| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 12.0, | |
| "eval_steps": 500, | |
| "global_step": 90492, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.18677596747875214, | |
| "learning_rate": 1.3320367751060821e-05, | |
| "loss": 1.6931, | |
| "step": 7541 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_AFQMC_loss": 0.02504170872271061, | |
| "eval_AFQMC_runtime": 99.0724, | |
| "eval_AFQMC_samples_per_second": 43.564, | |
| "eval_AFQMC_steps_per_second": 0.343, | |
| "eval_emb_eval_pearson_cosine": 0.49435896960848713, | |
| "eval_emb_eval_spearman_cosine": 0.5280909639875639, | |
| "step": 7541 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_ATEC_loss": 0.01953265070915222, | |
| "eval_ATEC_runtime": 6.6017, | |
| "eval_ATEC_samples_per_second": 3029.521, | |
| "eval_ATEC_steps_per_second": 23.782, | |
| "step": 7541 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_BQ_loss": 0.01803545467555523, | |
| "eval_BQ_runtime": 3.4373, | |
| "eval_BQ_samples_per_second": 2909.235, | |
| "eval_BQ_steps_per_second": 22.983, | |
| "step": 7541 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_Cmnli_loss": 0.020238544791936874, | |
| "eval_Cmnli_runtime": 3.9735, | |
| "eval_Cmnli_samples_per_second": 2092.612, | |
| "eval_Cmnli_steps_per_second": 16.358, | |
| "step": 7541 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_LCQMC_loss": 0.03518352285027504, | |
| "eval_LCQMC_runtime": 2.3275, | |
| "eval_LCQMC_samples_per_second": 3781.698, | |
| "eval_LCQMC_steps_per_second": 29.645, | |
| "step": 7541 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_Ocnli_loss": 0.025195566937327385, | |
| "eval_Ocnli_runtime": 0.6266, | |
| "eval_Ocnli_samples_per_second": 2947.795, | |
| "eval_Ocnli_steps_per_second": 23.94, | |
| "step": 7541 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_PAWSX_loss": 0.067341148853302, | |
| "eval_PAWSX_runtime": 0.9538, | |
| "eval_PAWSX_samples_per_second": 2096.982, | |
| "eval_PAWSX_steps_per_second": 16.776, | |
| "step": 7541 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_QBQTC_loss": 8.280766487121582, | |
| "eval_QBQTC_runtime": 7.6679, | |
| "eval_QBQTC_samples_per_second": 2608.269, | |
| "eval_QBQTC_steps_per_second": 20.475, | |
| "step": 7541 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_STS-B_loss": 8.6417875289917, | |
| "eval_STS-B_runtime": 0.5653, | |
| "eval_STS-B_samples_per_second": 2579.365, | |
| "eval_STS-B_steps_per_second": 21.229, | |
| "step": 7541 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.29912641644477844, | |
| "learning_rate": 1.92609255130006e-05, | |
| "loss": 1.5717, | |
| "step": 15082 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_AFQMC_loss": 0.023414788767695427, | |
| "eval_AFQMC_runtime": 99.0838, | |
| "eval_AFQMC_samples_per_second": 43.559, | |
| "eval_AFQMC_steps_per_second": 0.343, | |
| "eval_emb_eval_pearson_cosine": 0.541482089845575, | |
| "eval_emb_eval_spearman_cosine": 0.584542245914602, | |
| "step": 15082 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_ATEC_loss": 0.01733938232064247, | |
| "eval_ATEC_runtime": 6.5234, | |
| "eval_ATEC_samples_per_second": 3065.879, | |
| "eval_ATEC_steps_per_second": 24.067, | |
| "step": 15082 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_BQ_loss": 0.015580276027321815, | |
| "eval_BQ_runtime": 3.419, | |
| "eval_BQ_samples_per_second": 2924.795, | |
| "eval_BQ_steps_per_second": 23.106, | |
| "step": 15082 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_Cmnli_loss": 0.016321830451488495, | |
| "eval_Cmnli_runtime": 3.7867, | |
| "eval_Cmnli_samples_per_second": 2195.824, | |
| "eval_Cmnli_steps_per_second": 17.165, | |
| "step": 15082 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_LCQMC_loss": 0.02696206048130989, | |
| "eval_LCQMC_runtime": 2.3672, | |
| "eval_LCQMC_samples_per_second": 3718.264, | |
| "eval_LCQMC_steps_per_second": 29.148, | |
| "step": 15082 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_Ocnli_loss": 0.018722666427493095, | |
| "eval_Ocnli_runtime": 0.6105, | |
| "eval_Ocnli_samples_per_second": 3025.526, | |
| "eval_Ocnli_steps_per_second": 24.571, | |
| "step": 15082 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_PAWSX_loss": 0.06007164344191551, | |
| "eval_PAWSX_runtime": 0.9605, | |
| "eval_PAWSX_samples_per_second": 2082.25, | |
| "eval_PAWSX_steps_per_second": 16.658, | |
| "step": 15082 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_QBQTC_loss": 8.381814002990723, | |
| "eval_QBQTC_runtime": 7.644, | |
| "eval_QBQTC_samples_per_second": 2616.427, | |
| "eval_QBQTC_steps_per_second": 20.539, | |
| "step": 15082 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_STS-B_loss": 9.617568969726562, | |
| "eval_STS-B_runtime": 0.5589, | |
| "eval_STS-B_samples_per_second": 2608.657, | |
| "eval_STS-B_steps_per_second": 21.47, | |
| "step": 15082 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 0.2338990569114685, | |
| "learning_rate": 1.7779829671031307e-05, | |
| "loss": 1.5301, | |
| "step": 22623 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_AFQMC_loss": 0.02241475135087967, | |
| "eval_AFQMC_runtime": 99.9714, | |
| "eval_AFQMC_samples_per_second": 43.172, | |
| "eval_AFQMC_steps_per_second": 0.34, | |
| "eval_emb_eval_pearson_cosine": 0.5913082581080403, | |
| "eval_emb_eval_spearman_cosine": 0.6383284889220768, | |
| "step": 22623 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_ATEC_loss": 0.016517719253897667, | |
| "eval_ATEC_runtime": 6.5842, | |
| "eval_ATEC_samples_per_second": 3037.594, | |
| "eval_ATEC_steps_per_second": 23.845, | |
| "step": 22623 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_BQ_loss": 0.014284521341323853, | |
| "eval_BQ_runtime": 3.406, | |
| "eval_BQ_samples_per_second": 2936.005, | |
| "eval_BQ_steps_per_second": 23.194, | |
| "step": 22623 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_Cmnli_loss": 0.01529396791011095, | |
| "eval_Cmnli_runtime": 3.7388, | |
| "eval_Cmnli_samples_per_second": 2223.987, | |
| "eval_Cmnli_steps_per_second": 17.385, | |
| "step": 22623 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_LCQMC_loss": 0.020633986219763756, | |
| "eval_LCQMC_runtime": 2.3364, | |
| "eval_LCQMC_samples_per_second": 3767.314, | |
| "eval_LCQMC_steps_per_second": 29.532, | |
| "step": 22623 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_Ocnli_loss": 0.016242269426584244, | |
| "eval_Ocnli_runtime": 0.6209, | |
| "eval_Ocnli_samples_per_second": 2974.536, | |
| "eval_Ocnli_steps_per_second": 24.157, | |
| "step": 22623 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_PAWSX_loss": 0.05045855790376663, | |
| "eval_PAWSX_runtime": 0.9593, | |
| "eval_PAWSX_samples_per_second": 2084.846, | |
| "eval_PAWSX_steps_per_second": 16.679, | |
| "step": 22623 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_QBQTC_loss": 8.840312957763672, | |
| "eval_QBQTC_runtime": 7.6443, | |
| "eval_QBQTC_samples_per_second": 2616.334, | |
| "eval_QBQTC_steps_per_second": 20.538, | |
| "step": 22623 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_STS-B_loss": 9.837035179138184, | |
| "eval_STS-B_runtime": 0.5658, | |
| "eval_STS-B_samples_per_second": 2577.011, | |
| "eval_STS-B_steps_per_second": 21.21, | |
| "step": 22623 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 0.1766250729560852, | |
| "learning_rate": 1.629912674479141e-05, | |
| "loss": 1.4768, | |
| "step": 30164 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_AFQMC_loss": 0.021405402570962906, | |
| "eval_AFQMC_runtime": 100.3018, | |
| "eval_AFQMC_samples_per_second": 43.03, | |
| "eval_AFQMC_steps_per_second": 0.339, | |
| "eval_emb_eval_pearson_cosine": 0.6125367634857398, | |
| "eval_emb_eval_spearman_cosine": 0.6570670709310811, | |
| "step": 30164 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_ATEC_loss": 0.015135602094233036, | |
| "eval_ATEC_runtime": 6.5473, | |
| "eval_ATEC_samples_per_second": 3054.678, | |
| "eval_ATEC_steps_per_second": 23.979, | |
| "step": 30164 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_BQ_loss": 0.013757712207734585, | |
| "eval_BQ_runtime": 3.4539, | |
| "eval_BQ_samples_per_second": 2895.245, | |
| "eval_BQ_steps_per_second": 22.872, | |
| "step": 30164 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_Cmnli_loss": 0.015052303671836853, | |
| "eval_Cmnli_runtime": 3.7534, | |
| "eval_Cmnli_samples_per_second": 2215.324, | |
| "eval_Cmnli_steps_per_second": 17.318, | |
| "step": 30164 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_LCQMC_loss": 0.019115839153528214, | |
| "eval_LCQMC_runtime": 2.3344, | |
| "eval_LCQMC_samples_per_second": 3770.582, | |
| "eval_LCQMC_steps_per_second": 29.558, | |
| "step": 30164 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_Ocnli_loss": 0.015967663377523422, | |
| "eval_Ocnli_runtime": 0.603, | |
| "eval_Ocnli_samples_per_second": 3063.145, | |
| "eval_Ocnli_steps_per_second": 24.877, | |
| "step": 30164 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_PAWSX_loss": 0.04721539840102196, | |
| "eval_PAWSX_runtime": 0.9557, | |
| "eval_PAWSX_samples_per_second": 2092.706, | |
| "eval_PAWSX_steps_per_second": 16.742, | |
| "step": 30164 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_QBQTC_loss": 9.168432235717773, | |
| "eval_QBQTC_runtime": 7.6741, | |
| "eval_QBQTC_samples_per_second": 2606.178, | |
| "eval_QBQTC_steps_per_second": 20.458, | |
| "step": 30164 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_STS-B_loss": 9.83575439453125, | |
| "eval_STS-B_runtime": 0.5632, | |
| "eval_STS-B_samples_per_second": 2588.593, | |
| "eval_STS-B_steps_per_second": 21.305, | |
| "step": 30164 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 0.13791993260383606, | |
| "learning_rate": 1.481822736068682e-05, | |
| "loss": 1.4141, | |
| "step": 37705 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_AFQMC_loss": 0.0204468946903944, | |
| "eval_AFQMC_runtime": 99.1315, | |
| "eval_AFQMC_samples_per_second": 43.538, | |
| "eval_AFQMC_steps_per_second": 0.343, | |
| "eval_emb_eval_pearson_cosine": 0.6315631932372178, | |
| "eval_emb_eval_spearman_cosine": 0.6690982617504025, | |
| "step": 37705 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_ATEC_loss": 0.014196612872183323, | |
| "eval_ATEC_runtime": 6.5521, | |
| "eval_ATEC_samples_per_second": 3052.435, | |
| "eval_ATEC_steps_per_second": 23.962, | |
| "step": 37705 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_BQ_loss": 0.013593867421150208, | |
| "eval_BQ_runtime": 3.4128, | |
| "eval_BQ_samples_per_second": 2930.177, | |
| "eval_BQ_steps_per_second": 23.148, | |
| "step": 37705 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_Cmnli_loss": 0.015099190175533295, | |
| "eval_Cmnli_runtime": 3.8007, | |
| "eval_Cmnli_samples_per_second": 2187.75, | |
| "eval_Cmnli_steps_per_second": 17.102, | |
| "step": 37705 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_LCQMC_loss": 0.017175855115056038, | |
| "eval_LCQMC_runtime": 2.4095, | |
| "eval_LCQMC_samples_per_second": 3653.013, | |
| "eval_LCQMC_steps_per_second": 28.636, | |
| "step": 37705 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_Ocnli_loss": 0.015738315880298615, | |
| "eval_Ocnli_runtime": 0.619, | |
| "eval_Ocnli_samples_per_second": 2983.626, | |
| "eval_Ocnli_steps_per_second": 24.231, | |
| "step": 37705 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_PAWSX_loss": 0.046284567564725876, | |
| "eval_PAWSX_runtime": 0.959, | |
| "eval_PAWSX_samples_per_second": 2085.505, | |
| "eval_PAWSX_steps_per_second": 16.684, | |
| "step": 37705 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_QBQTC_loss": 9.86181640625, | |
| "eval_QBQTC_runtime": 7.9334, | |
| "eval_QBQTC_samples_per_second": 2520.974, | |
| "eval_QBQTC_steps_per_second": 19.79, | |
| "step": 37705 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_STS-B_loss": 9.911561965942383, | |
| "eval_STS-B_runtime": 0.5701, | |
| "eval_STS-B_samples_per_second": 2557.501, | |
| "eval_STS-B_steps_per_second": 21.049, | |
| "step": 37705 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 0.17065556347370148, | |
| "learning_rate": 1.3337327976582224e-05, | |
| "loss": 1.3461, | |
| "step": 45246 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_AFQMC_loss": 0.02002647891640663, | |
| "eval_AFQMC_runtime": 98.4869, | |
| "eval_AFQMC_samples_per_second": 43.823, | |
| "eval_AFQMC_steps_per_second": 0.345, | |
| "eval_emb_eval_pearson_cosine": 0.6436085641934666, | |
| "eval_emb_eval_spearman_cosine": 0.6715343325157711, | |
| "step": 45246 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_ATEC_loss": 0.014070386998355389, | |
| "eval_ATEC_runtime": 6.5822, | |
| "eval_ATEC_samples_per_second": 3038.48, | |
| "eval_ATEC_steps_per_second": 23.852, | |
| "step": 45246 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_BQ_loss": 0.013585967943072319, | |
| "eval_BQ_runtime": 3.6468, | |
| "eval_BQ_samples_per_second": 2742.113, | |
| "eval_BQ_steps_per_second": 21.663, | |
| "step": 45246 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_Cmnli_loss": 0.01478442084044218, | |
| "eval_Cmnli_runtime": 3.7572, | |
| "eval_Cmnli_samples_per_second": 2213.061, | |
| "eval_Cmnli_steps_per_second": 17.3, | |
| "step": 45246 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_LCQMC_loss": 0.016025548800826073, | |
| "eval_LCQMC_runtime": 2.3232, | |
| "eval_LCQMC_samples_per_second": 3788.767, | |
| "eval_LCQMC_steps_per_second": 29.701, | |
| "step": 45246 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_Ocnli_loss": 0.015464934520423412, | |
| "eval_Ocnli_runtime": 0.6071, | |
| "eval_Ocnli_samples_per_second": 3042.383, | |
| "eval_Ocnli_steps_per_second": 24.708, | |
| "step": 45246 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_PAWSX_loss": 0.04284413903951645, | |
| "eval_PAWSX_runtime": 0.9891, | |
| "eval_PAWSX_samples_per_second": 2021.991, | |
| "eval_PAWSX_steps_per_second": 16.176, | |
| "step": 45246 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_QBQTC_loss": 10.840497016906738, | |
| "eval_QBQTC_runtime": 7.7281, | |
| "eval_QBQTC_samples_per_second": 2587.958, | |
| "eval_QBQTC_steps_per_second": 20.315, | |
| "step": 45246 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_STS-B_loss": 9.943366050720215, | |
| "eval_STS-B_runtime": 0.5591, | |
| "eval_STS-B_samples_per_second": 2607.892, | |
| "eval_STS-B_steps_per_second": 21.464, | |
| "step": 45246 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "grad_norm": 0.13601745665073395, | |
| "learning_rate": 1.185642859247763e-05, | |
| "loss": 1.2856, | |
| "step": 52787 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_AFQMC_loss": 0.019535699859261513, | |
| "eval_AFQMC_runtime": 99.2494, | |
| "eval_AFQMC_samples_per_second": 43.486, | |
| "eval_AFQMC_steps_per_second": 0.343, | |
| "eval_emb_eval_pearson_cosine": 0.6473204770905479, | |
| "eval_emb_eval_spearman_cosine": 0.6723246242283224, | |
| "step": 52787 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_ATEC_loss": 0.013532574288547039, | |
| "eval_ATEC_runtime": 6.5765, | |
| "eval_ATEC_samples_per_second": 3041.133, | |
| "eval_ATEC_steps_per_second": 23.873, | |
| "step": 52787 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_BQ_loss": 0.013674370013177395, | |
| "eval_BQ_runtime": 3.4566, | |
| "eval_BQ_samples_per_second": 2892.978, | |
| "eval_BQ_steps_per_second": 22.855, | |
| "step": 52787 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_Cmnli_loss": 0.014647725969552994, | |
| "eval_Cmnli_runtime": 3.7546, | |
| "eval_Cmnli_samples_per_second": 2214.61, | |
| "eval_Cmnli_steps_per_second": 17.312, | |
| "step": 52787 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_LCQMC_loss": 0.0150056267157197, | |
| "eval_LCQMC_runtime": 2.3629, | |
| "eval_LCQMC_samples_per_second": 3725.146, | |
| "eval_LCQMC_steps_per_second": 29.202, | |
| "step": 52787 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_Ocnli_loss": 0.015559999272227287, | |
| "eval_Ocnli_runtime": 0.6231, | |
| "eval_Ocnli_samples_per_second": 2964.212, | |
| "eval_Ocnli_steps_per_second": 24.073, | |
| "step": 52787 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_PAWSX_loss": 0.04360537603497505, | |
| "eval_PAWSX_runtime": 0.9535, | |
| "eval_PAWSX_samples_per_second": 2097.49, | |
| "eval_PAWSX_steps_per_second": 16.78, | |
| "step": 52787 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_QBQTC_loss": 11.554633140563965, | |
| "eval_QBQTC_runtime": 7.7436, | |
| "eval_QBQTC_samples_per_second": 2582.791, | |
| "eval_QBQTC_steps_per_second": 20.275, | |
| "step": 52787 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_STS-B_loss": 10.235774993896484, | |
| "eval_STS-B_runtime": 0.5543, | |
| "eval_STS-B_samples_per_second": 2630.224, | |
| "eval_STS-B_steps_per_second": 21.648, | |
| "step": 52787 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 0.11353704333305359, | |
| "learning_rate": 1.0375332750508335e-05, | |
| "loss": 1.2182, | |
| "step": 60328 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_AFQMC_loss": 0.019351305440068245, | |
| "eval_AFQMC_runtime": 99.553, | |
| "eval_AFQMC_samples_per_second": 43.354, | |
| "eval_AFQMC_steps_per_second": 0.342, | |
| "eval_emb_eval_pearson_cosine": 0.6494222678001456, | |
| "eval_emb_eval_spearman_cosine": 0.6703225826686093, | |
| "step": 60328 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_ATEC_loss": 0.013181576505303383, | |
| "eval_ATEC_runtime": 6.522, | |
| "eval_ATEC_samples_per_second": 3066.526, | |
| "eval_ATEC_steps_per_second": 24.072, | |
| "step": 60328 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_BQ_loss": 0.013695988804101944, | |
| "eval_BQ_runtime": 3.4134, | |
| "eval_BQ_samples_per_second": 2929.642, | |
| "eval_BQ_steps_per_second": 23.144, | |
| "step": 60328 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_Cmnli_loss": 0.014423331245779991, | |
| "eval_Cmnli_runtime": 3.7623, | |
| "eval_Cmnli_samples_per_second": 2210.105, | |
| "eval_Cmnli_steps_per_second": 17.277, | |
| "step": 60328 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_LCQMC_loss": 0.015052268281579018, | |
| "eval_LCQMC_runtime": 2.3257, | |
| "eval_LCQMC_samples_per_second": 3784.705, | |
| "eval_LCQMC_steps_per_second": 29.669, | |
| "step": 60328 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_Ocnli_loss": 0.015219747088849545, | |
| "eval_Ocnli_runtime": 0.6121, | |
| "eval_Ocnli_samples_per_second": 3017.401, | |
| "eval_Ocnli_steps_per_second": 24.505, | |
| "step": 60328 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_PAWSX_loss": 0.042021822184324265, | |
| "eval_PAWSX_runtime": 0.9526, | |
| "eval_PAWSX_samples_per_second": 2099.597, | |
| "eval_PAWSX_steps_per_second": 16.797, | |
| "step": 60328 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_QBQTC_loss": 12.265329360961914, | |
| "eval_QBQTC_runtime": 7.6635, | |
| "eval_QBQTC_samples_per_second": 2609.768, | |
| "eval_QBQTC_steps_per_second": 20.487, | |
| "step": 60328 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_STS-B_loss": 10.596503257751465, | |
| "eval_STS-B_runtime": 0.5656, | |
| "eval_STS-B_samples_per_second": 2577.705, | |
| "eval_STS-B_steps_per_second": 21.216, | |
| "step": 60328 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "grad_norm": 0.10075096040964127, | |
| "learning_rate": 8.89443336640374e-06, | |
| "loss": 1.1546, | |
| "step": 67869 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_AFQMC_loss": 0.018916338682174683, | |
| "eval_AFQMC_runtime": 99.1097, | |
| "eval_AFQMC_samples_per_second": 43.548, | |
| "eval_AFQMC_steps_per_second": 0.343, | |
| "eval_emb_eval_pearson_cosine": 0.6461004194477242, | |
| "eval_emb_eval_spearman_cosine": 0.6620616757187626, | |
| "step": 67869 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_ATEC_loss": 0.01316931750625372, | |
| "eval_ATEC_runtime": 6.5342, | |
| "eval_ATEC_samples_per_second": 3060.808, | |
| "eval_ATEC_steps_per_second": 24.027, | |
| "step": 67869 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_BQ_loss": 0.013916433788836002, | |
| "eval_BQ_runtime": 3.4228, | |
| "eval_BQ_samples_per_second": 2921.626, | |
| "eval_BQ_steps_per_second": 23.081, | |
| "step": 67869 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_Cmnli_loss": 0.014616083353757858, | |
| "eval_Cmnli_runtime": 3.7166, | |
| "eval_Cmnli_samples_per_second": 2237.257, | |
| "eval_Cmnli_steps_per_second": 17.489, | |
| "step": 67869 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_LCQMC_loss": 0.014678360894322395, | |
| "eval_LCQMC_runtime": 2.3376, | |
| "eval_LCQMC_samples_per_second": 3765.326, | |
| "eval_LCQMC_steps_per_second": 29.517, | |
| "step": 67869 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_Ocnli_loss": 0.015178242698311806, | |
| "eval_Ocnli_runtime": 0.6061, | |
| "eval_Ocnli_samples_per_second": 3047.588, | |
| "eval_Ocnli_steps_per_second": 24.75, | |
| "step": 67869 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_PAWSX_loss": 0.04116755351424217, | |
| "eval_PAWSX_runtime": 0.9482, | |
| "eval_PAWSX_samples_per_second": 2109.261, | |
| "eval_PAWSX_steps_per_second": 16.874, | |
| "step": 67869 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_QBQTC_loss": 12.928996086120605, | |
| "eval_QBQTC_runtime": 7.7135, | |
| "eval_QBQTC_samples_per_second": 2592.855, | |
| "eval_QBQTC_steps_per_second": 20.354, | |
| "step": 67869 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_STS-B_loss": 10.769329071044922, | |
| "eval_STS-B_runtime": 0.557, | |
| "eval_STS-B_samples_per_second": 2617.49, | |
| "eval_STS-B_steps_per_second": 21.543, | |
| "step": 67869 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 116.47360229492188, | |
| "learning_rate": 7.413533982299147e-06, | |
| "loss": 1.091, | |
| "step": 75410 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_AFQMC_loss": 0.01876525580883026, | |
| "eval_AFQMC_runtime": 106.9735, | |
| "eval_AFQMC_samples_per_second": 40.346, | |
| "eval_AFQMC_steps_per_second": 0.318, | |
| "eval_emb_eval_pearson_cosine": 0.6425398472325708, | |
| "eval_emb_eval_spearman_cosine": 0.6571917650236837, | |
| "step": 75410 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_ATEC_loss": 0.012936480343341827, | |
| "eval_ATEC_runtime": 6.5457, | |
| "eval_ATEC_samples_per_second": 3055.455, | |
| "eval_ATEC_steps_per_second": 23.985, | |
| "step": 75410 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_BQ_loss": 0.014092645607888699, | |
| "eval_BQ_runtime": 3.4559, | |
| "eval_BQ_samples_per_second": 2893.566, | |
| "eval_BQ_steps_per_second": 22.859, | |
| "step": 75410 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_Cmnli_loss": 0.01457986794412136, | |
| "eval_Cmnli_runtime": 3.7514, | |
| "eval_Cmnli_samples_per_second": 2216.51, | |
| "eval_Cmnli_steps_per_second": 17.327, | |
| "step": 75410 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_LCQMC_loss": 0.014272717759013176, | |
| "eval_LCQMC_runtime": 2.3604, | |
| "eval_LCQMC_samples_per_second": 3729.02, | |
| "eval_LCQMC_steps_per_second": 29.232, | |
| "step": 75410 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_Ocnli_loss": 0.015037407167255878, | |
| "eval_Ocnli_runtime": 0.6116, | |
| "eval_Ocnli_samples_per_second": 3020.096, | |
| "eval_Ocnli_steps_per_second": 24.527, | |
| "step": 75410 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_PAWSX_loss": 0.04113338142633438, | |
| "eval_PAWSX_runtime": 0.9594, | |
| "eval_PAWSX_samples_per_second": 2084.624, | |
| "eval_PAWSX_steps_per_second": 16.677, | |
| "step": 75410 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_QBQTC_loss": 13.890397071838379, | |
| "eval_QBQTC_runtime": 7.674, | |
| "eval_QBQTC_samples_per_second": 2606.201, | |
| "eval_QBQTC_steps_per_second": 20.459, | |
| "step": 75410 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_STS-B_loss": 10.956206321716309, | |
| "eval_STS-B_runtime": 0.5649, | |
| "eval_STS-B_samples_per_second": 2580.888, | |
| "eval_STS-B_steps_per_second": 21.242, | |
| "step": 75410 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "grad_norm": 0.15993598103523254, | |
| "learning_rate": 5.933027513923951e-06, | |
| "loss": 1.0267, | |
| "step": 82951 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_AFQMC_loss": 0.01858402043581009, | |
| "eval_AFQMC_runtime": 99.2423, | |
| "eval_AFQMC_samples_per_second": 43.49, | |
| "eval_AFQMC_steps_per_second": 0.343, | |
| "eval_emb_eval_pearson_cosine": 0.635671675332461, | |
| "eval_emb_eval_spearman_cosine": 0.6462278753331322, | |
| "step": 82951 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_ATEC_loss": 0.012706396169960499, | |
| "eval_ATEC_runtime": 6.5392, | |
| "eval_ATEC_samples_per_second": 3058.477, | |
| "eval_ATEC_steps_per_second": 24.009, | |
| "step": 82951 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_BQ_loss": 0.014143843203783035, | |
| "eval_BQ_runtime": 3.3932, | |
| "eval_BQ_samples_per_second": 2947.098, | |
| "eval_BQ_steps_per_second": 23.282, | |
| "step": 82951 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_Cmnli_loss": 0.014601893723011017, | |
| "eval_Cmnli_runtime": 3.7177, | |
| "eval_Cmnli_samples_per_second": 2236.627, | |
| "eval_Cmnli_steps_per_second": 17.484, | |
| "step": 82951 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_LCQMC_loss": 0.01407212857156992, | |
| "eval_LCQMC_runtime": 2.3166, | |
| "eval_LCQMC_samples_per_second": 3799.506, | |
| "eval_LCQMC_steps_per_second": 29.785, | |
| "step": 82951 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_Ocnli_loss": 0.015255914069712162, | |
| "eval_Ocnli_runtime": 0.6096, | |
| "eval_Ocnli_samples_per_second": 3029.719, | |
| "eval_Ocnli_steps_per_second": 24.605, | |
| "step": 82951 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_PAWSX_loss": 0.04009222611784935, | |
| "eval_PAWSX_runtime": 0.9569, | |
| "eval_PAWSX_samples_per_second": 2090.135, | |
| "eval_PAWSX_steps_per_second": 16.721, | |
| "step": 82951 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_QBQTC_loss": 14.71971607208252, | |
| "eval_QBQTC_runtime": 7.651, | |
| "eval_QBQTC_samples_per_second": 2614.025, | |
| "eval_QBQTC_steps_per_second": 20.52, | |
| "step": 82951 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_STS-B_loss": 11.138467788696289, | |
| "eval_STS-B_runtime": 0.5605, | |
| "eval_STS-B_samples_per_second": 2601.08, | |
| "eval_STS-B_steps_per_second": 21.408, | |
| "step": 82951 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "grad_norm": 0.22925728559494019, | |
| "learning_rate": 4.451735214089958e-06, | |
| "loss": 0.9688, | |
| "step": 90492 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_AFQMC_loss": 0.018353162333369255, | |
| "eval_AFQMC_runtime": 98.1243, | |
| "eval_AFQMC_samples_per_second": 43.985, | |
| "eval_AFQMC_steps_per_second": 0.346, | |
| "eval_emb_eval_pearson_cosine": 0.6340788346277473, | |
| "eval_emb_eval_spearman_cosine": 0.6444001384260496, | |
| "step": 90492 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_ATEC_loss": 0.012524303048849106, | |
| "eval_ATEC_runtime": 6.5509, | |
| "eval_ATEC_samples_per_second": 3052.999, | |
| "eval_ATEC_steps_per_second": 23.966, | |
| "step": 90492 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_BQ_loss": 0.014260655269026756, | |
| "eval_BQ_runtime": 3.4399, | |
| "eval_BQ_samples_per_second": 2907.038, | |
| "eval_BQ_steps_per_second": 22.966, | |
| "step": 90492 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_Cmnli_loss": 0.014628582634031773, | |
| "eval_Cmnli_runtime": 3.7252, | |
| "eval_Cmnli_samples_per_second": 2232.102, | |
| "eval_Cmnli_steps_per_second": 17.449, | |
| "step": 90492 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_LCQMC_loss": 0.013899387791752815, | |
| "eval_LCQMC_runtime": 2.349, | |
| "eval_LCQMC_samples_per_second": 3747.087, | |
| "eval_LCQMC_steps_per_second": 29.374, | |
| "step": 90492 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_Ocnli_loss": 0.015396999195218086, | |
| "eval_Ocnli_runtime": 0.6119, | |
| "eval_Ocnli_samples_per_second": 3018.253, | |
| "eval_Ocnli_steps_per_second": 24.512, | |
| "step": 90492 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_PAWSX_loss": 0.04036952182650566, | |
| "eval_PAWSX_runtime": 0.9649, | |
| "eval_PAWSX_samples_per_second": 2072.698, | |
| "eval_PAWSX_steps_per_second": 16.582, | |
| "step": 90492 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_QBQTC_loss": 15.251015663146973, | |
| "eval_QBQTC_runtime": 7.662, | |
| "eval_QBQTC_samples_per_second": 2610.3, | |
| "eval_QBQTC_steps_per_second": 20.491, | |
| "step": 90492 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_STS-B_loss": 11.509617805480957, | |
| "eval_STS-B_runtime": 0.5625, | |
| "eval_STS-B_samples_per_second": 2592.013, | |
| "eval_STS-B_steps_per_second": 21.333, | |
| "step": 90492 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 113115, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 15, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 128, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |