |
| "eval_runtime": 13.4014, | |
| "eval_samples_per_second": 468.907, | |
| "eval_steps_per_second": 58.651, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "eval_accuracy": 0.6855506300926208, | |
| "eval_loss": 0.7566074132919312, | |
| "eval_runtime": 13.3927, | |
| "eval_samples_per_second": 469.21, | |
| "eval_steps_per_second": 58.689, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 3.830049261083744e-05, | |
| "loss": 0.6186, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "eval_accuracy": 0.6952577829360962, | |
| "eval_loss": 0.734920859336853, | |
| "eval_runtime": 13.4003, | |
| "eval_samples_per_second": 468.944, | |
| "eval_steps_per_second": 58.655, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "eval_accuracy": 0.6968491673469543, | |
| "eval_loss": 0.7476750612258911, | |
| "eval_runtime": 13.3899, | |
| "eval_samples_per_second": 469.31, | |
| "eval_steps_per_second": 58.701, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 3.768472906403941e-05, | |
| "loss": 0.6154, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "eval_accuracy": 0.6992361545562744, | |
| "eval_loss": 0.7323787212371826, | |
| "eval_runtime": 13.4055, | |
| "eval_samples_per_second": 468.764, | |
| "eval_steps_per_second": 58.633, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "eval_accuracy": 0.6936664581298828, | |
| "eval_loss": 0.7456046938896179, | |
| "eval_runtime": 13.3722, | |
| "eval_samples_per_second": 469.932, | |
| "eval_steps_per_second": 58.779, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "eval_accuracy": 0.6892107129096985, | |
| "eval_loss": 0.7425976991653442, | |
| "eval_runtime": 13.3595, | |
| "eval_samples_per_second": 470.377, | |
| "eval_steps_per_second": 58.835, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 3.7068965517241385e-05, | |
| "loss": 0.6239, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "eval_accuracy": 0.700509250164032, | |
| "eval_loss": 0.736376941204071, | |
| "eval_runtime": 13.3381, | |
| "eval_samples_per_second": 471.133, | |
| "eval_steps_per_second": 58.929, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "eval_accuracy": 0.6992361545562744, | |
| "eval_loss": 0.7204196453094482, | |
| "eval_runtime": 13.3897, | |
| "eval_samples_per_second": 469.316, | |
| "eval_steps_per_second": 58.702, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 3.645320197044335e-05, | |
| "loss": 0.6181, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "eval_accuracy": 0.702896237373352, | |
| "eval_loss": 0.728840708732605, | |
| "eval_runtime": 13.3661, | |
| "eval_samples_per_second": 470.144, | |
| "eval_steps_per_second": 58.805, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "eval_accuracy": 0.7022597193717957, | |
| "eval_loss": 0.7289478182792664, | |
| "eval_runtime": 13.3368, | |
| "eval_samples_per_second": 471.176, | |
| "eval_steps_per_second": 58.935, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "eval_accuracy": 0.7017822861671448, | |
| "eval_loss": 0.7217112183570862, | |
| "eval_runtime": 13.3515, | |
| "eval_samples_per_second": 470.66, | |
| "eval_steps_per_second": 58.87, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 3.583743842364532e-05, | |
| "loss": 0.6225, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "eval_accuracy": 0.6963717341423035, | |
| "eval_loss": 0.7319472432136536, | |
| "eval_runtime": 13.3549, | |
| "eval_samples_per_second": 470.538, | |
| "eval_steps_per_second": 58.855, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "eval_accuracy": 0.6997135877609253, | |
| "eval_loss": 0.7350678443908691, | |
| "eval_runtime": 13.4093, | |
| "eval_samples_per_second": 468.63, | |
| "eval_steps_per_second": 58.616, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 3.522167487684729e-05, | |
| "loss": 0.6206, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "eval_accuracy": 0.6992361545562744, | |
| "eval_loss": 0.7226902842521667, | |
| "eval_runtime": 13.4077, | |
| "eval_samples_per_second": 468.686, | |
| "eval_steps_per_second": 58.623, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.6949395537376404, | |
| "eval_loss": 0.7860310077667236, | |
| "eval_runtime": 13.3803, | |
| "eval_samples_per_second": 469.646, | |
| "eval_steps_per_second": 58.743, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "eval_accuracy": 0.7022597193717957, | |
| "eval_loss": 0.7564778923988342, | |
| "eval_runtime": 13.3381, | |
| "eval_samples_per_second": 471.13, | |
| "eval_steps_per_second": 58.929, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 3.4605911330049265e-05, | |
| "loss": 0.5444, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "eval_accuracy": 0.704805850982666, | |
| "eval_loss": 0.7792636156082153, | |
| "eval_runtime": 13.3882, | |
| "eval_samples_per_second": 469.368, | |
| "eval_steps_per_second": 58.708, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "eval_accuracy": 0.7030553817749023, | |
| "eval_loss": 0.7826818823814392, | |
| "eval_runtime": 13.354, | |
| "eval_samples_per_second": 470.571, | |
| "eval_steps_per_second": 58.859, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 3.399014778325123e-05, | |
| "loss": 0.4956, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "eval_accuracy": 0.7003501057624817, | |
| "eval_loss": 0.7699744701385498, | |
| "eval_runtime": 13.3655, | |
| "eval_samples_per_second": 470.166, | |
| "eval_steps_per_second": 58.808, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "eval_accuracy": 0.6955760717391968, | |
| "eval_loss": 0.8116973638534546, | |
| "eval_runtime": 13.3615, | |
| "eval_samples_per_second": 470.305, | |
| "eval_steps_per_second": 58.826, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "eval_accuracy": 0.6973265409469604, | |
| "eval_loss": 0.8015252351760864, | |
| "eval_runtime": 13.3418, | |
| "eval_samples_per_second": 471.002, | |
| "eval_steps_per_second": 58.913, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 3.3374384236453204e-05, | |
| "loss": 0.4992, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "eval_accuracy": 0.6947804093360901, | |
| "eval_loss": 0.7988014221191406, | |
| "eval_runtime": 13.3581, | |
| "eval_samples_per_second": 470.428, | |
| "eval_steps_per_second": 58.841, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "eval_accuracy": 0.6971673965454102, | |
| "eval_loss": 0.7811249494552612, | |
| "eval_runtime": 13.4127, | |
| "eval_samples_per_second": 468.511, | |
| "eval_steps_per_second": 58.601, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 3.275862068965517e-05, | |
| "loss": 0.5008, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "eval_accuracy": 0.6958943605422974, | |
| "eval_loss": 0.7732043266296387, | |
| "eval_runtime": 13.3777, | |
| "eval_samples_per_second": 469.736, | |
| "eval_steps_per_second": 58.754, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "eval_accuracy": 0.6947804093360901, | |
| "eval_loss": 0.8099920749664307, | |
| "eval_runtime": 13.4361, | |
| "eval_samples_per_second": 467.694, | |
| "eval_steps_per_second": 58.499, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "eval_accuracy": 0.6917568445205688, | |
| "eval_loss": 0.7906026244163513, | |
| "eval_runtime": 13.3744, | |
| "eval_samples_per_second": 469.852, | |
| "eval_steps_per_second": 58.769, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 3.2142857142857144e-05, | |
| "loss": 0.5138, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "eval_accuracy": 0.6957352161407471, | |
| "eval_loss": 0.8155683279037476, | |
| "eval_runtime": 13.328, | |
| "eval_samples_per_second": 471.489, | |
| "eval_steps_per_second": 58.974, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "step": 14600, | |
| "total_flos": 8.557886095148544e+16, | |
| "train_loss": 0.7061373245552794, | |
| "train_runtime": 5975.4138, | |
| "train_samples_per_second": 434.748, | |
| "train_steps_per_second": 6.795 | |
| } | |
| ], | |
| "max_steps": 40600, | |
| "num_train_epochs": 10, | |
| "total_flos": 8.557886095148544e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |