Download sbert_training/third_training/logs/output.log from jstAnotherCapi/sbert_training_raw_folder_HPC: direct link, hf CLI and curl.
- Browser
- Download file 409 kB
-
https://huggingface.co/jstAnotherCapi/sbert_training_raw_folder_HPC/resolve/main/sbert_training/third_training/logs/output.log
- Command line
-
hf download hf://jstAnotherCapi/sbert_training_raw_folder_HPC/sbert_training/third_training/logs/output.log
-
curl -L -o output.log https://huggingface.co/jstAnotherCapi/sbert_training_raw_folder_HPC/resolve/main/sbert_training/third_training/logs/output.log
409 kB
| Model running on: cuda | |
| {'loss': '11.08', 'grad_norm': '47.21', 'learning_rate': '4.741e-08', 'epoch': '0.0004765'} | |
| {'loss': '9.936', 'grad_norm': '37.53', 'learning_rate': '9.505e-08', 'epoch': '0.0009529'} | |
| {'loss': '8.653', 'grad_norm': '37.06', 'learning_rate': '1.427e-07', 'epoch': '0.001429'} | |
| {'loss': '6.911', 'grad_norm': '25.54', 'learning_rate': '1.903e-07', 'epoch': '0.001906'} | |
| {'loss': '5.663', 'grad_norm': '23.75', 'learning_rate': '2.38e-07', 'epoch': '0.002382'} | |
| {'loss': '4.915', 'grad_norm': '22.26', 'learning_rate': '2.856e-07', 'epoch': '0.002859'} | |
| {'loss': '4.24', 'grad_norm': '24.6', 'learning_rate': '3.333e-07', 'epoch': '0.003335'} | |
| {'loss': '3.755', 'grad_norm': '21.14', 'learning_rate': '3.809e-07', 'epoch': '0.003812'} | |
| {'loss': '3.508', 'grad_norm': '20.97', 'learning_rate': '4.286e-07', 'epoch': '0.004288'} | |
| {'loss': '3.175', 'grad_norm': '17.38', 'learning_rate': '4.762e-07', 'epoch': '0.004765'} | |
| {'loss': '3.117', 'grad_norm': '19.34', 'learning_rate': '5.239e-07', 'epoch': '0.005241'} | |
| {'loss': '2.861', 'grad_norm': '18.21', 'learning_rate': '5.715e-07', 'epoch': '0.005717'} | |
| {'loss': '2.926', 'grad_norm': '13', 'learning_rate': '6.191e-07', 'epoch': '0.006194'} | |
| {'loss': '2.739', 'grad_norm': '16.43', 'learning_rate': '6.668e-07', 'epoch': '0.00667'} | |
| {'loss': '2.59', 'grad_norm': '15.27', 'learning_rate': '7.144e-07', 'epoch': '0.007147'} | |
| {'loss': '2.605', 'grad_norm': '17.67', 'learning_rate': '7.621e-07', 'epoch': '0.007623'} | |
| {'loss': '2.625', 'grad_norm': '17.95', 'learning_rate': '8.097e-07', 'epoch': '0.0081'} | |
| {'loss': '2.408', 'grad_norm': '21.45', 'learning_rate': '8.574e-07', 'epoch': '0.008576'} | |
| {'loss': '2.343', 'grad_norm': '18.04', 'learning_rate': '9.05e-07', 'epoch': '0.009053'} | |
| {'loss': '2.272', 'grad_norm': '21.53', 'learning_rate': '9.527e-07', 'epoch': '0.009529'} | |
| {'loss': '2.139', 'grad_norm': '15.62', 'learning_rate': '1e-06', 'epoch': '0.01001'} | |
| {'loss': '2.209', 'grad_norm': '12.22', 'learning_rate': '1.048e-06', 'epoch': '0.01048'} | |
| {'loss': '2.138', 'grad_norm': '20.1', 'learning_rate': '1.096e-06', 'epoch': '0.01096'} | |
| {'loss': '2.084', 'grad_norm': '13.94', 'learning_rate': '1.143e-06', 'epoch': '0.01143'} | |
| {'loss': '2.098', 'grad_norm': '16.69', 'learning_rate': '1.191e-06', 'epoch': '0.01191'} | |
| {'loss': '2.061', 'grad_norm': '14.5', 'learning_rate': '1.239e-06', 'epoch': '0.01239'} | |
| {'loss': '2.003', 'grad_norm': '11.25', 'learning_rate': '1.286e-06', 'epoch': '0.01286'} | |
| {'loss': '1.992', 'grad_norm': '15.14', 'learning_rate': '1.334e-06', 'epoch': '0.01334'} | |
| {'loss': '1.892', 'grad_norm': '13.97', 'learning_rate': '1.381e-06', 'epoch': '0.01382'} | |
| {'loss': '1.911', 'grad_norm': '17.7', 'learning_rate': '1.429e-06', 'epoch': '0.01429'} | |
| {'loss': '1.925', 'grad_norm': '15.75', 'learning_rate': '1.477e-06', 'epoch': '0.01477'} | |
| {'loss': '1.878', 'grad_norm': '12.73', 'learning_rate': '1.524e-06', 'epoch': '0.01525'} | |
| {'loss': '1.856', 'grad_norm': '13.35', 'learning_rate': '1.572e-06', 'epoch': '0.01572'} | |
| {'loss': '1.99', 'grad_norm': '17.89', 'learning_rate': '1.62e-06', 'epoch': '0.0162'} | |
| {'loss': '1.967', 'grad_norm': '9.218', 'learning_rate': '1.667e-06', 'epoch': '0.01668'} | |
| {'loss': '1.714', 'grad_norm': '12.82', 'learning_rate': '1.715e-06', 'epoch': '0.01715'} | |
| {'loss': '1.786', 'grad_norm': '12.84', 'learning_rate': '1.763e-06', 'epoch': '0.01763'} | |
| {'loss': '1.74', 'grad_norm': '12.49', 'learning_rate': '1.81e-06', 'epoch': '0.01811'} | |
| {'loss': '1.7', 'grad_norm': '13.45', 'learning_rate': '1.858e-06', 'epoch': '0.01858'} | |
| {'loss': '1.719', 'grad_norm': '14.39', 'learning_rate': '1.906e-06', 'epoch': '0.01906'} | |
| {'loss': '1.641', 'grad_norm': '11.02', 'learning_rate': '1.953e-06', 'epoch': '0.01953'} | |
| {'loss': '1.607', 'grad_norm': '12.13', 'learning_rate': '2.001e-06', 'epoch': '0.02001'} | |
| {'loss': '1.65', 'grad_norm': '12.25', 'learning_rate': '2.048e-06', 'epoch': '0.02049'} | |
| {'loss': '1.59', 'grad_norm': '13.07', 'learning_rate': '2.096e-06', 'epoch': '0.02096'} | |
| {'loss': '1.599', 'grad_norm': '13.01', 'learning_rate': '2.144e-06', 'epoch': '0.02144'} | |
| {'loss': '1.513', 'grad_norm': '12.93', 'learning_rate': '2.191e-06', 'epoch': '0.02192'} | |
| {'loss': '1.585', 'grad_norm': '8.811', 'learning_rate': '2.239e-06', 'epoch': '0.02239'} | |
| {'loss': '1.674', 'grad_norm': '18.43', 'learning_rate': '2.287e-06', 'epoch': '0.02287'} | |
| {'loss': '1.568', 'grad_norm': '10.89', 'learning_rate': '2.334e-06', 'epoch': '0.02335'} | |
| {'loss': '1.409', 'grad_norm': '13.09', 'learning_rate': '2.382e-06', 'epoch': '0.02382'} | |
| {'loss': '1.49', 'grad_norm': '12.02', 'learning_rate': '2.43e-06', 'epoch': '0.0243'} | |
| {'loss': '1.49', 'grad_norm': '12.08', 'learning_rate': '2.477e-06', 'epoch': '0.02478'} | |
| {'loss': '1.509', 'grad_norm': '11.98', 'learning_rate': '2.525e-06', 'epoch': '0.02525'} | |
| {'loss': '1.497', 'grad_norm': '12.79', 'learning_rate': '2.573e-06', 'epoch': '0.02573'} | |
| {'loss': '1.399', 'grad_norm': '12.77', 'learning_rate': '2.62e-06', 'epoch': '0.0262'} | |
| {'loss': '1.466', 'grad_norm': '13.75', 'learning_rate': '2.668e-06', 'epoch': '0.02668'} | |
| {'loss': '1.374', 'grad_norm': '13.25', 'learning_rate': '2.716e-06', 'epoch': '0.02716'} | |
| {'loss': '1.396', 'grad_norm': '10.15', 'learning_rate': '2.763e-06', 'epoch': '0.02763'} | |
| {'loss': '1.385', 'grad_norm': '7.88', 'learning_rate': '2.811e-06', 'epoch': '0.02811'} | |
| {'loss': '1.512', 'grad_norm': '15', 'learning_rate': '2.858e-06', 'epoch': '0.02859'} | |
| {'eval_ms_marco_loss': '1.178', 'eval_val-ms-marco-768_cosine_accuracy': '0.9377', 'eval_val-ms-marco-512_cosine_accuracy': '0.938', 'eval_val-ms-marco-256_cosine_accuracy': '0.9367', 'eval_val-ms-marco-128_cosine_accuracy': '0.9347', 'eval_val-ms-marco-64_cosine_accuracy': '0.93', 'eval_sequential_score': '0.9377', 'eval_ms_marco_runtime': '33.77', 'eval_ms_marco_samples_per_second': '296.1', 'eval_ms_marco_steps_per_second': '9.269', 'epoch': '0.02859'} | |
| {'loss': '1.402', 'grad_norm': '13.74', 'learning_rate': '2.906e-06', 'epoch': '0.02906'} | |
| {'loss': '1.407', 'grad_norm': '11.24', 'learning_rate': '2.954e-06', 'epoch': '0.02954'} | |
| {'loss': '1.394', 'grad_norm': '11.73', 'learning_rate': '3.001e-06', 'epoch': '0.03002'} | |
| {'loss': '1.345', 'grad_norm': '15.82', 'learning_rate': '3.049e-06', 'epoch': '0.03049'} | |
| {'loss': '1.357', 'grad_norm': '16.76', 'learning_rate': '3.097e-06', 'epoch': '0.03097'} | |
| {'loss': '1.335', 'grad_norm': '9.757', 'learning_rate': '3.144e-06', 'epoch': '0.03145'} | |
| {'loss': '1.344', 'grad_norm': '11.39', 'learning_rate': '3.192e-06', 'epoch': '0.03192'} | |
| {'loss': '1.3', 'grad_norm': '10.38', 'learning_rate': '3.24e-06', 'epoch': '0.0324'} | |
| {'loss': '1.295', 'grad_norm': '6.58', 'learning_rate': '3.287e-06', 'epoch': '0.03288'} | |
| {'loss': '1.436', 'grad_norm': '11.4', 'learning_rate': '3.335e-06', 'epoch': '0.03335'} | |
| {'loss': '1.271', 'grad_norm': '10.7', 'learning_rate': '3.383e-06', 'epoch': '0.03383'} | |
| {'loss': '1.332', 'grad_norm': '6.852', 'learning_rate': '3.43e-06', 'epoch': '0.0343'} | |
| {'loss': '1.259', 'grad_norm': '9.928', 'learning_rate': '3.478e-06', 'epoch': '0.03478'} | |
| {'loss': '1.312', 'grad_norm': '14.51', 'learning_rate': '3.525e-06', 'epoch': '0.03526'} | |
| {'loss': '1.262', 'grad_norm': '9.447', 'learning_rate': '3.573e-06', 'epoch': '0.03573'} | |
| {'loss': '1.272', 'grad_norm': '13.95', 'learning_rate': '3.621e-06', 'epoch': '0.03621'} | |
| {'loss': '1.281', 'grad_norm': '13.25', 'learning_rate': '3.668e-06', 'epoch': '0.03669'} | |
| {'loss': '1.242', 'grad_norm': '10.59', 'learning_rate': '3.716e-06', 'epoch': '0.03716'} | |
| {'loss': '1.255', 'grad_norm': '12.64', 'learning_rate': '3.764e-06', 'epoch': '0.03764'} | |
| {'loss': '1.198', 'grad_norm': '14.36', 'learning_rate': '3.811e-06', 'epoch': '0.03812'} | |
| {'loss': '1.218', 'grad_norm': '8.265', 'learning_rate': '3.859e-06', 'epoch': '0.03859'} | |
| {'loss': '1.363', 'grad_norm': '11.3', 'learning_rate': '3.907e-06', 'epoch': '0.03907'} | |
| {'loss': '1.261', 'grad_norm': '13.75', 'learning_rate': '3.954e-06', 'epoch': '0.03955'} | |
| {'loss': '1.163', 'grad_norm': '14.96', 'learning_rate': '4.002e-06', 'epoch': '0.04002'} | |
| {'loss': '1.197', 'grad_norm': '13.72', 'learning_rate': '4.05e-06', 'epoch': '0.0405'} | |
| {'loss': '1.233', 'grad_norm': '11.37', 'learning_rate': '4.097e-06', 'epoch': '0.04097'} | |
| {'loss': '1.147', 'grad_norm': '13.2', 'learning_rate': '4.145e-06', 'epoch': '0.04145'} | |
| {'loss': '1.254', 'grad_norm': '11.93', 'learning_rate': '4.192e-06', 'epoch': '0.04193'} | |
| {'loss': '1.147', 'grad_norm': '10.9', 'learning_rate': '4.24e-06', 'epoch': '0.0424'} | |
| {'loss': '1.155', 'grad_norm': '11', 'learning_rate': '4.288e-06', 'epoch': '0.04288'} | |
| {'loss': '1.197', 'grad_norm': '9.609', 'learning_rate': '4.335e-06', 'epoch': '0.04336'} | |
| {'loss': '1.195', 'grad_norm': '12.44', 'learning_rate': '4.383e-06', 'epoch': '0.04383'} | |
| {'loss': '1.108', 'grad_norm': '6.595', 'learning_rate': '4.431e-06', 'epoch': '0.04431'} | |
| {'loss': '1.134', 'grad_norm': '16.12', 'learning_rate': '4.478e-06', 'epoch': '0.04479'} | |
| {'loss': '1.101', 'grad_norm': '9.545', 'learning_rate': '4.526e-06', 'epoch': '0.04526'} | |
| {'loss': '1.178', 'grad_norm': '8.713', 'learning_rate': '4.574e-06', 'epoch': '0.04574'} | |
| {'loss': '1.099', 'grad_norm': '8.986', 'learning_rate': '4.621e-06', 'epoch': '0.04622'} | |
| {'loss': '1.33', 'grad_norm': '12.28', 'learning_rate': '4.669e-06', 'epoch': '0.04669'} | |
| {'loss': '1.154', 'grad_norm': '14', 'learning_rate': '4.717e-06', 'epoch': '0.04717'} | |
| {'loss': '1.106', 'grad_norm': '13.72', 'learning_rate': '4.764e-06', 'epoch': '0.04765'} | |
| {'loss': '1.133', 'grad_norm': '13.73', 'learning_rate': '4.812e-06', 'epoch': '0.04812'} | |
| {'loss': '1.061', 'grad_norm': '9.074', 'learning_rate': '4.86e-06', 'epoch': '0.0486'} | |
| {'loss': '1.131', 'grad_norm': '11.97', 'learning_rate': '4.907e-06', 'epoch': '0.04907'} | |
| {'loss': '1.125', 'grad_norm': '11.12', 'learning_rate': '4.955e-06', 'epoch': '0.04955'} | |
| {'loss': '1.149', 'grad_norm': '8.186', 'learning_rate': '5.002e-06', 'epoch': '0.05003'} | |
| {'loss': '1.093', 'grad_norm': '8.937', 'learning_rate': '5.05e-06', 'epoch': '0.0505'} | |
| {'loss': '1.119', 'grad_norm': '8.818', 'learning_rate': '5.098e-06', 'epoch': '0.05098'} | |
| {'loss': '1.075', 'grad_norm': '8.276', 'learning_rate': '5.145e-06', 'epoch': '0.05146'} | |
| {'loss': '1.082', 'grad_norm': '10.39', 'learning_rate': '5.193e-06', 'epoch': '0.05193'} | |
| {'loss': '1.046', 'grad_norm': '12.17', 'learning_rate': '5.241e-06', 'epoch': '0.05241'} | |
| {'loss': '1.101', 'grad_norm': '12.46', 'learning_rate': '5.288e-06', 'epoch': '0.05289'} | |
| {'loss': '1.055', 'grad_norm': '10.96', 'learning_rate': '5.336e-06', 'epoch': '0.05336'} | |
| {'loss': '1.285', 'grad_norm': '8.357', 'learning_rate': '5.384e-06', 'epoch': '0.05384'} | |
| {'loss': '0.9956', 'grad_norm': '9.343', 'learning_rate': '5.431e-06', 'epoch': '0.05432'} | |
| {'loss': '1.026', 'grad_norm': '11.15', 'learning_rate': '5.479e-06', 'epoch': '0.05479'} | |
| {'loss': '1.024', 'grad_norm': '11.4', 'learning_rate': '5.527e-06', 'epoch': '0.05527'} | |
| {'loss': '0.9647', 'grad_norm': '6.347', 'learning_rate': '5.574e-06', 'epoch': '0.05574'} | |
| {'loss': '1.026', 'grad_norm': '12.28', 'learning_rate': '5.622e-06', 'epoch': '0.05622'} | |
| {'loss': '0.9448', 'grad_norm': '10.6', 'learning_rate': '5.669e-06', 'epoch': '0.0567'} | |
| {'loss': '1.018', 'grad_norm': '9.381', 'learning_rate': '5.717e-06', 'epoch': '0.05717'} | |
| {'eval_ms_marco_loss': '0.8012', 'eval_val-ms-marco-768_cosine_accuracy': '0.954', 'eval_val-ms-marco-512_cosine_accuracy': '0.9563', 'eval_val-ms-marco-256_cosine_accuracy': '0.9547', 'eval_val-ms-marco-128_cosine_accuracy': '0.9547', 'eval_val-ms-marco-64_cosine_accuracy': '0.948', 'eval_sequential_score': '0.954', 'eval_ms_marco_runtime': '34.45', 'eval_ms_marco_samples_per_second': '290.2', 'eval_ms_marco_steps_per_second': '9.085', 'epoch': '0.05717'} | |
| {'loss': '1.026', 'grad_norm': '9.052', 'learning_rate': '5.765e-06', 'epoch': '0.05765'} | |
| {'loss': '0.9607', 'grad_norm': '10.43', 'learning_rate': '5.812e-06', 'epoch': '0.05813'} | |
| {'loss': '0.9894', 'grad_norm': '3.387', 'learning_rate': '5.86e-06', 'epoch': '0.0586'} | |
| {'loss': '0.9962', 'grad_norm': '12.44', 'learning_rate': '5.908e-06', 'epoch': '0.05908'} | |
| {'loss': '0.9831', 'grad_norm': '7.736', 'learning_rate': '5.955e-06', 'epoch': '0.05956'} | |
| {'loss': '0.9342', 'grad_norm': '10.63', 'learning_rate': '6.003e-06', 'epoch': '0.06003'} | |
| {'loss': '1.004', 'grad_norm': '10.99', 'learning_rate': '6.051e-06', 'epoch': '0.06051'} | |
| {'loss': '0.9638', 'grad_norm': '13.09', 'learning_rate': '6.098e-06', 'epoch': '0.06099'} | |
| {'loss': '0.9518', 'grad_norm': '14.73', 'learning_rate': '6.146e-06', 'epoch': '0.06146'} | |
| {'loss': '0.9727', 'grad_norm': '13.23', 'learning_rate': '6.194e-06', 'epoch': '0.06194'} | |
| {'loss': '0.9432', 'grad_norm': '10.26', 'learning_rate': '6.241e-06', 'epoch': '0.06241'} | |
| {'loss': '0.9307', 'grad_norm': '9.605', 'learning_rate': '6.289e-06', 'epoch': '0.06289'} | |
| {'loss': '0.9572', 'grad_norm': '12.2', 'learning_rate': '6.336e-06', 'epoch': '0.06337'} | |
| {'loss': '0.973', 'grad_norm': '9.485', 'learning_rate': '6.384e-06', 'epoch': '0.06384'} | |
| {'loss': '1.017', 'grad_norm': '7.286', 'learning_rate': '6.432e-06', 'epoch': '0.06432'} | |
| {'loss': '0.8882', 'grad_norm': '9.43', 'learning_rate': '6.479e-06', 'epoch': '0.0648'} | |
| {'loss': '1.194', 'grad_norm': '11.34', 'learning_rate': '6.527e-06', 'epoch': '0.06527'} | |
| {'loss': '0.8948', 'grad_norm': '5.832', 'learning_rate': '6.575e-06', 'epoch': '0.06575'} | |
| {'loss': '0.9578', 'grad_norm': '9.027', 'learning_rate': '6.622e-06', 'epoch': '0.06623'} | |
| {'loss': '0.917', 'grad_norm': '11.09', 'learning_rate': '6.67e-06', 'epoch': '0.0667'} | |
| {'loss': '0.9454', 'grad_norm': '8.631', 'learning_rate': '6.718e-06', 'epoch': '0.06718'} | |
| {'loss': '0.9409', 'grad_norm': '8.539', 'learning_rate': '6.765e-06', 'epoch': '0.06766'} | |
| {'loss': '0.8882', 'grad_norm': '13.1', 'learning_rate': '6.813e-06', 'epoch': '0.06813'} | |
| {'loss': '0.9188', 'grad_norm': '7.752', 'learning_rate': '6.861e-06', 'epoch': '0.06861'} | |
| {'loss': '0.9227', 'grad_norm': '8.766', 'learning_rate': '6.908e-06', 'epoch': '0.06909'} | |
| {'loss': '0.9661', 'grad_norm': '6.428', 'learning_rate': '6.956e-06', 'epoch': '0.06956'} | |
| {'loss': '0.8688', 'grad_norm': '9.872', 'learning_rate': '7.004e-06', 'epoch': '0.07004'} | |
| {'loss': '0.9013', 'grad_norm': '6.915', 'learning_rate': '7.051e-06', 'epoch': '0.07051'} | |
| {'loss': '1.002', 'grad_norm': '10.11', 'learning_rate': '7.099e-06', 'epoch': '0.07099'} | |
| {'loss': '0.8745', 'grad_norm': '10.56', 'learning_rate': '7.146e-06', 'epoch': '0.07147'} | |
| {'loss': '0.8906', 'grad_norm': '9.3', 'learning_rate': '7.194e-06', 'epoch': '0.07194'} | |
| {'loss': '0.8522', 'grad_norm': '6.323', 'learning_rate': '7.242e-06', 'epoch': '0.07242'} | |
| {'loss': '0.8497', 'grad_norm': '10.48', 'learning_rate': '7.289e-06', 'epoch': '0.0729'} | |
| {'loss': '0.8335', 'grad_norm': '8.947', 'learning_rate': '7.337e-06', 'epoch': '0.07337'} | |
| {'loss': '0.818', 'grad_norm': '7.857', 'learning_rate': '7.385e-06', 'epoch': '0.07385'} | |
| {'loss': '0.846', 'grad_norm': '10.12', 'learning_rate': '7.432e-06', 'epoch': '0.07433'} | |
| {'loss': '0.8846', 'grad_norm': '7.471', 'learning_rate': '7.48e-06', 'epoch': '0.0748'} | |
| {'loss': '0.8745', 'grad_norm': '10.93', 'learning_rate': '7.528e-06', 'epoch': '0.07528'} | |
| {'loss': '1.006', 'grad_norm': '7.668', 'learning_rate': '7.575e-06', 'epoch': '0.07576'} | |
| {'loss': '0.8561', 'grad_norm': '8.401', 'learning_rate': '7.623e-06', 'epoch': '0.07623'} | |
| {'loss': '0.8799', 'grad_norm': '11.38', 'learning_rate': '7.671e-06', 'epoch': '0.07671'} | |
| {'loss': '0.8411', 'grad_norm': '5.315', 'learning_rate': '7.718e-06', 'epoch': '0.07718'} | |
| {'loss': '0.8606', 'grad_norm': '7.611', 'learning_rate': '7.766e-06', 'epoch': '0.07766'} | |
| {'loss': '0.7947', 'grad_norm': '8.072', 'learning_rate': '7.813e-06', 'epoch': '0.07814'} | |
| {'loss': '0.8888', 'grad_norm': '5.872', 'learning_rate': '7.861e-06', 'epoch': '0.07861'} | |
| {'loss': '0.8467', 'grad_norm': '9.192', 'learning_rate': '7.909e-06', 'epoch': '0.07909'} | |
| {'loss': '0.8642', 'grad_norm': '4.481', 'learning_rate': '7.956e-06', 'epoch': '0.07957'} | |
| {'loss': '0.8758', 'grad_norm': '8.913', 'learning_rate': '8.004e-06', 'epoch': '0.08004'} | |
| {'loss': '0.835', 'grad_norm': '7.887', 'learning_rate': '8.052e-06', 'epoch': '0.08052'} | |
| {'loss': '0.8003', 'grad_norm': '6.469', 'learning_rate': '8.099e-06', 'epoch': '0.081'} | |
| {'loss': '0.7646', 'grad_norm': '8.94', 'learning_rate': '8.147e-06', 'epoch': '0.08147'} | |
| {'loss': '0.8572', 'grad_norm': '8.477', 'learning_rate': '8.195e-06', 'epoch': '0.08195'} | |
| {'loss': '0.8054', 'grad_norm': '11.04', 'learning_rate': '8.242e-06', 'epoch': '0.08243'} | |
| {'loss': '0.7921', 'grad_norm': '12.22', 'learning_rate': '8.29e-06', 'epoch': '0.0829'} | |
| {'loss': '0.7855', 'grad_norm': '9.915', 'learning_rate': '8.338e-06', 'epoch': '0.08338'} | |
| {'loss': '0.8082', 'grad_norm': '7.777', 'learning_rate': '8.385e-06', 'epoch': '0.08386'} | |
| {'loss': '0.7932', 'grad_norm': '4.33', 'learning_rate': '8.433e-06', 'epoch': '0.08433'} | |
| {'loss': '0.7903', 'grad_norm': '6.693', 'learning_rate': '8.48e-06', 'epoch': '0.08481'} | |
| {'loss': '0.7626', 'grad_norm': '6.152', 'learning_rate': '8.528e-06', 'epoch': '0.08528'} | |
| {'loss': '0.7954', 'grad_norm': '10.46', 'learning_rate': '8.576e-06', 'epoch': '0.08576'} | |
| {'eval_ms_marco_loss': '0.5993', 'eval_val-ms-marco-768_cosine_accuracy': '0.965', 'eval_val-ms-marco-512_cosine_accuracy': '0.964', 'eval_val-ms-marco-256_cosine_accuracy': '0.9643', 'eval_val-ms-marco-128_cosine_accuracy': '0.9623', 'eval_val-ms-marco-64_cosine_accuracy': '0.9563', 'eval_sequential_score': '0.965', 'eval_ms_marco_runtime': '33.97', 'eval_ms_marco_samples_per_second': '294.4', 'eval_ms_marco_steps_per_second': '9.215', 'epoch': '0.08576'} | |
| {'loss': '0.7969', 'grad_norm': '7.389', 'learning_rate': '8.623e-06', 'epoch': '0.08624'} | |
| {'loss': '0.8019', 'grad_norm': '9.641', 'learning_rate': '8.671e-06', 'epoch': '0.08671'} | |
| {'loss': '0.8695', 'grad_norm': '8.274', 'learning_rate': '8.719e-06', 'epoch': '0.08719'} | |
| {'loss': '0.7626', 'grad_norm': '11.42', 'learning_rate': '8.766e-06', 'epoch': '0.08767'} | |
| {'loss': '0.8835', 'grad_norm': '10.11', 'learning_rate': '8.814e-06', 'epoch': '0.08814'} | |
| {'loss': '0.8015', 'grad_norm': '7.574', 'learning_rate': '8.862e-06', 'epoch': '0.08862'} | |
| {'loss': '0.777', 'grad_norm': '8.086', 'learning_rate': '8.909e-06', 'epoch': '0.0891'} | |
| {'loss': '0.7674', 'grad_norm': '8.004', 'learning_rate': '8.957e-06', 'epoch': '0.08957'} | |
| {'loss': '0.7663', 'grad_norm': '4.262', 'learning_rate': '9.005e-06', 'epoch': '0.09005'} | |
| {'loss': '0.7783', 'grad_norm': '8.701', 'learning_rate': '9.052e-06', 'epoch': '0.09053'} | |
| {'loss': '0.7523', 'grad_norm': '6.032', 'learning_rate': '9.1e-06', 'epoch': '0.091'} | |
| {'loss': '0.7715', 'grad_norm': '11.35', 'learning_rate': '9.148e-06', 'epoch': '0.09148'} | |
| {'loss': '0.7695', 'grad_norm': '8.772', 'learning_rate': '9.195e-06', 'epoch': '0.09195'} | |
| {'loss': '0.7726', 'grad_norm': '8.652', 'learning_rate': '9.243e-06', 'epoch': '0.09243'} | |
| {'loss': '0.743', 'grad_norm': '8.301', 'learning_rate': '9.29e-06', 'epoch': '0.09291'} | |
| {'loss': '0.7313', 'grad_norm': '8.475', 'learning_rate': '9.338e-06', 'epoch': '0.09338'} | |
| {'loss': '0.7234', 'grad_norm': '8.105', 'learning_rate': '9.386e-06', 'epoch': '0.09386'} | |
| {'loss': '0.727', 'grad_norm': '8.495', 'learning_rate': '9.433e-06', 'epoch': '0.09434'} | |
| {'loss': '0.7761', 'grad_norm': '10.44', 'learning_rate': '9.481e-06', 'epoch': '0.09481'} | |
| {'loss': '0.7293', 'grad_norm': '11.27', 'learning_rate': '9.529e-06', 'epoch': '0.09529'} | |
| {'loss': '0.7554', 'grad_norm': '8.721', 'learning_rate': '9.576e-06', 'epoch': '0.09577'} | |
| {'loss': '0.7124', 'grad_norm': '10.01', 'learning_rate': '9.624e-06', 'epoch': '0.09624'} | |
| {'loss': '0.7226', 'grad_norm': '10.56', 'learning_rate': '9.672e-06', 'epoch': '0.09672'} | |
| {'loss': '0.7438', 'grad_norm': '8.629', 'learning_rate': '9.719e-06', 'epoch': '0.0972'} | |
| {'loss': '0.6902', 'grad_norm': '9.424', 'learning_rate': '9.767e-06', 'epoch': '0.09767'} | |
| {'loss': '0.7207', 'grad_norm': '6.952', 'learning_rate': '9.815e-06', 'epoch': '0.09815'} | |
| {'loss': '0.7119', 'grad_norm': '4.265', 'learning_rate': '9.862e-06', 'epoch': '0.09863'} | |
| {'loss': '0.7489', 'grad_norm': '7.637', 'learning_rate': '9.91e-06', 'epoch': '0.0991'} | |
| {'loss': '0.7119', 'grad_norm': '5.501', 'learning_rate': '9.957e-06', 'epoch': '0.09958'} | |
| {'loss': '0.7097', 'grad_norm': '10.65', 'learning_rate': '1.001e-05', 'epoch': '0.1001'} | |
| {'loss': '0.668', 'grad_norm': '9.456', 'learning_rate': '1.005e-05', 'epoch': '0.1005'} | |
| {'loss': '0.7091', 'grad_norm': '5.078', 'learning_rate': '1.01e-05', 'epoch': '0.101'} | |
| {'loss': '0.6764', 'grad_norm': '7.546', 'learning_rate': '1.015e-05', 'epoch': '0.1015'} | |
| {'loss': '0.6851', 'grad_norm': '10.3', 'learning_rate': '1.02e-05', 'epoch': '0.102'} | |
| {'loss': '0.6975', 'grad_norm': '5.113', 'learning_rate': '1.024e-05', 'epoch': '0.1024'} | |
| {'loss': '0.6879', 'grad_norm': '7.575', 'learning_rate': '1.029e-05', 'epoch': '0.1029'} | |
| {'loss': '0.6657', 'grad_norm': '10.25', 'learning_rate': '1.034e-05', 'epoch': '0.1034'} | |
| {'loss': '0.6975', 'grad_norm': '7.988', 'learning_rate': '1.039e-05', 'epoch': '0.1039'} | |
| {'loss': '0.6837', 'grad_norm': '7.87', 'learning_rate': '1.043e-05', 'epoch': '0.1043'} | |
| {'loss': '0.6764', 'grad_norm': '6.79', 'learning_rate': '1.048e-05', 'epoch': '0.1048'} | |
| {'loss': '0.6817', 'grad_norm': '8.543', 'learning_rate': '1.053e-05', 'epoch': '0.1053'} | |
| {'loss': '0.6505', 'grad_norm': '8.771', 'learning_rate': '1.058e-05', 'epoch': '0.1058'} | |
| {'loss': '0.6879', 'grad_norm': '13.56', 'learning_rate': '1.062e-05', 'epoch': '0.1062'} | |
| {'loss': '0.6646', 'grad_norm': '10.4', 'learning_rate': '1.067e-05', 'epoch': '0.1067'} | |
| {'loss': '0.6673', 'grad_norm': '10.9', 'learning_rate': '1.072e-05', 'epoch': '0.1072'} | |
| {'loss': '0.7694', 'grad_norm': '8.594', 'learning_rate': '1.077e-05', 'epoch': '0.1077'} | |
| {'loss': '0.6128', 'grad_norm': '7.976', 'learning_rate': '1.082e-05', 'epoch': '0.1082'} | |
| {'loss': '0.6539', 'grad_norm': '5.839', 'learning_rate': '1.086e-05', 'epoch': '0.1086'} | |
| {'loss': '0.7059', 'grad_norm': '6.96', 'learning_rate': '1.091e-05', 'epoch': '0.1091'} | |
| {'loss': '0.6772', 'grad_norm': '7.562', 'learning_rate': '1.096e-05', 'epoch': '0.1096'} | |
| {'loss': '0.6251', 'grad_norm': '7.729', 'learning_rate': '1.101e-05', 'epoch': '0.1101'} | |
| {'loss': '0.675', 'grad_norm': '7.922', 'learning_rate': '1.105e-05', 'epoch': '0.1105'} | |
| {'loss': '0.666', 'grad_norm': '8.351', 'learning_rate': '1.11e-05', 'epoch': '0.111'} | |
| {'loss': '0.6493', 'grad_norm': '5.073', 'learning_rate': '1.115e-05', 'epoch': '0.1115'} | |
| {'loss': '0.6383', 'grad_norm': '8.534', 'learning_rate': '1.12e-05', 'epoch': '0.112'} | |
| {'loss': '0.6433', 'grad_norm': '7.615', 'learning_rate': '1.124e-05', 'epoch': '0.1124'} | |
| {'loss': '0.6267', 'grad_norm': '7.242', 'learning_rate': '1.129e-05', 'epoch': '0.1129'} | |
| {'loss': '0.6617', 'grad_norm': '7.703', 'learning_rate': '1.134e-05', 'epoch': '0.1134'} | |
| {'loss': '0.6637', 'grad_norm': '4.337', 'learning_rate': '1.139e-05', 'epoch': '0.1139'} | |
| {'loss': '0.7906', 'grad_norm': '9.315', 'learning_rate': '1.143e-05', 'epoch': '0.1143'} | |
| {'eval_ms_marco_loss': '0.4433', 'eval_val-ms-marco-768_cosine_accuracy': '0.973', 'eval_val-ms-marco-512_cosine_accuracy': '0.9737', 'eval_val-ms-marco-256_cosine_accuracy': '0.974', 'eval_val-ms-marco-128_cosine_accuracy': '0.972', 'eval_val-ms-marco-64_cosine_accuracy': '0.9677', 'eval_sequential_score': '0.973', 'eval_ms_marco_runtime': '33.93', 'eval_ms_marco_samples_per_second': '294.7', 'eval_ms_marco_steps_per_second': '9.224', 'epoch': '0.1143'} | |
| {'loss': '0.6432', 'grad_norm': '6.353', 'learning_rate': '1.148e-05', 'epoch': '0.1148'} | |
| {'loss': '0.6618', 'grad_norm': '7.431', 'learning_rate': '1.153e-05', 'epoch': '0.1153'} | |
| {'loss': '0.6102', 'grad_norm': '10.01', 'learning_rate': '1.158e-05', 'epoch': '0.1158'} | |
| {'loss': '0.6149', 'grad_norm': '9.996', 'learning_rate': '1.163e-05', 'epoch': '0.1163'} | |
| {'loss': '0.6115', 'grad_norm': '11.01', 'learning_rate': '1.167e-05', 'epoch': '0.1167'} | |
| {'loss': '0.6703', 'grad_norm': '9.097', 'learning_rate': '1.172e-05', 'epoch': '0.1172'} | |
| {'loss': '0.6568', 'grad_norm': '4.745', 'learning_rate': '1.177e-05', 'epoch': '0.1177'} | |
| {'loss': '0.6046', 'grad_norm': '6.8', 'learning_rate': '1.182e-05', 'epoch': '0.1182'} | |
| {'loss': '0.611', 'grad_norm': '7.163', 'learning_rate': '1.186e-05', 'epoch': '0.1186'} | |
| {'loss': '0.6196', 'grad_norm': '5.393', 'learning_rate': '1.191e-05', 'epoch': '0.1191'} | |
| {'loss': '0.6156', 'grad_norm': '9.592', 'learning_rate': '1.196e-05', 'epoch': '0.1196'} | |
| {'loss': '0.736', 'grad_norm': '149.6', 'learning_rate': '1.201e-05', 'epoch': '0.1201'} | |
| {'loss': '0.6222', 'grad_norm': '6.188', 'learning_rate': '1.205e-05', 'epoch': '0.1205'} | |
| {'loss': '0.6222', 'grad_norm': '5.012', 'learning_rate': '1.21e-05', 'epoch': '0.121'} | |
| {'loss': '0.741', 'grad_norm': '8.327', 'learning_rate': '1.215e-05', 'epoch': '0.1215'} | |
| {'loss': '0.6224', 'grad_norm': '8.008', 'learning_rate': '1.22e-05', 'epoch': '0.122'} | |
| {'loss': '0.6307', 'grad_norm': '4.849', 'learning_rate': '1.224e-05', 'epoch': '0.1224'} | |
| {'loss': '0.6011', 'grad_norm': '7.105', 'learning_rate': '1.229e-05', 'epoch': '0.1229'} | |
| {'loss': '0.7266', 'grad_norm': '5.641', 'learning_rate': '1.234e-05', 'epoch': '0.1234'} | |
| {'loss': '0.7607', 'grad_norm': '4.882', 'learning_rate': '1.239e-05', 'epoch': '0.1239'} | |
| {'loss': '0.6234', 'grad_norm': '4.994', 'learning_rate': '1.243e-05', 'epoch': '0.1244'} | |
| {'loss': '0.6477', 'grad_norm': '11.82', 'learning_rate': '1.248e-05', 'epoch': '0.1248'} | |
| {'loss': '0.6046', 'grad_norm': '5.838', 'learning_rate': '1.253e-05', 'epoch': '0.1253'} | |
| {'loss': '0.6221', 'grad_norm': '6.073', 'learning_rate': '1.258e-05', 'epoch': '0.1258'} | |
| {'loss': '0.62', 'grad_norm': '9.864', 'learning_rate': '1.263e-05', 'epoch': '0.1263'} | |
| {'loss': '0.5796', 'grad_norm': '6.804', 'learning_rate': '1.267e-05', 'epoch': '0.1267'} | |
| {'loss': '0.6334', 'grad_norm': '6.21', 'learning_rate': '1.272e-05', 'epoch': '0.1272'} | |
| {'loss': '0.7016', 'grad_norm': '7.559', 'learning_rate': '1.277e-05', 'epoch': '0.1277'} | |
| {'loss': '0.6407', 'grad_norm': '10.21', 'learning_rate': '1.282e-05', 'epoch': '0.1282'} | |
| {'loss': '0.614', 'grad_norm': '8.276', 'learning_rate': '1.286e-05', 'epoch': '0.1286'} | |
| {'loss': '0.6065', 'grad_norm': '8.045', 'learning_rate': '1.291e-05', 'epoch': '0.1291'} | |
| {'loss': '0.5783', 'grad_norm': '4.18', 'learning_rate': '1.296e-05', 'epoch': '0.1296'} | |
| {'loss': '0.5957', 'grad_norm': '8.767', 'learning_rate': '1.301e-05', 'epoch': '0.1301'} | |
| {'loss': '0.5829', 'grad_norm': '3.698', 'learning_rate': '1.305e-05', 'epoch': '0.1305'} | |
| {'loss': '0.6006', 'grad_norm': '3.569', 'learning_rate': '1.31e-05', 'epoch': '0.131'} | |
| {'loss': '0.562', 'grad_norm': '9.321', 'learning_rate': '1.315e-05', 'epoch': '0.1315'} | |
| {'loss': '0.7002', 'grad_norm': '4.875', 'learning_rate': '1.32e-05', 'epoch': '0.132'} | |
| {'loss': '0.5756', 'grad_norm': '5.38', 'learning_rate': '1.324e-05', 'epoch': '0.1325'} | |
| {'loss': '0.5861', 'grad_norm': '8.719', 'learning_rate': '1.329e-05', 'epoch': '0.1329'} | |
| {'loss': '0.6876', 'grad_norm': '5.882', 'learning_rate': '1.334e-05', 'epoch': '0.1334'} | |
| {'loss': '0.5746', 'grad_norm': '8.177', 'learning_rate': '1.339e-05', 'epoch': '0.1339'} | |
| {'loss': '0.5865', 'grad_norm': '7.963', 'learning_rate': '1.344e-05', 'epoch': '0.1344'} | |
| {'loss': '0.5587', 'grad_norm': '9.979', 'learning_rate': '1.348e-05', 'epoch': '0.1348'} | |
| {'loss': '0.6083', 'grad_norm': '4.344', 'learning_rate': '1.353e-05', 'epoch': '0.1353'} | |
| {'loss': '0.5797', 'grad_norm': '8.006', 'learning_rate': '1.358e-05', 'epoch': '0.1358'} | |
| {'loss': '0.5914', 'grad_norm': '6.621', 'learning_rate': '1.363e-05', 'epoch': '0.1363'} | |
| {'loss': '0.5794', 'grad_norm': '5.413', 'learning_rate': '1.367e-05', 'epoch': '0.1367'} | |
| {'loss': '0.5226', 'grad_norm': '6.824', 'learning_rate': '1.372e-05', 'epoch': '0.1372'} | |
| {'loss': '0.5671', 'grad_norm': '6.706', 'learning_rate': '1.377e-05', 'epoch': '0.1377'} | |
| {'loss': '0.5996', 'grad_norm': '6.209', 'learning_rate': '1.382e-05', 'epoch': '0.1382'} | |
| {'loss': '0.554', 'grad_norm': '3.856', 'learning_rate': '1.386e-05', 'epoch': '0.1386'} | |
| {'loss': '0.5364', 'grad_norm': '7.585', 'learning_rate': '1.391e-05', 'epoch': '0.1391'} | |
| {'loss': '0.5472', 'grad_norm': '5.093', 'learning_rate': '1.396e-05', 'epoch': '0.1396'} | |
| {'loss': '0.5823', 'grad_norm': '6.867', 'learning_rate': '1.401e-05', 'epoch': '0.1401'} | |
| {'loss': '0.5537', 'grad_norm': '5.496', 'learning_rate': '1.405e-05', 'epoch': '0.1406'} | |
| {'loss': '0.541', 'grad_norm': '7.412', 'learning_rate': '1.41e-05', 'epoch': '0.141'} | |
| {'loss': '0.5723', 'grad_norm': '7.294', 'learning_rate': '1.415e-05', 'epoch': '0.1415'} | |
| {'loss': '0.5228', 'grad_norm': '3.337', 'learning_rate': '1.42e-05', 'epoch': '0.142'} | |
| {'loss': '0.5682', 'grad_norm': '9.53', 'learning_rate': '1.425e-05', 'epoch': '0.1425'} | |
| {'loss': '0.5356', 'grad_norm': '5.105', 'learning_rate': '1.429e-05', 'epoch': '0.1429'} | |
| {'eval_ms_marco_loss': '0.3603', 'eval_val-ms-marco-768_cosine_accuracy': '0.977', 'eval_val-ms-marco-512_cosine_accuracy': '0.9783', 'eval_val-ms-marco-256_cosine_accuracy': '0.9783', 'eval_val-ms-marco-128_cosine_accuracy': '0.976', 'eval_val-ms-marco-64_cosine_accuracy': '0.9733', 'eval_sequential_score': '0.977', 'eval_ms_marco_runtime': '34.06', 'eval_ms_marco_samples_per_second': '293.6', 'eval_ms_marco_steps_per_second': '9.189', 'epoch': '0.1429'} | |
| {'loss': '0.5634', 'grad_norm': '9.812', 'learning_rate': '1.434e-05', 'epoch': '0.1434'} | |
| {'loss': '0.5195', 'grad_norm': '6.194', 'learning_rate': '1.439e-05', 'epoch': '0.1439'} | |
| {'loss': '0.5184', 'grad_norm': '7.948', 'learning_rate': '1.444e-05', 'epoch': '0.1444'} | |
| {'loss': '0.572', 'grad_norm': '4.293', 'learning_rate': '1.448e-05', 'epoch': '0.1448'} | |
| {'loss': '0.5468', 'grad_norm': '8.03', 'learning_rate': '1.453e-05', 'epoch': '0.1453'} | |
| {'loss': '0.6488', 'grad_norm': '9.418', 'learning_rate': '1.458e-05', 'epoch': '0.1458'} | |
| {'loss': '0.5817', 'grad_norm': '8.421', 'learning_rate': '1.463e-05', 'epoch': '0.1463'} | |
| {'loss': '0.5685', 'grad_norm': '9.703', 'learning_rate': '1.467e-05', 'epoch': '0.1467'} | |
| {'loss': '0.5466', 'grad_norm': '6.393', 'learning_rate': '1.472e-05', 'epoch': '0.1472'} | |
| {'loss': '0.5232', 'grad_norm': '6.974', 'learning_rate': '1.477e-05', 'epoch': '0.1477'} | |
| {'loss': '0.5409', 'grad_norm': '6.054', 'learning_rate': '1.482e-05', 'epoch': '0.1482'} | |
| {'loss': '0.5483', 'grad_norm': '6.194', 'learning_rate': '1.486e-05', 'epoch': '0.1487'} | |
| {'loss': '0.5391', 'grad_norm': '3.982', 'learning_rate': '1.491e-05', 'epoch': '0.1491'} | |
| {'loss': '0.5218', 'grad_norm': '4.021', 'learning_rate': '1.496e-05', 'epoch': '0.1496'} | |
| {'loss': '0.5548', 'grad_norm': '5.235', 'learning_rate': '1.501e-05', 'epoch': '0.1501'} | |
| {'loss': '0.5391', 'grad_norm': '8.183', 'learning_rate': '1.506e-05', 'epoch': '0.1506'} | |
| {'loss': '0.507', 'grad_norm': '6.046', 'learning_rate': '1.51e-05', 'epoch': '0.151'} | |
| {'loss': '0.5455', 'grad_norm': '11.48', 'learning_rate': '1.515e-05', 'epoch': '0.1515'} | |
| {'loss': '0.5662', 'grad_norm': '6.591', 'learning_rate': '1.52e-05', 'epoch': '0.152'} | |
| {'loss': '0.5087', 'grad_norm': '4.372', 'learning_rate': '1.525e-05', 'epoch': '0.1525'} | |
| {'loss': '0.5439', 'grad_norm': '9.377', 'learning_rate': '1.529e-05', 'epoch': '0.1529'} | |
| {'loss': '0.5324', 'grad_norm': '5.822', 'learning_rate': '1.534e-05', 'epoch': '0.1534'} | |
| {'loss': '0.522', 'grad_norm': '3.916', 'learning_rate': '1.539e-05', 'epoch': '0.1539'} | |
| {'loss': '0.5107', 'grad_norm': '9.271', 'learning_rate': '1.544e-05', 'epoch': '0.1544'} | |
| {'loss': '0.5235', 'grad_norm': '10.1', 'learning_rate': '1.548e-05', 'epoch': '0.1548'} | |
| {'loss': '0.6659', 'grad_norm': '8.385', 'learning_rate': '1.553e-05', 'epoch': '0.1553'} | |
| {'loss': '0.5339', 'grad_norm': '9.078', 'learning_rate': '1.558e-05', 'epoch': '0.1558'} | |
| {'loss': '0.5234', 'grad_norm': '7.446', 'learning_rate': '1.563e-05', 'epoch': '0.1563'} | |
| {'loss': '0.4988', 'grad_norm': '7.866', 'learning_rate': '1.567e-05', 'epoch': '0.1568'} | |
| {'loss': '0.5295', 'grad_norm': '6.055', 'learning_rate': '1.572e-05', 'epoch': '0.1572'} | |
| {'loss': '0.5015', 'grad_norm': '4.367', 'learning_rate': '1.577e-05', 'epoch': '0.1577'} | |
| {'loss': '0.5328', 'grad_norm': '11.15', 'learning_rate': '1.582e-05', 'epoch': '0.1582'} | |
| {'loss': '0.516', 'grad_norm': '5.022', 'learning_rate': '1.587e-05', 'epoch': '0.1587'} | |
| {'loss': '0.4862', 'grad_norm': '7.541', 'learning_rate': '1.591e-05', 'epoch': '0.1591'} | |
| {'loss': '0.5631', 'grad_norm': '5.79', 'learning_rate': '1.596e-05', 'epoch': '0.1596'} | |
| {'loss': '0.4963', 'grad_norm': '10.74', 'learning_rate': '1.601e-05', 'epoch': '0.1601'} | |
| {'loss': '0.5095', 'grad_norm': '6.675', 'learning_rate': '1.606e-05', 'epoch': '0.1606'} | |
| {'loss': '0.5957', 'grad_norm': '6.418', 'learning_rate': '1.61e-05', 'epoch': '0.161'} | |
| {'loss': '0.5019', 'grad_norm': '4.194', 'learning_rate': '1.615e-05', 'epoch': '0.1615'} | |
| {'loss': '0.5601', 'grad_norm': '9.271', 'learning_rate': '1.62e-05', 'epoch': '0.162'} | |
| {'loss': '0.4936', 'grad_norm': '3.128', 'learning_rate': '1.625e-05', 'epoch': '0.1625'} | |
| {'loss': '0.5341', 'grad_norm': '8.354', 'learning_rate': '1.629e-05', 'epoch': '0.1629'} | |
| {'loss': '0.4935', 'grad_norm': '3.106', 'learning_rate': '1.634e-05', 'epoch': '0.1634'} | |
| {'loss': '0.6443', 'grad_norm': '5.56', 'learning_rate': '1.639e-05', 'epoch': '0.1639'} | |
| {'loss': '0.5025', 'grad_norm': '9.201', 'learning_rate': '1.644e-05', 'epoch': '0.1644'} | |
| {'loss': '0.5172', 'grad_norm': '4.674', 'learning_rate': '1.648e-05', 'epoch': '0.1649'} | |
| {'loss': '0.5297', 'grad_norm': '5.902', 'learning_rate': '1.653e-05', 'epoch': '0.1653'} | |
| {'loss': '0.4959', 'grad_norm': '7.687', 'learning_rate': '1.658e-05', 'epoch': '0.1658'} | |
| {'loss': '0.5257', 'grad_norm': '10.25', 'learning_rate': '1.663e-05', 'epoch': '0.1663'} | |
| {'loss': '0.5136', 'grad_norm': '7.469', 'learning_rate': '1.668e-05', 'epoch': '0.1668'} | |
| {'loss': '0.4847', 'grad_norm': '6.95', 'learning_rate': '1.672e-05', 'epoch': '0.1672'} | |
| {'loss': '0.5374', 'grad_norm': '8.588', 'learning_rate': '1.677e-05', 'epoch': '0.1677'} | |
| {'loss': '0.6244', 'grad_norm': '7.648', 'learning_rate': '1.682e-05', 'epoch': '0.1682'} | |
| {'loss': '0.4967', 'grad_norm': '3.17', 'learning_rate': '1.687e-05', 'epoch': '0.1687'} | |
| {'loss': '0.4911', 'grad_norm': '7.376', 'learning_rate': '1.691e-05', 'epoch': '0.1691'} | |
| {'loss': '0.515', 'grad_norm': '1.849', 'learning_rate': '1.696e-05', 'epoch': '0.1696'} | |
| {'loss': '0.5153', 'grad_norm': '6.751', 'learning_rate': '1.701e-05', 'epoch': '0.1701'} | |
| {'loss': '0.4599', 'grad_norm': '5.835', 'learning_rate': '1.706e-05', 'epoch': '0.1706'} | |
| {'loss': '0.5996', 'grad_norm': '9.196', 'learning_rate': '1.71e-05', 'epoch': '0.171'} | |
| {'loss': '0.4657', 'grad_norm': '3.065', 'learning_rate': '1.715e-05', 'epoch': '0.1715'} | |
| {'eval_ms_marco_loss': '0.3186', 'eval_val-ms-marco-768_cosine_accuracy': '0.9773', 'eval_val-ms-marco-512_cosine_accuracy': '0.9783', 'eval_val-ms-marco-256_cosine_accuracy': '0.9777', 'eval_val-ms-marco-128_cosine_accuracy': '0.9767', 'eval_val-ms-marco-64_cosine_accuracy': '0.9743', 'eval_sequential_score': '0.9773', 'eval_ms_marco_runtime': '33.73', 'eval_ms_marco_samples_per_second': '296.5', 'eval_ms_marco_steps_per_second': '9.28', 'epoch': '0.1715'} | |
| {'loss': '0.4969', 'grad_norm': '9.177', 'learning_rate': '1.72e-05', 'epoch': '0.172'} | |
| {'loss': '0.4861', 'grad_norm': '10.28', 'learning_rate': '1.725e-05', 'epoch': '0.1725'} | |
| {'loss': '0.486', 'grad_norm': '4.39', 'learning_rate': '1.729e-05', 'epoch': '0.173'} | |
| {'loss': '0.5145', 'grad_norm': '7.949', 'learning_rate': '1.734e-05', 'epoch': '0.1734'} | |
| {'loss': '0.4794', 'grad_norm': '5.153', 'learning_rate': '1.739e-05', 'epoch': '0.1739'} | |
| {'loss': '0.5191', 'grad_norm': '7.245', 'learning_rate': '1.744e-05', 'epoch': '0.1744'} | |
| {'loss': '0.4887', 'grad_norm': '7.882', 'learning_rate': '1.749e-05', 'epoch': '0.1749'} | |
| {'loss': '0.5252', 'grad_norm': '5.878', 'learning_rate': '1.753e-05', 'epoch': '0.1753'} | |
| {'loss': '0.4772', 'grad_norm': '6.254', 'learning_rate': '1.758e-05', 'epoch': '0.1758'} | |
| {'loss': '0.5123', 'grad_norm': '5.368', 'learning_rate': '1.763e-05', 'epoch': '0.1763'} | |
| {'loss': '0.462', 'grad_norm': '7.13', 'learning_rate': '1.768e-05', 'epoch': '0.1768'} | |
| {'loss': '0.4405', 'grad_norm': '9.669', 'learning_rate': '1.772e-05', 'epoch': '0.1772'} | |
| {'loss': '0.4753', 'grad_norm': '8.311', 'learning_rate': '1.777e-05', 'epoch': '0.1777'} | |
| {'loss': '0.5112', 'grad_norm': '9.121', 'learning_rate': '1.782e-05', 'epoch': '0.1782'} | |
| {'loss': '0.4808', 'grad_norm': '10.57', 'learning_rate': '1.787e-05', 'epoch': '0.1787'} | |
| {'loss': '0.4866', 'grad_norm': '8.51', 'learning_rate': '1.791e-05', 'epoch': '0.1791'} | |
| {'loss': '0.4982', 'grad_norm': '7.421', 'learning_rate': '1.796e-05', 'epoch': '0.1796'} | |
| {'loss': '0.5215', 'grad_norm': '4.879', 'learning_rate': '1.801e-05', 'epoch': '0.1801'} | |
| {'loss': '0.4696', 'grad_norm': '4.511', 'learning_rate': '1.806e-05', 'epoch': '0.1806'} | |
| {'loss': '0.482', 'grad_norm': '2.763', 'learning_rate': '1.81e-05', 'epoch': '0.1811'} | |
| {'loss': '0.5949', 'grad_norm': '1.522', 'learning_rate': '1.815e-05', 'epoch': '0.1815'} | |
| {'loss': '0.469', 'grad_norm': '5.621', 'learning_rate': '1.82e-05', 'epoch': '0.182'} | |
| {'loss': '0.5537', 'grad_norm': '4.517', 'learning_rate': '1.825e-05', 'epoch': '0.1825'} | |
| {'loss': '0.4725', 'grad_norm': '5.026', 'learning_rate': '1.83e-05', 'epoch': '0.183'} | |
| {'loss': '0.4627', 'grad_norm': '10.72', 'learning_rate': '1.834e-05', 'epoch': '0.1834'} | |
| {'loss': '0.484', 'grad_norm': '5.597', 'learning_rate': '1.839e-05', 'epoch': '0.1839'} | |
| {'loss': '0.4872', 'grad_norm': '2.742', 'learning_rate': '1.844e-05', 'epoch': '0.1844'} | |
| {'loss': '0.4577', 'grad_norm': '6.543', 'learning_rate': '1.849e-05', 'epoch': '0.1849'} | |
| {'loss': '0.47', 'grad_norm': '5.102', 'learning_rate': '1.853e-05', 'epoch': '0.1853'} | |
| {'loss': '0.4643', 'grad_norm': '7.629', 'learning_rate': '1.858e-05', 'epoch': '0.1858'} | |
| {'loss': '0.4805', 'grad_norm': '6.143', 'learning_rate': '1.863e-05', 'epoch': '0.1863'} | |
| {'loss': '0.4542', 'grad_norm': '7.218', 'learning_rate': '1.868e-05', 'epoch': '0.1868'} | |
| {'loss': '0.4547', 'grad_norm': '6.961', 'learning_rate': '1.872e-05', 'epoch': '0.1872'} | |
| {'loss': '0.4797', 'grad_norm': '3.938', 'learning_rate': '1.877e-05', 'epoch': '0.1877'} | |
| {'loss': '0.4468', 'grad_norm': '3.92', 'learning_rate': '1.882e-05', 'epoch': '0.1882'} | |
| {'loss': '0.595', 'grad_norm': '9.098', 'learning_rate': '1.887e-05', 'epoch': '0.1887'} | |
| {'loss': '0.4629', 'grad_norm': '7.792', 'learning_rate': '1.891e-05', 'epoch': '0.1892'} | |
| {'loss': '0.4524', 'grad_norm': '7.331', 'learning_rate': '1.896e-05', 'epoch': '0.1896'} | |
| {'loss': '0.4661', 'grad_norm': '6.16', 'learning_rate': '1.901e-05', 'epoch': '0.1901'} | |
| {'loss': '0.4553', 'grad_norm': '6.606', 'learning_rate': '1.906e-05', 'epoch': '0.1906'} | |
| {'loss': '0.4421', 'grad_norm': '5.588', 'learning_rate': '1.911e-05', 'epoch': '0.1911'} | |
| {'loss': '0.4966', 'grad_norm': '6.648', 'learning_rate': '1.915e-05', 'epoch': '0.1915'} | |
| {'loss': '0.4442', 'grad_norm': '4.438', 'learning_rate': '1.92e-05', 'epoch': '0.192'} | |
| {'loss': '0.4671', 'grad_norm': '3.159', 'learning_rate': '1.925e-05', 'epoch': '0.1925'} | |
| {'loss': '0.4596', 'grad_norm': '4.73', 'learning_rate': '1.93e-05', 'epoch': '0.193'} | |
| {'loss': '0.4604', 'grad_norm': '3.764', 'learning_rate': '1.934e-05', 'epoch': '0.1934'} | |
| {'loss': '0.4233', 'grad_norm': '6.101', 'learning_rate': '1.939e-05', 'epoch': '0.1939'} | |
| {'loss': '0.4359', 'grad_norm': '4.294', 'learning_rate': '1.944e-05', 'epoch': '0.1944'} | |
| {'loss': '0.4668', 'grad_norm': '6.466', 'learning_rate': '1.949e-05', 'epoch': '0.1949'} | |
| {'loss': '0.4954', 'grad_norm': '7.606', 'learning_rate': '1.953e-05', 'epoch': '0.1953'} | |
| {'loss': '0.4364', 'grad_norm': '5.485', 'learning_rate': '1.958e-05', 'epoch': '0.1958'} | |
| {'loss': '0.5159', 'grad_norm': '4.045', 'learning_rate': '1.963e-05', 'epoch': '0.1963'} | |
| {'loss': '0.4405', 'grad_norm': '7.222', 'learning_rate': '1.968e-05', 'epoch': '0.1968'} | |
| {'loss': '0.4377', 'grad_norm': '4.009', 'learning_rate': '1.972e-05', 'epoch': '0.1973'} | |
| {'loss': '0.4658', 'grad_norm': '5.657', 'learning_rate': '1.977e-05', 'epoch': '0.1977'} | |
| {'loss': '0.4367', 'grad_norm': '4.816', 'learning_rate': '1.982e-05', 'epoch': '0.1982'} | |
| {'loss': '0.442', 'grad_norm': '6.688', 'learning_rate': '1.987e-05', 'epoch': '0.1987'} | |
| {'loss': '0.4314', 'grad_norm': '9.802', 'learning_rate': '1.992e-05', 'epoch': '0.1992'} | |
| {'loss': '0.4311', 'grad_norm': '6.931', 'learning_rate': '1.996e-05', 'epoch': '0.1996'} | |
| {'loss': '0.4538', 'grad_norm': '6.756', 'learning_rate': '2e-05', 'epoch': '0.2001'} | |
| {'eval_ms_marco_loss': '0.2679', 'eval_val-ms-marco-768_cosine_accuracy': '0.982', 'eval_val-ms-marco-512_cosine_accuracy': '0.9837', 'eval_val-ms-marco-256_cosine_accuracy': '0.984', 'eval_val-ms-marco-128_cosine_accuracy': '0.9823', 'eval_val-ms-marco-64_cosine_accuracy': '0.985', 'eval_sequential_score': '0.982', 'eval_ms_marco_runtime': '33.94', 'eval_ms_marco_samples_per_second': '294.6', 'eval_ms_marco_steps_per_second': '9.222', 'epoch': '0.2001'} | |
| {'loss': '0.4587', 'grad_norm': '3.748', 'learning_rate': '1.999e-05', 'epoch': '0.2006'} | |
| {'loss': '0.4362', 'grad_norm': '3.201', 'learning_rate': '1.999e-05', 'epoch': '0.2011'} | |
| {'loss': '0.4498', 'grad_norm': '11.43', 'learning_rate': '1.998e-05', 'epoch': '0.2015'} | |
| {'loss': '0.4344', 'grad_norm': '7.368', 'learning_rate': '1.998e-05', 'epoch': '0.202'} | |
| {'loss': '0.4451', 'grad_norm': '4.13', 'learning_rate': '1.997e-05', 'epoch': '0.2025'} | |
| {'loss': '0.4704', 'grad_norm': '2.673', 'learning_rate': '1.997e-05', 'epoch': '0.203'} | |
| {'loss': '0.3962', 'grad_norm': '5.933', 'learning_rate': '1.996e-05', 'epoch': '0.2034'} | |
| {'loss': '0.4494', 'grad_norm': '4.648', 'learning_rate': '1.996e-05', 'epoch': '0.2039'} | |
| {'loss': '0.4129', 'grad_norm': '4.145', 'learning_rate': '1.995e-05', 'epoch': '0.2044'} | |
| {'loss': '0.429', 'grad_norm': '4.029', 'learning_rate': '1.995e-05', 'epoch': '0.2049'} | |
| {'loss': '0.4263', 'grad_norm': '7.615', 'learning_rate': '1.994e-05', 'epoch': '0.2054'} | |
| {'loss': '0.4425', 'grad_norm': '5.553', 'learning_rate': '1.994e-05', 'epoch': '0.2058'} | |
| {'loss': '0.4127', 'grad_norm': '7.676', 'learning_rate': '1.993e-05', 'epoch': '0.2063'} | |
| {'loss': '0.4265', 'grad_norm': '6.009', 'learning_rate': '1.992e-05', 'epoch': '0.2068'} | |
| {'loss': '0.4541', 'grad_norm': '2.863', 'learning_rate': '1.992e-05', 'epoch': '0.2073'} | |
| {'loss': '0.428', 'grad_norm': '5.955', 'learning_rate': '1.991e-05', 'epoch': '0.2077'} | |
| {'loss': '0.4219', 'grad_norm': '2.581', 'learning_rate': '1.991e-05', 'epoch': '0.2082'} | |
| {'loss': '0.4264', 'grad_norm': '2.911', 'learning_rate': '1.99e-05', 'epoch': '0.2087'} | |
| {'loss': '0.4384', 'grad_norm': '6.202', 'learning_rate': '1.99e-05', 'epoch': '0.2092'} | |
| {'loss': '0.5526', 'grad_norm': '3.975', 'learning_rate': '1.989e-05', 'epoch': '0.2096'} | |
| {'loss': '0.5351', 'grad_norm': '4.039', 'learning_rate': '1.989e-05', 'epoch': '0.2101'} | |
| {'loss': '0.425', 'grad_norm': '10.27', 'learning_rate': '1.988e-05', 'epoch': '0.2106'} | |
| {'loss': '0.4274', 'grad_norm': '8.487', 'learning_rate': '1.988e-05', 'epoch': '0.2111'} | |
| {'loss': '0.4015', 'grad_norm': '6.376', 'learning_rate': '1.987e-05', 'epoch': '0.2115'} | |
| {'loss': '0.4102', 'grad_norm': '5.853', 'learning_rate': '1.987e-05', 'epoch': '0.212'} | |
| {'loss': '0.4043', 'grad_norm': '5.727', 'learning_rate': '1.986e-05', 'epoch': '0.2125'} | |
| {'loss': '0.5318', 'grad_norm': '1.899', 'learning_rate': '1.986e-05', 'epoch': '0.213'} | |
| {'loss': '0.4114', 'grad_norm': '5.146', 'learning_rate': '1.985e-05', 'epoch': '0.2134'} | |
| {'loss': '0.4231', 'grad_norm': '7.406', 'learning_rate': '1.985e-05', 'epoch': '0.2139'} | |
| {'loss': '0.4254', 'grad_norm': '9.161', 'learning_rate': '1.984e-05', 'epoch': '0.2144'} | |
| {'loss': '0.4118', 'grad_norm': '3.981', 'learning_rate': '1.983e-05', 'epoch': '0.2149'} | |
| {'loss': '0.4006', 'grad_norm': '5.367', 'learning_rate': '1.983e-05', 'epoch': '0.2154'} | |
| {'loss': '0.4179', 'grad_norm': '1.837', 'learning_rate': '1.982e-05', 'epoch': '0.2158'} | |
| {'loss': '0.4975', 'grad_norm': '3.851', 'learning_rate': '1.982e-05', 'epoch': '0.2163'} | |
| {'loss': '0.3887', 'grad_norm': '3.747', 'learning_rate': '1.981e-05', 'epoch': '0.2168'} | |
| {'loss': '0.4059', 'grad_norm': '4.817', 'learning_rate': '1.981e-05', 'epoch': '0.2173'} | |
| {'loss': '0.4337', 'grad_norm': '6.486', 'learning_rate': '1.98e-05', 'epoch': '0.2177'} | |
| {'loss': '0.4389', 'grad_norm': '3.993', 'learning_rate': '1.98e-05', 'epoch': '0.2182'} | |
| {'loss': '0.4134', 'grad_norm': '4.442', 'learning_rate': '1.979e-05', 'epoch': '0.2187'} | |
| {'loss': '0.3918', 'grad_norm': '2.097', 'learning_rate': '1.979e-05', 'epoch': '0.2192'} | |
| {'loss': '0.383', 'grad_norm': '5.488', 'learning_rate': '1.978e-05', 'epoch': '0.2196'} | |
| {'loss': '0.4167', 'grad_norm': '8.53', 'learning_rate': '1.978e-05', 'epoch': '0.2201'} | |
| {'loss': '0.4184', 'grad_norm': '6.235', 'learning_rate': '1.977e-05', 'epoch': '0.2206'} | |
| {'loss': '0.3992', 'grad_norm': '3.572', 'learning_rate': '1.977e-05', 'epoch': '0.2211'} | |
| {'loss': '0.4022', 'grad_norm': '3.723', 'learning_rate': '1.976e-05', 'epoch': '0.2215'} | |
| {'loss': '0.3914', 'grad_norm': '7.121', 'learning_rate': '1.976e-05', 'epoch': '0.222'} | |
| {'loss': '0.4006', 'grad_norm': '3.874', 'learning_rate': '1.975e-05', 'epoch': '0.2225'} | |
| {'loss': '0.3958', 'grad_norm': '2.498', 'learning_rate': '1.974e-05', 'epoch': '0.223'} | |
| {'loss': '0.4264', 'grad_norm': '6.113', 'learning_rate': '1.974e-05', 'epoch': '0.2235'} | |
| {'loss': '0.4371', 'grad_norm': '4.382', 'learning_rate': '1.973e-05', 'epoch': '0.2239'} | |
| {'loss': '0.3899', 'grad_norm': '3.506', 'learning_rate': '1.973e-05', 'epoch': '0.2244'} | |
| {'loss': '0.3974', 'grad_norm': '6.145', 'learning_rate': '1.972e-05', 'epoch': '0.2249'} | |
| {'loss': '0.3819', 'grad_norm': '4.069', 'learning_rate': '1.972e-05', 'epoch': '0.2254'} | |
| {'loss': '0.4292', 'grad_norm': '1.71', 'learning_rate': '1.971e-05', 'epoch': '0.2258'} | |
| {'loss': '0.4737', 'grad_norm': '4.026', 'learning_rate': '1.971e-05', 'epoch': '0.2263'} | |
| {'loss': '0.5026', 'grad_norm': '6.768', 'learning_rate': '1.97e-05', 'epoch': '0.2268'} | |
| {'loss': '0.4045', 'grad_norm': '2.878', 'learning_rate': '1.97e-05', 'epoch': '0.2273'} | |
| {'loss': '0.3968', 'grad_norm': '5.246', 'learning_rate': '1.969e-05', 'epoch': '0.2277'} | |
| {'loss': '0.4124', 'grad_norm': '6.618', 'learning_rate': '1.969e-05', 'epoch': '0.2282'} | |
| {'loss': '0.4042', 'grad_norm': '3.278', 'learning_rate': '1.968e-05', 'epoch': '0.2287'} | |
| {'eval_ms_marco_loss': '0.2409', 'eval_val-ms-marco-768_cosine_accuracy': '0.9847', 'eval_val-ms-marco-512_cosine_accuracy': '0.9847', 'eval_val-ms-marco-256_cosine_accuracy': '0.9867', 'eval_val-ms-marco-128_cosine_accuracy': '0.9847', 'eval_val-ms-marco-64_cosine_accuracy': '0.9843', 'eval_sequential_score': '0.9847', 'eval_ms_marco_runtime': '33.99', 'eval_ms_marco_samples_per_second': '294.2', 'eval_ms_marco_steps_per_second': '9.208', 'epoch': '0.2287'} | |
| {'loss': '0.3839', 'grad_norm': '5.843', 'learning_rate': '1.968e-05', 'epoch': '0.2292'} | |
| {'loss': '0.5505', 'grad_norm': '3.546', 'learning_rate': '1.967e-05', 'epoch': '0.2296'} | |
| {'loss': '0.372', 'grad_norm': '7.377', 'learning_rate': '1.967e-05', 'epoch': '0.2301'} | |
| {'loss': '0.4251', 'grad_norm': '4.666', 'learning_rate': '1.966e-05', 'epoch': '0.2306'} | |
| {'loss': '0.511', 'grad_norm': '3.454', 'learning_rate': '1.965e-05', 'epoch': '0.2311'} | |
| {'loss': '0.3887', 'grad_norm': '5.38', 'learning_rate': '1.965e-05', 'epoch': '0.2316'} | |
| {'loss': '0.4097', 'grad_norm': '9.022', 'learning_rate': '1.964e-05', 'epoch': '0.232'} | |
| {'loss': '0.4048', 'grad_norm': '5.368', 'learning_rate': '1.964e-05', 'epoch': '0.2325'} | |
| {'loss': '0.37', 'grad_norm': '5.202', 'learning_rate': '1.963e-05', 'epoch': '0.233'} | |
| {'loss': '0.3735', 'grad_norm': '3.426', 'learning_rate': '1.963e-05', 'epoch': '0.2335'} | |
| {'loss': '0.3836', 'grad_norm': '7.832', 'learning_rate': '1.962e-05', 'epoch': '0.2339'} | |
| {'loss': '0.3806', 'grad_norm': '8.911', 'learning_rate': '1.962e-05', 'epoch': '0.2344'} | |
| {'loss': '0.3737', 'grad_norm': '4.602', 'learning_rate': '1.961e-05', 'epoch': '0.2349'} | |
| {'loss': '0.3958', 'grad_norm': '6.151', 'learning_rate': '1.961e-05', 'epoch': '0.2354'} | |
| {'loss': '0.4003', 'grad_norm': '4.999', 'learning_rate': '1.96e-05', 'epoch': '0.2358'} | |
| {'loss': '0.4804', 'grad_norm': '2.999', 'learning_rate': '1.96e-05', 'epoch': '0.2363'} | |
| {'loss': '0.367', 'grad_norm': '6.144', 'learning_rate': '1.959e-05', 'epoch': '0.2368'} | |
| {'loss': '0.3576', 'grad_norm': '1.665', 'learning_rate': '1.959e-05', 'epoch': '0.2373'} | |
| {'loss': '0.4284', 'grad_norm': '4.34', 'learning_rate': '1.958e-05', 'epoch': '0.2377'} | |
| {'loss': '0.364', 'grad_norm': '2.946', 'learning_rate': '1.958e-05', 'epoch': '0.2382'} | |
| {'loss': '0.3511', 'grad_norm': '6.535', 'learning_rate': '1.957e-05', 'epoch': '0.2387'} | |
| {'loss': '0.3882', 'grad_norm': '2.864', 'learning_rate': '1.956e-05', 'epoch': '0.2392'} | |
| {'loss': '0.4169', 'grad_norm': '5.773', 'learning_rate': '1.956e-05', 'epoch': '0.2397'} | |
| {'loss': '0.4108', 'grad_norm': '3.75', 'learning_rate': '1.955e-05', 'epoch': '0.2401'} | |
| {'loss': '0.3639', 'grad_norm': '2.726', 'learning_rate': '1.955e-05', 'epoch': '0.2406'} | |
| {'loss': '0.39', 'grad_norm': '6.493', 'learning_rate': '1.954e-05', 'epoch': '0.2411'} | |
| {'loss': '0.3804', 'grad_norm': '7.314', 'learning_rate': '1.954e-05', 'epoch': '0.2416'} | |
| {'loss': '0.3998', 'grad_norm': '3.667', 'learning_rate': '1.953e-05', 'epoch': '0.242'} | |
| {'loss': '0.4721', 'grad_norm': '2.817', 'learning_rate': '1.953e-05', 'epoch': '0.2425'} | |
| {'loss': '0.3723', 'grad_norm': '2.843', 'learning_rate': '1.952e-05', 'epoch': '0.243'} | |
| {'loss': '0.3797', 'grad_norm': '3.594', 'learning_rate': '1.952e-05', 'epoch': '0.2435'} | |
| {'loss': '0.3743', 'grad_norm': '9.829', 'learning_rate': '1.951e-05', 'epoch': '0.2439'} | |
| {'loss': '0.3943', 'grad_norm': '4.887', 'learning_rate': '1.951e-05', 'epoch': '0.2444'} | |
| {'loss': '0.3802', 'grad_norm': '7.327', 'learning_rate': '1.95e-05', 'epoch': '0.2449'} | |
| {'loss': '0.383', 'grad_norm': '8.933', 'learning_rate': '1.95e-05', 'epoch': '0.2454'} | |
| {'loss': '0.3943', 'grad_norm': '3.555', 'learning_rate': '1.949e-05', 'epoch': '0.2458'} | |
| {'loss': '0.3614', 'grad_norm': '6.389', 'learning_rate': '1.949e-05', 'epoch': '0.2463'} | |
| {'loss': '0.3721', 'grad_norm': '4.069', 'learning_rate': '1.948e-05', 'epoch': '0.2468'} | |
| {'loss': '0.3684', 'grad_norm': '6.087', 'learning_rate': '1.947e-05', 'epoch': '0.2473'} | |
| {'loss': '0.3753', 'grad_norm': '6.265', 'learning_rate': '1.947e-05', 'epoch': '0.2478'} | |
| {'loss': '0.3799', 'grad_norm': '6.04', 'learning_rate': '1.946e-05', 'epoch': '0.2482'} | |
| {'loss': '0.3634', 'grad_norm': '5.033', 'learning_rate': '1.946e-05', 'epoch': '0.2487'} | |
| {'loss': '0.5191', 'grad_norm': '5.866', 'learning_rate': '1.945e-05', 'epoch': '0.2492'} | |
| {'loss': '0.3542', 'grad_norm': '6.951', 'learning_rate': '1.945e-05', 'epoch': '0.2497'} | |
| {'loss': '0.3522', 'grad_norm': '4.506', 'learning_rate': '1.944e-05', 'epoch': '0.2501'} | |
| {'loss': '0.399', 'grad_norm': '3.27', 'learning_rate': '1.944e-05', 'epoch': '0.2506'} | |
| {'loss': '0.4056', 'grad_norm': '2.908', 'learning_rate': '1.943e-05', 'epoch': '0.2511'} | |
| {'loss': '0.3978', 'grad_norm': '1.789', 'learning_rate': '1.943e-05', 'epoch': '0.2516'} | |
| {'loss': '0.3721', 'grad_norm': '7.558', 'learning_rate': '1.942e-05', 'epoch': '0.252'} | |
| {'loss': '0.3571', 'grad_norm': '2.986', 'learning_rate': '1.942e-05', 'epoch': '0.2525'} | |
| {'loss': '0.3497', 'grad_norm': '3.652', 'learning_rate': '1.941e-05', 'epoch': '0.253'} | |
| {'loss': '0.3993', 'grad_norm': '4.294', 'learning_rate': '1.941e-05', 'epoch': '0.2535'} | |
| {'loss': '0.3662', 'grad_norm': '3.097', 'learning_rate': '1.94e-05', 'epoch': '0.2539'} | |
| {'loss': '0.3726', 'grad_norm': '6.318', 'learning_rate': '1.94e-05', 'epoch': '0.2544'} | |
| {'loss': '0.3883', 'grad_norm': '6.025', 'learning_rate': '1.939e-05', 'epoch': '0.2549'} | |
| {'loss': '0.3387', 'grad_norm': '1.5', 'learning_rate': '1.938e-05', 'epoch': '0.2554'} | |
| {'loss': '0.3801', 'grad_norm': '5.878', 'learning_rate': '1.938e-05', 'epoch': '0.2559'} | |
| {'loss': '0.3501', 'grad_norm': '4.048', 'learning_rate': '1.937e-05', 'epoch': '0.2563'} | |
| {'loss': '0.3721', 'grad_norm': '4.402', 'learning_rate': '1.937e-05', 'epoch': '0.2568'} | |
| {'loss': '0.3598', 'grad_norm': '2.966', 'learning_rate': '1.936e-05', 'epoch': '0.2573'} | |
| {'eval_ms_marco_loss': '0.2141', 'eval_val-ms-marco-768_cosine_accuracy': '0.986', 'eval_val-ms-marco-512_cosine_accuracy': '0.9857', 'eval_val-ms-marco-256_cosine_accuracy': '0.9843', 'eval_val-ms-marco-128_cosine_accuracy': '0.9847', 'eval_val-ms-marco-64_cosine_accuracy': '0.985', 'eval_sequential_score': '0.986', 'eval_ms_marco_runtime': '34.3', 'eval_ms_marco_samples_per_second': '291.6', 'eval_ms_marco_steps_per_second': '9.126', 'epoch': '0.2573'} | |
| {'loss': '0.3822', 'grad_norm': '5.143', 'learning_rate': '1.936e-05', 'epoch': '0.2578'} | |
| {'loss': '0.368', 'grad_norm': '2.447', 'learning_rate': '1.935e-05', 'epoch': '0.2582'} | |
| {'loss': '0.3716', 'grad_norm': '5.418', 'learning_rate': '1.935e-05', 'epoch': '0.2587'} | |
| {'loss': '0.343', 'grad_norm': '3.541', 'learning_rate': '1.934e-05', 'epoch': '0.2592'} | |
| {'loss': '0.3477', 'grad_norm': '4.677', 'learning_rate': '1.934e-05', 'epoch': '0.2597'} | |
| {'loss': '0.3409', 'grad_norm': '4.891', 'learning_rate': '1.933e-05', 'epoch': '0.2601'} | |
| {'loss': '0.3566', 'grad_norm': '5.317', 'learning_rate': '1.933e-05', 'epoch': '0.2606'} | |
| {'loss': '0.3494', 'grad_norm': '3.571', 'learning_rate': '1.932e-05', 'epoch': '0.2611'} | |
| {'loss': '0.3381', 'grad_norm': '7.582', 'learning_rate': '1.932e-05', 'epoch': '0.2616'} | |
| {'loss': '0.3327', 'grad_norm': '3.058', 'learning_rate': '1.931e-05', 'epoch': '0.262'} | |
| {'loss': '0.3694', 'grad_norm': '5.272', 'learning_rate': '1.931e-05', 'epoch': '0.2625'} | |
| {'loss': '0.3618', 'grad_norm': '6.979', 'learning_rate': '1.93e-05', 'epoch': '0.263'} | |
| {'loss': '0.3828', 'grad_norm': '5.798', 'learning_rate': '1.929e-05', 'epoch': '0.2635'} | |
| {'loss': '0.3689', 'grad_norm': '8.336', 'learning_rate': '1.929e-05', 'epoch': '0.264'} | |
| {'loss': '0.3829', 'grad_norm': '5.193', 'learning_rate': '1.928e-05', 'epoch': '0.2644'} | |
| {'loss': '0.3847', 'grad_norm': '7.256', 'learning_rate': '1.928e-05', 'epoch': '0.2649'} | |
| {'loss': '0.337', 'grad_norm': '3.219', 'learning_rate': '1.927e-05', 'epoch': '0.2654'} | |
| {'loss': '0.4651', 'grad_norm': '6.793', 'learning_rate': '1.927e-05', 'epoch': '0.2659'} | |
| {'loss': '0.3636', 'grad_norm': '9.085', 'learning_rate': '1.926e-05', 'epoch': '0.2663'} | |
| {'loss': '0.3755', 'grad_norm': '4.295', 'learning_rate': '1.926e-05', 'epoch': '0.2668'} | |
| {'loss': '0.4308', 'grad_norm': '3.282', 'learning_rate': '1.925e-05', 'epoch': '0.2673'} | |
| {'loss': '0.3364', 'grad_norm': '5.851', 'learning_rate': '1.925e-05', 'epoch': '0.2678'} | |
| {'loss': '0.3465', 'grad_norm': '1.252', 'learning_rate': '1.924e-05', 'epoch': '0.2682'} | |
| {'loss': '0.3468', 'grad_norm': '5.246', 'learning_rate': '1.924e-05', 'epoch': '0.2687'} | |
| {'loss': '0.3684', 'grad_norm': '5.803', 'learning_rate': '1.923e-05', 'epoch': '0.2692'} | |
| {'loss': '0.3338', 'grad_norm': '6.85', 'learning_rate': '1.923e-05', 'epoch': '0.2697'} | |
| {'loss': '0.3402', 'grad_norm': '3.636', 'learning_rate': '1.922e-05', 'epoch': '0.2701'} | |
| {'loss': '0.4934', 'grad_norm': '5.264', 'learning_rate': '1.922e-05', 'epoch': '0.2706'} | |
| {'loss': '0.3375', 'grad_norm': '2.778', 'learning_rate': '1.921e-05', 'epoch': '0.2711'} | |
| {'loss': '0.3469', 'grad_norm': '4.239', 'learning_rate': '1.92e-05', 'epoch': '0.2716'} | |
| {'loss': '0.3349', 'grad_norm': '9.689', 'learning_rate': '1.92e-05', 'epoch': '0.2721'} | |
| {'loss': '0.3574', 'grad_norm': '3.81', 'learning_rate': '1.919e-05', 'epoch': '0.2725'} | |
| {'loss': '0.3614', 'grad_norm': '12.86', 'learning_rate': '1.919e-05', 'epoch': '0.273'} | |
| {'loss': '0.4198', 'grad_norm': '7.782', 'learning_rate': '1.918e-05', 'epoch': '0.2735'} | |
| {'loss': '0.3431', 'grad_norm': '2.679', 'learning_rate': '1.918e-05', 'epoch': '0.274'} | |
| {'loss': '0.3251', 'grad_norm': '6.507', 'learning_rate': '1.917e-05', 'epoch': '0.2744'} | |
| {'loss': '0.3683', 'grad_norm': '8.295', 'learning_rate': '1.917e-05', 'epoch': '0.2749'} | |
| {'loss': '0.408', 'grad_norm': '4.199', 'learning_rate': '1.916e-05', 'epoch': '0.2754'} | |
| {'loss': '0.3011', 'grad_norm': '4.904', 'learning_rate': '1.916e-05', 'epoch': '0.2759'} | |
| {'loss': '0.343', 'grad_norm': '4.85', 'learning_rate': '1.915e-05', 'epoch': '0.2763'} | |
| {'loss': '0.3249', 'grad_norm': '8.8', 'learning_rate': '1.915e-05', 'epoch': '0.2768'} | |
| {'loss': '0.3392', 'grad_norm': '7.471', 'learning_rate': '1.914e-05', 'epoch': '0.2773'} | |
| {'loss': '0.3642', 'grad_norm': '1.816', 'learning_rate': '1.914e-05', 'epoch': '0.2778'} | |
| {'loss': '0.3347', 'grad_norm': '1.299', 'learning_rate': '1.913e-05', 'epoch': '0.2782'} | |
| {'loss': '0.3333', 'grad_norm': '5.692', 'learning_rate': '1.913e-05', 'epoch': '0.2787'} | |
| {'loss': '0.3397', 'grad_norm': '5.194', 'learning_rate': '1.912e-05', 'epoch': '0.2792'} | |
| {'loss': '0.3257', 'grad_norm': '7.792', 'learning_rate': '1.911e-05', 'epoch': '0.2797'} | |
| {'loss': '0.3237', 'grad_norm': '5.265', 'learning_rate': '1.911e-05', 'epoch': '0.2802'} | |
| {'loss': '0.3507', 'grad_norm': '8.713', 'learning_rate': '1.91e-05', 'epoch': '0.2806'} | |
| {'loss': '0.325', 'grad_norm': '1.49', 'learning_rate': '1.91e-05', 'epoch': '0.2811'} | |
| {'loss': '0.354', 'grad_norm': '4.392', 'learning_rate': '1.909e-05', 'epoch': '0.2816'} | |
| {'loss': '0.3503', 'grad_norm': '8.807', 'learning_rate': '1.909e-05', 'epoch': '0.2821'} | |
| {'loss': '0.3221', 'grad_norm': '1.938', 'learning_rate': '1.908e-05', 'epoch': '0.2825'} | |
| {'loss': '0.4367', 'grad_norm': '2.139', 'learning_rate': '1.908e-05', 'epoch': '0.283'} | |
| {'loss': '0.3442', 'grad_norm': '4.953', 'learning_rate': '1.907e-05', 'epoch': '0.2835'} | |
| {'loss': '0.3282', 'grad_norm': '7.775', 'learning_rate': '1.907e-05', 'epoch': '0.284'} | |
| {'loss': '0.4677', 'grad_norm': '4.788', 'learning_rate': '1.906e-05', 'epoch': '0.2844'} | |
| {'loss': '0.3044', 'grad_norm': '3.358', 'learning_rate': '1.906e-05', 'epoch': '0.2849'} | |
| {'loss': '0.3363', 'grad_norm': '7.955', 'learning_rate': '1.905e-05', 'epoch': '0.2854'} | |
| {'loss': '0.3187', 'grad_norm': '7.837', 'learning_rate': '1.905e-05', 'epoch': '0.2859'} | |
| {'eval_ms_marco_loss': '0.1885', 'eval_val-ms-marco-768_cosine_accuracy': '0.985', 'eval_val-ms-marco-512_cosine_accuracy': '0.985', 'eval_val-ms-marco-256_cosine_accuracy': '0.987', 'eval_val-ms-marco-128_cosine_accuracy': '0.9867', 'eval_val-ms-marco-64_cosine_accuracy': '0.9837', 'eval_sequential_score': '0.985', 'eval_ms_marco_runtime': '34.1', 'eval_ms_marco_samples_per_second': '293.2', 'eval_ms_marco_steps_per_second': '9.178', 'epoch': '0.2859'} | |
| {'loss': '0.3274', 'grad_norm': '1.085', 'learning_rate': '1.904e-05', 'epoch': '0.2863'} | |
| {'loss': '0.3019', 'grad_norm': '6.932', 'learning_rate': '1.904e-05', 'epoch': '0.2868'} | |
| {'loss': '0.4151', 'grad_norm': '4.096', 'learning_rate': '1.903e-05', 'epoch': '0.2873'} | |
| {'loss': '0.3667', 'grad_norm': '3.757', 'learning_rate': '1.902e-05', 'epoch': '0.2878'} | |
| {'loss': '0.3393', 'grad_norm': '1.528', 'learning_rate': '1.902e-05', 'epoch': '0.2883'} | |
| {'loss': '0.3538', 'grad_norm': '5.492', 'learning_rate': '1.901e-05', 'epoch': '0.2887'} | |
| {'loss': '0.3148', 'grad_norm': '2.312', 'learning_rate': '1.901e-05', 'epoch': '0.2892'} | |
| {'loss': '0.3085', 'grad_norm': '7.377', 'learning_rate': '1.9e-05', 'epoch': '0.2897'} | |
| {'loss': '0.3226', 'grad_norm': '2.071', 'learning_rate': '1.9e-05', 'epoch': '0.2902'} | |
| {'loss': '0.4473', 'grad_norm': '5.224', 'learning_rate': '1.899e-05', 'epoch': '0.2906'} | |
| {'loss': '0.3223', 'grad_norm': '3.26', 'learning_rate': '1.899e-05', 'epoch': '0.2911'} | |
| {'loss': '0.3301', 'grad_norm': '4.853', 'learning_rate': '1.898e-05', 'epoch': '0.2916'} | |
| {'loss': '0.3384', 'grad_norm': '5.206', 'learning_rate': '1.898e-05', 'epoch': '0.2921'} | |
| {'loss': '0.3486', 'grad_norm': '1.474', 'learning_rate': '1.897e-05', 'epoch': '0.2925'} | |
| {'loss': '0.3245', 'grad_norm': '3.477', 'learning_rate': '1.897e-05', 'epoch': '0.293'} | |
| {'loss': '0.2893', 'grad_norm': '2.228', 'learning_rate': '1.896e-05', 'epoch': '0.2935'} | |
| {'loss': '0.3491', 'grad_norm': '3.039', 'learning_rate': '1.896e-05', 'epoch': '0.294'} | |
| {'loss': '0.365', 'grad_norm': '3.733', 'learning_rate': '1.895e-05', 'epoch': '0.2944'} | |
| {'loss': '0.3566', 'grad_norm': '1.46', 'learning_rate': '1.895e-05', 'epoch': '0.2949'} | |
| {'loss': '0.3301', 'grad_norm': '2.54', 'learning_rate': '1.894e-05', 'epoch': '0.2954'} | |
| {'loss': '0.4054', 'grad_norm': '3.943', 'learning_rate': '1.893e-05', 'epoch': '0.2959'} | |
| {'loss': '0.4414', 'grad_norm': '3.947', 'learning_rate': '1.893e-05', 'epoch': '0.2964'} | |
| {'loss': '0.3162', 'grad_norm': '4.994', 'learning_rate': '1.892e-05', 'epoch': '0.2968'} | |
| {'loss': '0.326', 'grad_norm': '6.735', 'learning_rate': '1.892e-05', 'epoch': '0.2973'} | |
| {'loss': '0.3491', 'grad_norm': '3.574', 'learning_rate': '1.891e-05', 'epoch': '0.2978'} | |
| {'loss': '0.3204', 'grad_norm': '6.085', 'learning_rate': '1.891e-05', 'epoch': '0.2983'} | |
| {'loss': '0.3291', 'grad_norm': '6.429', 'learning_rate': '1.89e-05', 'epoch': '0.2987'} | |
| {'loss': '0.3155', 'grad_norm': '5.965', 'learning_rate': '1.89e-05', 'epoch': '0.2992'} | |
| {'loss': '0.4554', 'grad_norm': '1.724', 'learning_rate': '1.889e-05', 'epoch': '0.2997'} | |
| {'loss': '0.43', 'grad_norm': '2.356', 'learning_rate': '1.889e-05', 'epoch': '0.3002'} | |
| {'loss': '0.2899', 'grad_norm': '4.836', 'learning_rate': '1.888e-05', 'epoch': '0.3006'} | |
| {'loss': '0.2873', 'grad_norm': '3.104', 'learning_rate': '1.888e-05', 'epoch': '0.3011'} | |
| {'loss': '0.3221', 'grad_norm': '6.13', 'learning_rate': '1.887e-05', 'epoch': '0.3016'} | |
| {'loss': '0.3156', 'grad_norm': '3.983', 'learning_rate': '1.887e-05', 'epoch': '0.3021'} | |
| {'loss': '0.2909', 'grad_norm': '4.807', 'learning_rate': '1.886e-05', 'epoch': '0.3025'} | |
| {'loss': '0.3105', 'grad_norm': '5.458', 'learning_rate': '1.886e-05', 'epoch': '0.303'} | |
| {'loss': '0.294', 'grad_norm': '3.293', 'learning_rate': '1.885e-05', 'epoch': '0.3035'} | |
| {'loss': '0.3033', 'grad_norm': '3.7', 'learning_rate': '1.884e-05', 'epoch': '0.304'} | |
| {'loss': '0.3118', 'grad_norm': '3.977', 'learning_rate': '1.884e-05', 'epoch': '0.3045'} | |
| {'loss': '0.306', 'grad_norm': '6.076', 'learning_rate': '1.883e-05', 'epoch': '0.3049'} | |
| {'loss': '0.3253', 'grad_norm': '2.563', 'learning_rate': '1.883e-05', 'epoch': '0.3054'} | |
| {'loss': '0.2917', 'grad_norm': '1.549', 'learning_rate': '1.882e-05', 'epoch': '0.3059'} | |
| {'loss': '0.3485', 'grad_norm': '3.774', 'learning_rate': '1.882e-05', 'epoch': '0.3064'} | |
| {'loss': '0.3107', 'grad_norm': '5.245', 'learning_rate': '1.881e-05', 'epoch': '0.3068'} | |
| {'loss': '0.3006', 'grad_norm': '4.879', 'learning_rate': '1.881e-05', 'epoch': '0.3073'} | |
| {'loss': '0.3218', 'grad_norm': '5.302', 'learning_rate': '1.88e-05', 'epoch': '0.3078'} | |
| {'loss': '0.282', 'grad_norm': '3.375', 'learning_rate': '1.88e-05', 'epoch': '0.3083'} | |
| {'loss': '0.2928', 'grad_norm': '0.8942', 'learning_rate': '1.879e-05', 'epoch': '0.3087'} | |
| {'loss': '0.2973', 'grad_norm': '2.593', 'learning_rate': '1.879e-05', 'epoch': '0.3092'} | |
| {'loss': '0.3125', 'grad_norm': '6.244', 'learning_rate': '1.878e-05', 'epoch': '0.3097'} | |
| {'loss': '0.3012', 'grad_norm': '4.482', 'learning_rate': '1.878e-05', 'epoch': '0.3102'} | |
| {'loss': '0.3134', 'grad_norm': '5.489', 'learning_rate': '1.877e-05', 'epoch': '0.3106'} | |
| {'loss': '0.3086', 'grad_norm': '6.349', 'learning_rate': '1.877e-05', 'epoch': '0.3111'} | |
| {'loss': '0.3238', 'grad_norm': '4.979', 'learning_rate': '1.876e-05', 'epoch': '0.3116'} | |
| {'loss': '0.3261', 'grad_norm': '2.221', 'learning_rate': '1.875e-05', 'epoch': '0.3121'} | |
| {'loss': '0.3114', 'grad_norm': '6.05', 'learning_rate': '1.875e-05', 'epoch': '0.3126'} | |
| {'loss': '0.3111', 'grad_norm': '6.22', 'learning_rate': '1.874e-05', 'epoch': '0.313'} | |
| {'loss': '0.3032', 'grad_norm': '6.747', 'learning_rate': '1.874e-05', 'epoch': '0.3135'} | |
| {'loss': '0.334', 'grad_norm': '5.272', 'learning_rate': '1.873e-05', 'epoch': '0.314'} | |
| {'loss': '0.3708', 'grad_norm': '6.252', 'learning_rate': '1.873e-05', 'epoch': '0.3145'} | |
| {'eval_ms_marco_loss': '0.1592', 'eval_val-ms-marco-768_cosine_accuracy': '0.989', 'eval_val-ms-marco-512_cosine_accuracy': '0.9893', 'eval_val-ms-marco-256_cosine_accuracy': '0.9893', 'eval_val-ms-marco-128_cosine_accuracy': '0.99', 'eval_val-ms-marco-64_cosine_accuracy': '0.9893', 'eval_sequential_score': '0.989', 'eval_ms_marco_runtime': '34.19', 'eval_ms_marco_samples_per_second': '292.5', 'eval_ms_marco_steps_per_second': '9.155', 'epoch': '0.3145'} | |
| {'loss': '0.3076', 'grad_norm': '7.013', 'learning_rate': '1.872e-05', 'epoch': '0.3149'} | |
| {'loss': '0.3068', 'grad_norm': '3.432', 'learning_rate': '1.872e-05', 'epoch': '0.3154'} | |
| {'loss': '0.283', 'grad_norm': '2.023', 'learning_rate': '1.871e-05', 'epoch': '0.3159'} | |
| {'loss': '0.4728', 'grad_norm': '9.806', 'learning_rate': '1.871e-05', 'epoch': '0.3164'} | |
| {'loss': '0.3441', 'grad_norm': '5.105', 'learning_rate': '1.87e-05', 'epoch': '0.3168'} | |
| {'loss': '0.2919', 'grad_norm': '1.812', 'learning_rate': '1.87e-05', 'epoch': '0.3173'} | |
| {'loss': '0.3272', 'grad_norm': '4.472', 'learning_rate': '1.869e-05', 'epoch': '0.3178'} | |
| {'loss': '0.3059', 'grad_norm': '3.869', 'learning_rate': '1.869e-05', 'epoch': '0.3183'} | |
| {'loss': '0.334', 'grad_norm': '7.78', 'learning_rate': '1.868e-05', 'epoch': '0.3187'} | |
| {'loss': '0.3281', 'grad_norm': '6.263', 'learning_rate': '1.868e-05', 'epoch': '0.3192'} | |
| {'loss': '0.2821', 'grad_norm': '3.22', 'learning_rate': '1.867e-05', 'epoch': '0.3197'} | |
| {'loss': '0.3011', 'grad_norm': '4.204', 'learning_rate': '1.866e-05', 'epoch': '0.3202'} | |
| {'loss': '0.3022', 'grad_norm': '4.136', 'learning_rate': '1.866e-05', 'epoch': '0.3207'} | |
| {'loss': '0.288', 'grad_norm': '4.133', 'learning_rate': '1.865e-05', 'epoch': '0.3211'} | |
| {'loss': '0.3111', 'grad_norm': '6.193', 'learning_rate': '1.865e-05', 'epoch': '0.3216'} | |
| {'loss': '0.3061', 'grad_norm': '4.846', 'learning_rate': '1.864e-05', 'epoch': '0.3221'} | |
| {'loss': '0.3157', 'grad_norm': '4.463', 'learning_rate': '1.864e-05', 'epoch': '0.3226'} | |
| {'loss': '0.3027', 'grad_norm': '5.582', 'learning_rate': '1.863e-05', 'epoch': '0.323'} | |
| {'loss': '0.3227', 'grad_norm': '2.692', 'learning_rate': '1.863e-05', 'epoch': '0.3235'} | |
| {'loss': '0.3784', 'grad_norm': '3.283', 'learning_rate': '1.862e-05', 'epoch': '0.324'} | |
| {'loss': '0.3371', 'grad_norm': '4.407', 'learning_rate': '1.862e-05', 'epoch': '0.3245'} | |
| {'loss': '0.2934', 'grad_norm': '3.435', 'learning_rate': '1.861e-05', 'epoch': '0.3249'} | |
| {'loss': '0.2896', 'grad_norm': '5.668', 'learning_rate': '1.861e-05', 'epoch': '0.3254'} | |
| {'loss': '0.3028', 'grad_norm': '6.6', 'learning_rate': '1.86e-05', 'epoch': '0.3259'} | |
| {'loss': '0.3222', 'grad_norm': '6.524', 'learning_rate': '1.86e-05', 'epoch': '0.3264'} | |
| {'loss': '0.2543', 'grad_norm': '4.724', 'learning_rate': '1.859e-05', 'epoch': '0.3268'} | |
| {'loss': '0.3206', 'grad_norm': '1.751', 'learning_rate': '1.859e-05', 'epoch': '0.3273'} | |
| {'loss': '0.2796', 'grad_norm': '2.4', 'learning_rate': '1.858e-05', 'epoch': '0.3278'} | |
| {'loss': '0.3294', 'grad_norm': '7.78', 'learning_rate': '1.857e-05', 'epoch': '0.3283'} | |
| {'loss': '0.2879', 'grad_norm': '4.372', 'learning_rate': '1.857e-05', 'epoch': '0.3288'} | |
| {'loss': '0.3038', 'grad_norm': '0.9565', 'learning_rate': '1.856e-05', 'epoch': '0.3292'} | |
| {'loss': '0.3079', 'grad_norm': '7.965', 'learning_rate': '1.856e-05', 'epoch': '0.3297'} | |
| {'loss': '0.3823', 'grad_norm': '4.871', 'learning_rate': '1.855e-05', 'epoch': '0.3302'} | |
| {'loss': '0.2877', 'grad_norm': '2.683', 'learning_rate': '1.855e-05', 'epoch': '0.3307'} | |
| {'loss': '0.3138', 'grad_norm': '4.137', 'learning_rate': '1.854e-05', 'epoch': '0.3311'} | |
| {'loss': '0.3329', 'grad_norm': '4.015', 'learning_rate': '1.854e-05', 'epoch': '0.3316'} | |
| {'loss': '0.2733', 'grad_norm': '3.12', 'learning_rate': '1.853e-05', 'epoch': '0.3321'} | |
| {'loss': '0.2666', 'grad_norm': '2.76', 'learning_rate': '1.853e-05', 'epoch': '0.3326'} | |
| {'loss': '0.2738', 'grad_norm': '6.909', 'learning_rate': '1.852e-05', 'epoch': '0.333'} | |
| {'loss': '0.2884', 'grad_norm': '5.107', 'learning_rate': '1.852e-05', 'epoch': '0.3335'} | |
| {'loss': '0.2871', 'grad_norm': '6.287', 'learning_rate': '1.851e-05', 'epoch': '0.334'} | |
| {'loss': '0.3168', 'grad_norm': '1.671', 'learning_rate': '1.851e-05', 'epoch': '0.3345'} | |
| {'loss': '0.2864', 'grad_norm': '4.323', 'learning_rate': '1.85e-05', 'epoch': '0.3349'} | |
| {'loss': '0.3791', 'grad_norm': '3.039', 'learning_rate': '1.85e-05', 'epoch': '0.3354'} | |
| {'loss': '0.3308', 'grad_norm': '2.06', 'learning_rate': '1.849e-05', 'epoch': '0.3359'} | |
| {'loss': '0.2795', 'grad_norm': '5.889', 'learning_rate': '1.848e-05', 'epoch': '0.3364'} | |
| {'loss': '0.2811', 'grad_norm': '3.811', 'learning_rate': '1.848e-05', 'epoch': '0.3369'} | |
| {'loss': '0.2675', 'grad_norm': '6.544', 'learning_rate': '1.847e-05', 'epoch': '0.3373'} | |
| {'loss': '0.2872', 'grad_norm': '5.285', 'learning_rate': '1.847e-05', 'epoch': '0.3378'} | |
| {'loss': '0.2945', 'grad_norm': '4.477', 'learning_rate': '1.846e-05', 'epoch': '0.3383'} | |
| {'loss': '0.2949', 'grad_norm': '2.541', 'learning_rate': '1.846e-05', 'epoch': '0.3388'} | |
| {'loss': '0.5347', 'grad_norm': '76.22', 'learning_rate': '1.845e-05', 'epoch': '0.3392'} | |
| {'loss': '0.3957', 'grad_norm': '3.089', 'learning_rate': '1.845e-05', 'epoch': '0.3397'} | |
| {'loss': '0.2794', 'grad_norm': '2.858', 'learning_rate': '1.844e-05', 'epoch': '0.3402'} | |
| {'loss': '0.2901', 'grad_norm': '8.225', 'learning_rate': '1.844e-05', 'epoch': '0.3407'} | |
| {'loss': '0.2821', 'grad_norm': '4.444', 'learning_rate': '1.843e-05', 'epoch': '0.3411'} | |
| {'loss': '0.2981', 'grad_norm': '2.146', 'learning_rate': '1.843e-05', 'epoch': '0.3416'} | |
| {'loss': '0.294', 'grad_norm': '7.379', 'learning_rate': '1.842e-05', 'epoch': '0.3421'} | |
| {'loss': '0.2505', 'grad_norm': '2.344', 'learning_rate': '1.842e-05', 'epoch': '0.3426'} | |
| {'loss': '0.3035', 'grad_norm': '7.336', 'learning_rate': '1.841e-05', 'epoch': '0.343'} | |
| {'eval_ms_marco_loss': '0.1458', 'eval_val-ms-marco-768_cosine_accuracy': '0.99', 'eval_val-ms-marco-512_cosine_accuracy': '0.9903', 'eval_val-ms-marco-256_cosine_accuracy': '0.9897', 'eval_val-ms-marco-128_cosine_accuracy': '0.9897', 'eval_val-ms-marco-64_cosine_accuracy': '0.9883', 'eval_sequential_score': '0.99', 'eval_ms_marco_runtime': '34.57', 'eval_ms_marco_samples_per_second': '289.3', 'eval_ms_marco_steps_per_second': '9.054', 'epoch': '0.343'} | |
| {'loss': '0.2866', 'grad_norm': '2.917', 'learning_rate': '1.841e-05', 'epoch': '0.3435'} | |
| {'loss': '0.262', 'grad_norm': '2.62', 'learning_rate': '1.84e-05', 'epoch': '0.344'} | |
| {'loss': '0.3109', 'grad_norm': '7.1', 'learning_rate': '1.839e-05', 'epoch': '0.3445'} | |
| {'loss': '0.3114', 'grad_norm': '3.677', 'learning_rate': '1.839e-05', 'epoch': '0.3449'} | |
| {'loss': '0.3852', 'grad_norm': '6.286', 'learning_rate': '1.838e-05', 'epoch': '0.3454'} | |
| {'loss': '0.299', 'grad_norm': '3.939', 'learning_rate': '1.838e-05', 'epoch': '0.3459'} | |
| {'loss': '0.2937', 'grad_norm': '6.234', 'learning_rate': '1.837e-05', 'epoch': '0.3464'} | |
| {'loss': '0.2753', 'grad_norm': '5.053', 'learning_rate': '1.837e-05', 'epoch': '0.3469'} | |
| {'loss': '0.2972', 'grad_norm': '2.46', 'learning_rate': '1.836e-05', 'epoch': '0.3473'} | |
| {'loss': '0.2558', 'grad_norm': '4.72', 'learning_rate': '1.836e-05', 'epoch': '0.3478'} | |
| {'loss': '0.2723', 'grad_norm': '5.542', 'learning_rate': '1.835e-05', 'epoch': '0.3483'} | |
| {'loss': '0.2665', 'grad_norm': '7.764', 'learning_rate': '1.835e-05', 'epoch': '0.3488'} | |
| {'loss': '0.273', 'grad_norm': '5.882', 'learning_rate': '1.834e-05', 'epoch': '0.3492'} | |
| {'loss': '0.2676', 'grad_norm': '6.875', 'learning_rate': '1.834e-05', 'epoch': '0.3497'} | |
| {'loss': '0.3851', 'grad_norm': '2.924', 'learning_rate': '1.833e-05', 'epoch': '0.3502'} | |
| {'loss': '0.2698', 'grad_norm': '3.669', 'learning_rate': '1.833e-05', 'epoch': '0.3507'} | |
| {'loss': '0.4253', 'grad_norm': '0.87', 'learning_rate': '1.832e-05', 'epoch': '0.3511'} | |
| {'loss': '0.3955', 'grad_norm': '4.549', 'learning_rate': '1.832e-05', 'epoch': '0.3516'} | |
| {'loss': '0.2771', 'grad_norm': '2.07', 'learning_rate': '1.831e-05', 'epoch': '0.3521'} | |
| {'loss': '0.2772', 'grad_norm': '4.777', 'learning_rate': '1.83e-05', 'epoch': '0.3526'} | |
| {'loss': '0.2937', 'grad_norm': '4.41', 'learning_rate': '1.83e-05', 'epoch': '0.353'} | |
| {'loss': '0.2894', 'grad_norm': '2.303', 'learning_rate': '1.829e-05', 'epoch': '0.3535'} | |
| {'loss': '0.2799', 'grad_norm': '6.163', 'learning_rate': '1.829e-05', 'epoch': '0.354'} | |
| {'loss': '0.275', 'grad_norm': '1.879', 'learning_rate': '1.828e-05', 'epoch': '0.3545'} | |
| {'loss': '0.2861', 'grad_norm': '9.589', 'learning_rate': '1.828e-05', 'epoch': '0.355'} | |
| {'loss': '0.3806', 'grad_norm': '4.314', 'learning_rate': '1.827e-05', 'epoch': '0.3554'} | |
| {'loss': '0.2899', 'grad_norm': '8.154', 'learning_rate': '1.827e-05', 'epoch': '0.3559'} | |
| {'loss': '0.2885', 'grad_norm': '6.419', 'learning_rate': '1.826e-05', 'epoch': '0.3564'} | |
| {'loss': '0.295', 'grad_norm': '7.714', 'learning_rate': '1.826e-05', 'epoch': '0.3569'} | |
| {'loss': '0.2891', 'grad_norm': '3.074', 'learning_rate': '1.825e-05', 'epoch': '0.3573'} | |
| {'loss': '0.2707', 'grad_norm': '4.95', 'learning_rate': '1.825e-05', 'epoch': '0.3578'} | |
| {'loss': '0.2885', 'grad_norm': '4.604', 'learning_rate': '1.824e-05', 'epoch': '0.3583'} | |
| {'loss': '0.2827', 'grad_norm': '4.298', 'learning_rate': '1.824e-05', 'epoch': '0.3588'} | |
| {'loss': '0.3216', 'grad_norm': '5.869', 'learning_rate': '1.823e-05', 'epoch': '0.3592'} | |
| {'loss': '0.2812', 'grad_norm': '6.99', 'learning_rate': '1.823e-05', 'epoch': '0.3597'} | |
| {'loss': '0.2704', 'grad_norm': '5.647', 'learning_rate': '1.822e-05', 'epoch': '0.3602'} | |
| {'loss': '0.306', 'grad_norm': '0.5873', 'learning_rate': '1.821e-05', 'epoch': '0.3607'} | |
| {'loss': '0.3873', 'grad_norm': '4.339', 'learning_rate': '1.821e-05', 'epoch': '0.3611'} | |
| {'loss': '0.3836', 'grad_norm': '3.475', 'learning_rate': '1.82e-05', 'epoch': '0.3616'} | |
| {'loss': '0.2698', 'grad_norm': '2.85', 'learning_rate': '1.82e-05', 'epoch': '0.3621'} | |
| {'loss': '0.2972', 'grad_norm': '3.926', 'learning_rate': '1.819e-05', 'epoch': '0.3626'} | |
| {'loss': '0.2821', 'grad_norm': '2.59', 'learning_rate': '1.819e-05', 'epoch': '0.3631'} | |
| {'loss': '0.4201', 'grad_norm': '5.014', 'learning_rate': '1.818e-05', 'epoch': '0.3635'} | |
| {'loss': '0.3896', 'grad_norm': '2.167', 'learning_rate': '1.818e-05', 'epoch': '0.364'} | |
| {'loss': '0.2905', 'grad_norm': '2.612', 'learning_rate': '1.817e-05', 'epoch': '0.3645'} | |
| {'loss': '0.2907', 'grad_norm': '1.803', 'learning_rate': '1.817e-05', 'epoch': '0.365'} | |
| {'loss': '0.2961', 'grad_norm': '3.68', 'learning_rate': '1.816e-05', 'epoch': '0.3654'} | |
| {'loss': '0.2696', 'grad_norm': '4.567', 'learning_rate': '1.816e-05', 'epoch': '0.3659'} | |
| {'loss': '0.2833', 'grad_norm': '6.986', 'learning_rate': '1.815e-05', 'epoch': '0.3664'} | |
| {'loss': '0.3933', 'grad_norm': '1.681', 'learning_rate': '1.815e-05', 'epoch': '0.3669'} | |
| {'loss': '0.4816', 'grad_norm': '7.568', 'learning_rate': '1.814e-05', 'epoch': '0.3673'} | |
| {'loss': '0.2438', 'grad_norm': '3.053', 'learning_rate': '1.814e-05', 'epoch': '0.3678'} | |
| {'loss': '0.2798', 'grad_norm': '4.073', 'learning_rate': '1.813e-05', 'epoch': '0.3683'} | |
| {'loss': '0.2943', 'grad_norm': '3.819', 'learning_rate': '1.812e-05', 'epoch': '0.3688'} | |
| {'loss': '0.2652', 'grad_norm': '5.114', 'learning_rate': '1.812e-05', 'epoch': '0.3692'} | |
| {'loss': '0.2709', 'grad_norm': '1.737', 'learning_rate': '1.811e-05', 'epoch': '0.3697'} | |
| {'loss': '0.2756', 'grad_norm': '0.997', 'learning_rate': '1.811e-05', 'epoch': '0.3702'} | |
| {'loss': '0.2846', 'grad_norm': '1.635', 'learning_rate': '1.81e-05', 'epoch': '0.3707'} | |
| {'loss': '0.2496', 'grad_norm': '3.921', 'learning_rate': '1.81e-05', 'epoch': '0.3712'} | |
| {'loss': '0.476', 'grad_norm': '5.803', 'learning_rate': '1.809e-05', 'epoch': '0.3716'} | |
| {'eval_ms_marco_loss': '0.1401', 'eval_val-ms-marco-768_cosine_accuracy': '0.9917', 'eval_val-ms-marco-512_cosine_accuracy': '0.9907', 'eval_val-ms-marco-256_cosine_accuracy': '0.9897', 'eval_val-ms-marco-128_cosine_accuracy': '0.991', 'eval_val-ms-marco-64_cosine_accuracy': '0.989', 'eval_sequential_score': '0.9917', 'eval_ms_marco_runtime': '34.02', 'eval_ms_marco_samples_per_second': '294', 'eval_ms_marco_steps_per_second': '9.202', 'epoch': '0.3716'} | |
| {'loss': '0.2376', 'grad_norm': '4.544', 'learning_rate': '1.809e-05', 'epoch': '0.3721'} | |
| {'loss': '0.252', 'grad_norm': '2.879', 'learning_rate': '1.808e-05', 'epoch': '0.3726'} | |
| {'loss': '0.2729', 'grad_norm': '3.968', 'learning_rate': '1.808e-05', 'epoch': '0.3731'} | |
| {'loss': '0.2502', 'grad_norm': '2.296', 'learning_rate': '1.807e-05', 'epoch': '0.3735'} | |
| {'loss': '0.2657', 'grad_norm': '7.954', 'learning_rate': '1.807e-05', 'epoch': '0.374'} | |
| {'loss': '0.2586', 'grad_norm': '3.24', 'learning_rate': '1.806e-05', 'epoch': '0.3745'} | |
| {'loss': '0.2724', 'grad_norm': '5.604', 'learning_rate': '1.806e-05', 'epoch': '0.375'} | |
| {'loss': '0.2895', 'grad_norm': '3.644', 'learning_rate': '1.805e-05', 'epoch': '0.3754'} | |
| {'loss': '0.2762', 'grad_norm': '7.258', 'learning_rate': '1.805e-05', 'epoch': '0.3759'} | |
| {'loss': '0.2592', 'grad_norm': '0.9138', 'learning_rate': '1.804e-05', 'epoch': '0.3764'} | |
| {'loss': '0.2597', 'grad_norm': '2.204', 'learning_rate': '1.803e-05', 'epoch': '0.3769'} | |
| {'loss': '0.2569', 'grad_norm': '1.658', 'learning_rate': '1.803e-05', 'epoch': '0.3773'} | |
| {'loss': '0.2755', 'grad_norm': '1.118', 'learning_rate': '1.802e-05', 'epoch': '0.3778'} | |
| {'loss': '0.4316', 'grad_norm': '3.775', 'learning_rate': '1.802e-05', 'epoch': '0.3783'} | |
| {'loss': '0.2508', 'grad_norm': '7.403', 'learning_rate': '1.801e-05', 'epoch': '0.3788'} | |
| {'loss': '0.2571', 'grad_norm': '4.766', 'learning_rate': '1.801e-05', 'epoch': '0.3793'} | |
| {'loss': '0.2985', 'grad_norm': '1.901', 'learning_rate': '1.8e-05', 'epoch': '0.3797'} | |
| {'loss': '0.2862', 'grad_norm': '4.444', 'learning_rate': '1.8e-05', 'epoch': '0.3802'} | |
| {'loss': '0.2391', 'grad_norm': '6.05', 'learning_rate': '1.799e-05', 'epoch': '0.3807'} | |
| {'loss': '0.2862', 'grad_norm': '4.413', 'learning_rate': '1.799e-05', 'epoch': '0.3812'} | |
| {'loss': '0.2815', 'grad_norm': '3.796', 'learning_rate': '1.798e-05', 'epoch': '0.3816'} | |
| {'loss': '0.2807', 'grad_norm': '4.269', 'learning_rate': '1.798e-05', 'epoch': '0.3821'} | |
| {'loss': '0.2725', 'grad_norm': '4.53', 'learning_rate': '1.797e-05', 'epoch': '0.3826'} | |
| {'loss': '0.2567', 'grad_norm': '5.931', 'learning_rate': '1.797e-05', 'epoch': '0.3831'} | |
| {'loss': '0.2635', 'grad_norm': '7.174', 'learning_rate': '1.796e-05', 'epoch': '0.3835'} | |
| {'loss': '0.4264', 'grad_norm': '1.236', 'learning_rate': '1.796e-05', 'epoch': '0.384'} | |
| {'loss': '0.2544', 'grad_norm': '4.616', 'learning_rate': '1.795e-05', 'epoch': '0.3845'} | |
| {'loss': '0.2503', 'grad_norm': '1.184', 'learning_rate': '1.794e-05', 'epoch': '0.385'} | |
| {'loss': '0.2708', 'grad_norm': '7.823', 'learning_rate': '1.794e-05', 'epoch': '0.3854'} | |
| {'loss': '0.2724', 'grad_norm': '1.488', 'learning_rate': '1.793e-05', 'epoch': '0.3859'} | |
| {'loss': '0.2858', 'grad_norm': '2.7', 'learning_rate': '1.793e-05', 'epoch': '0.3864'} | |
| {'loss': '0.2859', 'grad_norm': '2.85', 'learning_rate': '1.792e-05', 'epoch': '0.3869'} | |
| {'loss': '0.2704', 'grad_norm': '4.014', 'learning_rate': '1.792e-05', 'epoch': '0.3874'} | |
| {'loss': '0.4027', 'grad_norm': '7.784', 'learning_rate': '1.791e-05', 'epoch': '0.3878'} | |
| {'loss': '0.2584', 'grad_norm': '3.148', 'learning_rate': '1.791e-05', 'epoch': '0.3883'} | |
| {'loss': '0.2784', 'grad_norm': '7.83', 'learning_rate': '1.79e-05', 'epoch': '0.3888'} | |
| {'loss': '0.2543', 'grad_norm': '1.946', 'learning_rate': '1.79e-05', 'epoch': '0.3893'} | |
| {'loss': '0.3542', 'grad_norm': '5.098', 'learning_rate': '1.789e-05', 'epoch': '0.3897'} | |
| {'loss': '0.2529', 'grad_norm': '6.404', 'learning_rate': '1.789e-05', 'epoch': '0.3902'} | |
| {'loss': '0.2449', 'grad_norm': '0.8693', 'learning_rate': '1.788e-05', 'epoch': '0.3907'} | |
| {'loss': '0.3122', 'grad_norm': '4.437', 'learning_rate': '1.788e-05', 'epoch': '0.3912'} | |
| {'loss': '0.2649', 'grad_norm': '8.011', 'learning_rate': '1.787e-05', 'epoch': '0.3916'} | |
| {'loss': '0.2647', 'grad_norm': '4.856', 'learning_rate': '1.787e-05', 'epoch': '0.3921'} | |
| {'loss': '0.2707', 'grad_norm': '5.593', 'learning_rate': '1.786e-05', 'epoch': '0.3926'} | |
| {'loss': '0.2777', 'grad_norm': '10.82', 'learning_rate': '1.785e-05', 'epoch': '0.3931'} | |
| {'loss': '0.2435', 'grad_norm': '4.682', 'learning_rate': '1.785e-05', 'epoch': '0.3935'} | |
| {'loss': '0.2514', 'grad_norm': '3.008', 'learning_rate': '1.784e-05', 'epoch': '0.394'} | |
| {'loss': '0.2615', 'grad_norm': '9.21', 'learning_rate': '1.784e-05', 'epoch': '0.3945'} | |
| {'loss': '0.2224', 'grad_norm': '1.998', 'learning_rate': '1.783e-05', 'epoch': '0.395'} | |
| {'loss': '0.2407', 'grad_norm': '2.784', 'learning_rate': '1.783e-05', 'epoch': '0.3955'} | |
| {'loss': '0.2686', 'grad_norm': '4.4', 'learning_rate': '1.782e-05', 'epoch': '0.3959'} | |
| {'loss': '0.2341', 'grad_norm': '3.461', 'learning_rate': '1.782e-05', 'epoch': '0.3964'} | |
| {'loss': '0.2385', 'grad_norm': '5.527', 'learning_rate': '1.781e-05', 'epoch': '0.3969'} | |
| {'loss': '0.264', 'grad_norm': '4.344', 'learning_rate': '1.781e-05', 'epoch': '0.3974'} | |
| {'loss': '0.2184', 'grad_norm': '0.8479', 'learning_rate': '1.78e-05', 'epoch': '0.3978'} | |
| {'loss': '0.2557', 'grad_norm': '3.346', 'learning_rate': '1.78e-05', 'epoch': '0.3983'} | |
| {'loss': '0.2482', 'grad_norm': '5.354', 'learning_rate': '1.779e-05', 'epoch': '0.3988'} | |
| {'loss': '0.249', 'grad_norm': '0.8029', 'learning_rate': '1.779e-05', 'epoch': '0.3993'} | |
| {'loss': '0.2562', 'grad_norm': '7.284', 'learning_rate': '1.778e-05', 'epoch': '0.3997'} | |
| {'loss': '0.2366', 'grad_norm': '1.893', 'learning_rate': '1.778e-05', 'epoch': '0.4002'} | |
| {'eval_ms_marco_loss': '0.1185', 'eval_val-ms-marco-768_cosine_accuracy': '0.994', 'eval_val-ms-marco-512_cosine_accuracy': '0.9937', 'eval_val-ms-marco-256_cosine_accuracy': '0.9937', 'eval_val-ms-marco-128_cosine_accuracy': '0.993', 'eval_val-ms-marco-64_cosine_accuracy': '0.9917', 'eval_sequential_score': '0.994', 'eval_ms_marco_runtime': '33.83', 'eval_ms_marco_samples_per_second': '295.6', 'eval_ms_marco_steps_per_second': '9.251', 'epoch': '0.4002'} | |
| {'loss': '0.2694', 'grad_norm': '1.982', 'learning_rate': '1.777e-05', 'epoch': '0.4007'} | |
| {'loss': '0.2421', 'grad_norm': '7.531', 'learning_rate': '1.776e-05', 'epoch': '0.4012'} | |
| {'loss': '0.238', 'grad_norm': '4.446', 'learning_rate': '1.776e-05', 'epoch': '0.4016'} | |
| {'loss': '0.2519', 'grad_norm': '7.186', 'learning_rate': '1.775e-05', 'epoch': '0.4021'} | |
| {'loss': '0.2574', 'grad_norm': '2.302', 'learning_rate': '1.775e-05', 'epoch': '0.4026'} | |
| {'loss': '0.2465', 'grad_norm': '4.322', 'learning_rate': '1.774e-05', 'epoch': '0.4031'} | |
| {'loss': '0.2524', 'grad_norm': '4.529', 'learning_rate': '1.774e-05', 'epoch': '0.4036'} | |
| {'loss': '0.2367', 'grad_norm': '1.126', 'learning_rate': '1.773e-05', 'epoch': '0.404'} | |
| {'loss': '0.2422', 'grad_norm': '5.136', 'learning_rate': '1.773e-05', 'epoch': '0.4045'} | |
| {'loss': '0.2639', 'grad_norm': '4.564', 'learning_rate': '1.772e-05', 'epoch': '0.405'} | |
| {'loss': '0.2864', 'grad_norm': '4.405', 'learning_rate': '1.772e-05', 'epoch': '0.4055'} | |
| {'loss': '0.2798', 'grad_norm': '2.13', 'learning_rate': '1.771e-05', 'epoch': '0.4059'} | |
| {'loss': '0.2481', 'grad_norm': '3.378', 'learning_rate': '1.771e-05', 'epoch': '0.4064'} | |
| {'loss': '0.2512', 'grad_norm': '2.355', 'learning_rate': '1.77e-05', 'epoch': '0.4069'} | |
| {'loss': '0.2103', 'grad_norm': '1.417', 'learning_rate': '1.77e-05', 'epoch': '0.4074'} | |
| {'loss': '0.253', 'grad_norm': '3.957', 'learning_rate': '1.769e-05', 'epoch': '0.4078'} | |
| {'loss': '0.2727', 'grad_norm': '1.094', 'learning_rate': '1.769e-05', 'epoch': '0.4083'} | |
| {'loss': '0.2475', 'grad_norm': '6.958', 'learning_rate': '1.768e-05', 'epoch': '0.4088'} | |
| {'loss': '0.2472', 'grad_norm': '2.504', 'learning_rate': '1.767e-05', 'epoch': '0.4093'} | |
| {'loss': '0.2569', 'grad_norm': '2.719', 'learning_rate': '1.767e-05', 'epoch': '0.4097'} | |
| {'loss': '0.2694', 'grad_norm': '6.863', 'learning_rate': '1.766e-05', 'epoch': '0.4102'} | |
| {'loss': '0.3635', 'grad_norm': '2.155', 'learning_rate': '1.766e-05', 'epoch': '0.4107'} | |
| {'loss': '0.2573', 'grad_norm': '7.952', 'learning_rate': '1.765e-05', 'epoch': '0.4112'} | |
| {'loss': '0.2415', 'grad_norm': '5.846', 'learning_rate': '1.765e-05', 'epoch': '0.4117'} | |
| {'loss': '0.2315', 'grad_norm': '6.832', 'learning_rate': '1.764e-05', 'epoch': '0.4121'} | |
| {'loss': '0.2156', 'grad_norm': '5.436', 'learning_rate': '1.764e-05', 'epoch': '0.4126'} | |
| {'loss': '0.2389', 'grad_norm': '1.559', 'learning_rate': '1.763e-05', 'epoch': '0.4131'} | |
| {'loss': '0.2595', 'grad_norm': '1.675', 'learning_rate': '1.763e-05', 'epoch': '0.4136'} | |
| {'loss': '0.261', 'grad_norm': '5.752', 'learning_rate': '1.762e-05', 'epoch': '0.414'} | |
| {'loss': '0.2428', 'grad_norm': '7.145', 'learning_rate': '1.762e-05', 'epoch': '0.4145'} | |
| {'loss': '0.2534', 'grad_norm': '5.752', 'learning_rate': '1.761e-05', 'epoch': '0.415'} | |
| {'loss': '0.2343', 'grad_norm': '4.594', 'learning_rate': '1.761e-05', 'epoch': '0.4155'} | |
| {'loss': '0.2584', 'grad_norm': '4.684', 'learning_rate': '1.76e-05', 'epoch': '0.4159'} | |
| {'loss': '0.3749', 'grad_norm': '1.694', 'learning_rate': '1.76e-05', 'epoch': '0.4164'} | |
| {'loss': '0.2296', 'grad_norm': '5.171', 'learning_rate': '1.759e-05', 'epoch': '0.4169'} | |
| {'loss': '0.2429', 'grad_norm': '3.335', 'learning_rate': '1.758e-05', 'epoch': '0.4174'} | |
| {'loss': '0.2614', 'grad_norm': '5.071', 'learning_rate': '1.758e-05', 'epoch': '0.4178'} | |
| {'loss': '0.2283', 'grad_norm': '7.767', 'learning_rate': '1.757e-05', 'epoch': '0.4183'} | |
| {'loss': '0.225', 'grad_norm': '5.195', 'learning_rate': '1.757e-05', 'epoch': '0.4188'} | |
| {'loss': '0.2335', 'grad_norm': '3.482', 'learning_rate': '1.756e-05', 'epoch': '0.4193'} | |
| {'loss': '0.2388', 'grad_norm': '3.279', 'learning_rate': '1.756e-05', 'epoch': '0.4198'} | |
| {'loss': '0.2375', 'grad_norm': '6.519', 'learning_rate': '1.755e-05', 'epoch': '0.4202'} | |
| {'loss': '0.2628', 'grad_norm': '4.571', 'learning_rate': '1.755e-05', 'epoch': '0.4207'} | |
| {'loss': '0.2398', 'grad_norm': '5.08', 'learning_rate': '1.754e-05', 'epoch': '0.4212'} | |
| {'loss': '0.263', 'grad_norm': '1.835', 'learning_rate': '1.754e-05', 'epoch': '0.4217'} | |
| {'loss': '0.247', 'grad_norm': '0.8368', 'learning_rate': '1.753e-05', 'epoch': '0.4221'} | |
| {'loss': '0.2435', 'grad_norm': '5.138', 'learning_rate': '1.753e-05', 'epoch': '0.4226'} | |
| {'loss': '0.2404', 'grad_norm': '4.62', 'learning_rate': '1.752e-05', 'epoch': '0.4231'} | |
| {'loss': '0.233', 'grad_norm': '4.377', 'learning_rate': '1.752e-05', 'epoch': '0.4236'} | |
| {'loss': '0.2278', 'grad_norm': '2.016', 'learning_rate': '1.751e-05', 'epoch': '0.424'} | |
| {'loss': '0.385', 'grad_norm': '6.321', 'learning_rate': '1.751e-05', 'epoch': '0.4245'} | |
| {'loss': '0.2492', 'grad_norm': '5.968', 'learning_rate': '1.75e-05', 'epoch': '0.425'} | |
| {'loss': '0.3565', 'grad_norm': '2.481', 'learning_rate': '1.749e-05', 'epoch': '0.4255'} | |
| {'loss': '0.2316', 'grad_norm': '5.53', 'learning_rate': '1.749e-05', 'epoch': '0.4259'} | |
| {'loss': '0.2424', 'grad_norm': '3.013', 'learning_rate': '1.748e-05', 'epoch': '0.4264'} | |
| {'loss': '0.3504', 'grad_norm': '7.567', 'learning_rate': '1.748e-05', 'epoch': '0.4269'} | |
| {'loss': '0.271', 'grad_norm': '0.6651', 'learning_rate': '1.747e-05', 'epoch': '0.4274'} | |
| {'loss': '0.2555', 'grad_norm': '2.725', 'learning_rate': '1.747e-05', 'epoch': '0.4279'} | |
| {'loss': '0.2495', 'grad_norm': '2.092', 'learning_rate': '1.746e-05', 'epoch': '0.4283'} | |
| {'loss': '0.2422', 'grad_norm': '4.624', 'learning_rate': '1.746e-05', 'epoch': '0.4288'} | |
| {'eval_ms_marco_loss': '0.1148', 'eval_val-ms-marco-768_cosine_accuracy': '0.9923', 'eval_val-ms-marco-512_cosine_accuracy': '0.9917', 'eval_val-ms-marco-256_cosine_accuracy': '0.9923', 'eval_val-ms-marco-128_cosine_accuracy': '0.992', 'eval_val-ms-marco-64_cosine_accuracy': '0.992', 'eval_sequential_score': '0.9923', 'eval_ms_marco_runtime': '34.03', 'eval_ms_marco_samples_per_second': '293.9', 'eval_ms_marco_steps_per_second': '9.198', 'epoch': '0.4288'} | |
| {'loss': '0.3331', 'grad_norm': '3.338', 'learning_rate': '1.745e-05', 'epoch': '0.4293'} | |
| {'loss': '0.3184', 'grad_norm': '2.466', 'learning_rate': '1.745e-05', 'epoch': '0.4298'} | |
| {'loss': '0.2598', 'grad_norm': '4.256', 'learning_rate': '1.744e-05', 'epoch': '0.4302'} | |
| {'loss': '0.2252', 'grad_norm': '1.036', 'learning_rate': '1.744e-05', 'epoch': '0.4307'} | |
| {'loss': '0.2241', 'grad_norm': '1.471', 'learning_rate': '1.743e-05', 'epoch': '0.4312'} | |
| {'loss': '0.2138', 'grad_norm': '1.679', 'learning_rate': '1.743e-05', 'epoch': '0.4317'} | |
| {'loss': '0.3504', 'grad_norm': '6.035', 'learning_rate': '1.742e-05', 'epoch': '0.4321'} | |
| {'loss': '0.252', 'grad_norm': '6.638', 'learning_rate': '1.742e-05', 'epoch': '0.4326'} | |
| {'loss': '0.2118', 'grad_norm': '1.888', 'learning_rate': '1.741e-05', 'epoch': '0.4331'} | |
| {'loss': '0.264', 'grad_norm': '4.365', 'learning_rate': '1.74e-05', 'epoch': '0.4336'} | |
| {'loss': '0.2125', 'grad_norm': '7.964', 'learning_rate': '1.74e-05', 'epoch': '0.434'} | |
| {'loss': '0.2291', 'grad_norm': '4.259', 'learning_rate': '1.739e-05', 'epoch': '0.4345'} | |
| {'loss': '0.2678', 'grad_norm': '4.503', 'learning_rate': '1.739e-05', 'epoch': '0.435'} | |
| {'loss': '0.2467', 'grad_norm': '4.312', 'learning_rate': '1.738e-05', 'epoch': '0.4355'} | |
| {'loss': '0.2264', 'grad_norm': '4.148', 'learning_rate': '1.738e-05', 'epoch': '0.436'} | |
| {'loss': '0.2393', 'grad_norm': '2.267', 'learning_rate': '1.737e-05', 'epoch': '0.4364'} | |
| {'loss': '0.2525', 'grad_norm': '3.144', 'learning_rate': '1.737e-05', 'epoch': '0.4369'} | |
| {'loss': '0.3562', 'grad_norm': '5.399', 'learning_rate': '1.736e-05', 'epoch': '0.4374'} | |
| {'loss': '0.2441', 'grad_norm': '2.043', 'learning_rate': '1.736e-05', 'epoch': '0.4379'} | |
| {'loss': '0.2402', 'grad_norm': '6.708', 'learning_rate': '1.735e-05', 'epoch': '0.4383'} | |
| {'loss': '0.2526', 'grad_norm': '1.829', 'learning_rate': '1.735e-05', 'epoch': '0.4388'} | |
| {'loss': '0.234', 'grad_norm': '3.411', 'learning_rate': '1.734e-05', 'epoch': '0.4393'} | |
| {'loss': '0.2211', 'grad_norm': '2.088', 'learning_rate': '1.734e-05', 'epoch': '0.4398'} | |
| {'loss': '0.2358', 'grad_norm': '3.707', 'learning_rate': '1.733e-05', 'epoch': '0.4402'} | |
| {'loss': '0.3457', 'grad_norm': '4.256', 'learning_rate': '1.733e-05', 'epoch': '0.4407'} | |
| {'loss': '0.2086', 'grad_norm': '5.153', 'learning_rate': '1.732e-05', 'epoch': '0.4412'} | |
| {'loss': '0.2223', 'grad_norm': '3.85', 'learning_rate': '1.731e-05', 'epoch': '0.4417'} | |
| {'loss': '0.2674', 'grad_norm': '3.234', 'learning_rate': '1.731e-05', 'epoch': '0.4421'} | |
| {'loss': '0.2464', 'grad_norm': '4.04', 'learning_rate': '1.73e-05', 'epoch': '0.4426'} | |
| {'loss': '0.2419', 'grad_norm': '3.413', 'learning_rate': '1.73e-05', 'epoch': '0.4431'} | |
| {'loss': '0.2236', 'grad_norm': '4.989', 'learning_rate': '1.729e-05', 'epoch': '0.4436'} | |
| {'loss': '0.2237', 'grad_norm': '4.454', 'learning_rate': '1.729e-05', 'epoch': '0.4441'} | |
| {'loss': '0.2108', 'grad_norm': '2.204', 'learning_rate': '1.728e-05', 'epoch': '0.4445'} | |
| {'loss': '0.2351', 'grad_norm': '4.725', 'learning_rate': '1.728e-05', 'epoch': '0.445'} | |
| {'loss': '0.232', 'grad_norm': '1.294', 'learning_rate': '1.727e-05', 'epoch': '0.4455'} | |
| {'loss': '0.2312', 'grad_norm': '2.452', 'learning_rate': '1.727e-05', 'epoch': '0.446'} | |
| {'loss': '0.2416', 'grad_norm': '4.873', 'learning_rate': '1.726e-05', 'epoch': '0.4464'} | |
| {'loss': '0.2346', 'grad_norm': '4.8', 'learning_rate': '1.726e-05', 'epoch': '0.4469'} | |
| {'loss': '0.2496', 'grad_norm': '4.746', 'learning_rate': '1.725e-05', 'epoch': '0.4474'} | |
| {'loss': '0.2257', 'grad_norm': '5.524', 'learning_rate': '1.725e-05', 'epoch': '0.4479'} | |
| {'loss': '0.2439', 'grad_norm': '7.197', 'learning_rate': '1.724e-05', 'epoch': '0.4483'} | |
| {'loss': '0.2229', 'grad_norm': '2.793', 'learning_rate': '1.724e-05', 'epoch': '0.4488'} | |
| {'loss': '0.2507', 'grad_norm': '3.006', 'learning_rate': '1.723e-05', 'epoch': '0.4493'} | |
| {'loss': '0.2388', 'grad_norm': '1.527', 'learning_rate': '1.722e-05', 'epoch': '0.4498'} | |
| {'loss': '0.2181', 'grad_norm': '3.683', 'learning_rate': '1.722e-05', 'epoch': '0.4502'} | |
| {'loss': '0.3868', 'grad_norm': '3.417', 'learning_rate': '1.721e-05', 'epoch': '0.4507'} | |
| {'loss': '0.2278', 'grad_norm': '3.446', 'learning_rate': '1.721e-05', 'epoch': '0.4512'} | |
| {'loss': '0.2346', 'grad_norm': '0.7926', 'learning_rate': '1.72e-05', 'epoch': '0.4517'} | |
| {'loss': '0.2316', 'grad_norm': '4.328', 'learning_rate': '1.72e-05', 'epoch': '0.4522'} | |
| {'loss': '0.2155', 'grad_norm': '3.071', 'learning_rate': '1.719e-05', 'epoch': '0.4526'} | |
| {'loss': '0.2451', 'grad_norm': '3.925', 'learning_rate': '1.719e-05', 'epoch': '0.4531'} | |
| {'loss': '0.2353', 'grad_norm': '2.603', 'learning_rate': '1.718e-05', 'epoch': '0.4536'} | |
| {'loss': '0.2318', 'grad_norm': '2.527', 'learning_rate': '1.718e-05', 'epoch': '0.4541'} | |
| {'loss': '0.2466', 'grad_norm': '4.07', 'learning_rate': '1.717e-05', 'epoch': '0.4545'} | |
| {'loss': '0.2399', 'grad_norm': '4.137', 'learning_rate': '1.717e-05', 'epoch': '0.455'} | |
| {'loss': '0.2452', 'grad_norm': '3.326', 'learning_rate': '1.716e-05', 'epoch': '0.4555'} | |
| {'loss': '0.243', 'grad_norm': '2.952', 'learning_rate': '1.716e-05', 'epoch': '0.456'} | |
| {'loss': '0.1985', 'grad_norm': '2.033', 'learning_rate': '1.715e-05', 'epoch': '0.4564'} | |
| {'loss': '0.2244', 'grad_norm': '1.82', 'learning_rate': '1.715e-05', 'epoch': '0.4569'} | |
| {'loss': '0.2131', 'grad_norm': '5.32', 'learning_rate': '1.714e-05', 'epoch': '0.4574'} | |
| {'eval_ms_marco_loss': '0.09898', 'eval_val-ms-marco-768_cosine_accuracy': '0.994', 'eval_val-ms-marco-512_cosine_accuracy': '0.994', 'eval_val-ms-marco-256_cosine_accuracy': '0.9943', 'eval_val-ms-marco-128_cosine_accuracy': '0.993', 'eval_val-ms-marco-64_cosine_accuracy': '0.9933', 'eval_sequential_score': '0.994', 'eval_ms_marco_runtime': '34.01', 'eval_ms_marco_samples_per_second': '294', 'eval_ms_marco_steps_per_second': '9.203', 'epoch': '0.4574'} | |
| {'loss': '0.2489', 'grad_norm': '5.35', 'learning_rate': '1.713e-05', 'epoch': '0.4579'} | |
| {'loss': '0.2114', 'grad_norm': '2.648', 'learning_rate': '1.713e-05', 'epoch': '0.4583'} | |
| {'loss': '0.2338', 'grad_norm': '5.931', 'learning_rate': '1.712e-05', 'epoch': '0.4588'} | |
| {'loss': '0.2179', 'grad_norm': '6.422', 'learning_rate': '1.712e-05', 'epoch': '0.4593'} | |
| {'loss': '0.2288', 'grad_norm': '4.719', 'learning_rate': '1.711e-05', 'epoch': '0.4598'} | |
| {'loss': '0.2419', 'grad_norm': '0.9469', 'learning_rate': '1.711e-05', 'epoch': '0.4603'} | |
| {'loss': '0.2187', 'grad_norm': '6.844', 'learning_rate': '1.71e-05', 'epoch': '0.4607'} | |
| {'loss': '0.2477', 'grad_norm': '8.949', 'learning_rate': '1.71e-05', 'epoch': '0.4612'} | |
| {'loss': '0.224', 'grad_norm': '1.101', 'learning_rate': '1.709e-05', 'epoch': '0.4617'} | |
| {'loss': '0.2148', 'grad_norm': '2.776', 'learning_rate': '1.709e-05', 'epoch': '0.4622'} | |
| {'loss': '0.196', 'grad_norm': '2.316', 'learning_rate': '1.708e-05', 'epoch': '0.4626'} | |
| {'loss': '0.2436', 'grad_norm': '2.828', 'learning_rate': '1.708e-05', 'epoch': '0.4631'} | |
| {'loss': '0.2127', 'grad_norm': '0.8157', 'learning_rate': '1.707e-05', 'epoch': '0.4636'} | |
| {'loss': '0.2189', 'grad_norm': '2.974', 'learning_rate': '1.707e-05', 'epoch': '0.4641'} | |
| {'loss': '0.218', 'grad_norm': '5.09', 'learning_rate': '1.706e-05', 'epoch': '0.4645'} | |
| {'loss': '0.2407', 'grad_norm': '2.595', 'learning_rate': '1.706e-05', 'epoch': '0.465'} | |
| {'loss': '0.2375', 'grad_norm': '4.587', 'learning_rate': '1.705e-05', 'epoch': '0.4655'} | |
| {'loss': '0.2129', 'grad_norm': '1.622', 'learning_rate': '1.704e-05', 'epoch': '0.466'} | |
| {'loss': '0.2461', 'grad_norm': '5.058', 'learning_rate': '1.704e-05', 'epoch': '0.4664'} | |
| {'loss': '0.3458', 'grad_norm': '5.596', 'learning_rate': '1.703e-05', 'epoch': '0.4669'} | |
| {'loss': '0.2099', 'grad_norm': '3.652', 'learning_rate': '1.703e-05', 'epoch': '0.4674'} | |
| {'loss': '0.2254', 'grad_norm': '2.493', 'learning_rate': '1.702e-05', 'epoch': '0.4679'} | |
| {'loss': '0.3291', 'grad_norm': '3.23', 'learning_rate': '1.702e-05', 'epoch': '0.4684'} | |
| {'loss': '0.2321', 'grad_norm': '1.434', 'learning_rate': '1.701e-05', 'epoch': '0.4688'} | |
| {'loss': '0.209', 'grad_norm': '4.505', 'learning_rate': '1.701e-05', 'epoch': '0.4693'} | |
| {'loss': '0.2259', 'grad_norm': '4.86', 'learning_rate': '1.7e-05', 'epoch': '0.4698'} | |
| {'loss': '0.2303', 'grad_norm': '6.516', 'learning_rate': '1.7e-05', 'epoch': '0.4703'} | |
| {'loss': '0.2408', 'grad_norm': '1.964', 'learning_rate': '1.699e-05', 'epoch': '0.4707'} | |
| {'loss': '0.2328', 'grad_norm': '2.163', 'learning_rate': '1.699e-05', 'epoch': '0.4712'} | |
| {'loss': '0.2182', 'grad_norm': '5.062', 'learning_rate': '1.698e-05', 'epoch': '0.4717'} | |
| {'loss': '0.2094', 'grad_norm': '4.117', 'learning_rate': '1.698e-05', 'epoch': '0.4722'} | |
| {'loss': '0.2274', 'grad_norm': '3.318', 'learning_rate': '1.697e-05', 'epoch': '0.4726'} | |
| {'loss': '0.2158', 'grad_norm': '8.467', 'learning_rate': '1.697e-05', 'epoch': '0.4731'} | |
| {'loss': '0.2263', 'grad_norm': '1.225', 'learning_rate': '1.696e-05', 'epoch': '0.4736'} | |
| {'loss': '0.2194', 'grad_norm': '6.165', 'learning_rate': '1.695e-05', 'epoch': '0.4741'} | |
| {'loss': '0.2222', 'grad_norm': '3.537', 'learning_rate': '1.695e-05', 'epoch': '0.4745'} | |
| {'loss': '0.2291', 'grad_norm': '1.999', 'learning_rate': '1.694e-05', 'epoch': '0.475'} | |
| {'loss': '0.2155', 'grad_norm': '0.7095', 'learning_rate': '1.694e-05', 'epoch': '0.4755'} | |
| {'loss': '0.2202', 'grad_norm': '4.27', 'learning_rate': '1.693e-05', 'epoch': '0.476'} | |
| {'loss': '0.194', 'grad_norm': '3.871', 'learning_rate': '1.693e-05', 'epoch': '0.4765'} | |
| {'loss': '0.2146', 'grad_norm': '4.638', 'learning_rate': '1.692e-05', 'epoch': '0.4769'} | |
| {'loss': '0.2381', 'grad_norm': '7.583', 'learning_rate': '1.692e-05', 'epoch': '0.4774'} | |
| {'loss': '0.2263', 'grad_norm': '2.108', 'learning_rate': '1.691e-05', 'epoch': '0.4779'} | |
| {'loss': '0.2051', 'grad_norm': '7.175', 'learning_rate': '1.691e-05', 'epoch': '0.4784'} | |
| {'loss': '0.2117', 'grad_norm': '4.465', 'learning_rate': '1.69e-05', 'epoch': '0.4788'} | |
| {'loss': '0.2053', 'grad_norm': '4.587', 'learning_rate': '1.69e-05', 'epoch': '0.4793'} | |
| {'loss': '0.2237', 'grad_norm': '3.999', 'learning_rate': '1.689e-05', 'epoch': '0.4798'} | |
| {'loss': '0.211', 'grad_norm': '5.115', 'learning_rate': '1.689e-05', 'epoch': '0.4803'} | |
| {'loss': '0.2239', 'grad_norm': '4.755', 'learning_rate': '1.688e-05', 'epoch': '0.4807'} | |
| {'loss': '0.2306', 'grad_norm': '4.294', 'learning_rate': '1.688e-05', 'epoch': '0.4812'} | |
| {'loss': '0.2309', 'grad_norm': '1.766', 'learning_rate': '1.687e-05', 'epoch': '0.4817'} | |
| {'loss': '0.3253', 'grad_norm': '3.031', 'learning_rate': '1.686e-05', 'epoch': '0.4822'} | |
| {'loss': '0.2107', 'grad_norm': '3.534', 'learning_rate': '1.686e-05', 'epoch': '0.4826'} | |
| {'loss': '0.2253', 'grad_norm': '9.85', 'learning_rate': '1.685e-05', 'epoch': '0.4831'} | |
| {'loss': '0.2141', 'grad_norm': '2.004', 'learning_rate': '1.685e-05', 'epoch': '0.4836'} | |
| {'loss': '0.2083', 'grad_norm': '9.151', 'learning_rate': '1.684e-05', 'epoch': '0.4841'} | |
| {'loss': '0.3294', 'grad_norm': '1.634', 'learning_rate': '1.684e-05', 'epoch': '0.4845'} | |
| {'loss': '0.1987', 'grad_norm': '3.633', 'learning_rate': '1.683e-05', 'epoch': '0.485'} | |
| {'loss': '0.1953', 'grad_norm': '6.52', 'learning_rate': '1.683e-05', 'epoch': '0.4855'} | |
| {'loss': '0.2447', 'grad_norm': '9.139', 'learning_rate': '1.682e-05', 'epoch': '0.486'} | |
| {'eval_ms_marco_loss': '0.09406', 'eval_val-ms-marco-768_cosine_accuracy': '0.9937', 'eval_val-ms-marco-512_cosine_accuracy': '0.9947', 'eval_val-ms-marco-256_cosine_accuracy': '0.9953', 'eval_val-ms-marco-128_cosine_accuracy': '0.994', 'eval_val-ms-marco-64_cosine_accuracy': '0.9923', 'eval_sequential_score': '0.9937', 'eval_ms_marco_runtime': '33.7', 'eval_ms_marco_samples_per_second': '296.7', 'eval_ms_marco_steps_per_second': '9.287', 'epoch': '0.486'} | |
| {'loss': '0.2503', 'grad_norm': '0.7233', 'learning_rate': '1.682e-05', 'epoch': '0.4865'} | |
| {'loss': '0.2058', 'grad_norm': '0.8996', 'learning_rate': '1.681e-05', 'epoch': '0.4869'} | |
| {'loss': '0.4621', 'grad_norm': '2.427', 'learning_rate': '1.681e-05', 'epoch': '0.4874'} | |
| {'loss': '0.1958', 'grad_norm': '1.912', 'learning_rate': '1.68e-05', 'epoch': '0.4879'} | |
| {'loss': '0.2248', 'grad_norm': '3.216', 'learning_rate': '1.68e-05', 'epoch': '0.4884'} | |
| {'loss': '0.25', 'grad_norm': '4.349', 'learning_rate': '1.679e-05', 'epoch': '0.4888'} | |
| {'loss': '0.2073', 'grad_norm': '3.75', 'learning_rate': '1.679e-05', 'epoch': '0.4893'} | |
| {'loss': '0.3281', 'grad_norm': '2.999', 'learning_rate': '1.678e-05', 'epoch': '0.4898'} | |
| {'loss': '0.2154', 'grad_norm': '2.019', 'learning_rate': '1.677e-05', 'epoch': '0.4903'} | |
| {'loss': '0.2031', 'grad_norm': '2.763', 'learning_rate': '1.677e-05', 'epoch': '0.4907'} | |
| {'loss': '0.2277', 'grad_norm': '0.6343', 'learning_rate': '1.676e-05', 'epoch': '0.4912'} | |
| {'loss': '0.2226', 'grad_norm': '4.826', 'learning_rate': '1.676e-05', 'epoch': '0.4917'} | |
| {'loss': '0.2169', 'grad_norm': '6.05', 'learning_rate': '1.675e-05', 'epoch': '0.4922'} | |
| {'loss': '0.3371', 'grad_norm': '3.143', 'learning_rate': '1.675e-05', 'epoch': '0.4926'} | |
| {'loss': '0.205', 'grad_norm': '5.382', 'learning_rate': '1.674e-05', 'epoch': '0.4931'} | |
| {'loss': '0.2148', 'grad_norm': '9.79', 'learning_rate': '1.674e-05', 'epoch': '0.4936'} | |
| {'loss': '0.2258', 'grad_norm': '2.555', 'learning_rate': '1.673e-05', 'epoch': '0.4941'} | |
| {'loss': '0.2302', 'grad_norm': '1.825', 'learning_rate': '1.673e-05', 'epoch': '0.4946'} | |
| {'loss': '0.3564', 'grad_norm': '1.182', 'learning_rate': '1.672e-05', 'epoch': '0.495'} | |
| {'loss': '0.231', 'grad_norm': '3.563', 'learning_rate': '1.672e-05', 'epoch': '0.4955'} | |
| {'loss': '0.2328', 'grad_norm': '2.193', 'learning_rate': '1.671e-05', 'epoch': '0.496'} | |
| {'loss': '0.2428', 'grad_norm': '8.15', 'learning_rate': '1.671e-05', 'epoch': '0.4965'} | |
| {'loss': '0.2455', 'grad_norm': '10.21', 'learning_rate': '1.67e-05', 'epoch': '0.4969'} | |
| {'loss': '0.1976', 'grad_norm': '0.7771', 'learning_rate': '1.67e-05', 'epoch': '0.4974'} | |
| {'loss': '0.2353', 'grad_norm': '1.677', 'learning_rate': '1.669e-05', 'epoch': '0.4979'} | |
| {'loss': '0.2514', 'grad_norm': '2.167', 'learning_rate': '1.668e-05', 'epoch': '0.4984'} | |
| {'loss': '0.2343', 'grad_norm': '5.626', 'learning_rate': '1.668e-05', 'epoch': '0.4988'} | |
| {'loss': '0.2179', 'grad_norm': '4.204', 'learning_rate': '1.667e-05', 'epoch': '0.4993'} | |
| {'loss': '0.2041', 'grad_norm': '4.719', 'learning_rate': '1.667e-05', 'epoch': '0.4998'} | |
| {'loss': '0.2085', 'grad_norm': '5.228', 'learning_rate': '1.666e-05', 'epoch': '0.5003'} | |
| {'loss': '0.3893', 'grad_norm': '1.67', 'learning_rate': '1.666e-05', 'epoch': '0.5007'} | |
| {'loss': '0.2157', 'grad_norm': '4.294', 'learning_rate': '1.665e-05', 'epoch': '0.5012'} | |
| {'loss': '0.2073', 'grad_norm': '1.774', 'learning_rate': '1.665e-05', 'epoch': '0.5017'} | |
| {'loss': '0.2289', 'grad_norm': '2.547', 'learning_rate': '1.664e-05', 'epoch': '0.5022'} | |
| {'loss': '0.2106', 'grad_norm': '8.165', 'learning_rate': '1.664e-05', 'epoch': '0.5027'} | |
| {'loss': '0.3046', 'grad_norm': '0.8766', 'learning_rate': '1.663e-05', 'epoch': '0.5031'} | |
| {'loss': '0.2299', 'grad_norm': '4.653', 'learning_rate': '1.663e-05', 'epoch': '0.5036'} | |
| {'loss': '0.2253', 'grad_norm': '9.033', 'learning_rate': '1.662e-05', 'epoch': '0.5041'} | |
| {'loss': '0.2314', 'grad_norm': '3.888', 'learning_rate': '1.662e-05', 'epoch': '0.5046'} | |
| {'loss': '0.2089', 'grad_norm': '1.719', 'learning_rate': '1.661e-05', 'epoch': '0.505'} | |
| {'loss': '0.2125', 'grad_norm': '4.272', 'learning_rate': '1.661e-05', 'epoch': '0.5055'} | |
| {'loss': '0.1991', 'grad_norm': '4.386', 'learning_rate': '1.66e-05', 'epoch': '0.506'} | |
| {'loss': '0.3041', 'grad_norm': '1.472', 'learning_rate': '1.659e-05', 'epoch': '0.5065'} | |
| {'loss': '0.2217', 'grad_norm': '1.366', 'learning_rate': '1.659e-05', 'epoch': '0.5069'} | |
| {'loss': '0.2172', 'grad_norm': '2.671', 'learning_rate': '1.658e-05', 'epoch': '0.5074'} | |
| {'loss': '0.1949', 'grad_norm': '5.971', 'learning_rate': '1.658e-05', 'epoch': '0.5079'} | |
| {'loss': '0.2426', 'grad_norm': '3.671', 'learning_rate': '1.657e-05', 'epoch': '0.5084'} | |
| {'loss': '0.3077', 'grad_norm': '4.061', 'learning_rate': '1.657e-05', 'epoch': '0.5088'} | |
| {'loss': '0.3125', 'grad_norm': '0.8993', 'learning_rate': '1.656e-05', 'epoch': '0.5093'} | |
| {'loss': '0.2061', 'grad_norm': '2.278', 'learning_rate': '1.656e-05', 'epoch': '0.5098'} | |
| {'loss': '0.3229', 'grad_norm': '3.048', 'learning_rate': '1.655e-05', 'epoch': '0.5103'} | |
| {'loss': '0.2501', 'grad_norm': '2.744', 'learning_rate': '1.655e-05', 'epoch': '0.5108'} | |
| {'loss': '0.2157', 'grad_norm': '6.645', 'learning_rate': '1.654e-05', 'epoch': '0.5112'} | |
| {'loss': '0.2212', 'grad_norm': '7.538', 'learning_rate': '1.654e-05', 'epoch': '0.5117'} | |
| {'loss': '0.1982', 'grad_norm': '3.431', 'learning_rate': '1.653e-05', 'epoch': '0.5122'} | |
| {'loss': '0.2318', 'grad_norm': '6.887', 'learning_rate': '1.653e-05', 'epoch': '0.5127'} | |
| {'loss': '0.2046', 'grad_norm': '2', 'learning_rate': '1.652e-05', 'epoch': '0.5131'} | |
| {'loss': '0.2305', 'grad_norm': '7.858', 'learning_rate': '1.652e-05', 'epoch': '0.5136'} | |
| {'loss': '0.1938', 'grad_norm': '2.795', 'learning_rate': '1.651e-05', 'epoch': '0.5141'} | |
| {'loss': '0.1837', 'grad_norm': '1.657', 'learning_rate': '1.65e-05', 'epoch': '0.5146'} | |
| {'eval_ms_marco_loss': '0.08639', 'eval_val-ms-marco-768_cosine_accuracy': '0.9947', 'eval_val-ms-marco-512_cosine_accuracy': '0.995', 'eval_val-ms-marco-256_cosine_accuracy': '0.9957', 'eval_val-ms-marco-128_cosine_accuracy': '0.9953', 'eval_val-ms-marco-64_cosine_accuracy': '0.9943', 'eval_sequential_score': '0.9947', 'eval_ms_marco_runtime': '33.99', 'eval_ms_marco_samples_per_second': '294.2', 'eval_ms_marco_steps_per_second': '9.209', 'epoch': '0.5146'} | |
| {'loss': '0.1876', 'grad_norm': '1.68', 'learning_rate': '1.65e-05', 'epoch': '0.515'} | |
| {'loss': '0.2049', 'grad_norm': '2.425', 'learning_rate': '1.649e-05', 'epoch': '0.5155'} | |
| {'loss': '0.2064', 'grad_norm': '3.046', 'learning_rate': '1.649e-05', 'epoch': '0.516'} | |
| {'loss': '0.2004', 'grad_norm': '1.67', 'learning_rate': '1.648e-05', 'epoch': '0.5165'} | |
| {'loss': '0.2075', 'grad_norm': '4.806', 'learning_rate': '1.648e-05', 'epoch': '0.5169'} | |
| {'loss': '0.2', 'grad_norm': '3.74', 'learning_rate': '1.647e-05', 'epoch': '0.5174'} | |
| {'loss': '0.2064', 'grad_norm': '1.731', 'learning_rate': '1.647e-05', 'epoch': '0.5179'} | |
| {'loss': '0.2224', 'grad_norm': '6.855', 'learning_rate': '1.646e-05', 'epoch': '0.5184'} | |
| {'loss': '0.2054', 'grad_norm': '2.969', 'learning_rate': '1.646e-05', 'epoch': '0.5189'} | |
| {'loss': '0.1969', 'grad_norm': '2.252', 'learning_rate': '1.645e-05', 'epoch': '0.5193'} | |
| {'loss': '0.3367', 'grad_norm': '1.788', 'learning_rate': '1.645e-05', 'epoch': '0.5198'} | |
| {'loss': '0.2082', 'grad_norm': '2.119', 'learning_rate': '1.644e-05', 'epoch': '0.5203'} | |
| {'loss': '0.2145', 'grad_norm': '8.446', 'learning_rate': '1.644e-05', 'epoch': '0.5208'} | |
| {'loss': '0.2155', 'grad_norm': '5.556', 'learning_rate': '1.643e-05', 'epoch': '0.5212'} | |
| {'loss': '0.2116', 'grad_norm': '8.451', 'learning_rate': '1.643e-05', 'epoch': '0.5217'} | |
| {'loss': '0.1962', 'grad_norm': '1.065', 'learning_rate': '1.642e-05', 'epoch': '0.5222'} | |
| {'loss': '0.2079', 'grad_norm': '10.26', 'learning_rate': '1.641e-05', 'epoch': '0.5227'} | |
| {'loss': '0.2042', 'grad_norm': '2.117', 'learning_rate': '1.641e-05', 'epoch': '0.5231'} | |
| {'loss': '0.1948', 'grad_norm': '2.449', 'learning_rate': '1.64e-05', 'epoch': '0.5236'} | |
| {'loss': '0.2096', 'grad_norm': '5.881', 'learning_rate': '1.64e-05', 'epoch': '0.5241'} | |
| {'loss': '0.2129', 'grad_norm': '0.941', 'learning_rate': '1.639e-05', 'epoch': '0.5246'} | |
| {'loss': '0.1909', 'grad_norm': '0.9057', 'learning_rate': '1.639e-05', 'epoch': '0.525'} | |
| {'loss': '0.2035', 'grad_norm': '5.795', 'learning_rate': '1.638e-05', 'epoch': '0.5255'} | |
| {'loss': '0.3284', 'grad_norm': '2.882', 'learning_rate': '1.638e-05', 'epoch': '0.526'} | |
| {'loss': '0.3048', 'grad_norm': '7.97', 'learning_rate': '1.637e-05', 'epoch': '0.5265'} | |
| {'loss': '0.1857', 'grad_norm': '5.665', 'learning_rate': '1.637e-05', 'epoch': '0.527'} | |
| {'loss': '0.2041', 'grad_norm': '3.813', 'learning_rate': '1.636e-05', 'epoch': '0.5274'} | |
| {'loss': '0.1931', 'grad_norm': '2.145', 'learning_rate': '1.636e-05', 'epoch': '0.5279'} | |
| {'loss': '0.1957', 'grad_norm': '4.481', 'learning_rate': '1.635e-05', 'epoch': '0.5284'} | |
| {'loss': '0.2809', 'grad_norm': '5.774', 'learning_rate': '1.635e-05', 'epoch': '0.5289'} | |
| {'loss': '0.2109', 'grad_norm': '3.387', 'learning_rate': '1.634e-05', 'epoch': '0.5293'} | |
| {'loss': '0.2083', 'grad_norm': '4.493', 'learning_rate': '1.634e-05', 'epoch': '0.5298'} | |
| {'loss': '0.1986', 'grad_norm': '8.64', 'learning_rate': '1.633e-05', 'epoch': '0.5303'} | |
| {'loss': '0.2075', 'grad_norm': '1.123', 'learning_rate': '1.632e-05', 'epoch': '0.5308'} | |
| {'loss': '0.2152', 'grad_norm': '4.968', 'learning_rate': '1.632e-05', 'epoch': '0.5312'} | |
| {'loss': '0.1883', 'grad_norm': '2.642', 'learning_rate': '1.631e-05', 'epoch': '0.5317'} | |
| {'loss': '0.2182', 'grad_norm': '4.794', 'learning_rate': '1.631e-05', 'epoch': '0.5322'} | |
| {'loss': '0.2034', 'grad_norm': '3.736', 'learning_rate': '1.63e-05', 'epoch': '0.5327'} | |
| {'loss': '0.1953', 'grad_norm': '7.125', 'learning_rate': '1.63e-05', 'epoch': '0.5331'} | |
| {'loss': '0.1898', 'grad_norm': '5.947', 'learning_rate': '1.629e-05', 'epoch': '0.5336'} | |
| {'loss': '0.2904', 'grad_norm': '0.7326', 'learning_rate': '1.629e-05', 'epoch': '0.5341'} | |
| {'loss': '0.2158', 'grad_norm': '4.708', 'learning_rate': '1.628e-05', 'epoch': '0.5346'} | |
| {'loss': '0.2322', 'grad_norm': '6.261', 'learning_rate': '1.628e-05', 'epoch': '0.5351'} | |
| {'loss': '0.1969', 'grad_norm': '4.848', 'learning_rate': '1.627e-05', 'epoch': '0.5355'} | |
| {'loss': '0.1962', 'grad_norm': '8.072', 'learning_rate': '1.627e-05', 'epoch': '0.536'} | |
| {'loss': '0.218', 'grad_norm': '3.622', 'learning_rate': '1.626e-05', 'epoch': '0.5365'} | |
| {'loss': '0.188', 'grad_norm': '1.838', 'learning_rate': '1.626e-05', 'epoch': '0.537'} | |
| {'loss': '0.1944', 'grad_norm': '6.386', 'learning_rate': '1.625e-05', 'epoch': '0.5374'} | |
| {'loss': '0.3593', 'grad_norm': '6.172', 'learning_rate': '1.625e-05', 'epoch': '0.5379'} | |
| {'loss': '0.1914', 'grad_norm': '0.9621', 'learning_rate': '1.624e-05', 'epoch': '0.5384'} | |
| {'loss': '0.1875', 'grad_norm': '6.888', 'learning_rate': '1.623e-05', 'epoch': '0.5389'} | |
| {'loss': '0.2191', 'grad_norm': '1.717', 'learning_rate': '1.623e-05', 'epoch': '0.5393'} | |
| {'loss': '0.3023', 'grad_norm': '4.957', 'learning_rate': '1.622e-05', 'epoch': '0.5398'} | |
| {'loss': '0.2035', 'grad_norm': '2.449', 'learning_rate': '1.622e-05', 'epoch': '0.5403'} | |
| {'loss': '0.2242', 'grad_norm': '7.604', 'learning_rate': '1.621e-05', 'epoch': '0.5408'} | |
| {'loss': '0.2127', 'grad_norm': '7.4', 'learning_rate': '1.621e-05', 'epoch': '0.5412'} | |
| {'loss': '0.2028', 'grad_norm': '8.771', 'learning_rate': '1.62e-05', 'epoch': '0.5417'} | |
| {'loss': '0.1989', 'grad_norm': '2.991', 'learning_rate': '1.62e-05', 'epoch': '0.5422'} | |
| {'loss': '0.2108', 'grad_norm': '7.083', 'learning_rate': '1.619e-05', 'epoch': '0.5427'} | |
| {'loss': '0.3231', 'grad_norm': '4.361', 'learning_rate': '1.619e-05', 'epoch': '0.5432'} | |
| {'eval_ms_marco_loss': '0.0819', 'eval_val-ms-marco-768_cosine_accuracy': '0.994', 'eval_val-ms-marco-512_cosine_accuracy': '0.9937', 'eval_val-ms-marco-256_cosine_accuracy': '0.9947', 'eval_val-ms-marco-128_cosine_accuracy': '0.9943', 'eval_val-ms-marco-64_cosine_accuracy': '0.994', 'eval_sequential_score': '0.994', 'eval_ms_marco_runtime': '34.03', 'eval_ms_marco_samples_per_second': '293.8', 'eval_ms_marco_steps_per_second': '9.197', 'epoch': '0.5432'} | |
| {'loss': '0.1741', 'grad_norm': '4.103', 'learning_rate': '1.618e-05', 'epoch': '0.5436'} | |
| {'loss': '0.1821', 'grad_norm': '2.025', 'learning_rate': '1.618e-05', 'epoch': '0.5441'} | |
| {'loss': '0.2026', 'grad_norm': '4.008', 'learning_rate': '1.617e-05', 'epoch': '0.5446'} | |
| {'loss': '0.2086', 'grad_norm': '4.774', 'learning_rate': '1.617e-05', 'epoch': '0.5451'} | |
| {'loss': '0.1922', 'grad_norm': '2.763', 'learning_rate': '1.616e-05', 'epoch': '0.5455'} | |
| {'loss': '0.2136', 'grad_norm': '2.56', 'learning_rate': '1.616e-05', 'epoch': '0.546'} | |
| {'loss': '0.2112', 'grad_norm': '1.724', 'learning_rate': '1.615e-05', 'epoch': '0.5465'} | |
| {'loss': '0.1842', 'grad_norm': '6.019', 'learning_rate': '1.614e-05', 'epoch': '0.547'} | |
| {'loss': '0.3321', 'grad_norm': '5.215', 'learning_rate': '1.614e-05', 'epoch': '0.5474'} | |
| {'loss': '0.1818', 'grad_norm': '4.283', 'learning_rate': '1.613e-05', 'epoch': '0.5479'} | |
| {'loss': '0.2086', 'grad_norm': '3.885', 'learning_rate': '1.613e-05', 'epoch': '0.5484'} | |
| {'loss': '0.3002', 'grad_norm': '1.592', 'learning_rate': '1.612e-05', 'epoch': '0.5489'} | |
| {'loss': '0.2076', 'grad_norm': '0.9938', 'learning_rate': '1.612e-05', 'epoch': '0.5493'} | |
| {'loss': '0.189', 'grad_norm': '2.612', 'learning_rate': '1.611e-05', 'epoch': '0.5498'} | |
| {'loss': '0.208', 'grad_norm': '3.386', 'learning_rate': '1.611e-05', 'epoch': '0.5503'} | |
| {'loss': '0.1938', 'grad_norm': '1.903', 'learning_rate': '1.61e-05', 'epoch': '0.5508'} | |
| {'loss': '0.2154', 'grad_norm': '6.835', 'learning_rate': '1.61e-05', 'epoch': '0.5513'} | |
| {'loss': '0.2064', 'grad_norm': '4.017', 'learning_rate': '1.609e-05', 'epoch': '0.5517'} | |
| {'loss': '0.3004', 'grad_norm': '2.535', 'learning_rate': '1.609e-05', 'epoch': '0.5522'} | |
| {'loss': '0.2034', 'grad_norm': '3.86', 'learning_rate': '1.608e-05', 'epoch': '0.5527'} | |
| {'loss': '0.2244', 'grad_norm': '8.619', 'learning_rate': '1.608e-05', 'epoch': '0.5532'} | |
| {'loss': '0.1797', 'grad_norm': '4.444', 'learning_rate': '1.607e-05', 'epoch': '0.5536'} | |
| {'loss': '0.2757', 'grad_norm': '2.214', 'learning_rate': '1.607e-05', 'epoch': '0.5541'} | |
| {'loss': '0.2005', 'grad_norm': '6.223', 'learning_rate': '1.606e-05', 'epoch': '0.5546'} | |
| {'loss': '0.1862', 'grad_norm': '3.332', 'learning_rate': '1.605e-05', 'epoch': '0.5551'} | |
| {'loss': '0.202', 'grad_norm': '4.437', 'learning_rate': '1.605e-05', 'epoch': '0.5555'} | |
| {'loss': '0.1864', 'grad_norm': '6.808', 'learning_rate': '1.604e-05', 'epoch': '0.556'} | |
| {'loss': '0.1904', 'grad_norm': '0.9245', 'learning_rate': '1.604e-05', 'epoch': '0.5565'} | |
| {'loss': '0.1961', 'grad_norm': '1.859', 'learning_rate': '1.603e-05', 'epoch': '0.557'} | |
| {'loss': '0.227', 'grad_norm': '7.502', 'learning_rate': '1.603e-05', 'epoch': '0.5574'} | |
| {'loss': '0.1907', 'grad_norm': '4.988', 'learning_rate': '1.602e-05', 'epoch': '0.5579'} | |
| {'loss': '0.2005', 'grad_norm': '4.408', 'learning_rate': '1.602e-05', 'epoch': '0.5584'} | |
| {'loss': '0.1917', 'grad_norm': '2.265', 'learning_rate': '1.601e-05', 'epoch': '0.5589'} | |
| {'loss': '0.1911', 'grad_norm': '2.876', 'learning_rate': '1.601e-05', 'epoch': '0.5594'} | |
| {'loss': '0.2015', 'grad_norm': '2.496', 'learning_rate': '1.6e-05', 'epoch': '0.5598'} | |
| {'loss': '0.3178', 'grad_norm': '3.819', 'learning_rate': '1.6e-05', 'epoch': '0.5603'} | |
| {'loss': '0.18', 'grad_norm': '6.127', 'learning_rate': '1.599e-05', 'epoch': '0.5608'} | |
| {'loss': '0.1726', 'grad_norm': '2.334', 'learning_rate': '1.599e-05', 'epoch': '0.5613'} | |
| {'loss': '0.1755', 'grad_norm': '0.957', 'learning_rate': '1.598e-05', 'epoch': '0.5617'} | |
| {'loss': '0.1763', 'grad_norm': '1.094', 'learning_rate': '1.598e-05', 'epoch': '0.5622'} | |
| {'loss': '0.2024', 'grad_norm': '0.6813', 'learning_rate': '1.597e-05', 'epoch': '0.5627'} | |
| {'loss': '0.2176', 'grad_norm': '2.502', 'learning_rate': '1.596e-05', 'epoch': '0.5632'} | |
| {'loss': '0.1977', 'grad_norm': '0.7922', 'learning_rate': '1.596e-05', 'epoch': '0.5636'} | |
| {'loss': '0.2001', 'grad_norm': '1.803', 'learning_rate': '1.595e-05', 'epoch': '0.5641'} | |
| {'loss': '0.1962', 'grad_norm': '8.298', 'learning_rate': '1.595e-05', 'epoch': '0.5646'} | |
| {'loss': '0.1807', 'grad_norm': '3.868', 'learning_rate': '1.594e-05', 'epoch': '0.5651'} | |
| {'loss': '0.2097', 'grad_norm': '2.116', 'learning_rate': '1.594e-05', 'epoch': '0.5655'} | |
| {'loss': '0.1917', 'grad_norm': '3.038', 'learning_rate': '1.593e-05', 'epoch': '0.566'} | |
| {'loss': '0.1895', 'grad_norm': '4.893', 'learning_rate': '1.593e-05', 'epoch': '0.5665'} | |
| {'loss': '0.2152', 'grad_norm': '3.219', 'learning_rate': '1.592e-05', 'epoch': '0.567'} | |
| {'loss': '0.2837', 'grad_norm': '1.207', 'learning_rate': '1.592e-05', 'epoch': '0.5675'} | |
| {'loss': '0.1783', 'grad_norm': '0.6278', 'learning_rate': '1.591e-05', 'epoch': '0.5679'} | |
| {'loss': '0.2108', 'grad_norm': '1.421', 'learning_rate': '1.591e-05', 'epoch': '0.5684'} | |
| {'loss': '0.1973', 'grad_norm': '4.686', 'learning_rate': '1.59e-05', 'epoch': '0.5689'} | |
| {'loss': '0.1904', 'grad_norm': '5.643', 'learning_rate': '1.59e-05', 'epoch': '0.5694'} | |
| {'loss': '0.1886', 'grad_norm': '5.859', 'learning_rate': '1.589e-05', 'epoch': '0.5698'} | |
| {'loss': '0.2054', 'grad_norm': '2.527', 'learning_rate': '1.589e-05', 'epoch': '0.5703'} | |
| {'loss': '0.1934', 'grad_norm': '7.012', 'learning_rate': '1.588e-05', 'epoch': '0.5708'} | |
| {'loss': '0.205', 'grad_norm': '3.13', 'learning_rate': '1.587e-05', 'epoch': '0.5713'} | |
| {'loss': '0.1973', 'grad_norm': '5.352', 'learning_rate': '1.587e-05', 'epoch': '0.5717'} | |
| {'eval_ms_marco_loss': '0.07452', 'eval_val-ms-marco-768_cosine_accuracy': '0.996', 'eval_val-ms-marco-512_cosine_accuracy': '0.9957', 'eval_val-ms-marco-256_cosine_accuracy': '0.9963', 'eval_val-ms-marco-128_cosine_accuracy': '0.9947', 'eval_val-ms-marco-64_cosine_accuracy': '0.994', 'eval_sequential_score': '0.996', 'eval_ms_marco_runtime': '33.92', 'eval_ms_marco_samples_per_second': '294.9', 'eval_ms_marco_steps_per_second': '9.229', 'epoch': '0.5717'} | |
| {'loss': '0.1745', 'grad_norm': '2.067', 'learning_rate': '1.586e-05', 'epoch': '0.5722'} | |
| {'loss': '0.2508', 'grad_norm': '5.698', 'learning_rate': '1.586e-05', 'epoch': '0.5727'} | |
| {'loss': '0.2208', 'grad_norm': '0.7348', 'learning_rate': '1.585e-05', 'epoch': '0.5732'} | |
| {'loss': '0.3162', 'grad_norm': '3.846', 'learning_rate': '1.585e-05', 'epoch': '0.5736'} | |
| {'loss': '0.1912', 'grad_norm': '4.213', 'learning_rate': '1.584e-05', 'epoch': '0.5741'} | |
| {'loss': '0.1915', 'grad_norm': '2.204', 'learning_rate': '1.584e-05', 'epoch': '0.5746'} | |
| {'loss': '0.1752', 'grad_norm': '4.033', 'learning_rate': '1.583e-05', 'epoch': '0.5751'} | |
| {'loss': '0.1882', 'grad_norm': '4.171', 'learning_rate': '1.583e-05', 'epoch': '0.5756'} | |
| {'loss': '0.1727', 'grad_norm': '4.488', 'learning_rate': '1.582e-05', 'epoch': '0.576'} | |
| {'loss': '0.1975', 'grad_norm': '2.155', 'learning_rate': '1.582e-05', 'epoch': '0.5765'} | |
| {'loss': '0.1854', 'grad_norm': '2.636', 'learning_rate': '1.581e-05', 'epoch': '0.577'} | |
| {'loss': '0.1987', 'grad_norm': '2.527', 'learning_rate': '1.581e-05', 'epoch': '0.5775'} | |
| {'loss': '0.1842', 'grad_norm': '2.946', 'learning_rate': '1.58e-05', 'epoch': '0.5779'} | |
| {'loss': '0.1924', 'grad_norm': '3.261', 'learning_rate': '1.58e-05', 'epoch': '0.5784'} | |
| {'loss': '0.2518', 'grad_norm': '2.614', 'learning_rate': '1.579e-05', 'epoch': '0.5789'} | |
| {'loss': '0.1955', 'grad_norm': '2.634', 'learning_rate': '1.578e-05', 'epoch': '0.5794'} | |
| {'loss': '0.1781', 'grad_norm': '5.407', 'learning_rate': '1.578e-05', 'epoch': '0.5798'} | |
| {'loss': '0.2033', 'grad_norm': '5.352', 'learning_rate': '1.577e-05', 'epoch': '0.5803'} | |
| {'loss': '0.2809', 'grad_norm': '0.8371', 'learning_rate': '1.577e-05', 'epoch': '0.5808'} | |
| {'loss': '0.1871', 'grad_norm': '5.265', 'learning_rate': '1.576e-05', 'epoch': '0.5813'} | |
| {'loss': '0.1913', 'grad_norm': '3.019', 'learning_rate': '1.576e-05', 'epoch': '0.5817'} | |
| {'loss': '0.1701', 'grad_norm': '4.832', 'learning_rate': '1.575e-05', 'epoch': '0.5822'} | |
| {'loss': '0.1949', 'grad_norm': '1.753', 'learning_rate': '1.575e-05', 'epoch': '0.5827'} | |
| {'loss': '0.3041', 'grad_norm': '6.528', 'learning_rate': '1.574e-05', 'epoch': '0.5832'} | |
| {'loss': '0.3381', 'grad_norm': '3.126', 'learning_rate': '1.574e-05', 'epoch': '0.5837'} | |
| {'loss': '0.1772', 'grad_norm': '3.08', 'learning_rate': '1.573e-05', 'epoch': '0.5841'} | |
| {'loss': '0.1895', 'grad_norm': '1.705', 'learning_rate': '1.573e-05', 'epoch': '0.5846'} | |
| {'loss': '0.1908', 'grad_norm': '6.15', 'learning_rate': '1.572e-05', 'epoch': '0.5851'} | |
| {'loss': '0.1962', 'grad_norm': '0.7544', 'learning_rate': '1.572e-05', 'epoch': '0.5856'} | |
| {'loss': '0.1971', 'grad_norm': '1.898', 'learning_rate': '1.571e-05', 'epoch': '0.586'} | |
| {'loss': '0.1805', 'grad_norm': '6.546', 'learning_rate': '1.571e-05', 'epoch': '0.5865'} | |
| {'loss': '0.1872', 'grad_norm': '2.266', 'learning_rate': '1.57e-05', 'epoch': '0.587'} | |
| {'loss': '0.1797', 'grad_norm': '5.133', 'learning_rate': '1.569e-05', 'epoch': '0.5875'} | |
| {'loss': '0.3226', 'grad_norm': '2.062', 'learning_rate': '1.569e-05', 'epoch': '0.5879'} | |
| {'loss': '0.2006', 'grad_norm': '6.341', 'learning_rate': '1.568e-05', 'epoch': '0.5884'} | |
| {'loss': '0.1736', 'grad_norm': '2.943', 'learning_rate': '1.568e-05', 'epoch': '0.5889'} | |
| {'loss': '0.1886', 'grad_norm': '1.549', 'learning_rate': '1.567e-05', 'epoch': '0.5894'} | |
| {'loss': '0.1925', 'grad_norm': '0.2097', 'learning_rate': '1.567e-05', 'epoch': '0.5898'} | |
| {'loss': '0.1728', 'grad_norm': '5.535', 'learning_rate': '1.566e-05', 'epoch': '0.5903'} | |
| {'loss': '0.1684', 'grad_norm': '6.159', 'learning_rate': '1.566e-05', 'epoch': '0.5908'} | |
| {'loss': '0.1895', 'grad_norm': '1.14', 'learning_rate': '1.565e-05', 'epoch': '0.5913'} | |
| {'loss': '0.1899', 'grad_norm': '11.28', 'learning_rate': '1.565e-05', 'epoch': '0.5918'} | |
| {'loss': '0.179', 'grad_norm': '4.438', 'learning_rate': '1.564e-05', 'epoch': '0.5922'} | |
| {'loss': '0.1883', 'grad_norm': '4.49', 'learning_rate': '1.564e-05', 'epoch': '0.5927'} | |
| {'loss': '0.3218', 'grad_norm': '1.106', 'learning_rate': '1.563e-05', 'epoch': '0.5932'} | |
| {'loss': '0.2085', 'grad_norm': '2.614', 'learning_rate': '1.563e-05', 'epoch': '0.5937'} | |
| {'loss': '0.2185', 'grad_norm': '5.649', 'learning_rate': '1.562e-05', 'epoch': '0.5941'} | |
| {'loss': '0.192', 'grad_norm': '4.159', 'learning_rate': '1.562e-05', 'epoch': '0.5946'} | |
| {'loss': '0.1842', 'grad_norm': '2.472', 'learning_rate': '1.561e-05', 'epoch': '0.5951'} | |
| {'loss': '0.1787', 'grad_norm': '3.811', 'learning_rate': '1.56e-05', 'epoch': '0.5956'} | |
| {'loss': '0.1943', 'grad_norm': '1.558', 'learning_rate': '1.56e-05', 'epoch': '0.596'} | |
| {'loss': '0.18', 'grad_norm': '0.7678', 'learning_rate': '1.559e-05', 'epoch': '0.5965'} | |
| {'loss': '0.2003', 'grad_norm': '5.101', 'learning_rate': '1.559e-05', 'epoch': '0.597'} | |
| {'loss': '0.1646', 'grad_norm': '5.538', 'learning_rate': '1.558e-05', 'epoch': '0.5975'} | |
| {'loss': '0.1916', 'grad_norm': '3.967', 'learning_rate': '1.558e-05', 'epoch': '0.5979'} | |
| {'loss': '0.172', 'grad_norm': '0.8652', 'learning_rate': '1.557e-05', 'epoch': '0.5984'} | |
| {'loss': '0.179', 'grad_norm': '1.133', 'learning_rate': '1.557e-05', 'epoch': '0.5989'} | |
| {'loss': '0.1697', 'grad_norm': '1.457', 'learning_rate': '1.556e-05', 'epoch': '0.5994'} | |
| {'loss': '0.1833', 'grad_norm': '5.53', 'learning_rate': '1.556e-05', 'epoch': '0.5999'} | |
| {'loss': '0.1811', 'grad_norm': '4.049', 'learning_rate': '1.555e-05', 'epoch': '0.6003'} | |
| {'eval_ms_marco_loss': '0.07285', 'eval_val-ms-marco-768_cosine_accuracy': '0.996', 'eval_val-ms-marco-512_cosine_accuracy': '0.9963', 'eval_val-ms-marco-256_cosine_accuracy': '0.9963', 'eval_val-ms-marco-128_cosine_accuracy': '0.9967', 'eval_val-ms-marco-64_cosine_accuracy': '0.995', 'eval_sequential_score': '0.996', 'eval_ms_marco_runtime': '34.02', 'eval_ms_marco_samples_per_second': '294', 'eval_ms_marco_steps_per_second': '9.201', 'epoch': '0.6003'} | |
| {'loss': '0.2006', 'grad_norm': '5.161', 'learning_rate': '1.555e-05', 'epoch': '0.6008'} | |
| {'loss': '0.1954', 'grad_norm': '1.475', 'learning_rate': '1.554e-05', 'epoch': '0.6013'} | |
| {'loss': '0.1683', 'grad_norm': '6.017', 'learning_rate': '1.554e-05', 'epoch': '0.6018'} | |
| {'loss': '0.1912', 'grad_norm': '4.097', 'learning_rate': '1.553e-05', 'epoch': '0.6022'} | |
| {'loss': '0.1888', 'grad_norm': '4.173', 'learning_rate': '1.553e-05', 'epoch': '0.6027'} | |
| {'loss': '0.2527', 'grad_norm': '5.343', 'learning_rate': '1.552e-05', 'epoch': '0.6032'} | |
| {'loss': '0.196', 'grad_norm': '4.322', 'learning_rate': '1.551e-05', 'epoch': '0.6037'} | |
| {'loss': '0.2778', 'grad_norm': '3.119', 'learning_rate': '1.551e-05', 'epoch': '0.6041'} | |
| {'loss': '0.2789', 'grad_norm': '3.69', 'learning_rate': '1.55e-05', 'epoch': '0.6046'} | |
| {'loss': '0.1767', 'grad_norm': '4.081', 'learning_rate': '1.55e-05', 'epoch': '0.6051'} | |
| {'loss': '0.1847', 'grad_norm': '5.133', 'learning_rate': '1.549e-05', 'epoch': '0.6056'} | |
| {'loss': '0.183', 'grad_norm': '4.445', 'learning_rate': '1.549e-05', 'epoch': '0.606'} | |
| {'loss': '0.1927', 'grad_norm': '8.471', 'learning_rate': '1.548e-05', 'epoch': '0.6065'} | |
| {'loss': '0.1635', 'grad_norm': '0.7156', 'learning_rate': '1.548e-05', 'epoch': '0.607'} | |
| {'loss': '0.189', 'grad_norm': '5.111', 'learning_rate': '1.547e-05', 'epoch': '0.6075'} | |
| {'loss': '0.205', 'grad_norm': '1.705', 'learning_rate': '1.547e-05', 'epoch': '0.608'} | |
| {'loss': '0.1616', 'grad_norm': '1.913', 'learning_rate': '1.546e-05', 'epoch': '0.6084'} | |
| {'loss': '0.1684', 'grad_norm': '3.081', 'learning_rate': '1.546e-05', 'epoch': '0.6089'} | |
| {'loss': '0.1908', 'grad_norm': '5.647', 'learning_rate': '1.545e-05', 'epoch': '0.6094'} | |
| {'loss': '0.2573', 'grad_norm': '5.311', 'learning_rate': '1.545e-05', 'epoch': '0.6099'} | |
| {'loss': '0.1767', 'grad_norm': '1.987', 'learning_rate': '1.544e-05', 'epoch': '0.6103'} | |
| {'loss': '0.172', 'grad_norm': '4.129', 'learning_rate': '1.544e-05', 'epoch': '0.6108'} | |
| {'loss': '0.1759', 'grad_norm': '1.601', 'learning_rate': '1.543e-05', 'epoch': '0.6113'} | |
| {'loss': '0.1948', 'grad_norm': '2.08', 'learning_rate': '1.542e-05', 'epoch': '0.6118'} | |
| {'loss': '0.1702', 'grad_norm': '5.843', 'learning_rate': '1.542e-05', 'epoch': '0.6122'} | |
| {'loss': '0.1971', 'grad_norm': '6.056', 'learning_rate': '1.541e-05', 'epoch': '0.6127'} | |
| {'loss': '0.1888', 'grad_norm': '5.762', 'learning_rate': '1.541e-05', 'epoch': '0.6132'} | |
| {'loss': '0.1845', 'grad_norm': '1.994', 'learning_rate': '1.54e-05', 'epoch': '0.6137'} | |
| {'loss': '0.1933', 'grad_norm': '5.169', 'learning_rate': '1.54e-05', 'epoch': '0.6141'} | |
| {'loss': '0.1818', 'grad_norm': '1.184', 'learning_rate': '1.539e-05', 'epoch': '0.6146'} | |
| {'loss': '0.3148', 'grad_norm': '4.015', 'learning_rate': '1.539e-05', 'epoch': '0.6151'} | |
| {'loss': '0.1848', 'grad_norm': '5.42', 'learning_rate': '1.538e-05', 'epoch': '0.6156'} | |
| {'loss': '0.4711', 'grad_norm': '6.727', 'learning_rate': '1.538e-05', 'epoch': '0.6161'} | |
| {'loss': '0.1784', 'grad_norm': '1.701', 'learning_rate': '1.537e-05', 'epoch': '0.6165'} | |
| {'loss': '0.1718', 'grad_norm': '4.339', 'learning_rate': '1.537e-05', 'epoch': '0.617'} | |
| {'loss': '0.1876', 'grad_norm': '7.47', 'learning_rate': '1.536e-05', 'epoch': '0.6175'} | |
| {'loss': '0.1677', 'grad_norm': '7.438', 'learning_rate': '1.536e-05', 'epoch': '0.618'} | |
| {'loss': '0.1804', 'grad_norm': '6.938', 'learning_rate': '1.535e-05', 'epoch': '0.6184'} | |
| {'loss': '0.1756', 'grad_norm': '3.48', 'learning_rate': '1.535e-05', 'epoch': '0.6189'} | |
| {'loss': '0.1888', 'grad_norm': '6.175', 'learning_rate': '1.534e-05', 'epoch': '0.6194'} | |
| {'loss': '0.1531', 'grad_norm': '4.705', 'learning_rate': '1.533e-05', 'epoch': '0.6199'} | |
| {'loss': '0.1636', 'grad_norm': '4.539', 'learning_rate': '1.533e-05', 'epoch': '0.6203'} | |
| {'loss': '0.195', 'grad_norm': '1.317', 'learning_rate': '1.532e-05', 'epoch': '0.6208'} | |
| {'loss': '0.3056', 'grad_norm': '0.1906', 'learning_rate': '1.532e-05', 'epoch': '0.6213'} | |
| {'loss': '0.1834', 'grad_norm': '1.756', 'learning_rate': '1.531e-05', 'epoch': '0.6218'} | |
| {'loss': '0.1984', 'grad_norm': '6.214', 'learning_rate': '1.531e-05', 'epoch': '0.6222'} | |
| {'loss': '0.1808', 'grad_norm': '3.704', 'learning_rate': '1.53e-05', 'epoch': '0.6227'} | |
| {'loss': '0.1799', 'grad_norm': '0.6368', 'learning_rate': '1.53e-05', 'epoch': '0.6232'} | |
| {'loss': '0.1807', 'grad_norm': '5.178', 'learning_rate': '1.529e-05', 'epoch': '0.6237'} | |
| {'loss': '0.1876', 'grad_norm': '6.298', 'learning_rate': '1.529e-05', 'epoch': '0.6241'} | |
| {'loss': '0.3616', 'grad_norm': '7.594', 'learning_rate': '1.528e-05', 'epoch': '0.6246'} | |
| {'loss': '0.1637', 'grad_norm': '1.212', 'learning_rate': '1.528e-05', 'epoch': '0.6251'} | |
| {'loss': '0.1848', 'grad_norm': '1.357', 'learning_rate': '1.527e-05', 'epoch': '0.6256'} | |
| {'loss': '0.1943', 'grad_norm': '0.8911', 'learning_rate': '1.527e-05', 'epoch': '0.6261'} | |
| {'loss': '0.1919', 'grad_norm': '1.543', 'learning_rate': '1.526e-05', 'epoch': '0.6265'} | |
| {'loss': '0.1786', 'grad_norm': '4.307', 'learning_rate': '1.526e-05', 'epoch': '0.627'} | |
| {'loss': '0.1944', 'grad_norm': '6.011', 'learning_rate': '1.525e-05', 'epoch': '0.6275'} | |
| {'loss': '0.2012', 'grad_norm': '2.083', 'learning_rate': '1.524e-05', 'epoch': '0.628'} | |
| {'loss': '0.181', 'grad_norm': '1.984', 'learning_rate': '1.524e-05', 'epoch': '0.6284'} | |
| {'loss': '0.1791', 'grad_norm': '3.598', 'learning_rate': '1.523e-05', 'epoch': '0.6289'} | |
| {'eval_ms_marco_loss': '0.06583', 'eval_val-ms-marco-768_cosine_accuracy': '0.9967', 'eval_val-ms-marco-512_cosine_accuracy': '0.9963', 'eval_val-ms-marco-256_cosine_accuracy': '0.9963', 'eval_val-ms-marco-128_cosine_accuracy': '0.996', 'eval_val-ms-marco-64_cosine_accuracy': '0.996', 'eval_sequential_score': '0.9967', 'eval_ms_marco_runtime': '33.84', 'eval_ms_marco_samples_per_second': '295.5', 'eval_ms_marco_steps_per_second': '9.249', 'epoch': '0.6289'} | |
| {'loss': '0.1626', 'grad_norm': '5.023', 'learning_rate': '1.523e-05', 'epoch': '0.6294'} | |
| {'loss': '0.1975', 'grad_norm': '2.089', 'learning_rate': '1.522e-05', 'epoch': '0.6299'} | |
| {'loss': '0.1696', 'grad_norm': '1.07', 'learning_rate': '1.522e-05', 'epoch': '0.6303'} | |
| {'loss': '0.212', 'grad_norm': '4.758', 'learning_rate': '1.521e-05', 'epoch': '0.6308'} | |
| {'loss': '0.1834', 'grad_norm': '3.156', 'learning_rate': '1.521e-05', 'epoch': '0.6313'} | |
| {'loss': '0.1909', 'grad_norm': '9.028', 'learning_rate': '1.52e-05', 'epoch': '0.6318'} | |
| {'loss': '0.1789', 'grad_norm': '4.934', 'learning_rate': '1.52e-05', 'epoch': '0.6322'} | |
| {'loss': '0.1401', 'grad_norm': '4.618', 'learning_rate': '1.519e-05', 'epoch': '0.6327'} | |
| {'loss': '0.1702', 'grad_norm': '1.974', 'learning_rate': '1.519e-05', 'epoch': '0.6332'} | |
| {'loss': '0.2582', 'grad_norm': '2.726', 'learning_rate': '1.518e-05', 'epoch': '0.6337'} | |
| {'loss': '0.1712', 'grad_norm': '1.317', 'learning_rate': '1.518e-05', 'epoch': '0.6342'} | |
| {'loss': '0.1741', 'grad_norm': '3.986', 'learning_rate': '1.517e-05', 'epoch': '0.6346'} | |
| {'loss': '0.192', 'grad_norm': '2.879', 'learning_rate': '1.517e-05', 'epoch': '0.6351'} | |
| {'loss': '0.1888', 'grad_norm': '2.302', 'learning_rate': '1.516e-05', 'epoch': '0.6356'} | |
| {'loss': '0.3157', 'grad_norm': '1.015', 'learning_rate': '1.515e-05', 'epoch': '0.6361'} | |
| {'loss': '0.1936', 'grad_norm': '4.475', 'learning_rate': '1.515e-05', 'epoch': '0.6365'} | |
| {'loss': '0.1803', 'grad_norm': '2.987', 'learning_rate': '1.514e-05', 'epoch': '0.637'} | |
| {'loss': '0.1904', 'grad_norm': '1.723', 'learning_rate': '1.514e-05', 'epoch': '0.6375'} | |
| {'loss': '0.1804', 'grad_norm': '2.951', 'learning_rate': '1.513e-05', 'epoch': '0.638'} | |
| {'loss': '0.1732', 'grad_norm': '5.205', 'learning_rate': '1.513e-05', 'epoch': '0.6384'} | |
| {'loss': '0.1721', 'grad_norm': '3.563', 'learning_rate': '1.512e-05', 'epoch': '0.6389'} | |
| {'loss': '0.181', 'grad_norm': '4.18', 'learning_rate': '1.512e-05', 'epoch': '0.6394'} | |
| {'loss': '0.1799', 'grad_norm': '8.648', 'learning_rate': '1.511e-05', 'epoch': '0.6399'} | |
| {'loss': '0.1651', 'grad_norm': '3.552', 'learning_rate': '1.511e-05', 'epoch': '0.6403'} | |
| {'loss': '0.1719', 'grad_norm': '0.3289', 'learning_rate': '1.51e-05', 'epoch': '0.6408'} | |
| {'loss': '0.1864', 'grad_norm': '3.458', 'learning_rate': '1.51e-05', 'epoch': '0.6413'} | |
| {'loss': '0.1843', 'grad_norm': '2.118', 'learning_rate': '1.509e-05', 'epoch': '0.6418'} | |
| {'loss': '0.1881', 'grad_norm': '2.721', 'learning_rate': '1.509e-05', 'epoch': '0.6423'} | |
| {'loss': '0.1616', 'grad_norm': '5.476', 'learning_rate': '1.508e-05', 'epoch': '0.6427'} | |
| {'loss': '0.1804', 'grad_norm': '5.654', 'learning_rate': '1.508e-05', 'epoch': '0.6432'} | |
| {'loss': '0.1785', 'grad_norm': '3.344', 'learning_rate': '1.507e-05', 'epoch': '0.6437'} | |
| {'loss': '0.1733', 'grad_norm': '5.523', 'learning_rate': '1.506e-05', 'epoch': '0.6442'} | |
| {'loss': '0.1952', 'grad_norm': '3.389', 'learning_rate': '1.506e-05', 'epoch': '0.6446'} | |
| {'loss': '0.1741', 'grad_norm': '6.859', 'learning_rate': '1.505e-05', 'epoch': '0.6451'} | |
| {'loss': '0.1862', 'grad_norm': '0.7682', 'learning_rate': '1.505e-05', 'epoch': '0.6456'} | |
| {'loss': '0.1739', 'grad_norm': '1.687', 'learning_rate': '1.504e-05', 'epoch': '0.6461'} | |
| {'loss': '0.1615', 'grad_norm': '9.557', 'learning_rate': '1.504e-05', 'epoch': '0.6465'} | |
| {'loss': '0.1532', 'grad_norm': '2.294', 'learning_rate': '1.503e-05', 'epoch': '0.647'} | |
| {'loss': '0.1644', 'grad_norm': '5.244', 'learning_rate': '1.503e-05', 'epoch': '0.6475'} | |
| {'loss': '0.167', 'grad_norm': '3.104', 'learning_rate': '1.502e-05', 'epoch': '0.648'} | |
| {'loss': '0.1819', 'grad_norm': '8.789', 'learning_rate': '1.502e-05', 'epoch': '0.6484'} | |
| {'loss': '0.1996', 'grad_norm': '4.376', 'learning_rate': '1.501e-05', 'epoch': '0.6489'} | |
| {'loss': '0.1866', 'grad_norm': '0.2381', 'learning_rate': '1.501e-05', 'epoch': '0.6494'} | |
| {'loss': '0.1803', 'grad_norm': '0.4173', 'learning_rate': '1.5e-05', 'epoch': '0.6499'} | |
| {'loss': '0.1889', 'grad_norm': '5.361', 'learning_rate': '1.5e-05', 'epoch': '0.6504'} | |
| {'loss': '0.1687', 'grad_norm': '5.285', 'learning_rate': '1.499e-05', 'epoch': '0.6508'} | |
| {'loss': '0.1849', 'grad_norm': '1.9', 'learning_rate': '1.499e-05', 'epoch': '0.6513'} | |
| {'loss': '0.1701', 'grad_norm': '2.249', 'learning_rate': '1.498e-05', 'epoch': '0.6518'} | |
| {'loss': '0.1765', 'grad_norm': '2.104', 'learning_rate': '1.497e-05', 'epoch': '0.6523'} | |
| {'loss': '0.1607', 'grad_norm': '3.488', 'learning_rate': '1.497e-05', 'epoch': '0.6527'} | |
| {'loss': '0.2695', 'grad_norm': '4.263', 'learning_rate': '1.496e-05', 'epoch': '0.6532'} | |
| {'loss': '0.1604', 'grad_norm': '4.663', 'learning_rate': '1.496e-05', 'epoch': '0.6537'} | |
| {'loss': '0.2953', 'grad_norm': '6.87', 'learning_rate': '1.495e-05', 'epoch': '0.6542'} | |
| {'loss': '0.1645', 'grad_norm': '1.428', 'learning_rate': '1.495e-05', 'epoch': '0.6546'} | |
| {'loss': '0.1933', 'grad_norm': '4.502', 'learning_rate': '1.494e-05', 'epoch': '0.6551'} | |
| {'loss': '0.1985', 'grad_norm': '3.802', 'learning_rate': '1.494e-05', 'epoch': '0.6556'} | |
| {'loss': '0.1861', 'grad_norm': '7.475', 'learning_rate': '1.493e-05', 'epoch': '0.6561'} | |
| {'loss': '0.2943', 'grad_norm': '0.2623', 'learning_rate': '1.493e-05', 'epoch': '0.6565'} | |
| {'loss': '0.1968', 'grad_norm': '3.706', 'learning_rate': '1.492e-05', 'epoch': '0.657'} | |
| {'loss': '0.2772', 'grad_norm': '3.406', 'learning_rate': '1.492e-05', 'epoch': '0.6575'} | |
| {'eval_ms_marco_loss': '0.06267', 'eval_val-ms-marco-768_cosine_accuracy': '0.9977', 'eval_val-ms-marco-512_cosine_accuracy': '0.9973', 'eval_val-ms-marco-256_cosine_accuracy': '0.9977', 'eval_val-ms-marco-128_cosine_accuracy': '0.9977', 'eval_val-ms-marco-64_cosine_accuracy': '0.997', 'eval_sequential_score': '0.9977', 'eval_ms_marco_runtime': '33.92', 'eval_ms_marco_samples_per_second': '294.8', 'eval_ms_marco_steps_per_second': '9.228', 'epoch': '0.6575'} | |
| {'loss': '0.1548', 'grad_norm': '0.6334', 'learning_rate': '1.491e-05', 'epoch': '0.658'} | |
| {'loss': '0.1687', 'grad_norm': '3.334', 'learning_rate': '1.491e-05', 'epoch': '0.6585'} | |
| {'loss': '0.1794', 'grad_norm': '4.018', 'learning_rate': '1.49e-05', 'epoch': '0.6589'} | |
| {'loss': '0.1826', 'grad_norm': '1.982', 'learning_rate': '1.49e-05', 'epoch': '0.6594'} | |
| {'loss': '0.1627', 'grad_norm': '5.814', 'learning_rate': '1.489e-05', 'epoch': '0.6599'} | |
| {'loss': '0.1412', 'grad_norm': '2.224', 'learning_rate': '1.488e-05', 'epoch': '0.6604'} | |
| {'loss': '0.1831', 'grad_norm': '2.764', 'learning_rate': '1.488e-05', 'epoch': '0.6608'} | |
| {'loss': '0.2886', 'grad_norm': '3.861', 'learning_rate': '1.487e-05', 'epoch': '0.6613'} | |
| {'loss': '0.1654', 'grad_norm': '7.571', 'learning_rate': '1.487e-05', 'epoch': '0.6618'} | |
| {'loss': '0.1851', 'grad_norm': '0.8808', 'learning_rate': '1.486e-05', 'epoch': '0.6623'} | |
| {'loss': '0.2874', 'grad_norm': '3.479', 'learning_rate': '1.486e-05', 'epoch': '0.6627'} | |
| {'loss': '0.1755', 'grad_norm': '2.281', 'learning_rate': '1.485e-05', 'epoch': '0.6632'} | |
| {'loss': '0.164', 'grad_norm': '3.032', 'learning_rate': '1.485e-05', 'epoch': '0.6637'} | |
| {'loss': '0.1587', 'grad_norm': '1.251', 'learning_rate': '1.484e-05', 'epoch': '0.6642'} | |
| {'loss': '0.1567', 'grad_norm': '4.402', 'learning_rate': '1.484e-05', 'epoch': '0.6646'} | |
| {'loss': '0.1747', 'grad_norm': '0.3272', 'learning_rate': '1.483e-05', 'epoch': '0.6651'} | |
| {'loss': '0.1575', 'grad_norm': '6.342', 'learning_rate': '1.483e-05', 'epoch': '0.6656'} | |
| {'loss': '0.1642', 'grad_norm': '5.809', 'learning_rate': '1.482e-05', 'epoch': '0.6661'} | |
| {'loss': '0.1775', 'grad_norm': '5.302', 'learning_rate': '1.482e-05', 'epoch': '0.6666'} | |
| {'loss': '0.173', 'grad_norm': '3.039', 'learning_rate': '1.481e-05', 'epoch': '0.667'} | |
| {'loss': '0.2946', 'grad_norm': '1.684', 'learning_rate': '1.481e-05', 'epoch': '0.6675'} | |
| {'loss': '0.2122', 'grad_norm': '3.486', 'learning_rate': '1.48e-05', 'epoch': '0.668'} | |
| {'loss': '0.1514', 'grad_norm': '2.867', 'learning_rate': '1.479e-05', 'epoch': '0.6685'} | |
| {'loss': '0.1745', 'grad_norm': '1.449', 'learning_rate': '1.479e-05', 'epoch': '0.6689'} | |
| {'loss': '0.1766', 'grad_norm': '6.95', 'learning_rate': '1.478e-05', 'epoch': '0.6694'} | |
| {'loss': '0.1572', 'grad_norm': '3.397', 'learning_rate': '1.478e-05', 'epoch': '0.6699'} | |
| {'loss': '0.1613', 'grad_norm': '4.649', 'learning_rate': '1.477e-05', 'epoch': '0.6704'} | |
| {'loss': '0.1651', 'grad_norm': '2.908', 'learning_rate': '1.477e-05', 'epoch': '0.6708'} | |
| {'loss': '0.1671', 'grad_norm': '6.138', 'learning_rate': '1.476e-05', 'epoch': '0.6713'} | |
| {'loss': '0.1805', 'grad_norm': '3.829', 'learning_rate': '1.476e-05', 'epoch': '0.6718'} | |
| {'loss': '0.1774', 'grad_norm': '3.975', 'learning_rate': '1.475e-05', 'epoch': '0.6723'} | |
| {'loss': '0.1724', 'grad_norm': '0.6219', 'learning_rate': '1.475e-05', 'epoch': '0.6727'} | |
| {'loss': '0.1826', 'grad_norm': '1.481', 'learning_rate': '1.474e-05', 'epoch': '0.6732'} | |
| {'loss': '0.3296', 'grad_norm': '1.023', 'learning_rate': '1.474e-05', 'epoch': '0.6737'} | |
| {'loss': '0.1577', 'grad_norm': '1.3', 'learning_rate': '1.473e-05', 'epoch': '0.6742'} | |
| {'loss': '0.2422', 'grad_norm': '2.559', 'learning_rate': '1.473e-05', 'epoch': '0.6747'} | |
| {'loss': '0.1903', 'grad_norm': '1.979', 'learning_rate': '1.472e-05', 'epoch': '0.6751'} | |
| {'loss': '0.1754', 'grad_norm': '8.728', 'learning_rate': '1.472e-05', 'epoch': '0.6756'} | |
| {'loss': '0.1587', 'grad_norm': '2.565', 'learning_rate': '1.471e-05', 'epoch': '0.6761'} | |
| {'loss': '0.1436', 'grad_norm': '3.348', 'learning_rate': '1.47e-05', 'epoch': '0.6766'} | |
| {'loss': '0.1681', 'grad_norm': '0.6837', 'learning_rate': '1.47e-05', 'epoch': '0.677'} | |
| {'loss': '0.2506', 'grad_norm': '3.387', 'learning_rate': '1.469e-05', 'epoch': '0.6775'} | |
| {'loss': '0.1653', 'grad_norm': '1.596', 'learning_rate': '1.469e-05', 'epoch': '0.678'} | |
| {'loss': '0.1736', 'grad_norm': '0.7384', 'learning_rate': '1.468e-05', 'epoch': '0.6785'} | |
| {'loss': '0.1766', 'grad_norm': '6.351', 'learning_rate': '1.468e-05', 'epoch': '0.6789'} | |
| {'loss': '0.285', 'grad_norm': '0.3153', 'learning_rate': '1.467e-05', 'epoch': '0.6794'} | |
| {'loss': '0.162', 'grad_norm': '5.854', 'learning_rate': '1.467e-05', 'epoch': '0.6799'} | |
| {'loss': '0.1728', 'grad_norm': '5.665', 'learning_rate': '1.466e-05', 'epoch': '0.6804'} | |
| {'loss': '0.1727', 'grad_norm': '4.252', 'learning_rate': '1.466e-05', 'epoch': '0.6808'} | |
| {'loss': '0.1656', 'grad_norm': '1.919', 'learning_rate': '1.465e-05', 'epoch': '0.6813'} | |
| {'loss': '0.1697', 'grad_norm': '5.525', 'learning_rate': '1.465e-05', 'epoch': '0.6818'} | |
| {'loss': '0.1702', 'grad_norm': '4.523', 'learning_rate': '1.464e-05', 'epoch': '0.6823'} | |
| {'loss': '0.1365', 'grad_norm': '3.912', 'learning_rate': '1.464e-05', 'epoch': '0.6828'} | |
| {'loss': '0.1611', 'grad_norm': '3.824', 'learning_rate': '1.463e-05', 'epoch': '0.6832'} | |
| {'loss': '0.1886', 'grad_norm': '1.659', 'learning_rate': '1.463e-05', 'epoch': '0.6837'} | |
| {'loss': '0.1666', 'grad_norm': '2.946', 'learning_rate': '1.462e-05', 'epoch': '0.6842'} | |
| {'loss': '0.2771', 'grad_norm': '1.478', 'learning_rate': '1.461e-05', 'epoch': '0.6847'} | |
| {'loss': '0.198', 'grad_norm': '4.181', 'learning_rate': '1.461e-05', 'epoch': '0.6851'} | |
| {'loss': '0.1594', 'grad_norm': '6.13', 'learning_rate': '1.46e-05', 'epoch': '0.6856'} | |
| {'loss': '0.1687', 'grad_norm': '1.948', 'learning_rate': '1.46e-05', 'epoch': '0.6861'} | |
| {'eval_ms_marco_loss': '0.05764', 'eval_val-ms-marco-768_cosine_accuracy': '0.9973', 'eval_val-ms-marco-512_cosine_accuracy': '0.9963', 'eval_val-ms-marco-256_cosine_accuracy': '0.9973', 'eval_val-ms-marco-128_cosine_accuracy': '0.9973', 'eval_val-ms-marco-64_cosine_accuracy': '0.998', 'eval_sequential_score': '0.9973', 'eval_ms_marco_runtime': '33.78', 'eval_ms_marco_samples_per_second': '296', 'eval_ms_marco_steps_per_second': '9.264', 'epoch': '0.6861'} | |
| {'loss': '0.1858', 'grad_norm': '6.827', 'learning_rate': '1.459e-05', 'epoch': '0.6866'} | |
| {'loss': '0.1793', 'grad_norm': '5.629', 'learning_rate': '1.459e-05', 'epoch': '0.687'} | |
| {'loss': '0.1778', 'grad_norm': '3.185', 'learning_rate': '1.458e-05', 'epoch': '0.6875'} | |
| {'loss': '0.1621', 'grad_norm': '4.654', 'learning_rate': '1.458e-05', 'epoch': '0.688'} | |
| {'loss': '0.1592', 'grad_norm': '3.796', 'learning_rate': '1.457e-05', 'epoch': '0.6885'} | |
| {'loss': '0.165', 'grad_norm': '2.601', 'learning_rate': '1.457e-05', 'epoch': '0.6889'} | |
| {'loss': '0.2048', 'grad_norm': '4.785', 'learning_rate': '1.456e-05', 'epoch': '0.6894'} | |
| {'loss': '0.1657', 'grad_norm': '2.265', 'learning_rate': '1.456e-05', 'epoch': '0.6899'} | |
| {'loss': '0.2973', 'grad_norm': '3.371', 'learning_rate': '1.455e-05', 'epoch': '0.6904'} | |
| {'loss': '0.1585', 'grad_norm': '3.412', 'learning_rate': '1.455e-05', 'epoch': '0.6909'} | |
| {'loss': '0.186', 'grad_norm': '0.7947', 'learning_rate': '1.454e-05', 'epoch': '0.6913'} | |
| {'loss': '0.149', 'grad_norm': '1.934', 'learning_rate': '1.454e-05', 'epoch': '0.6918'} | |
| {'loss': '0.1581', 'grad_norm': '5.397', 'learning_rate': '1.453e-05', 'epoch': '0.6923'} | |
| {'loss': '0.1716', 'grad_norm': '8.197', 'learning_rate': '1.452e-05', 'epoch': '0.6928'} | |
| {'loss': '0.1659', 'grad_norm': '1.94', 'learning_rate': '1.452e-05', 'epoch': '0.6932'} | |
| {'loss': '0.1725', 'grad_norm': '2.493', 'learning_rate': '1.451e-05', 'epoch': '0.6937'} | |
| {'loss': '0.1473', 'grad_norm': '3.573', 'learning_rate': '1.451e-05', 'epoch': '0.6942'} | |
| {'loss': '0.1929', 'grad_norm': '1.761', 'learning_rate': '1.45e-05', 'epoch': '0.6947'} | |
| {'loss': '0.1761', 'grad_norm': '2.946', 'learning_rate': '1.45e-05', 'epoch': '0.6951'} | |
| {'loss': '0.1561', 'grad_norm': '1.528', 'learning_rate': '1.449e-05', 'epoch': '0.6956'} | |
| {'loss': '0.1698', 'grad_norm': '4.075', 'learning_rate': '1.449e-05', 'epoch': '0.6961'} | |
| {'loss': '0.1732', 'grad_norm': '1.402', 'learning_rate': '1.448e-05', 'epoch': '0.6966'} | |
| {'loss': '0.1562', 'grad_norm': '7.001', 'learning_rate': '1.448e-05', 'epoch': '0.697'} | |
| {'loss': '0.1515', 'grad_norm': '3.045', 'learning_rate': '1.447e-05', 'epoch': '0.6975'} | |
| {'loss': '0.1704', 'grad_norm': '4.426', 'learning_rate': '1.447e-05', 'epoch': '0.698'} | |
| {'loss': '0.1809', 'grad_norm': '1.632', 'learning_rate': '1.446e-05', 'epoch': '0.6985'} | |
| {'loss': '0.1579', 'grad_norm': '4.311', 'learning_rate': '1.446e-05', 'epoch': '0.699'} | |
| {'loss': '0.1341', 'grad_norm': '3.031', 'learning_rate': '1.445e-05', 'epoch': '0.6994'} | |
| {'loss': '0.1468', 'grad_norm': '6.574', 'learning_rate': '1.445e-05', 'epoch': '0.6999'} | |
| {'loss': '0.1651', 'grad_norm': '4.543', 'learning_rate': '1.444e-05', 'epoch': '0.7004'} | |
| {'loss': '0.157', 'grad_norm': '3.726', 'learning_rate': '1.443e-05', 'epoch': '0.7009'} | |
| {'loss': '0.1495', 'grad_norm': '2.412', 'learning_rate': '1.443e-05', 'epoch': '0.7013'} | |
| {'loss': '0.1689', 'grad_norm': '6.049', 'learning_rate': '1.442e-05', 'epoch': '0.7018'} | |
| {'loss': '0.2489', 'grad_norm': '0.5762', 'learning_rate': '1.442e-05', 'epoch': '0.7023'} | |
| {'loss': '0.1576', 'grad_norm': '1.663', 'learning_rate': '1.441e-05', 'epoch': '0.7028'} | |
| {'loss': '0.2673', 'grad_norm': '7.566', 'learning_rate': '1.441e-05', 'epoch': '0.7032'} | |
| {'loss': '0.1804', 'grad_norm': '5.227', 'learning_rate': '1.44e-05', 'epoch': '0.7037'} | |
| {'loss': '0.1625', 'grad_norm': '3.038', 'learning_rate': '1.44e-05', 'epoch': '0.7042'} | |
| {'loss': '0.1794', 'grad_norm': '0.7381', 'learning_rate': '1.439e-05', 'epoch': '0.7047'} | |
| {'loss': '0.1797', 'grad_norm': '0.3581', 'learning_rate': '1.439e-05', 'epoch': '0.7051'} | |
| {'loss': '0.1484', 'grad_norm': '1.859', 'learning_rate': '1.438e-05', 'epoch': '0.7056'} | |
| {'loss': '0.1456', 'grad_norm': '2.836', 'learning_rate': '1.438e-05', 'epoch': '0.7061'} | |
| {'loss': '0.1706', 'grad_norm': '5.082', 'learning_rate': '1.437e-05', 'epoch': '0.7066'} | |
| {'loss': '0.414', 'grad_norm': '2.29', 'learning_rate': '1.437e-05', 'epoch': '0.7071'} | |
| {'loss': '0.1643', 'grad_norm': '1.277', 'learning_rate': '1.436e-05', 'epoch': '0.7075'} | |
| {'loss': '0.1468', 'grad_norm': '1.44', 'learning_rate': '1.436e-05', 'epoch': '0.708'} | |
| {'loss': '0.1869', 'grad_norm': '2.138', 'learning_rate': '1.435e-05', 'epoch': '0.7085'} | |
| {'loss': '0.1629', 'grad_norm': '0.2549', 'learning_rate': '1.434e-05', 'epoch': '0.709'} | |
| {'loss': '0.3187', 'grad_norm': '0.962', 'learning_rate': '1.434e-05', 'epoch': '0.7094'} | |
| {'loss': '0.1461', 'grad_norm': '3.05', 'learning_rate': '1.433e-05', 'epoch': '0.7099'} | |
| {'loss': '0.1769', 'grad_norm': '2.155', 'learning_rate': '1.433e-05', 'epoch': '0.7104'} | |
| {'loss': '0.152', 'grad_norm': '4.514', 'learning_rate': '1.432e-05', 'epoch': '0.7109'} | |
| {'loss': '0.3244', 'grad_norm': '1.37', 'learning_rate': '1.432e-05', 'epoch': '0.7113'} | |
| {'loss': '0.1595', 'grad_norm': '2.165', 'learning_rate': '1.431e-05', 'epoch': '0.7118'} | |
| {'loss': '0.177', 'grad_norm': '2.223', 'learning_rate': '1.431e-05', 'epoch': '0.7123'} | |
| {'loss': '0.1496', 'grad_norm': '5.089', 'learning_rate': '1.43e-05', 'epoch': '0.7128'} | |
| {'loss': '0.1537', 'grad_norm': '0.6881', 'learning_rate': '1.43e-05', 'epoch': '0.7132'} | |
| {'loss': '0.2856', 'grad_norm': '2.905', 'learning_rate': '1.429e-05', 'epoch': '0.7137'} | |
| {'loss': '0.1607', 'grad_norm': '0.7641', 'learning_rate': '1.429e-05', 'epoch': '0.7142'} | |
| {'loss': '0.1758', 'grad_norm': '5.452', 'learning_rate': '1.428e-05', 'epoch': '0.7147'} | |
| {'eval_ms_marco_loss': '0.053', 'eval_val-ms-marco-768_cosine_accuracy': '0.9977', 'eval_val-ms-marco-512_cosine_accuracy': '0.9977', 'eval_val-ms-marco-256_cosine_accuracy': '0.9977', 'eval_val-ms-marco-128_cosine_accuracy': '0.9973', 'eval_val-ms-marco-64_cosine_accuracy': '0.996', 'eval_sequential_score': '0.9977', 'eval_ms_marco_runtime': '33.99', 'eval_ms_marco_samples_per_second': '294.2', 'eval_ms_marco_steps_per_second': '9.207', 'epoch': '0.7147'} | |
| {'loss': '0.1757', 'grad_norm': '6.954', 'learning_rate': '1.428e-05', 'epoch': '0.7152'} | |
| {'loss': '0.1658', 'grad_norm': '2.383', 'learning_rate': '1.427e-05', 'epoch': '0.7156'} | |
| {'loss': '0.1527', 'grad_norm': '2.061', 'learning_rate': '1.427e-05', 'epoch': '0.7161'} | |
| {'loss': '0.1645', 'grad_norm': '2.348', 'learning_rate': '1.426e-05', 'epoch': '0.7166'} | |
| {'loss': '0.1857', 'grad_norm': '0.9667', 'learning_rate': '1.425e-05', 'epoch': '0.7171'} | |
| {'loss': '0.1568', 'grad_norm': '2.257', 'learning_rate': '1.425e-05', 'epoch': '0.7175'} | |
| {'loss': '0.153', 'grad_norm': '1.935', 'learning_rate': '1.424e-05', 'epoch': '0.718'} | |
| {'loss': '0.1591', 'grad_norm': '3.037', 'learning_rate': '1.424e-05', 'epoch': '0.7185'} | |
| {'loss': '0.1749', 'grad_norm': '7.562', 'learning_rate': '1.423e-05', 'epoch': '0.719'} | |
| {'loss': '0.1707', 'grad_norm': '4.419', 'learning_rate': '1.423e-05', 'epoch': '0.7194'} | |
| {'loss': '0.1651', 'grad_norm': '0.7177', 'learning_rate': '1.422e-05', 'epoch': '0.7199'} | |
| {'loss': '0.1536', 'grad_norm': '1.969', 'learning_rate': '1.422e-05', 'epoch': '0.7204'} | |
| {'loss': '0.1745', 'grad_norm': '0.6826', 'learning_rate': '1.421e-05', 'epoch': '0.7209'} | |
| {'loss': '0.1625', 'grad_norm': '1.96', 'learning_rate': '1.421e-05', 'epoch': '0.7213'} | |
| {'loss': '0.1564', 'grad_norm': '0.4081', 'learning_rate': '1.42e-05', 'epoch': '0.7218'} | |
| {'loss': '0.1581', 'grad_norm': '0.9375', 'learning_rate': '1.42e-05', 'epoch': '0.7223'} | |
| {'loss': '0.2598', 'grad_norm': '5.644', 'learning_rate': '1.419e-05', 'epoch': '0.7228'} | |
| {'loss': '0.1591', 'grad_norm': '2.473', 'learning_rate': '1.419e-05', 'epoch': '0.7233'} | |
| {'loss': '0.1767', 'grad_norm': '1.276', 'learning_rate': '1.418e-05', 'epoch': '0.7237'} | |
| {'loss': '0.1557', 'grad_norm': '2.937', 'learning_rate': '1.418e-05', 'epoch': '0.7242'} | |
| {'loss': '0.1645', 'grad_norm': '6.802', 'learning_rate': '1.417e-05', 'epoch': '0.7247'} | |
| {'loss': '0.1741', 'grad_norm': '3.467', 'learning_rate': '1.416e-05', 'epoch': '0.7252'} | |
| {'loss': '0.1659', 'grad_norm': '4.741', 'learning_rate': '1.416e-05', 'epoch': '0.7256'} | |
| {'loss': '0.1647', 'grad_norm': '2.057', 'learning_rate': '1.415e-05', 'epoch': '0.7261'} | |
| {'loss': '0.138', 'grad_norm': '0.7675', 'learning_rate': '1.415e-05', 'epoch': '0.7266'} | |
| {'loss': '0.2759', 'grad_norm': '1.712', 'learning_rate': '1.414e-05', 'epoch': '0.7271'} | |
| {'loss': '0.1569', 'grad_norm': '5.997', 'learning_rate': '1.414e-05', 'epoch': '0.7275'} | |
| {'loss': '0.1589', 'grad_norm': '1.357', 'learning_rate': '1.413e-05', 'epoch': '0.728'} | |
| {'loss': '0.1528', 'grad_norm': '8.112', 'learning_rate': '1.413e-05', 'epoch': '0.7285'} | |
| {'loss': '0.1695', 'grad_norm': '5.649', 'learning_rate': '1.412e-05', 'epoch': '0.729'} | |
| {'loss': '0.1724', 'grad_norm': '3.803', 'learning_rate': '1.412e-05', 'epoch': '0.7294'} | |
| {'loss': '0.1479', 'grad_norm': '2.221', 'learning_rate': '1.411e-05', 'epoch': '0.7299'} | |
| {'loss': '0.1369', 'grad_norm': '0.4634', 'learning_rate': '1.411e-05', 'epoch': '0.7304'} | |
| {'loss': '0.1723', 'grad_norm': '4.332', 'learning_rate': '1.41e-05', 'epoch': '0.7309'} | |
| {'loss': '0.1675', 'grad_norm': '6.859', 'learning_rate': '1.41e-05', 'epoch': '0.7314'} | |
| {'loss': '0.1762', 'grad_norm': '4.568', 'learning_rate': '1.409e-05', 'epoch': '0.7318'} | |
| {'loss': '0.1661', 'grad_norm': '1.039', 'learning_rate': '1.409e-05', 'epoch': '0.7323'} | |
| {'loss': '0.2577', 'grad_norm': '3.028', 'learning_rate': '1.408e-05', 'epoch': '0.7328'} | |
| {'loss': '0.2649', 'grad_norm': '2.689', 'learning_rate': '1.407e-05', 'epoch': '0.7333'} | |
| {'loss': '0.2229', 'grad_norm': '1.835', 'learning_rate': '1.407e-05', 'epoch': '0.7337'} | |
| {'loss': '0.1662', 'grad_norm': '3.545', 'learning_rate': '1.406e-05', 'epoch': '0.7342'} | |
| {'loss': '0.1555', 'grad_norm': '4.182', 'learning_rate': '1.406e-05', 'epoch': '0.7347'} | |
| {'loss': '0.1641', 'grad_norm': '4.387', 'learning_rate': '1.405e-05', 'epoch': '0.7352'} | |
| {'loss': '0.1623', 'grad_norm': '6.804', 'learning_rate': '1.405e-05', 'epoch': '0.7356'} | |
| {'loss': '0.1426', 'grad_norm': '1.555', 'learning_rate': '1.404e-05', 'epoch': '0.7361'} | |
| {'loss': '0.1635', 'grad_norm': '1.752', 'learning_rate': '1.404e-05', 'epoch': '0.7366'} | |
| {'loss': '0.1738', 'grad_norm': '1.838', 'learning_rate': '1.403e-05', 'epoch': '0.7371'} | |
| {'loss': '0.2915', 'grad_norm': '3.093', 'learning_rate': '1.403e-05', 'epoch': '0.7375'} | |
| {'loss': '0.1552', 'grad_norm': '4.246', 'learning_rate': '1.402e-05', 'epoch': '0.738'} | |
| {'loss': '0.1406', 'grad_norm': '2.012', 'learning_rate': '1.402e-05', 'epoch': '0.7385'} | |
| {'loss': '0.1455', 'grad_norm': '6.15', 'learning_rate': '1.401e-05', 'epoch': '0.739'} | |
| {'loss': '0.1847', 'grad_norm': '1.905', 'learning_rate': '1.401e-05', 'epoch': '0.7395'} | |
| {'loss': '0.1658', 'grad_norm': '2.856', 'learning_rate': '1.4e-05', 'epoch': '0.7399'} | |
| {'loss': '0.1301', 'grad_norm': '15.26', 'learning_rate': '1.4e-05', 'epoch': '0.7404'} | |
| {'loss': '0.1481', 'grad_norm': '3.392', 'learning_rate': '1.399e-05', 'epoch': '0.7409'} | |
| {'loss': '0.1739', 'grad_norm': '3.924', 'learning_rate': '1.398e-05', 'epoch': '0.7414'} | |
| {'loss': '0.1669', 'grad_norm': '4.078', 'learning_rate': '1.398e-05', 'epoch': '0.7418'} | |
| {'loss': '0.1389', 'grad_norm': '0.4537', 'learning_rate': '1.397e-05', 'epoch': '0.7423'} | |
| {'loss': '0.1483', 'grad_norm': '0.9126', 'learning_rate': '1.397e-05', 'epoch': '0.7428'} | |
| {'loss': '0.1618', 'grad_norm': '2.128', 'learning_rate': '1.396e-05', 'epoch': '0.7433'} | |
| {'eval_ms_marco_loss': '0.05384', 'eval_val-ms-marco-768_cosine_accuracy': '0.997', 'eval_val-ms-marco-512_cosine_accuracy': '0.9973', 'eval_val-ms-marco-256_cosine_accuracy': '0.9967', 'eval_val-ms-marco-128_cosine_accuracy': '0.996', 'eval_val-ms-marco-64_cosine_accuracy': '0.997', 'eval_sequential_score': '0.997', 'eval_ms_marco_runtime': '33.98', 'eval_ms_marco_samples_per_second': '294.3', 'eval_ms_marco_steps_per_second': '9.211', 'epoch': '0.7433'} | |
| {'loss': '0.151', 'grad_norm': '4.784', 'learning_rate': '1.396e-05', 'epoch': '0.7437'} | |
| {'loss': '0.1792', 'grad_norm': '1.549', 'learning_rate': '1.395e-05', 'epoch': '0.7442'} | |
| {'loss': '0.1389', 'grad_norm': '2.731', 'learning_rate': '1.395e-05', 'epoch': '0.7447'} | |
| {'loss': '0.1455', 'grad_norm': '1.816', 'learning_rate': '1.394e-05', 'epoch': '0.7452'} | |
| {'loss': '0.1412', 'grad_norm': '5.256', 'learning_rate': '1.394e-05', 'epoch': '0.7456'} | |
| {'loss': '0.1627', 'grad_norm': '3.233', 'learning_rate': '1.393e-05', 'epoch': '0.7461'} | |
| {'loss': '0.1577', 'grad_norm': '7.629', 'learning_rate': '1.393e-05', 'epoch': '0.7466'} | |
| {'loss': '0.1387', 'grad_norm': '0.9993', 'learning_rate': '1.392e-05', 'epoch': '0.7471'} | |
| {'loss': '0.2982', 'grad_norm': '4.191', 'learning_rate': '1.392e-05', 'epoch': '0.7476'} | |
| {'loss': '0.1744', 'grad_norm': '3.02', 'learning_rate': '1.391e-05', 'epoch': '0.748'} | |
| {'loss': '0.1487', 'grad_norm': '5.211', 'learning_rate': '1.391e-05', 'epoch': '0.7485'} | |
| {'loss': '0.1603', 'grad_norm': '1.463', 'learning_rate': '1.39e-05', 'epoch': '0.749'} | |
| {'loss': '0.1713', 'grad_norm': '4.19', 'learning_rate': '1.389e-05', 'epoch': '0.7495'} | |
| {'loss': '0.1562', 'grad_norm': '7.81', 'learning_rate': '1.389e-05', 'epoch': '0.7499'} | |
| {'loss': '0.2621', 'grad_norm': '1.528', 'learning_rate': '1.388e-05', 'epoch': '0.7504'} | |
| {'loss': '0.1645', 'grad_norm': '2.486', 'learning_rate': '1.388e-05', 'epoch': '0.7509'} | |
| {'loss': '0.1447', 'grad_norm': '4.823', 'learning_rate': '1.387e-05', 'epoch': '0.7514'} | |
| {'loss': '0.1579', 'grad_norm': '2.097', 'learning_rate': '1.387e-05', 'epoch': '0.7518'} | |
| {'loss': '0.1442', 'grad_norm': '6.89', 'learning_rate': '1.386e-05', 'epoch': '0.7523'} | |
| {'loss': '0.2615', 'grad_norm': '1.596', 'learning_rate': '1.386e-05', 'epoch': '0.7528'} | |
| {'loss': '0.1628', 'grad_norm': '1.6', 'learning_rate': '1.385e-05', 'epoch': '0.7533'} | |
| {'loss': '0.2568', 'grad_norm': '1.192', 'learning_rate': '1.385e-05', 'epoch': '0.7537'} | |
| {'loss': '0.1339', 'grad_norm': '5.355', 'learning_rate': '1.384e-05', 'epoch': '0.7542'} | |
| {'loss': '0.1678', 'grad_norm': '7.837', 'learning_rate': '1.384e-05', 'epoch': '0.7547'} | |
| {'loss': '0.1604', 'grad_norm': '2.266', 'learning_rate': '1.383e-05', 'epoch': '0.7552'} | |
| {'loss': '0.1501', 'grad_norm': '1.532', 'learning_rate': '1.383e-05', 'epoch': '0.7557'} | |
| {'loss': '0.1324', 'grad_norm': '1.035', 'learning_rate': '1.382e-05', 'epoch': '0.7561'} | |
| {'loss': '0.1541', 'grad_norm': '1.149', 'learning_rate': '1.382e-05', 'epoch': '0.7566'} | |
| {'loss': '0.1716', 'grad_norm': '0.6527', 'learning_rate': '1.381e-05', 'epoch': '0.7571'} | |
| {'loss': '0.1692', 'grad_norm': '4.064', 'learning_rate': '1.38e-05', 'epoch': '0.7576'} | |
| {'loss': '0.1412', 'grad_norm': '1.221', 'learning_rate': '1.38e-05', 'epoch': '0.758'} | |
| {'loss': '0.1639', 'grad_norm': '9.066', 'learning_rate': '1.379e-05', 'epoch': '0.7585'} | |
| {'loss': '0.1456', 'grad_norm': '0.4473', 'learning_rate': '1.379e-05', 'epoch': '0.759'} | |
| {'loss': '0.1483', 'grad_norm': '1.056', 'learning_rate': '1.378e-05', 'epoch': '0.7595'} | |
| {'loss': '0.1524', 'grad_norm': '2.036', 'learning_rate': '1.378e-05', 'epoch': '0.7599'} | |
| {'loss': '0.2883', 'grad_norm': '2.678', 'learning_rate': '1.377e-05', 'epoch': '0.7604'} | |
| {'loss': '0.1673', 'grad_norm': '3.841', 'learning_rate': '1.377e-05', 'epoch': '0.7609'} | |
| {'loss': '0.1469', 'grad_norm': '4.699', 'learning_rate': '1.376e-05', 'epoch': '0.7614'} | |
| {'loss': '0.1515', 'grad_norm': '5.48', 'learning_rate': '1.376e-05', 'epoch': '0.7618'} | |
| {'loss': '0.1422', 'grad_norm': '3.553', 'learning_rate': '1.375e-05', 'epoch': '0.7623'} | |
| {'loss': '0.2486', 'grad_norm': '2.166', 'learning_rate': '1.375e-05', 'epoch': '0.7628'} | |
| {'loss': '0.1419', 'grad_norm': '5.254', 'learning_rate': '1.374e-05', 'epoch': '0.7633'} | |
| {'loss': '0.1299', 'grad_norm': '0.6157', 'learning_rate': '1.374e-05', 'epoch': '0.7637'} | |
| {'loss': '0.1497', 'grad_norm': '1.059', 'learning_rate': '1.373e-05', 'epoch': '0.7642'} | |
| {'loss': '0.1589', 'grad_norm': '3.854', 'learning_rate': '1.373e-05', 'epoch': '0.7647'} | |
| {'loss': '0.1609', 'grad_norm': '2.391', 'learning_rate': '1.372e-05', 'epoch': '0.7652'} | |
| {'loss': '0.1352', 'grad_norm': '2.528', 'learning_rate': '1.371e-05', 'epoch': '0.7657'} | |
| {'loss': '0.1631', 'grad_norm': '7.935', 'learning_rate': '1.371e-05', 'epoch': '0.7661'} | |
| {'loss': '0.1421', 'grad_norm': '3.291', 'learning_rate': '1.37e-05', 'epoch': '0.7666'} | |
| {'loss': '0.1578', 'grad_norm': '3.157', 'learning_rate': '1.37e-05', 'epoch': '0.7671'} | |
| {'loss': '0.1424', 'grad_norm': '2.472', 'learning_rate': '1.369e-05', 'epoch': '0.7676'} | |
| {'loss': '0.1563', 'grad_norm': '5.108', 'learning_rate': '1.369e-05', 'epoch': '0.768'} | |
| {'loss': '0.1433', 'grad_norm': '2.563', 'learning_rate': '1.368e-05', 'epoch': '0.7685'} | |
| {'loss': '0.1337', 'grad_norm': '0.9748', 'learning_rate': '1.368e-05', 'epoch': '0.769'} | |
| {'loss': '0.1413', 'grad_norm': '5.862', 'learning_rate': '1.367e-05', 'epoch': '0.7695'} | |
| {'loss': '0.1617', 'grad_norm': '3.685', 'learning_rate': '1.367e-05', 'epoch': '0.7699'} | |
| {'loss': '0.1508', 'grad_norm': '3.63', 'learning_rate': '1.366e-05', 'epoch': '0.7704'} | |
| {'loss': '0.1538', 'grad_norm': '3.909', 'learning_rate': '1.366e-05', 'epoch': '0.7709'} | |
| {'loss': '0.1483', 'grad_norm': '1.694', 'learning_rate': '1.365e-05', 'epoch': '0.7714'} | |
| {'loss': '0.16', 'grad_norm': '2.468', 'learning_rate': '1.365e-05', 'epoch': '0.7718'} | |
| {'eval_ms_marco_loss': '0.0458', 'eval_val-ms-marco-768_cosine_accuracy': '0.9983', 'eval_val-ms-marco-512_cosine_accuracy': '0.9983', 'eval_val-ms-marco-256_cosine_accuracy': '0.9987', 'eval_val-ms-marco-128_cosine_accuracy': '0.9983', 'eval_val-ms-marco-64_cosine_accuracy': '0.998', 'eval_sequential_score': '0.9983', 'eval_ms_marco_runtime': '33.93', 'eval_ms_marco_samples_per_second': '294.7', 'eval_ms_marco_steps_per_second': '9.224', 'epoch': '0.7718'} | |
| {'loss': '0.1525', 'grad_norm': '5.885', 'learning_rate': '1.364e-05', 'epoch': '0.7723'} | |
| {'loss': '0.1282', 'grad_norm': '4.456', 'learning_rate': '1.364e-05', 'epoch': '0.7728'} | |
| {'loss': '0.1504', 'grad_norm': '2.655', 'learning_rate': '1.363e-05', 'epoch': '0.7733'} | |
| {'loss': '0.1264', 'grad_norm': '2.73', 'learning_rate': '1.362e-05', 'epoch': '0.7738'} | |
| {'loss': '0.1428', 'grad_norm': '2.73', 'learning_rate': '1.362e-05', 'epoch': '0.7742'} | |
| {'loss': '0.158', 'grad_norm': '8.461', 'learning_rate': '1.361e-05', 'epoch': '0.7747'} | |
| {'loss': '0.1666', 'grad_norm': '8.194', 'learning_rate': '1.361e-05', 'epoch': '0.7752'} | |
| {'loss': '0.1627', 'grad_norm': '1.136', 'learning_rate': '1.36e-05', 'epoch': '0.7757'} | |
| {'loss': '0.246', 'grad_norm': '1.187', 'learning_rate': '1.36e-05', 'epoch': '0.7761'} | |
| {'loss': '0.1586', 'grad_norm': '4.798', 'learning_rate': '1.359e-05', 'epoch': '0.7766'} | |
| {'loss': '0.1622', 'grad_norm': '7.506', 'learning_rate': '1.359e-05', 'epoch': '0.7771'} | |
| {'loss': '0.148', 'grad_norm': '0.5114', 'learning_rate': '1.358e-05', 'epoch': '0.7776'} | |
| {'loss': '0.1562', 'grad_norm': '1.424', 'learning_rate': '1.358e-05', 'epoch': '0.778'} | |
| {'loss': '0.1564', 'grad_norm': '2.124', 'learning_rate': '1.357e-05', 'epoch': '0.7785'} | |
| {'loss': '0.1512', 'grad_norm': '1.428', 'learning_rate': '1.357e-05', 'epoch': '0.779'} | |
| {'loss': '0.1428', 'grad_norm': '4.621', 'learning_rate': '1.356e-05', 'epoch': '0.7795'} | |
| {'loss': '0.1579', 'grad_norm': '3.52', 'learning_rate': '1.356e-05', 'epoch': '0.7799'} | |
| {'loss': '0.1401', 'grad_norm': '0.5217', 'learning_rate': '1.355e-05', 'epoch': '0.7804'} | |
| {'loss': '0.1147', 'grad_norm': '0.8174', 'learning_rate': '1.355e-05', 'epoch': '0.7809'} | |
| {'loss': '0.1391', 'grad_norm': '0.5512', 'learning_rate': '1.354e-05', 'epoch': '0.7814'} | |
| {'loss': '0.263', 'grad_norm': '4.143', 'learning_rate': '1.353e-05', 'epoch': '0.7819'} | |
| {'loss': '0.162', 'grad_norm': '5.433', 'learning_rate': '1.353e-05', 'epoch': '0.7823'} | |
| {'loss': '0.1442', 'grad_norm': '0.5708', 'learning_rate': '1.352e-05', 'epoch': '0.7828'} | |
| {'loss': '0.2707', 'grad_norm': '5.05', 'learning_rate': '1.352e-05', 'epoch': '0.7833'} | |
| {'loss': '0.1497', 'grad_norm': '1.609', 'learning_rate': '1.351e-05', 'epoch': '0.7838'} | |
| {'loss': '0.1313', 'grad_norm': '2.969', 'learning_rate': '1.351e-05', 'epoch': '0.7842'} | |
| {'loss': '0.1509', 'grad_norm': '1.642', 'learning_rate': '1.35e-05', 'epoch': '0.7847'} | |
| {'loss': '0.1503', 'grad_norm': '3.763', 'learning_rate': '1.35e-05', 'epoch': '0.7852'} | |
| {'loss': '0.1419', 'grad_norm': '2.847', 'learning_rate': '1.349e-05', 'epoch': '0.7857'} | |
| {'loss': '0.1597', 'grad_norm': '7.738', 'learning_rate': '1.349e-05', 'epoch': '0.7861'} | |
| {'loss': '0.1418', 'grad_norm': '2.217', 'learning_rate': '1.348e-05', 'epoch': '0.7866'} | |
| {'loss': '0.1407', 'grad_norm': '1.603', 'learning_rate': '1.348e-05', 'epoch': '0.7871'} | |
| {'loss': '0.2604', 'grad_norm': '0.7271', 'learning_rate': '1.347e-05', 'epoch': '0.7876'} | |
| {'loss': '0.1299', 'grad_norm': '4.028', 'learning_rate': '1.347e-05', 'epoch': '0.788'} | |
| {'loss': '0.1495', 'grad_norm': '4.617', 'learning_rate': '1.346e-05', 'epoch': '0.7885'} | |
| {'loss': '0.2315', 'grad_norm': '1.234', 'learning_rate': '1.346e-05', 'epoch': '0.789'} | |
| {'loss': '0.1689', 'grad_norm': '2.33', 'learning_rate': '1.345e-05', 'epoch': '0.7895'} | |
| {'loss': '0.1784', 'grad_norm': '1.927', 'learning_rate': '1.344e-05', 'epoch': '0.79'} | |
| {'loss': '0.1492', 'grad_norm': '7.694', 'learning_rate': '1.344e-05', 'epoch': '0.7904'} | |
| {'loss': '0.233', 'grad_norm': '5.265', 'learning_rate': '1.343e-05', 'epoch': '0.7909'} | |
| {'loss': '0.1403', 'grad_norm': '0.6057', 'learning_rate': '1.343e-05', 'epoch': '0.7914'} | |
| {'loss': '0.1539', 'grad_norm': '2.322', 'learning_rate': '1.342e-05', 'epoch': '0.7919'} | |
| {'loss': '0.1548', 'grad_norm': '5.671', 'learning_rate': '1.342e-05', 'epoch': '0.7923'} | |
| {'loss': '0.1413', 'grad_norm': '3.294', 'learning_rate': '1.341e-05', 'epoch': '0.7928'} | |
| {'loss': '0.1462', 'grad_norm': '0.9124', 'learning_rate': '1.341e-05', 'epoch': '0.7933'} | |
| {'loss': '0.169', 'grad_norm': '4.171', 'learning_rate': '1.34e-05', 'epoch': '0.7938'} | |
| {'loss': '0.1347', 'grad_norm': '3.973', 'learning_rate': '1.34e-05', 'epoch': '0.7942'} | |
| {'loss': '0.2894', 'grad_norm': '0.7139', 'learning_rate': '1.339e-05', 'epoch': '0.7947'} | |
| {'loss': '0.2282', 'grad_norm': '4.101', 'learning_rate': '1.339e-05', 'epoch': '0.7952'} | |
| {'loss': '0.2692', 'grad_norm': '2.802', 'learning_rate': '1.338e-05', 'epoch': '0.7957'} | |
| {'loss': '0.1491', 'grad_norm': '0.8161', 'learning_rate': '1.338e-05', 'epoch': '0.7961'} | |
| {'loss': '0.1433', 'grad_norm': '5.063', 'learning_rate': '1.337e-05', 'epoch': '0.7966'} | |
| {'loss': '0.1504', 'grad_norm': '6.401', 'learning_rate': '1.337e-05', 'epoch': '0.7971'} | |
| {'loss': '0.1323', 'grad_norm': '7.375', 'learning_rate': '1.336e-05', 'epoch': '0.7976'} | |
| {'loss': '0.162', 'grad_norm': '5.665', 'learning_rate': '1.335e-05', 'epoch': '0.7981'} | |
| {'loss': '0.1481', 'grad_norm': '3.427', 'learning_rate': '1.335e-05', 'epoch': '0.7985'} | |
| {'loss': '0.1556', 'grad_norm': '2.353', 'learning_rate': '1.334e-05', 'epoch': '0.799'} | |
| {'loss': '0.1275', 'grad_norm': '1.895', 'learning_rate': '1.334e-05', 'epoch': '0.7995'} | |
| {'loss': '0.1549', 'grad_norm': '0.278', 'learning_rate': '1.333e-05', 'epoch': '0.8'} | |
| {'loss': '0.2422', 'grad_norm': '2.024', 'learning_rate': '1.333e-05', 'epoch': '0.8004'} | |
| {'eval_ms_marco_loss': '0.04606', 'eval_val-ms-marco-768_cosine_accuracy': '0.9977', 'eval_val-ms-marco-512_cosine_accuracy': '0.9977', 'eval_val-ms-marco-256_cosine_accuracy': '0.9977', 'eval_val-ms-marco-128_cosine_accuracy': '0.9973', 'eval_val-ms-marco-64_cosine_accuracy': '0.997', 'eval_sequential_score': '0.9977', 'eval_ms_marco_runtime': '33.98', 'eval_ms_marco_samples_per_second': '294.2', 'eval_ms_marco_steps_per_second': '9.21', 'epoch': '0.8004'} | |
| {'loss': '0.1466', 'grad_norm': '0.9063', 'learning_rate': '1.332e-05', 'epoch': '0.8009'} | |
| {'loss': '0.1279', 'grad_norm': '0.2147', 'learning_rate': '1.332e-05', 'epoch': '0.8014'} | |
| {'loss': '0.1532', 'grad_norm': '2.82', 'learning_rate': '1.331e-05', 'epoch': '0.8019'} | |
| {'loss': '0.1532', 'grad_norm': '6.361', 'learning_rate': '1.331e-05', 'epoch': '0.8023'} | |
| {'loss': '0.3616', 'grad_norm': '0.8726', 'learning_rate': '1.33e-05', 'epoch': '0.8028'} | |
| {'loss': '0.1599', 'grad_norm': '4.154', 'learning_rate': '1.33e-05', 'epoch': '0.8033'} | |
| {'loss': '0.172', 'grad_norm': '1.964', 'learning_rate': '1.329e-05', 'epoch': '0.8038'} | |
| {'loss': '0.1614', 'grad_norm': '0.1362', 'learning_rate': '1.329e-05', 'epoch': '0.8042'} | |
| {'loss': '0.1389', 'grad_norm': '6.641', 'learning_rate': '1.328e-05', 'epoch': '0.8047'} | |
| {'loss': '0.1628', 'grad_norm': '7.109', 'learning_rate': '1.328e-05', 'epoch': '0.8052'} | |
| {'loss': '0.2644', 'grad_norm': '8.434', 'learning_rate': '1.327e-05', 'epoch': '0.8057'} | |
| {'loss': '0.2577', 'grad_norm': '2.749', 'learning_rate': '1.326e-05', 'epoch': '0.8062'} | |
| {'loss': '0.158', 'grad_norm': '0.7221', 'learning_rate': '1.326e-05', 'epoch': '0.8066'} | |
| {'loss': '0.1432', 'grad_norm': '1.892', 'learning_rate': '1.325e-05', 'epoch': '0.8071'} | |
| {'loss': '0.1426', 'grad_norm': '2.263', 'learning_rate': '1.325e-05', 'epoch': '0.8076'} | |
| {'loss': '0.1368', 'grad_norm': '1.333', 'learning_rate': '1.324e-05', 'epoch': '0.8081'} | |
| {'loss': '0.1721', 'grad_norm': '2.31', 'learning_rate': '1.324e-05', 'epoch': '0.8085'} | |
| {'loss': '0.129', 'grad_norm': '4.279', 'learning_rate': '1.323e-05', 'epoch': '0.809'} | |
| {'loss': '0.1505', 'grad_norm': '3.152', 'learning_rate': '1.323e-05', 'epoch': '0.8095'} | |
| {'loss': '0.145', 'grad_norm': '4.296', 'learning_rate': '1.322e-05', 'epoch': '0.81'} | |
| {'loss': '0.1512', 'grad_norm': '0.784', 'learning_rate': '1.322e-05', 'epoch': '0.8104'} | |
| {'loss': '0.1658', 'grad_norm': '2.511', 'learning_rate': '1.321e-05', 'epoch': '0.8109'} | |
| {'loss': '0.137', 'grad_norm': '0.7395', 'learning_rate': '1.321e-05', 'epoch': '0.8114'} | |
| {'loss': '0.1452', 'grad_norm': '3.344', 'learning_rate': '1.32e-05', 'epoch': '0.8119'} | |
| {'loss': '0.1478', 'grad_norm': '0.8738', 'learning_rate': '1.32e-05', 'epoch': '0.8123'} | |
| {'loss': '0.1548', 'grad_norm': '0.8814', 'learning_rate': '1.319e-05', 'epoch': '0.8128'} | |
| {'loss': '0.1353', 'grad_norm': '1.075', 'learning_rate': '1.319e-05', 'epoch': '0.8133'} | |
| {'loss': '0.142', 'grad_norm': '1.256', 'learning_rate': '1.318e-05', 'epoch': '0.8138'} | |
| {'loss': '0.2618', 'grad_norm': '3.725', 'learning_rate': '1.318e-05', 'epoch': '0.8143'} | |
| {'loss': '0.1554', 'grad_norm': '2.028', 'learning_rate': '1.317e-05', 'epoch': '0.8147'} | |
| {'loss': '0.1605', 'grad_norm': '7.145', 'learning_rate': '1.316e-05', 'epoch': '0.8152'} | |
| {'loss': '0.1408', 'grad_norm': '1.752', 'learning_rate': '1.316e-05', 'epoch': '0.8157'} | |
| {'loss': '0.1328', 'grad_norm': '0.9129', 'learning_rate': '1.315e-05', 'epoch': '0.8162'} | |
| {'loss': '0.1673', 'grad_norm': '0.2318', 'learning_rate': '1.315e-05', 'epoch': '0.8166'} | |
| {'loss': '0.1458', 'grad_norm': '5.311', 'learning_rate': '1.314e-05', 'epoch': '0.8171'} | |
| {'loss': '0.1273', 'grad_norm': '7.68', 'learning_rate': '1.314e-05', 'epoch': '0.8176'} | |
| {'loss': '0.1399', 'grad_norm': '1.364', 'learning_rate': '1.313e-05', 'epoch': '0.8181'} | |
| {'loss': '0.1432', 'grad_norm': '1.229', 'learning_rate': '1.313e-05', 'epoch': '0.8185'} | |
| {'loss': '0.4004', 'grad_norm': '3.104', 'learning_rate': '1.312e-05', 'epoch': '0.819'} | |
| {'loss': '0.1473', 'grad_norm': '0.1727', 'learning_rate': '1.312e-05', 'epoch': '0.8195'} | |
| {'loss': '0.1409', 'grad_norm': '1.011', 'learning_rate': '1.311e-05', 'epoch': '0.82'} | |
| {'loss': '0.1606', 'grad_norm': '3.049', 'learning_rate': '1.311e-05', 'epoch': '0.8204'} | |
| {'loss': '0.1364', 'grad_norm': '6.173', 'learning_rate': '1.31e-05', 'epoch': '0.8209'} | |
| {'loss': '0.1518', 'grad_norm': '1.855', 'learning_rate': '1.31e-05', 'epoch': '0.8214'} | |
| {'loss': '0.1389', 'grad_norm': '0.4136', 'learning_rate': '1.309e-05', 'epoch': '0.8219'} | |
| {'loss': '0.142', 'grad_norm': '0.3789', 'learning_rate': '1.309e-05', 'epoch': '0.8224'} | |
| {'loss': '0.1494', 'grad_norm': '1.817', 'learning_rate': '1.308e-05', 'epoch': '0.8228'} | |
| {'loss': '0.1532', 'grad_norm': '9.075', 'learning_rate': '1.307e-05', 'epoch': '0.8233'} | |
| {'loss': '0.1382', 'grad_norm': '2.388', 'learning_rate': '1.307e-05', 'epoch': '0.8238'} | |
| {'loss': '0.1376', 'grad_norm': '2.215', 'learning_rate': '1.306e-05', 'epoch': '0.8243'} | |
| {'loss': '0.1362', 'grad_norm': '3.267', 'learning_rate': '1.306e-05', 'epoch': '0.8247'} | |
| {'loss': '0.1333', 'grad_norm': '4.605', 'learning_rate': '1.305e-05', 'epoch': '0.8252'} | |
| {'loss': '0.1542', 'grad_norm': '0.7239', 'learning_rate': '1.305e-05', 'epoch': '0.8257'} | |
| {'loss': '0.1652', 'grad_norm': '3.517', 'learning_rate': '1.304e-05', 'epoch': '0.8262'} | |
| {'loss': '0.1556', 'grad_norm': '0.5823', 'learning_rate': '1.304e-05', 'epoch': '0.8266'} | |
| {'loss': '0.1478', 'grad_norm': '6.29', 'learning_rate': '1.303e-05', 'epoch': '0.8271'} | |
| {'loss': '0.1562', 'grad_norm': '4.818', 'learning_rate': '1.303e-05', 'epoch': '0.8276'} | |
| {'loss': '0.1511', 'grad_norm': '2.538', 'learning_rate': '1.302e-05', 'epoch': '0.8281'} | |
| {'loss': '0.1326', 'grad_norm': '2.092', 'learning_rate': '1.302e-05', 'epoch': '0.8285'} | |
| {'loss': '0.1534', 'grad_norm': '2.609', 'learning_rate': '1.301e-05', 'epoch': '0.829'} | |
| {'eval_ms_marco_loss': '0.04569', 'eval_val-ms-marco-768_cosine_accuracy': '0.9977', 'eval_val-ms-marco-512_cosine_accuracy': '0.9977', 'eval_val-ms-marco-256_cosine_accuracy': '0.9977', 'eval_val-ms-marco-128_cosine_accuracy': '0.9977', 'eval_val-ms-marco-64_cosine_accuracy': '0.9967', 'eval_sequential_score': '0.9977', 'eval_ms_marco_runtime': '33.88', 'eval_ms_marco_samples_per_second': '295.2', 'eval_ms_marco_steps_per_second': '9.24', 'epoch': '0.829'} | |
| {'loss': '0.1247', 'grad_norm': '5.214', 'learning_rate': '1.301e-05', 'epoch': '0.8295'} | |
| {'loss': '0.1519', 'grad_norm': '5', 'learning_rate': '1.3e-05', 'epoch': '0.83'} | |
| {'loss': '0.2578', 'grad_norm': '1.26', 'learning_rate': '1.3e-05', 'epoch': '0.8305'} | |
| {'loss': '0.2523', 'grad_norm': '1.899', 'learning_rate': '1.299e-05', 'epoch': '0.8309'} | |
| {'loss': '0.1565', 'grad_norm': '6.589', 'learning_rate': '1.298e-05', 'epoch': '0.8314'} | |
| {'loss': '0.1541', 'grad_norm': '4.05', 'learning_rate': '1.298e-05', 'epoch': '0.8319'} | |
| {'loss': '0.1449', 'grad_norm': '3.063', 'learning_rate': '1.297e-05', 'epoch': '0.8324'} | |
| {'loss': '0.1335', 'grad_norm': '7.163', 'learning_rate': '1.297e-05', 'epoch': '0.8328'} | |
| {'loss': '0.2147', 'grad_norm': '2.877', 'learning_rate': '1.296e-05', 'epoch': '0.8333'} | |
| {'loss': '0.1286', 'grad_norm': '3.681', 'learning_rate': '1.296e-05', 'epoch': '0.8338'} | |
| {'loss': '0.145', 'grad_norm': '4.605', 'learning_rate': '1.295e-05', 'epoch': '0.8343'} | |
| {'loss': '0.2317', 'grad_norm': '2.144', 'learning_rate': '1.295e-05', 'epoch': '0.8347'} | |
| {'loss': '0.1587', 'grad_norm': '0.4492', 'learning_rate': '1.294e-05', 'epoch': '0.8352'} | |
| {'loss': '0.1255', 'grad_norm': '1.251', 'learning_rate': '1.294e-05', 'epoch': '0.8357'} | |
| {'loss': '0.1571', 'grad_norm': '4.122', 'learning_rate': '1.293e-05', 'epoch': '0.8362'} | |
| {'loss': '0.1374', 'grad_norm': '4.301', 'learning_rate': '1.293e-05', 'epoch': '0.8366'} | |
| {'loss': '0.1549', 'grad_norm': '0.2745', 'learning_rate': '1.292e-05', 'epoch': '0.8371'} | |
| {'loss': '0.142', 'grad_norm': '5.049', 'learning_rate': '1.292e-05', 'epoch': '0.8376'} | |
| {'loss': '0.1668', 'grad_norm': '5.081', 'learning_rate': '1.291e-05', 'epoch': '0.8381'} | |
| {'loss': '0.233', 'grad_norm': '5.425', 'learning_rate': '1.291e-05', 'epoch': '0.8386'} | |
| {'loss': '0.1433', 'grad_norm': '3.987', 'learning_rate': '1.29e-05', 'epoch': '0.839'} | |
| {'loss': '0.1277', 'grad_norm': '0.7348', 'learning_rate': '1.289e-05', 'epoch': '0.8395'} | |
| {'loss': '0.1391', 'grad_norm': '2.092', 'learning_rate': '1.289e-05', 'epoch': '0.84'} | |
| {'loss': '0.1163', 'grad_norm': '1.277', 'learning_rate': '1.288e-05', 'epoch': '0.8405'} | |
| {'loss': '0.1267', 'grad_norm': '1.662', 'learning_rate': '1.288e-05', 'epoch': '0.8409'} | |
| {'loss': '0.1373', 'grad_norm': '1.701', 'learning_rate': '1.287e-05', 'epoch': '0.8414'} | |
| {'loss': '0.1494', 'grad_norm': '7.527', 'learning_rate': '1.287e-05', 'epoch': '0.8419'} | |
| {'loss': '0.262', 'grad_norm': '1.581', 'learning_rate': '1.286e-05', 'epoch': '0.8424'} | |
| {'loss': '0.2218', 'grad_norm': '2.32', 'learning_rate': '1.286e-05', 'epoch': '0.8428'} | |
| {'loss': '0.1365', 'grad_norm': '6.645', 'learning_rate': '1.285e-05', 'epoch': '0.8433'} | |
| {'loss': '0.1447', 'grad_norm': '0.7617', 'learning_rate': '1.285e-05', 'epoch': '0.8438'} | |
| {'loss': '0.1579', 'grad_norm': '7.202', 'learning_rate': '1.284e-05', 'epoch': '0.8443'} | |
| {'loss': '0.153', 'grad_norm': '7.064', 'learning_rate': '1.284e-05', 'epoch': '0.8447'} | |
| {'loss': '0.152', 'grad_norm': '4.651', 'learning_rate': '1.283e-05', 'epoch': '0.8452'} | |
| {'loss': '0.1569', 'grad_norm': '0.8587', 'learning_rate': '1.283e-05', 'epoch': '0.8457'} | |
| {'loss': '0.1377', 'grad_norm': '1.543', 'learning_rate': '1.282e-05', 'epoch': '0.8462'} | |
| {'loss': '0.1511', 'grad_norm': '6.429', 'learning_rate': '1.282e-05', 'epoch': '0.8467'} | |
| {'loss': '0.1546', 'grad_norm': '1.226', 'learning_rate': '1.281e-05', 'epoch': '0.8471'} | |
| {'loss': '0.1396', 'grad_norm': '1.632', 'learning_rate': '1.28e-05', 'epoch': '0.8476'} | |
| {'loss': '0.1485', 'grad_norm': '2.386', 'learning_rate': '1.28e-05', 'epoch': '0.8481'} | |
| {'loss': '0.1354', 'grad_norm': '1.496', 'learning_rate': '1.279e-05', 'epoch': '0.8486'} | |
| {'loss': '0.1429', 'grad_norm': '2.683', 'learning_rate': '1.279e-05', 'epoch': '0.849'} | |
| {'loss': '0.1335', 'grad_norm': '1.597', 'learning_rate': '1.278e-05', 'epoch': '0.8495'} | |
| {'loss': '0.1564', 'grad_norm': '3.203', 'learning_rate': '1.278e-05', 'epoch': '0.85'} | |
| {'loss': '0.1545', 'grad_norm': '0.4051', 'learning_rate': '1.277e-05', 'epoch': '0.8505'} | |
| {'loss': '0.2815', 'grad_norm': '0.4841', 'learning_rate': '1.277e-05', 'epoch': '0.8509'} | |
| {'loss': '0.1477', 'grad_norm': '1.882', 'learning_rate': '1.276e-05', 'epoch': '0.8514'} | |
| {'loss': '0.1316', 'grad_norm': '1.659', 'learning_rate': '1.276e-05', 'epoch': '0.8519'} | |
| {'loss': '0.1448', 'grad_norm': '5.961', 'learning_rate': '1.275e-05', 'epoch': '0.8524'} | |
| {'loss': '0.1399', 'grad_norm': '2.394', 'learning_rate': '1.275e-05', 'epoch': '0.8528'} | |
| {'loss': '0.1245', 'grad_norm': '1.711', 'learning_rate': '1.274e-05', 'epoch': '0.8533'} | |
| {'loss': '0.138', 'grad_norm': '2.563', 'learning_rate': '1.274e-05', 'epoch': '0.8538'} | |
| {'loss': '0.2935', 'grad_norm': '1.954', 'learning_rate': '1.273e-05', 'epoch': '0.8543'} | |
| {'loss': '0.2597', 'grad_norm': '1.44', 'learning_rate': '1.273e-05', 'epoch': '0.8548'} | |
| {'loss': '0.1289', 'grad_norm': '1.047', 'learning_rate': '1.272e-05', 'epoch': '0.8552'} | |
| {'loss': '0.1434', 'grad_norm': '2.229', 'learning_rate': '1.271e-05', 'epoch': '0.8557'} | |
| {'loss': '0.1537', 'grad_norm': '3.11', 'learning_rate': '1.271e-05', 'epoch': '0.8562'} | |
| {'loss': '0.1566', 'grad_norm': '3.167', 'learning_rate': '1.27e-05', 'epoch': '0.8567'} | |
| {'loss': '0.457', 'grad_norm': '0.9147', 'learning_rate': '1.27e-05', 'epoch': '0.8571'} | |
| {'loss': '0.1239', 'grad_norm': '4.788', 'learning_rate': '1.269e-05', 'epoch': '0.8576'} | |
| {'eval_ms_marco_loss': '0.0404', 'eval_val-ms-marco-768_cosine_accuracy': '0.9983', 'eval_val-ms-marco-512_cosine_accuracy': '0.9987', 'eval_val-ms-marco-256_cosine_accuracy': '0.9983', 'eval_val-ms-marco-128_cosine_accuracy': '0.9987', 'eval_val-ms-marco-64_cosine_accuracy': '0.998', 'eval_sequential_score': '0.9983', 'eval_ms_marco_runtime': '33.96', 'eval_ms_marco_samples_per_second': '294.5', 'eval_ms_marco_steps_per_second': '9.217', 'epoch': '0.8576'} | |
| {'loss': '0.1274', 'grad_norm': '0.8463', 'learning_rate': '1.269e-05', 'epoch': '0.8581'} | |
| {'loss': '0.2503', 'grad_norm': '5.306', 'learning_rate': '1.268e-05', 'epoch': '0.8586'} | |
| {'loss': '0.1528', 'grad_norm': '0.3876', 'learning_rate': '1.268e-05', 'epoch': '0.859'} | |
| {'loss': '0.1319', 'grad_norm': '3.909', 'learning_rate': '1.267e-05', 'epoch': '0.8595'} | |
| {'loss': '0.143', 'grad_norm': '5.271', 'learning_rate': '1.267e-05', 'epoch': '0.86'} | |
| {'loss': '0.2747', 'grad_norm': '4.795', 'learning_rate': '1.266e-05', 'epoch': '0.8605'} | |
| {'loss': '0.1268', 'grad_norm': '11', 'learning_rate': '1.266e-05', 'epoch': '0.8609'} | |
| {'loss': '0.2561', 'grad_norm': '1.48', 'learning_rate': '1.265e-05', 'epoch': '0.8614'} | |
| {'loss': '0.1341', 'grad_norm': '1.487', 'learning_rate': '1.265e-05', 'epoch': '0.8619'} | |
| {'loss': '0.1377', 'grad_norm': '4.498', 'learning_rate': '1.264e-05', 'epoch': '0.8624'} | |
| {'loss': '0.1182', 'grad_norm': '4.883', 'learning_rate': '1.264e-05', 'epoch': '0.8629'} | |
| {'loss': '0.1316', 'grad_norm': '4.985', 'learning_rate': '1.263e-05', 'epoch': '0.8633'} | |
| {'loss': '0.1462', 'grad_norm': '5.103', 'learning_rate': '1.262e-05', 'epoch': '0.8638'} | |
| {'loss': '0.1582', 'grad_norm': '5.288', 'learning_rate': '1.262e-05', 'epoch': '0.8643'} | |
| {'loss': '0.141', 'grad_norm': '3.95', 'learning_rate': '1.261e-05', 'epoch': '0.8648'} | |
| {'loss': '0.1198', 'grad_norm': '2.403', 'learning_rate': '1.261e-05', 'epoch': '0.8652'} | |
| {'loss': '0.1352', 'grad_norm': '6.108', 'learning_rate': '1.26e-05', 'epoch': '0.8657'} | |
| {'loss': '0.1512', 'grad_norm': '6.255', 'learning_rate': '1.26e-05', 'epoch': '0.8662'} | |
| {'loss': '0.1348', 'grad_norm': '1.989', 'learning_rate': '1.259e-05', 'epoch': '0.8667'} | |
| {'loss': '0.1412', 'grad_norm': '0.544', 'learning_rate': '1.259e-05', 'epoch': '0.8671'} | |
| {'loss': '0.1306', 'grad_norm': '0.6642', 'learning_rate': '1.258e-05', 'epoch': '0.8676'} | |
| {'loss': '0.1442', 'grad_norm': '4.831', 'learning_rate': '1.258e-05', 'epoch': '0.8681'} | |
| {'loss': '0.1334', 'grad_norm': '3.741', 'learning_rate': '1.257e-05', 'epoch': '0.8686'} | |
| {'loss': '0.1464', 'grad_norm': '2.099', 'learning_rate': '1.257e-05', 'epoch': '0.869'} | |
| {'loss': '0.1329', 'grad_norm': '1.3', 'learning_rate': '1.256e-05', 'epoch': '0.8695'} | |
| {'loss': '0.1502', 'grad_norm': '6.23', 'learning_rate': '1.256e-05', 'epoch': '0.87'} | |
| {'loss': '0.1467', 'grad_norm': '0.5691', 'learning_rate': '1.255e-05', 'epoch': '0.8705'} | |
| {'loss': '0.136', 'grad_norm': '4.885', 'learning_rate': '1.255e-05', 'epoch': '0.871'} | |
| {'loss': '0.1503', 'grad_norm': '1.109', 'learning_rate': '1.254e-05', 'epoch': '0.8714'} | |
| {'loss': '0.1311', 'grad_norm': '3.812', 'learning_rate': '1.253e-05', 'epoch': '0.8719'} | |
| {'loss': '0.1219', 'grad_norm': '1.274', 'learning_rate': '1.253e-05', 'epoch': '0.8724'} | |
| {'loss': '0.2302', 'grad_norm': '5.29', 'learning_rate': '1.252e-05', 'epoch': '0.8729'} | |
| {'loss': '0.3116', 'grad_norm': '1.706', 'learning_rate': '1.252e-05', 'epoch': '0.8733'} | |
| {'loss': '0.1291', 'grad_norm': '3.969', 'learning_rate': '1.251e-05', 'epoch': '0.8738'} | |
| {'loss': '0.1367', 'grad_norm': '0.3786', 'learning_rate': '1.251e-05', 'epoch': '0.8743'} | |
| {'loss': '0.1564', 'grad_norm': '1.108', 'learning_rate': '1.25e-05', 'epoch': '0.8748'} | |
| {'loss': '0.1358', 'grad_norm': '2.587', 'learning_rate': '1.25e-05', 'epoch': '0.8752'} | |
| {'loss': '0.127', 'grad_norm': '2.403', 'learning_rate': '1.249e-05', 'epoch': '0.8757'} | |
| {'loss': '0.1349', 'grad_norm': '0.9834', 'learning_rate': '1.249e-05', 'epoch': '0.8762'} | |
| {'loss': '0.2261', 'grad_norm': '4.134', 'learning_rate': '1.248e-05', 'epoch': '0.8767'} | |
| {'loss': '0.1278', 'grad_norm': '1.777', 'learning_rate': '1.248e-05', 'epoch': '0.8771'} | |
| {'loss': '0.127', 'grad_norm': '3.769', 'learning_rate': '1.247e-05', 'epoch': '0.8776'} | |
| {'loss': '0.1174', 'grad_norm': '7.675', 'learning_rate': '1.247e-05', 'epoch': '0.8781'} | |
| {'loss': '0.1539', 'grad_norm': '6.455', 'learning_rate': '1.246e-05', 'epoch': '0.8786'} | |
| {'loss': '0.1317', 'grad_norm': '3.569', 'learning_rate': '1.246e-05', 'epoch': '0.8791'} | |
| {'loss': '0.1273', 'grad_norm': '4.333', 'learning_rate': '1.245e-05', 'epoch': '0.8795'} | |
| {'loss': '0.1348', 'grad_norm': '1.58', 'learning_rate': '1.244e-05', 'epoch': '0.88'} | |
| {'loss': '0.1299', 'grad_norm': '4.531', 'learning_rate': '1.244e-05', 'epoch': '0.8805'} | |
| {'loss': '0.1191', 'grad_norm': '3.126', 'learning_rate': '1.243e-05', 'epoch': '0.881'} | |
| {'loss': '0.1379', 'grad_norm': '0.5199', 'learning_rate': '1.243e-05', 'epoch': '0.8814'} | |
| {'loss': '0.1391', 'grad_norm': '7.318', 'learning_rate': '1.242e-05', 'epoch': '0.8819'} | |
| {'loss': '0.1346', 'grad_norm': '6.269', 'learning_rate': '1.242e-05', 'epoch': '0.8824'} | |
| {'loss': '0.1382', 'grad_norm': '5.994', 'learning_rate': '1.241e-05', 'epoch': '0.8829'} | |
| {'loss': '0.1556', 'grad_norm': '2.239', 'learning_rate': '1.241e-05', 'epoch': '0.8833'} | |
| {'loss': '0.1371', 'grad_norm': '4.255', 'learning_rate': '1.24e-05', 'epoch': '0.8838'} | |
| {'loss': '0.1412', 'grad_norm': '0.2327', 'learning_rate': '1.24e-05', 'epoch': '0.8843'} | |
| {'loss': '0.1344', 'grad_norm': '0.4543', 'learning_rate': '1.239e-05', 'epoch': '0.8848'} | |
| {'loss': '0.1396', 'grad_norm': '3.658', 'learning_rate': '1.239e-05', 'epoch': '0.8852'} | |
| {'loss': '0.1273', 'grad_norm': '7.216', 'learning_rate': '1.238e-05', 'epoch': '0.8857'} | |
| {'loss': '0.128', 'grad_norm': '2.67', 'learning_rate': '1.238e-05', 'epoch': '0.8862'} | |
| {'eval_ms_marco_loss': '0.04009', 'eval_val-ms-marco-768_cosine_accuracy': '0.9977', 'eval_val-ms-marco-512_cosine_accuracy': '0.9983', 'eval_val-ms-marco-256_cosine_accuracy': '0.9983', 'eval_val-ms-marco-128_cosine_accuracy': '0.998', 'eval_val-ms-marco-64_cosine_accuracy': '0.998', 'eval_sequential_score': '0.9977', 'eval_ms_marco_runtime': '33.93', 'eval_ms_marco_samples_per_second': '294.7', 'eval_ms_marco_steps_per_second': '9.224', 'epoch': '0.8862'} | |
| {'loss': '0.1386', 'grad_norm': '3.847', 'learning_rate': '1.237e-05', 'epoch': '0.8867'} | |
| {'loss': '0.1249', 'grad_norm': '2.889', 'learning_rate': '1.237e-05', 'epoch': '0.8872'} | |
| {'loss': '0.1412', 'grad_norm': '2.109', 'learning_rate': '1.236e-05', 'epoch': '0.8876'} | |
| {'loss': '0.1316', 'grad_norm': '3.369', 'learning_rate': '1.235e-05', 'epoch': '0.8881'} | |
| {'loss': '0.1608', 'grad_norm': '2.367', 'learning_rate': '1.235e-05', 'epoch': '0.8886'} | |
| {'loss': '0.2131', 'grad_norm': '7.47', 'learning_rate': '1.234e-05', 'epoch': '0.8891'} | |
| {'loss': '0.2518', 'grad_norm': '7.134', 'learning_rate': '1.234e-05', 'epoch': '0.8895'} | |
| {'loss': '0.1227', 'grad_norm': '2.776', 'learning_rate': '1.233e-05', 'epoch': '0.89'} | |
| {'loss': '0.1461', 'grad_norm': '4.501', 'learning_rate': '1.233e-05', 'epoch': '0.8905'} | |
| {'loss': '0.1481', 'grad_norm': '2.853', 'learning_rate': '1.232e-05', 'epoch': '0.891'} | |
| {'loss': '0.1438', 'grad_norm': '1.087', 'learning_rate': '1.232e-05', 'epoch': '0.8914'} | |
| {'loss': '0.1217', 'grad_norm': '2.729', 'learning_rate': '1.231e-05', 'epoch': '0.8919'} | |
| {'loss': '0.1262', 'grad_norm': '4.777', 'learning_rate': '1.231e-05', 'epoch': '0.8924'} | |
| {'loss': '0.1274', 'grad_norm': '2.562', 'learning_rate': '1.23e-05', 'epoch': '0.8929'} | |
| {'loss': '0.1367', 'grad_norm': '0.6591', 'learning_rate': '1.23e-05', 'epoch': '0.8933'} | |
| {'loss': '0.15', 'grad_norm': '1.367', 'learning_rate': '1.229e-05', 'epoch': '0.8938'} | |
| {'loss': '0.1546', 'grad_norm': '0.9488', 'learning_rate': '1.229e-05', 'epoch': '0.8943'} | |
| {'loss': '0.1333', 'grad_norm': '0.3244', 'learning_rate': '1.228e-05', 'epoch': '0.8948'} | |
| {'loss': '0.1484', 'grad_norm': '3.785', 'learning_rate': '1.228e-05', 'epoch': '0.8953'} | |
| {'loss': '0.1155', 'grad_norm': '0.5855', 'learning_rate': '1.227e-05', 'epoch': '0.8957'} | |
| {'loss': '0.1288', 'grad_norm': '4.174', 'learning_rate': '1.226e-05', 'epoch': '0.8962'} | |
| {'loss': '0.1257', 'grad_norm': '2.265', 'learning_rate': '1.226e-05', 'epoch': '0.8967'} | |
| {'loss': '0.1211', 'grad_norm': '1.781', 'learning_rate': '1.225e-05', 'epoch': '0.8972'} | |
| {'loss': '0.1551', 'grad_norm': '3.074', 'learning_rate': '1.225e-05', 'epoch': '0.8976'} | |
| {'loss': '0.1318', 'grad_norm': '5.235', 'learning_rate': '1.224e-05', 'epoch': '0.8981'} | |
| {'loss': '0.1291', 'grad_norm': '7.25', 'learning_rate': '1.224e-05', 'epoch': '0.8986'} | |
| {'loss': '0.1373', 'grad_norm': '2.293', 'learning_rate': '1.223e-05', 'epoch': '0.8991'} | |
| {'loss': '0.1432', 'grad_norm': '2.286', 'learning_rate': '1.223e-05', 'epoch': '0.8995'} | |
| {'loss': '0.131', 'grad_norm': '5.572', 'learning_rate': '1.222e-05', 'epoch': '0.9'} | |
| {'loss': '0.1377', 'grad_norm': '0.5202', 'learning_rate': '1.222e-05', 'epoch': '0.9005'} | |
| {'loss': '0.1283', 'grad_norm': '2.252', 'learning_rate': '1.221e-05', 'epoch': '0.901'} | |
| {'loss': '0.2493', 'grad_norm': '5.14', 'learning_rate': '1.221e-05', 'epoch': '0.9014'} | |
| {'loss': '0.1269', 'grad_norm': '3.877', 'learning_rate': '1.22e-05', 'epoch': '0.9019'} | |
| {'loss': '0.1209', 'grad_norm': '5.179', 'learning_rate': '1.22e-05', 'epoch': '0.9024'} | |
| {'loss': '0.1445', 'grad_norm': '3.177', 'learning_rate': '1.219e-05', 'epoch': '0.9029'} | |
| {'loss': '0.1394', 'grad_norm': '8.358', 'learning_rate': '1.219e-05', 'epoch': '0.9033'} | |
| {'loss': '0.2561', 'grad_norm': '1.805', 'learning_rate': '1.218e-05', 'epoch': '0.9038'} | |
| {'loss': '0.1107', 'grad_norm': '0.3379', 'learning_rate': '1.217e-05', 'epoch': '0.9043'} | |
| {'loss': '0.1243', 'grad_norm': '0.4411', 'learning_rate': '1.217e-05', 'epoch': '0.9048'} | |
| {'loss': '0.1318', 'grad_norm': '2.68', 'learning_rate': '1.216e-05', 'epoch': '0.9053'} | |
| {'loss': '0.1178', 'grad_norm': '0.6738', 'learning_rate': '1.216e-05', 'epoch': '0.9057'} | |
| {'loss': '0.1198', 'grad_norm': '2.464', 'learning_rate': '1.215e-05', 'epoch': '0.9062'} | |
| {'loss': '0.131', 'grad_norm': '1.841', 'learning_rate': '1.215e-05', 'epoch': '0.9067'} | |
| {'loss': '0.1163', 'grad_norm': '4.54', 'learning_rate': '1.214e-05', 'epoch': '0.9072'} | |
| {'loss': '0.1389', 'grad_norm': '2.024', 'learning_rate': '1.214e-05', 'epoch': '0.9076'} | |
| {'loss': '0.1444', 'grad_norm': '0.7991', 'learning_rate': '1.213e-05', 'epoch': '0.9081'} | |
| {'loss': '0.131', 'grad_norm': '3.927', 'learning_rate': '1.213e-05', 'epoch': '0.9086'} | |
| {'loss': '0.1381', 'grad_norm': '1.864', 'learning_rate': '1.212e-05', 'epoch': '0.9091'} | |
| {'loss': '0.2792', 'grad_norm': '4.784', 'learning_rate': '1.212e-05', 'epoch': '0.9095'} | |
| {'loss': '0.2508', 'grad_norm': '2.863', 'learning_rate': '1.211e-05', 'epoch': '0.91'} | |
| {'loss': '0.1443', 'grad_norm': '5.473', 'learning_rate': '1.211e-05', 'epoch': '0.9105'} | |
| {'loss': '0.116', 'grad_norm': '7.488', 'learning_rate': '1.21e-05', 'epoch': '0.911'} | |
| {'loss': '0.1371', 'grad_norm': '2.556', 'learning_rate': '1.21e-05', 'epoch': '0.9114'} | |
| {'loss': '0.1317', 'grad_norm': '4.186', 'learning_rate': '1.209e-05', 'epoch': '0.9119'} | |
| {'loss': '0.1213', 'grad_norm': '1.45', 'learning_rate': '1.208e-05', 'epoch': '0.9124'} | |
| {'loss': '0.126', 'grad_norm': '1.753', 'learning_rate': '1.208e-05', 'epoch': '0.9129'} | |
| {'loss': '0.1092', 'grad_norm': '0.8057', 'learning_rate': '1.207e-05', 'epoch': '0.9134'} | |
| {'loss': '0.1387', 'grad_norm': '1.989', 'learning_rate': '1.207e-05', 'epoch': '0.9138'} | |
| {'loss': '0.1188', 'grad_norm': '0.8226', 'learning_rate': '1.206e-05', 'epoch': '0.9143'} | |
| {'loss': '0.266', 'grad_norm': '3.581', 'learning_rate': '1.206e-05', 'epoch': '0.9148'} | |
| {'eval_ms_marco_loss': '0.03672', 'eval_val-ms-marco-768_cosine_accuracy': '0.9983', 'eval_val-ms-marco-512_cosine_accuracy': '0.9983', 'eval_val-ms-marco-256_cosine_accuracy': '0.9983', 'eval_val-ms-marco-128_cosine_accuracy': '0.999', 'eval_val-ms-marco-64_cosine_accuracy': '0.9987', 'eval_sequential_score': '0.9983', 'eval_ms_marco_runtime': '34.04', 'eval_ms_marco_samples_per_second': '293.8', 'eval_ms_marco_steps_per_second': '9.196', 'epoch': '0.9148'} | |
| {'loss': '0.1305', 'grad_norm': '3.924', 'learning_rate': '1.205e-05', 'epoch': '0.9153'} | |
| {'loss': '0.136', 'grad_norm': '2.047', 'learning_rate': '1.205e-05', 'epoch': '0.9157'} | |
| {'loss': '0.1541', 'grad_norm': '0.3826', 'learning_rate': '1.204e-05', 'epoch': '0.9162'} | |
| {'loss': '0.1229', 'grad_norm': '2.092', 'learning_rate': '1.204e-05', 'epoch': '0.9167'} | |
| {'loss': '0.1267', 'grad_norm': '4.091', 'learning_rate': '1.203e-05', 'epoch': '0.9172'} | |
| {'loss': '0.1476', 'grad_norm': '0.2152', 'learning_rate': '1.203e-05', 'epoch': '0.9176'} | |
| {'loss': '0.1352', 'grad_norm': '3.415', 'learning_rate': '1.202e-05', 'epoch': '0.9181'} | |
| {'loss': '0.1347', 'grad_norm': '3.579', 'learning_rate': '1.202e-05', 'epoch': '0.9186'} | |
| {'loss': '0.1273', 'grad_norm': '0.9395', 'learning_rate': '1.201e-05', 'epoch': '0.9191'} | |
| {'loss': '0.1301', 'grad_norm': '0.3268', 'learning_rate': '1.201e-05', 'epoch': '0.9195'} | |
| {'loss': '0.1413', 'grad_norm': '0.6687', 'learning_rate': '1.2e-05', 'epoch': '0.92'} | |
| {'loss': '0.117', 'grad_norm': '2.845', 'learning_rate': '1.199e-05', 'epoch': '0.9205'} | |
| {'loss': '0.1194', 'grad_norm': '3.572', 'learning_rate': '1.199e-05', 'epoch': '0.921'} | |
| {'loss': '0.1307', 'grad_norm': '2.836', 'learning_rate': '1.198e-05', 'epoch': '0.9215'} | |
| {'loss': '0.129', 'grad_norm': '2.644', 'learning_rate': '1.198e-05', 'epoch': '0.9219'} | |
| {'loss': '0.2244', 'grad_norm': '2.516', 'learning_rate': '1.197e-05', 'epoch': '0.9224'} | |
| {'loss': '0.1286', 'grad_norm': '3.602', 'learning_rate': '1.197e-05', 'epoch': '0.9229'} | |
| {'loss': '0.2802', 'grad_norm': '4.716', 'learning_rate': '1.196e-05', 'epoch': '0.9234'} | |
| {'loss': '0.1283', 'grad_norm': '5.453', 'learning_rate': '1.196e-05', 'epoch': '0.9238'} | |
| {'loss': '0.3412', 'grad_norm': '1.469', 'learning_rate': '1.195e-05', 'epoch': '0.9243'} | |
| {'loss': '0.1445', 'grad_norm': '3.192', 'learning_rate': '1.195e-05', 'epoch': '0.9248'} | |
| {'loss': '0.1252', 'grad_norm': '5.757', 'learning_rate': '1.194e-05', 'epoch': '0.9253'} | |
| {'loss': '0.1226', 'grad_norm': '3.261', 'learning_rate': '1.194e-05', 'epoch': '0.9257'} | |
| {'loss': '0.1433', 'grad_norm': '2.293', 'learning_rate': '1.193e-05', 'epoch': '0.9262'} | |
| {'loss': '0.1343', 'grad_norm': '0.7635', 'learning_rate': '1.193e-05', 'epoch': '0.9267'} | |
| {'loss': '0.134', 'grad_norm': '2.535', 'learning_rate': '1.192e-05', 'epoch': '0.9272'} | |
| {'loss': '0.1143', 'grad_norm': '0.4973', 'learning_rate': '1.192e-05', 'epoch': '0.9276'} | |
| {'loss': '0.1391', 'grad_norm': '5.782', 'learning_rate': '1.191e-05', 'epoch': '0.9281'} | |
| {'loss': '0.1475', 'grad_norm': '3.832', 'learning_rate': '1.19e-05', 'epoch': '0.9286'} | |
| {'loss': '0.1331', 'grad_norm': '1.383', 'learning_rate': '1.19e-05', 'epoch': '0.9291'} | |
| {'loss': '0.1209', 'grad_norm': '0.8737', 'learning_rate': '1.189e-05', 'epoch': '0.9296'} | |
| {'loss': '0.1308', 'grad_norm': '1.89', 'learning_rate': '1.189e-05', 'epoch': '0.93'} | |
| {'loss': '0.1392', 'grad_norm': '0.841', 'learning_rate': '1.188e-05', 'epoch': '0.9305'} | |
| {'loss': '0.1295', 'grad_norm': '3.792', 'learning_rate': '1.188e-05', 'epoch': '0.931'} | |
| {'loss': '0.1231', 'grad_norm': '1.813', 'learning_rate': '1.187e-05', 'epoch': '0.9315'} | |
| {'loss': '0.1089', 'grad_norm': '4.527', 'learning_rate': '1.187e-05', 'epoch': '0.9319'} | |
| {'loss': '0.2391', 'grad_norm': '1.105', 'learning_rate': '1.186e-05', 'epoch': '0.9324'} | |
| {'loss': '0.1275', 'grad_norm': '4.488', 'learning_rate': '1.186e-05', 'epoch': '0.9329'} | |
| {'loss': '0.1311', 'grad_norm': '1.895', 'learning_rate': '1.185e-05', 'epoch': '0.9334'} | |
| {'loss': '0.1254', 'grad_norm': '4.684', 'learning_rate': '1.185e-05', 'epoch': '0.9338'} | |
| {'loss': '0.1137', 'grad_norm': '6.255', 'learning_rate': '1.184e-05', 'epoch': '0.9343'} | |
| {'loss': '0.1236', 'grad_norm': '0.2246', 'learning_rate': '1.184e-05', 'epoch': '0.9348'} | |
| {'loss': '0.1393', 'grad_norm': '4.973', 'learning_rate': '1.183e-05', 'epoch': '0.9353'} | |
| {'loss': '0.134', 'grad_norm': '3.368', 'learning_rate': '1.183e-05', 'epoch': '0.9357'} | |
| {'loss': '0.1571', 'grad_norm': '2.586', 'learning_rate': '1.182e-05', 'epoch': '0.9362'} | |
| {'loss': '0.127', 'grad_norm': '4.498', 'learning_rate': '1.181e-05', 'epoch': '0.9367'} | |
| {'loss': '0.1106', 'grad_norm': '0.2154', 'learning_rate': '1.181e-05', 'epoch': '0.9372'} | |
| {'loss': '0.1181', 'grad_norm': '4.884', 'learning_rate': '1.18e-05', 'epoch': '0.9377'} | |
| {'loss': '0.135', 'grad_norm': '5.039', 'learning_rate': '1.18e-05', 'epoch': '0.9381'} | |
| {'loss': '0.1194', 'grad_norm': '1.251', 'learning_rate': '1.179e-05', 'epoch': '0.9386'} | |
| {'loss': '0.2346', 'grad_norm': '4.416', 'learning_rate': '1.179e-05', 'epoch': '0.9391'} | |
| {'loss': '0.1459', 'grad_norm': '6.506', 'learning_rate': '1.178e-05', 'epoch': '0.9396'} | |
| {'loss': '0.2598', 'grad_norm': '1.779', 'learning_rate': '1.178e-05', 'epoch': '0.94'} | |
| {'loss': '0.2462', 'grad_norm': '1.846', 'learning_rate': '1.177e-05', 'epoch': '0.9405'} | |
| {'loss': '0.1505', 'grad_norm': '5.424', 'learning_rate': '1.177e-05', 'epoch': '0.941'} | |
| {'loss': '0.1221', 'grad_norm': '0.4421', 'learning_rate': '1.176e-05', 'epoch': '0.9415'} | |
| {'loss': '0.3017', 'grad_norm': '2.901', 'learning_rate': '1.176e-05', 'epoch': '0.9419'} | |
| {'loss': '0.1488', 'grad_norm': '6.264', 'learning_rate': '1.175e-05', 'epoch': '0.9424'} | |
| {'loss': '0.1298', 'grad_norm': '7.214', 'learning_rate': '1.175e-05', 'epoch': '0.9429'} | |
| {'loss': '0.1176', 'grad_norm': '2.61', 'learning_rate': '1.174e-05', 'epoch': '0.9434'} | |
| {'eval_ms_marco_loss': '0.03445', 'eval_val-ms-marco-768_cosine_accuracy': '0.9993', 'eval_val-ms-marco-512_cosine_accuracy': '0.9993', 'eval_val-ms-marco-256_cosine_accuracy': '0.9997', 'eval_val-ms-marco-128_cosine_accuracy': '0.9993', 'eval_val-ms-marco-64_cosine_accuracy': '0.9993', 'eval_sequential_score': '0.9993', 'eval_ms_marco_runtime': '33.92', 'eval_ms_marco_samples_per_second': '294.8', 'eval_ms_marco_steps_per_second': '9.227', 'epoch': '0.9434'} | |
| {'loss': '0.2264', 'grad_norm': '0.7979', 'learning_rate': '1.174e-05', 'epoch': '0.9438'} | |
| {'loss': '0.1299', 'grad_norm': '2.193', 'learning_rate': '1.173e-05', 'epoch': '0.9443'} | |
| {'loss': '0.1349', 'grad_norm': '1.713', 'learning_rate': '1.172e-05', 'epoch': '0.9448'} | |
| {'loss': '0.1284', 'grad_norm': '6.547', 'learning_rate': '1.172e-05', 'epoch': '0.9453'} | |
| {'loss': '0.12', 'grad_norm': '5.092', 'learning_rate': '1.171e-05', 'epoch': '0.9458'} | |
| {'loss': '0.1222', 'grad_norm': '0.5291', 'learning_rate': '1.171e-05', 'epoch': '0.9462'} | |
| {'loss': '0.1173', 'grad_norm': '3.554', 'learning_rate': '1.17e-05', 'epoch': '0.9467'} | |
| {'loss': '0.1299', 'grad_norm': '6.371', 'learning_rate': '1.17e-05', 'epoch': '0.9472'} | |
| {'loss': '0.1285', 'grad_norm': '0.6644', 'learning_rate': '1.169e-05', 'epoch': '0.9477'} | |
| {'loss': '0.1219', 'grad_norm': '1.552', 'learning_rate': '1.169e-05', 'epoch': '0.9481'} | |
| {'loss': '0.1184', 'grad_norm': '2.444', 'learning_rate': '1.168e-05', 'epoch': '0.9486'} | |
| {'loss': '0.1242', 'grad_norm': '3.603', 'learning_rate': '1.168e-05', 'epoch': '0.9491'} | |
| {'loss': '0.1385', 'grad_norm': '5.312', 'learning_rate': '1.167e-05', 'epoch': '0.9496'} | |
| {'loss': '0.1276', 'grad_norm': '2.173', 'learning_rate': '1.167e-05', 'epoch': '0.95'} | |
| {'loss': '0.1218', 'grad_norm': '4.505', 'learning_rate': '1.166e-05', 'epoch': '0.9505'} | |
| {'loss': '0.1333', 'grad_norm': '2.444', 'learning_rate': '1.166e-05', 'epoch': '0.951'} | |
| {'loss': '0.1262', 'grad_norm': '10.38', 'learning_rate': '1.165e-05', 'epoch': '0.9515'} | |
| {'loss': '0.1087', 'grad_norm': '0.2024', 'learning_rate': '1.165e-05', 'epoch': '0.9519'} | |
| {'loss': '0.1196', 'grad_norm': '0.7663', 'learning_rate': '1.164e-05', 'epoch': '0.9524'} | |
| {'loss': '0.1247', 'grad_norm': '0.5197', 'learning_rate': '1.163e-05', 'epoch': '0.9529'} | |
| {'loss': '0.1361', 'grad_norm': '4.703', 'learning_rate': '1.163e-05', 'epoch': '0.9534'} | |
| {'loss': '0.1146', 'grad_norm': '1.598', 'learning_rate': '1.162e-05', 'epoch': '0.9539'} | |
| {'loss': '0.1273', 'grad_norm': '0.5388', 'learning_rate': '1.162e-05', 'epoch': '0.9543'} | |
| {'loss': '0.1092', 'grad_norm': '5.312', 'learning_rate': '1.161e-05', 'epoch': '0.9548'} | |
| {'loss': '0.133', 'grad_norm': '2.008', 'learning_rate': '1.161e-05', 'epoch': '0.9553'} | |
| {'loss': '0.1287', 'grad_norm': '0.509', 'learning_rate': '1.16e-05', 'epoch': '0.9558'} | |
| {'loss': '0.2445', 'grad_norm': '6.83', 'learning_rate': '1.16e-05', 'epoch': '0.9562'} | |
| {'loss': '0.1221', 'grad_norm': '3.424', 'learning_rate': '1.159e-05', 'epoch': '0.9567'} | |
| {'loss': '0.13', 'grad_norm': '5.748', 'learning_rate': '1.159e-05', 'epoch': '0.9572'} | |
| {'loss': '0.1144', 'grad_norm': '6.406', 'learning_rate': '1.158e-05', 'epoch': '0.9577'} | |
| {'loss': '0.127', 'grad_norm': '9.911', 'learning_rate': '1.158e-05', 'epoch': '0.9581'} | |
| {'loss': '0.1229', 'grad_norm': '3.983', 'learning_rate': '1.157e-05', 'epoch': '0.9586'} | |
| {'loss': '0.1148', 'grad_norm': '7.821', 'learning_rate': '1.157e-05', 'epoch': '0.9591'} | |
| {'loss': '0.2779', 'grad_norm': '1.195', 'learning_rate': '1.156e-05', 'epoch': '0.9596'} | |
| {'loss': '0.1368', 'grad_norm': '3.363', 'learning_rate': '1.156e-05', 'epoch': '0.96'} | |
| {'loss': '0.1279', 'grad_norm': '4.321', 'learning_rate': '1.155e-05', 'epoch': '0.9605'} | |
| {'loss': '0.1188', 'grad_norm': '6.488', 'learning_rate': '1.154e-05', 'epoch': '0.961'} | |
| {'loss': '0.1299', 'grad_norm': '5.684', 'learning_rate': '1.154e-05', 'epoch': '0.9615'} | |
| {'loss': '0.1145', 'grad_norm': '7.017', 'learning_rate': '1.153e-05', 'epoch': '0.962'} | |
| {'loss': '0.1217', 'grad_norm': '1.495', 'learning_rate': '1.153e-05', 'epoch': '0.9624'} | |
| {'loss': '0.1239', 'grad_norm': '0.7789', 'learning_rate': '1.152e-05', 'epoch': '0.9629'} | |
| {'loss': '0.1138', 'grad_norm': '5.06', 'learning_rate': '1.152e-05', 'epoch': '0.9634'} | |
| {'loss': '0.1295', 'grad_norm': '0.6616', 'learning_rate': '1.151e-05', 'epoch': '0.9639'} | |
| {'loss': '0.1159', 'grad_norm': '1.052', 'learning_rate': '1.151e-05', 'epoch': '0.9643'} | |
| {'loss': '0.1916', 'grad_norm': '2.853', 'learning_rate': '1.15e-05', 'epoch': '0.9648'} | |
| {'loss': '0.1381', 'grad_norm': '2.32', 'learning_rate': '1.15e-05', 'epoch': '0.9653'} | |
| {'loss': '0.1158', 'grad_norm': '5.62', 'learning_rate': '1.149e-05', 'epoch': '0.9658'} | |
| {'loss': '0.1309', 'grad_norm': '2.894', 'learning_rate': '1.149e-05', 'epoch': '0.9662'} | |
| {'loss': '0.1299', 'grad_norm': '0.2965', 'learning_rate': '1.148e-05', 'epoch': '0.9667'} | |
| {'loss': '0.1037', 'grad_norm': '10.38', 'learning_rate': '1.148e-05', 'epoch': '0.9672'} | |
| {'loss': '0.3262', 'grad_norm': '8.103', 'learning_rate': '1.147e-05', 'epoch': '0.9677'} | |
| {'loss': '0.1156', 'grad_norm': '0.2429', 'learning_rate': '1.147e-05', 'epoch': '0.9681'} | |
| {'loss': '0.1153', 'grad_norm': '0.997', 'learning_rate': '1.146e-05', 'epoch': '0.9686'} | |
| {'loss': '0.1269', 'grad_norm': '1.11', 'learning_rate': '1.145e-05', 'epoch': '0.9691'} | |
| {'loss': '0.1261', 'grad_norm': '1.649', 'learning_rate': '1.145e-05', 'epoch': '0.9696'} | |
| {'loss': '0.1194', 'grad_norm': '0.4108', 'learning_rate': '1.144e-05', 'epoch': '0.9701'} | |
| {'loss': '0.1213', 'grad_norm': '1.247', 'learning_rate': '1.144e-05', 'epoch': '0.9705'} | |
| {'loss': '0.114', 'grad_norm': '2.148', 'learning_rate': '1.143e-05', 'epoch': '0.971'} | |
| {'loss': '0.124', 'grad_norm': '2.266', 'learning_rate': '1.143e-05', 'epoch': '0.9715'} | |
| {'loss': '0.1301', 'grad_norm': '3.69', 'learning_rate': '1.142e-05', 'epoch': '0.972'} | |
| {'eval_ms_marco_loss': '0.03441', 'eval_val-ms-marco-768_cosine_accuracy': '0.9993', 'eval_val-ms-marco-512_cosine_accuracy': '0.9993', 'eval_val-ms-marco-256_cosine_accuracy': '0.9997', 'eval_val-ms-marco-128_cosine_accuracy': '0.9997', 'eval_val-ms-marco-64_cosine_accuracy': '0.9993', 'eval_sequential_score': '0.9993', 'eval_ms_marco_runtime': '34.15', 'eval_ms_marco_samples_per_second': '292.9', 'eval_ms_marco_steps_per_second': '9.166', 'epoch': '0.972'} | |
| {'loss': '0.1189', 'grad_norm': '1.742', 'learning_rate': '1.142e-05', 'epoch': '0.9724'} | |
| {'loss': '0.1169', 'grad_norm': '2.46', 'learning_rate': '1.141e-05', 'epoch': '0.9729'} | |
| {'loss': '0.1083', 'grad_norm': '0.2765', 'learning_rate': '1.141e-05', 'epoch': '0.9734'} | |
| {'loss': '0.1106', 'grad_norm': '1.912', 'learning_rate': '1.14e-05', 'epoch': '0.9739'} | |
| {'loss': '0.1355', 'grad_norm': '2.647', 'learning_rate': '1.14e-05', 'epoch': '0.9743'} | |
| {'loss': '0.112', 'grad_norm': '0.2388', 'learning_rate': '1.139e-05', 'epoch': '0.9748'} | |
| {'loss': '0.1163', 'grad_norm': '0.9285', 'learning_rate': '1.139e-05', 'epoch': '0.9753'} | |
| {'loss': '0.1188', 'grad_norm': '0.9763', 'learning_rate': '1.138e-05', 'epoch': '0.9758'} | |
| {'loss': '0.1197', 'grad_norm': '0.8371', 'learning_rate': '1.138e-05', 'epoch': '0.9762'} | |
| {'loss': '0.1226', 'grad_norm': '5.401', 'learning_rate': '1.137e-05', 'epoch': '0.9767'} | |
| {'loss': '0.1204', 'grad_norm': '3.892', 'learning_rate': '1.136e-05', 'epoch': '0.9772'} | |
| {'loss': '0.112', 'grad_norm': '7.55', 'learning_rate': '1.136e-05', 'epoch': '0.9777'} | |
| {'loss': '0.1225', 'grad_norm': '3.738', 'learning_rate': '1.135e-05', 'epoch': '0.9782'} | |
| {'loss': '0.1132', 'grad_norm': '2.225', 'learning_rate': '1.135e-05', 'epoch': '0.9786'} | |
| {'loss': '0.1167', 'grad_norm': '7.272', 'learning_rate': '1.134e-05', 'epoch': '0.9791'} | |
| {'loss': '0.112', 'grad_norm': '1.777', 'learning_rate': '1.134e-05', 'epoch': '0.9796'} | |
| {'loss': '0.1311', 'grad_norm': '5.012', 'learning_rate': '1.133e-05', 'epoch': '0.9801'} | |
| {'loss': '0.1277', 'grad_norm': '5.221', 'learning_rate': '1.133e-05', 'epoch': '0.9805'} | |
| {'loss': '0.1986', 'grad_norm': '0.8324', 'learning_rate': '1.132e-05', 'epoch': '0.981'} | |
| {'loss': '0.107', 'grad_norm': '4.279', 'learning_rate': '1.132e-05', 'epoch': '0.9815'} | |
| {'loss': '0.1019', 'grad_norm': '5.675', 'learning_rate': '1.131e-05', 'epoch': '0.982'} | |
| {'loss': '0.1169', 'grad_norm': '6.281', 'learning_rate': '1.131e-05', 'epoch': '0.9824'} | |
| {'loss': '0.1223', 'grad_norm': '6.08', 'learning_rate': '1.13e-05', 'epoch': '0.9829'} | |
| {'loss': '0.2268', 'grad_norm': '9.164', 'learning_rate': '1.13e-05', 'epoch': '0.9834'} | |
| {'loss': '0.1285', 'grad_norm': '0.8953', 'learning_rate': '1.129e-05', 'epoch': '0.9839'} | |
| {'loss': '0.1215', 'grad_norm': '0.4212', 'learning_rate': '1.129e-05', 'epoch': '0.9843'} | |
| {'loss': '0.1208', 'grad_norm': '3.475', 'learning_rate': '1.128e-05', 'epoch': '0.9848'} | |
| {'loss': '0.127', 'grad_norm': '7.533', 'learning_rate': '1.127e-05', 'epoch': '0.9853'} | |
| {'loss': '0.1271', 'grad_norm': '4.407', 'learning_rate': '1.127e-05', 'epoch': '0.9858'} | |
| {'loss': '0.2201', 'grad_norm': '0.4725', 'learning_rate': '1.126e-05', 'epoch': '0.9863'} | |
| {'loss': '0.126', 'grad_norm': '7.705', 'learning_rate': '1.126e-05', 'epoch': '0.9867'} | |
| {'loss': '0.1137', 'grad_norm': '5.003', 'learning_rate': '1.125e-05', 'epoch': '0.9872'} | |
| {'loss': '0.119', 'grad_norm': '1.721', 'learning_rate': '1.125e-05', 'epoch': '0.9877'} | |
| {'loss': '0.2858', 'grad_norm': '4.558', 'learning_rate': '1.124e-05', 'epoch': '0.9882'} | |
| {'loss': '0.1373', 'grad_norm': '0.7364', 'learning_rate': '1.124e-05', 'epoch': '0.9886'} | |
| {'loss': '0.1287', 'grad_norm': '0.7433', 'learning_rate': '1.123e-05', 'epoch': '0.9891'} | |
| {'loss': '0.1101', 'grad_norm': '2.939', 'learning_rate': '1.123e-05', 'epoch': '0.9896'} | |
| {'loss': '0.1141', 'grad_norm': '0.523', 'learning_rate': '1.122e-05', 'epoch': '0.9901'} | |
| {'loss': '0.1219', 'grad_norm': '4.132', 'learning_rate': '1.122e-05', 'epoch': '0.9905'} | |
| {'loss': '0.2513', 'grad_norm': '4.267', 'learning_rate': '1.121e-05', 'epoch': '0.991'} | |
| {'loss': '0.1298', 'grad_norm': '1.453', 'learning_rate': '1.121e-05', 'epoch': '0.9915'} | |
| {'loss': '0.1311', 'grad_norm': '1.62', 'learning_rate': '1.12e-05', 'epoch': '0.992'} | |
| {'loss': '0.1252', 'grad_norm': '0.8644', 'learning_rate': '1.12e-05', 'epoch': '0.9924'} | |
| {'loss': '0.1308', 'grad_norm': '1.852', 'learning_rate': '1.119e-05', 'epoch': '0.9929'} | |
| {'loss': '0.1399', 'grad_norm': '5.853', 'learning_rate': '1.118e-05', 'epoch': '0.9934'} | |
| {'loss': '0.1222', 'grad_norm': '5.395', 'learning_rate': '1.118e-05', 'epoch': '0.9939'} | |
| {'loss': '0.1167', 'grad_norm': '4.097', 'learning_rate': '1.117e-05', 'epoch': '0.9944'} | |
| {'loss': '0.1152', 'grad_norm': '3.23', 'learning_rate': '1.117e-05', 'epoch': '0.9948'} | |
| {'loss': '0.1257', 'grad_norm': '0.1653', 'learning_rate': '1.116e-05', 'epoch': '0.9953'} | |
| {'loss': '0.1342', 'grad_norm': '6.297', 'learning_rate': '1.116e-05', 'epoch': '0.9958'} | |
| {'loss': '0.1162', 'grad_norm': '0.7501', 'learning_rate': '1.115e-05', 'epoch': '0.9963'} | |
| {'loss': '0.139', 'grad_norm': '0.162', 'learning_rate': '1.115e-05', 'epoch': '0.9967'} | |
| {'loss': '0.1272', 'grad_norm': '0.1229', 'learning_rate': '1.114e-05', 'epoch': '0.9972'} | |
| {'loss': '0.1244', 'grad_norm': '0.3829', 'learning_rate': '1.114e-05', 'epoch': '0.9977'} | |
| {'loss': '0.2075', 'grad_norm': '0.9956', 'learning_rate': '1.113e-05', 'epoch': '0.9982'} | |
| {'loss': '0.1418', 'grad_norm': '1.803', 'learning_rate': '1.113e-05', 'epoch': '0.9986'} | |
| {'loss': '0.1218', 'grad_norm': '1.718', 'learning_rate': '1.112e-05', 'epoch': '0.9991'} | |
| {'loss': '0.1117', 'grad_norm': '7.104', 'learning_rate': '1.112e-05', 'epoch': '0.9996'} | |
| {'loss': '0.1118', 'grad_norm': '6.318', 'learning_rate': '1.111e-05', 'epoch': '1'} | |
| {'loss': '0.14', 'grad_norm': '7.467', 'learning_rate': '1.111e-05', 'epoch': '1.001'} | |
| {'eval_ms_marco_loss': '0.03289', 'eval_val-ms-marco-768_cosine_accuracy': '0.9983', 'eval_val-ms-marco-512_cosine_accuracy': '0.9987', 'eval_val-ms-marco-256_cosine_accuracy': '0.999', 'eval_val-ms-marco-128_cosine_accuracy': '0.999', 'eval_val-ms-marco-64_cosine_accuracy': '0.9987', 'eval_sequential_score': '0.9983', 'eval_ms_marco_runtime': '34.39', 'eval_ms_marco_samples_per_second': '290.7', 'eval_ms_marco_steps_per_second': '9.1', 'epoch': '1.001'} | |
| {'loss': '0.1348', 'grad_norm': '9.528', 'learning_rate': '1.11e-05', 'epoch': '1.001'} | |
| {'loss': '0.1181', 'grad_norm': '0.5351', 'learning_rate': '1.109e-05', 'epoch': '1.001'} | |
| {'loss': '0.1079', 'grad_norm': '4.092', 'learning_rate': '1.109e-05', 'epoch': '1.002'} | |
| {'loss': '0.1208', 'grad_norm': '4.07', 'learning_rate': '1.108e-05', 'epoch': '1.002'} | |
| {'loss': '0.1199', 'grad_norm': '1.694', 'learning_rate': '1.108e-05', 'epoch': '1.003'} | |
| {'loss': '0.1044', 'grad_norm': '2.032', 'learning_rate': '1.107e-05', 'epoch': '1.003'} | |
| {'loss': '0.1198', 'grad_norm': '6.145', 'learning_rate': '1.107e-05', 'epoch': '1.004'} | |
| {'loss': '0.1177', 'grad_norm': '2.405', 'learning_rate': '1.106e-05', 'epoch': '1.004'} | |
| {'loss': '0.1355', 'grad_norm': '1.782', 'learning_rate': '1.106e-05', 'epoch': '1.005'} | |
| {'loss': '0.11', 'grad_norm': '7.899', 'learning_rate': '1.105e-05', 'epoch': '1.005'} | |
| {'loss': '0.2112', 'grad_norm': '2.236', 'learning_rate': '1.105e-05', 'epoch': '1.006'} | |
| {'loss': '0.1135', 'grad_norm': '0.4283', 'learning_rate': '1.104e-05', 'epoch': '1.006'} | |
| {'loss': '0.1128', 'grad_norm': '2.061', 'learning_rate': '1.104e-05', 'epoch': '1.007'} | |
| {'loss': '0.1211', 'grad_norm': '1.386', 'learning_rate': '1.103e-05', 'epoch': '1.007'} | |
| {'loss': '0.1182', 'grad_norm': '7.01', 'learning_rate': '1.103e-05', 'epoch': '1.008'} | |
| {'loss': '0.1295', 'grad_norm': '1.582', 'learning_rate': '1.102e-05', 'epoch': '1.008'} | |
| {'loss': '0.1172', 'grad_norm': '0.2282', 'learning_rate': '1.102e-05', 'epoch': '1.009'} | |
| {'loss': '0.1374', 'grad_norm': '2.643', 'learning_rate': '1.101e-05', 'epoch': '1.009'} | |
| {'loss': '0.1454', 'grad_norm': '1.066', 'learning_rate': '1.1e-05', 'epoch': '1.01'} | |
| {'loss': '0.1228', 'grad_norm': '0.2802', 'learning_rate': '1.1e-05', 'epoch': '1.01'} | |
| {'loss': '0.1095', 'grad_norm': '0.2903', 'learning_rate': '1.099e-05', 'epoch': '1.011'} | |
| {'loss': '0.3186', 'grad_norm': '5.634', 'learning_rate': '1.099e-05', 'epoch': '1.011'} | |
| {'loss': '0.1259', 'grad_norm': '3.427', 'learning_rate': '1.098e-05', 'epoch': '1.012'} | |
| {'loss': '0.1185', 'grad_norm': '2.446', 'learning_rate': '1.098e-05', 'epoch': '1.012'} | |
| {'loss': '0.1134', 'grad_norm': '2.777', 'learning_rate': '1.097e-05', 'epoch': '1.012'} | |
| {'loss': '0.1222', 'grad_norm': '2.126', 'learning_rate': '1.097e-05', 'epoch': '1.013'} | |
| {'loss': '0.2397', 'grad_norm': '2.105', 'learning_rate': '1.096e-05', 'epoch': '1.013'} | |
| {'loss': '0.2457', 'grad_norm': '0.4527', 'learning_rate': '1.096e-05', 'epoch': '1.014'} | |
| {'loss': '0.1209', 'grad_norm': '2.296', 'learning_rate': '1.095e-05', 'epoch': '1.014'} | |
| {'loss': '0.1235', 'grad_norm': '3.01', 'learning_rate': '1.095e-05', 'epoch': '1.015'} | |
| {'loss': '0.1273', 'grad_norm': '2.308', 'learning_rate': '1.094e-05', 'epoch': '1.015'} | |
| {'loss': '0.09917', 'grad_norm': '0.5791', 'learning_rate': '1.094e-05', 'epoch': '1.016'} | |
| {'loss': '0.115', 'grad_norm': '5.558', 'learning_rate': '1.093e-05', 'epoch': '1.016'} | |
| {'loss': '0.1115', 'grad_norm': '0.3108', 'learning_rate': '1.093e-05', 'epoch': '1.017'} | |
| {'loss': '0.114', 'grad_norm': '7.967', 'learning_rate': '1.092e-05', 'epoch': '1.017'} | |
| {'loss': '0.1203', 'grad_norm': '1.236', 'learning_rate': '1.091e-05', 'epoch': '1.018'} | |
| {'loss': '0.1124', 'grad_norm': '0.8639', 'learning_rate': '1.091e-05', 'epoch': '1.018'} | |
| {'loss': '0.1295', 'grad_norm': '4.966', 'learning_rate': '1.09e-05', 'epoch': '1.019'} | |
| {'loss': '0.1355', 'grad_norm': '0.7707', 'learning_rate': '1.09e-05', 'epoch': '1.019'} | |
| {'loss': '0.1191', 'grad_norm': '4.283', 'learning_rate': '1.089e-05', 'epoch': '1.02'} | |
| {'loss': '0.2308', 'grad_norm': '4.467', 'learning_rate': '1.089e-05', 'epoch': '1.02'} | |
| {'loss': '0.1012', 'grad_norm': '1.749', 'learning_rate': '1.088e-05', 'epoch': '1.021'} | |
| {'loss': '0.1068', 'grad_norm': '0.3267', 'learning_rate': '1.088e-05', 'epoch': '1.021'} | |
| {'loss': '0.1312', 'grad_norm': '4.083', 'learning_rate': '1.087e-05', 'epoch': '1.022'} | |
| {'loss': '0.1138', 'grad_norm': '0.8542', 'learning_rate': '1.087e-05', 'epoch': '1.022'} | |
| {'loss': '0.108', 'grad_norm': '1.852', 'learning_rate': '1.086e-05', 'epoch': '1.022'} | |
| {'loss': '0.1184', 'grad_norm': '2.441', 'learning_rate': '1.086e-05', 'epoch': '1.023'} | |
| {'loss': '0.1317', 'grad_norm': '7.837', 'learning_rate': '1.085e-05', 'epoch': '1.023'} | |
| {'loss': '0.1296', 'grad_norm': '1.864', 'learning_rate': '1.085e-05', 'epoch': '1.024'} | |
| {'loss': '0.1112', 'grad_norm': '2.287', 'learning_rate': '1.084e-05', 'epoch': '1.024'} | |
| {'loss': '0.1013', 'grad_norm': '2.776', 'learning_rate': '1.084e-05', 'epoch': '1.025'} | |
| {'loss': '0.103', 'grad_norm': '1.931', 'learning_rate': '1.083e-05', 'epoch': '1.025'} | |
| {'loss': '0.1232', 'grad_norm': '1.475', 'learning_rate': '1.082e-05', 'epoch': '1.026'} | |
| {'loss': '0.1293', 'grad_norm': '2.573', 'learning_rate': '1.082e-05', 'epoch': '1.026'} | |
| {'loss': '0.1194', 'grad_norm': '2.393', 'learning_rate': '1.081e-05', 'epoch': '1.027'} | |
| {'loss': '0.1158', 'grad_norm': '0.9718', 'learning_rate': '1.081e-05', 'epoch': '1.027'} | |
| {'loss': '0.216', 'grad_norm': '3.232', 'learning_rate': '1.08e-05', 'epoch': '1.028'} | |
| {'loss': '0.1224', 'grad_norm': '1.069', 'learning_rate': '1.08e-05', 'epoch': '1.028'} | |
| {'loss': '0.1227', 'grad_norm': '3.709', 'learning_rate': '1.079e-05', 'epoch': '1.029'} | |
| {'loss': '0.2211', 'grad_norm': '0.816', 'learning_rate': '1.079e-05', 'epoch': '1.029'} | |
| {'eval_ms_marco_loss': '0.03728', 'eval_val-ms-marco-768_cosine_accuracy': '0.9987', 'eval_val-ms-marco-512_cosine_accuracy': '0.998', 'eval_val-ms-marco-256_cosine_accuracy': '0.9983', 'eval_val-ms-marco-128_cosine_accuracy': '0.9983', 'eval_val-ms-marco-64_cosine_accuracy': '0.9977', 'eval_sequential_score': '0.9987', 'eval_ms_marco_runtime': '34.34', 'eval_ms_marco_samples_per_second': '291.2', 'eval_ms_marco_steps_per_second': '9.114', 'epoch': '1.029'} | |
| {'loss': '0.1032', 'grad_norm': '0.3468', 'learning_rate': '1.078e-05', 'epoch': '1.03'} | |
| {'loss': '0.1058', 'grad_norm': '0.8546', 'learning_rate': '1.078e-05', 'epoch': '1.03'} | |
| {'loss': '0.1074', 'grad_norm': '5.585', 'learning_rate': '1.077e-05', 'epoch': '1.031'} | |
| {'loss': '0.1214', 'grad_norm': '4.54', 'learning_rate': '1.077e-05', 'epoch': '1.031'} | |
| {'loss': '0.1196', 'grad_norm': '0.1778', 'learning_rate': '1.076e-05', 'epoch': '1.032'} | |
| {'loss': '0.128', 'grad_norm': '6.45', 'learning_rate': '1.076e-05', 'epoch': '1.032'} | |
| {'loss': '0.0995', 'grad_norm': '1.631', 'learning_rate': '1.075e-05', 'epoch': '1.032'} | |
| {'loss': '0.1073', 'grad_norm': '6.375', 'learning_rate': '1.075e-05', 'epoch': '1.033'} | |
| {'loss': '0.1031', 'grad_norm': '1.785', 'learning_rate': '1.074e-05', 'epoch': '1.033'} | |
| {'loss': '0.1023', 'grad_norm': '0.9074', 'learning_rate': '1.073e-05', 'epoch': '1.034'} | |
| {'loss': '0.1031', 'grad_norm': '3.184', 'learning_rate': '1.073e-05', 'epoch': '1.034'} | |
| {'loss': '0.111', 'grad_norm': '0.8641', 'learning_rate': '1.072e-05', 'epoch': '1.035'} | |
| {'loss': '0.1153', 'grad_norm': '4.773', 'learning_rate': '1.072e-05', 'epoch': '1.035'} | |
| {'loss': '0.2459', 'grad_norm': '0.5307', 'learning_rate': '1.071e-05', 'epoch': '1.036'} | |
| {'loss': '0.1101', 'grad_norm': '2.352', 'learning_rate': '1.071e-05', 'epoch': '1.036'} | |
| {'loss': '0.1474', 'grad_norm': '6.037', 'learning_rate': '1.07e-05', 'epoch': '1.037'} | |
| {'loss': '0.2293', 'grad_norm': '2.97', 'learning_rate': '1.07e-05', 'epoch': '1.037'} | |
| {'loss': '0.1108', 'grad_norm': '7.709', 'learning_rate': '1.069e-05', 'epoch': '1.038'} | |
| {'loss': '0.1292', 'grad_norm': '1.957', 'learning_rate': '1.069e-05', 'epoch': '1.038'} | |
| {'loss': '0.1157', 'grad_norm': '6.546', 'learning_rate': '1.068e-05', 'epoch': '1.039'} | |
| {'loss': '0.1042', 'grad_norm': '1.297', 'learning_rate': '1.068e-05', 'epoch': '1.039'} | |
| {'loss': '0.1145', 'grad_norm': '2.305', 'learning_rate': '1.067e-05', 'epoch': '1.04'} | |
| {'loss': '0.1038', 'grad_norm': '2.403', 'learning_rate': '1.067e-05', 'epoch': '1.04'} | |
| {'loss': '0.1179', 'grad_norm': '6.483', 'learning_rate': '1.066e-05', 'epoch': '1.041'} | |
| {'loss': '0.1198', 'grad_norm': '3.758', 'learning_rate': '1.066e-05', 'epoch': '1.041'} | |
| {'loss': '0.1198', 'grad_norm': '5.593', 'learning_rate': '1.065e-05', 'epoch': '1.042'} | |
| {'loss': '0.1037', 'grad_norm': '5.189', 'learning_rate': '1.064e-05', 'epoch': '1.042'} | |
| {'loss': '0.1103', 'grad_norm': '7.907', 'learning_rate': '1.064e-05', 'epoch': '1.042'} | |
| {'loss': '0.1186', 'grad_norm': '1.267', 'learning_rate': '1.063e-05', 'epoch': '1.043'} | |
| {'loss': '0.1104', 'grad_norm': '2.436', 'learning_rate': '1.063e-05', 'epoch': '1.043'} | |
| {'loss': '0.1134', 'grad_norm': '6.151', 'learning_rate': '1.062e-05', 'epoch': '1.044'} | |
| {'loss': '0.1229', 'grad_norm': '7.408', 'learning_rate': '1.062e-05', 'epoch': '1.044'} | |
| {'loss': '0.1112', 'grad_norm': '5.354', 'learning_rate': '1.061e-05', 'epoch': '1.045'} | |
| {'loss': '0.1137', 'grad_norm': '8.953', 'learning_rate': '1.061e-05', 'epoch': '1.045'} | |
| {'loss': '0.1209', 'grad_norm': '0.7484', 'learning_rate': '1.06e-05', 'epoch': '1.046'} | |
| {'loss': '0.108', 'grad_norm': '1.057', 'learning_rate': '1.06e-05', 'epoch': '1.046'} | |
| {'loss': '0.2266', 'grad_norm': '3.213', 'learning_rate': '1.059e-05', 'epoch': '1.047'} | |
| {'loss': '0.09884', 'grad_norm': '0.7109', 'learning_rate': '1.059e-05', 'epoch': '1.047'} | |
| {'loss': '0.1264', 'grad_norm': '0.4715', 'learning_rate': '1.058e-05', 'epoch': '1.048'} | |
| {'loss': '0.1074', 'grad_norm': '0.9201', 'learning_rate': '1.058e-05', 'epoch': '1.048'} | |
| {'loss': '0.1261', 'grad_norm': '4.702', 'learning_rate': '1.057e-05', 'epoch': '1.049'} | |
| {'loss': '0.1113', 'grad_norm': '1.211', 'learning_rate': '1.057e-05', 'epoch': '1.049'} | |
| {'loss': '0.1097', 'grad_norm': '0.7769', 'learning_rate': '1.056e-05', 'epoch': '1.05'} | |
| {'loss': '0.1018', 'grad_norm': '1.354', 'learning_rate': '1.055e-05', 'epoch': '1.05'} | |
| {'loss': '0.3401', 'grad_norm': '1.127', 'learning_rate': '1.055e-05', 'epoch': '1.051'} | |
| {'loss': '0.1146', 'grad_norm': '0.5098', 'learning_rate': '1.054e-05', 'epoch': '1.051'} | |
| {'loss': '0.1174', 'grad_norm': '0.3864', 'learning_rate': '1.054e-05', 'epoch': '1.052'} | |
| {'loss': '0.2081', 'grad_norm': '2.753', 'learning_rate': '1.053e-05', 'epoch': '1.052'} | |
| {'loss': '0.1141', 'grad_norm': '6.714', 'learning_rate': '1.053e-05', 'epoch': '1.052'} | |
| {'loss': '0.1286', 'grad_norm': '0.6767', 'learning_rate': '1.052e-05', 'epoch': '1.053'} | |
| {'loss': '0.1076', 'grad_norm': '0.22', 'learning_rate': '1.052e-05', 'epoch': '1.053'} | |
| {'loss': '0.1224', 'grad_norm': '0.6613', 'learning_rate': '1.051e-05', 'epoch': '1.054'} | |
| {'loss': '0.1129', 'grad_norm': '3.516', 'learning_rate': '1.051e-05', 'epoch': '1.054'} | |
| {'loss': '0.2019', 'grad_norm': '3.045', 'learning_rate': '1.05e-05', 'epoch': '1.055'} | |
| {'loss': '0.1053', 'grad_norm': '5.141', 'learning_rate': '1.05e-05', 'epoch': '1.055'} | |
| {'loss': '0.112', 'grad_norm': '1.471', 'learning_rate': '1.049e-05', 'epoch': '1.056'} | |
| {'loss': '0.1165', 'grad_norm': '4.227', 'learning_rate': '1.049e-05', 'epoch': '1.056'} | |
| {'loss': '0.1285', 'grad_norm': '1.124', 'learning_rate': '1.048e-05', 'epoch': '1.057'} | |
| {'loss': '0.1097', 'grad_norm': '3.399', 'learning_rate': '1.048e-05', 'epoch': '1.057'} | |
| {'loss': '0.1027', 'grad_norm': '3.647', 'learning_rate': '1.047e-05', 'epoch': '1.058'} | |
| {'eval_ms_marco_loss': '0.03489', 'eval_val-ms-marco-768_cosine_accuracy': '0.9987', 'eval_val-ms-marco-512_cosine_accuracy': '0.9983', 'eval_val-ms-marco-256_cosine_accuracy': '0.9987', 'eval_val-ms-marco-128_cosine_accuracy': '0.9983', 'eval_val-ms-marco-64_cosine_accuracy': '0.9987', 'eval_sequential_score': '0.9987', 'eval_ms_marco_runtime': '33.73', 'eval_ms_marco_samples_per_second': '296.5', 'eval_ms_marco_steps_per_second': '9.281', 'epoch': '1.058'} | |
| {'loss': '0.1187', 'grad_norm': '5.925', 'learning_rate': '1.046e-05', 'epoch': '1.058'} | |
| {'loss': '0.1085', 'grad_norm': '7.588', 'learning_rate': '1.046e-05', 'epoch': '1.059'} | |
| {'loss': '0.1165', 'grad_norm': '2.078', 'learning_rate': '1.045e-05', 'epoch': '1.059'} | |
| {'loss': '0.1126', 'grad_norm': '2.825', 'learning_rate': '1.045e-05', 'epoch': '1.06'} | |
| {'loss': '0.1184', 'grad_norm': '4.096', 'learning_rate': '1.044e-05', 'epoch': '1.06'} | |
| {'loss': '0.1166', 'grad_norm': '4.217', 'learning_rate': '1.044e-05', 'epoch': '1.061'} | |
| {'loss': '0.1034', 'grad_norm': '1.448', 'learning_rate': '1.043e-05', 'epoch': '1.061'} | |
| {'loss': '0.2187', 'grad_norm': '0.5886', 'learning_rate': '1.043e-05', 'epoch': '1.062'} | |
| {'loss': '0.1166', 'grad_norm': '6.555', 'learning_rate': '1.042e-05', 'epoch': '1.062'} | |
| {'loss': '0.2327', 'grad_norm': '0.6071', 'learning_rate': '1.042e-05', 'epoch': '1.062'} | |
| {'loss': '0.1119', 'grad_norm': '5.675', 'learning_rate': '1.041e-05', 'epoch': '1.063'} | |
| {'loss': '0.1296', 'grad_norm': '1.168', 'learning_rate': '1.041e-05', 'epoch': '1.063'} | |
| {'loss': '0.2222', 'grad_norm': '2.617', 'learning_rate': '1.04e-05', 'epoch': '1.064'} | |
| {'loss': '0.1187', 'grad_norm': '0.8349', 'learning_rate': '1.04e-05', 'epoch': '1.064'} | |
| {'loss': '0.1277', 'grad_norm': '1.17', 'learning_rate': '1.039e-05', 'epoch': '1.065'} | |
| {'loss': '0.1191', 'grad_norm': '0.8263', 'learning_rate': '1.039e-05', 'epoch': '1.065'} | |
| {'loss': '0.1089', 'grad_norm': '2.791', 'learning_rate': '1.038e-05', 'epoch': '1.066'} | |
| {'loss': '0.1246', 'grad_norm': '0.456', 'learning_rate': '1.037e-05', 'epoch': '1.066'} | |
| {'loss': '0.1157', 'grad_norm': '2.261', 'learning_rate': '1.037e-05', 'epoch': '1.067'} | |
| {'loss': '0.2153', 'grad_norm': '0.1837', 'learning_rate': '1.036e-05', 'epoch': '1.067'} | |
| {'loss': '0.1088', 'grad_norm': '3.484', 'learning_rate': '1.036e-05', 'epoch': '1.068'} | |
| {'loss': '0.1316', 'grad_norm': '1.109', 'learning_rate': '1.035e-05', 'epoch': '1.068'} | |
| {'loss': '0.1224', 'grad_norm': '1.916', 'learning_rate': '1.035e-05', 'epoch': '1.069'} | |
| {'loss': '0.1143', 'grad_norm': '0.4645', 'learning_rate': '1.034e-05', 'epoch': '1.069'} | |
| {'loss': '0.118', 'grad_norm': '5.106', 'learning_rate': '1.034e-05', 'epoch': '1.07'} | |
| {'loss': '0.1036', 'grad_norm': '0.9106', 'learning_rate': '1.033e-05', 'epoch': '1.07'} | |
| {'loss': '0.1156', 'grad_norm': '0.2982', 'learning_rate': '1.033e-05', 'epoch': '1.071'} | |
| {'loss': '0.09368', 'grad_norm': '0.8308', 'learning_rate': '1.032e-05', 'epoch': '1.071'} | |
| {'loss': '0.1919', 'grad_norm': '4.781', 'learning_rate': '1.032e-05', 'epoch': '1.072'} | |
| {'loss': '0.1169', 'grad_norm': '0.2589', 'learning_rate': '1.031e-05', 'epoch': '1.072'} | |
| {'loss': '0.09145', 'grad_norm': '0.3928', 'learning_rate': '1.031e-05', 'epoch': '1.072'} | |
| {'loss': '0.1035', 'grad_norm': '1.092', 'learning_rate': '1.03e-05', 'epoch': '1.073'} | |
| {'loss': '0.1058', 'grad_norm': '0.9142', 'learning_rate': '1.03e-05', 'epoch': '1.073'} | |
| {'loss': '0.11', 'grad_norm': '2.293', 'learning_rate': '1.029e-05', 'epoch': '1.074'} | |
| {'loss': '0.1064', 'grad_norm': '0.9888', 'learning_rate': '1.028e-05', 'epoch': '1.074'} | |
| {'loss': '0.1115', 'grad_norm': '2.413', 'learning_rate': '1.028e-05', 'epoch': '1.075'} | |
| {'loss': '0.1174', 'grad_norm': '6.23', 'learning_rate': '1.027e-05', 'epoch': '1.075'} | |
| {'loss': '0.1047', 'grad_norm': '0.7181', 'learning_rate': '1.027e-05', 'epoch': '1.076'} | |
| {'loss': '0.1012', 'grad_norm': '3.096', 'learning_rate': '1.026e-05', 'epoch': '1.076'} | |
| {'loss': '0.1028', 'grad_norm': '2.337', 'learning_rate': '1.026e-05', 'epoch': '1.077'} | |
| {'loss': '0.1089', 'grad_norm': '2.407', 'learning_rate': '1.025e-05', 'epoch': '1.077'} | |
| {'loss': '0.111', 'grad_norm': '2.117', 'learning_rate': '1.025e-05', 'epoch': '1.078'} | |
| {'loss': '0.106', 'grad_norm': '1.527', 'learning_rate': '1.024e-05', 'epoch': '1.078'} | |
| {'loss': '0.1155', 'grad_norm': '0.9138', 'learning_rate': '1.024e-05', 'epoch': '1.079'} | |
| {'loss': '0.207', 'grad_norm': '7.951', 'learning_rate': '1.023e-05', 'epoch': '1.079'} | |
| {'loss': '0.09006', 'grad_norm': '1.218', 'learning_rate': '1.023e-05', 'epoch': '1.08'} | |
| {'loss': '0.1075', 'grad_norm': '3.468', 'learning_rate': '1.022e-05', 'epoch': '1.08'} | |
| {'loss': '0.1919', 'grad_norm': '1.73', 'learning_rate': '1.022e-05', 'epoch': '1.081'} | |
| {'loss': '0.1094', 'grad_norm': '1.27', 'learning_rate': '1.021e-05', 'epoch': '1.081'} | |
| {'loss': '0.1013', 'grad_norm': '0.1321', 'learning_rate': '1.021e-05', 'epoch': '1.082'} | |
| {'loss': '0.1088', 'grad_norm': '7.961', 'learning_rate': '1.02e-05', 'epoch': '1.082'} | |
| {'loss': '0.105', 'grad_norm': '1.081', 'learning_rate': '1.019e-05', 'epoch': '1.082'} | |
| {'loss': '0.1084', 'grad_norm': '0.8059', 'learning_rate': '1.019e-05', 'epoch': '1.083'} | |
| {'loss': '0.116', 'grad_norm': '0.7255', 'learning_rate': '1.018e-05', 'epoch': '1.083'} | |
| {'loss': '0.1069', 'grad_norm': '2.082', 'learning_rate': '1.018e-05', 'epoch': '1.084'} | |
| {'loss': '0.1162', 'grad_norm': '1.65', 'learning_rate': '1.017e-05', 'epoch': '1.084'} | |
| {'loss': '0.1096', 'grad_norm': '1.11', 'learning_rate': '1.017e-05', 'epoch': '1.085'} | |
| {'loss': '0.2154', 'grad_norm': '2.139', 'learning_rate': '1.016e-05', 'epoch': '1.085'} | |
| {'loss': '0.1208', 'grad_norm': '2.208', 'learning_rate': '1.016e-05', 'epoch': '1.086'} | |
| {'loss': '0.1139', 'grad_norm': '5.812', 'learning_rate': '1.015e-05', 'epoch': '1.086'} | |
| {'eval_ms_marco_loss': '0.031', 'eval_val-ms-marco-768_cosine_accuracy': '0.9987', 'eval_val-ms-marco-512_cosine_accuracy': '0.9987', 'eval_val-ms-marco-256_cosine_accuracy': '0.999', 'eval_val-ms-marco-128_cosine_accuracy': '0.9987', 'eval_val-ms-marco-64_cosine_accuracy': '0.9983', 'eval_sequential_score': '0.9987', 'eval_ms_marco_runtime': '33.82', 'eval_ms_marco_samples_per_second': '295.7', 'eval_ms_marco_steps_per_second': '9.254', 'epoch': '1.086'} | |
| {'loss': '0.1805', 'grad_norm': '2.401', 'learning_rate': '1.015e-05', 'epoch': '1.087'} | |
| {'loss': '0.1066', 'grad_norm': '2.928', 'learning_rate': '1.014e-05', 'epoch': '1.087'} | |
| {'loss': '0.1142', 'grad_norm': '1.661', 'learning_rate': '1.014e-05', 'epoch': '1.088'} | |
| {'loss': '0.0989', 'grad_norm': '1.142', 'learning_rate': '1.013e-05', 'epoch': '1.088'} | |
| {'loss': '0.1077', 'grad_norm': '2.509', 'learning_rate': '1.013e-05', 'epoch': '1.089'} | |
| {'loss': '0.11', 'grad_norm': '5.815', 'learning_rate': '1.012e-05', 'epoch': '1.089'} | |
| {'loss': '0.1831', 'grad_norm': '3.227', 'learning_rate': '1.012e-05', 'epoch': '1.09'} | |
| {'loss': '0.1148', 'grad_norm': '0.2668', 'learning_rate': '1.011e-05', 'epoch': '1.09'} | |
| {'loss': '0.09468', 'grad_norm': '0.3514', 'learning_rate': '1.01e-05', 'epoch': '1.091'} | |
| {'loss': '0.1053', 'grad_norm': '0.2091', 'learning_rate': '1.01e-05', 'epoch': '1.091'} | |
| {'loss': '0.09706', 'grad_norm': '1.332', 'learning_rate': '1.009e-05', 'epoch': '1.092'} | |
| {'loss': '0.09817', 'grad_norm': '0.5859', 'learning_rate': '1.009e-05', 'epoch': '1.092'} | |
| {'loss': '0.2365', 'grad_norm': '1.081', 'learning_rate': '1.008e-05', 'epoch': '1.093'} | |
| {'loss': '0.113', 'grad_norm': '0.629', 'learning_rate': '1.008e-05', 'epoch': '1.093'} | |
| {'loss': '0.1017', 'grad_norm': '0.2569', 'learning_rate': '1.007e-05', 'epoch': '1.093'} | |
| {'loss': '0.09832', 'grad_norm': '1.177', 'learning_rate': '1.007e-05', 'epoch': '1.094'} | |
| {'loss': '0.112', 'grad_norm': '1.49', 'learning_rate': '1.006e-05', 'epoch': '1.094'} | |
| {'loss': '0.1025', 'grad_norm': '3.882', 'learning_rate': '1.006e-05', 'epoch': '1.095'} | |
| {'loss': '0.2415', 'grad_norm': '3.099', 'learning_rate': '1.005e-05', 'epoch': '1.095'} | |
| {'loss': '0.1182', 'grad_norm': '5.433', 'learning_rate': '1.005e-05', 'epoch': '1.096'} | |
| {'loss': '0.1012', 'grad_norm': '5.916', 'learning_rate': '1.004e-05', 'epoch': '1.096'} | |
| {'loss': '0.1016', 'grad_norm': '4.116', 'learning_rate': '1.004e-05', 'epoch': '1.097'} | |
| {'loss': '0.09726', 'grad_norm': '7.917', 'learning_rate': '1.003e-05', 'epoch': '1.097'} | |
| {'loss': '0.2358', 'grad_norm': '0.6349', 'learning_rate': '1.003e-05', 'epoch': '1.098'} | |
| {'loss': '0.09147', 'grad_norm': '3.309', 'learning_rate': '1.002e-05', 'epoch': '1.098'} | |
| {'loss': '0.1055', 'grad_norm': '1.132', 'learning_rate': '1.001e-05', 'epoch': '1.099'} | |
| {'loss': '0.1153', 'grad_norm': '3.489', 'learning_rate': '1.001e-05', 'epoch': '1.099'} | |
| {'loss': '0.1087', 'grad_norm': '2.58', 'learning_rate': '1e-05', 'epoch': '1.1'} | |
| {'loss': '0.1088', 'grad_norm': '4.126', 'learning_rate': '9.999e-06', 'epoch': '1.1'} | |
| {'loss': '0.1009', 'grad_norm': '5.741', 'learning_rate': '9.993e-06', 'epoch': '1.101'} | |
| {'loss': '0.1065', 'grad_norm': '1.372', 'learning_rate': '9.988e-06', 'epoch': '1.101'} | |
| {'loss': '0.09279', 'grad_norm': '2.597', 'learning_rate': '9.983e-06', 'epoch': '1.102'} | |
| {'loss': '0.09131', 'grad_norm': '1.114', 'learning_rate': '9.977e-06', 'epoch': '1.102'} | |
| {'loss': '0.09495', 'grad_norm': '2.224', 'learning_rate': '9.972e-06', 'epoch': '1.103'} | |
| {'loss': '0.09568', 'grad_norm': '3.408', 'learning_rate': '9.967e-06', 'epoch': '1.103'} | |
| {'loss': '0.1816', 'grad_norm': '2.281', 'learning_rate': '9.962e-06', 'epoch': '1.103'} | |
| {'loss': '0.1157', 'grad_norm': '0.4509', 'learning_rate': '9.956e-06', 'epoch': '1.104'} | |
| {'loss': '0.204', 'grad_norm': '6.034', 'learning_rate': '9.951e-06', 'epoch': '1.104'} | |
| {'loss': '0.1006', 'grad_norm': '3.559', 'learning_rate': '9.946e-06', 'epoch': '1.105'} | |
| {'loss': '0.1007', 'grad_norm': '0.477', 'learning_rate': '9.94e-06', 'epoch': '1.105'} | |
| {'loss': '0.09842', 'grad_norm': '1.07', 'learning_rate': '9.935e-06', 'epoch': '1.106'} | |
| {'loss': '0.09834', 'grad_norm': '1.292', 'learning_rate': '9.93e-06', 'epoch': '1.106'} | |
| {'loss': '0.08633', 'grad_norm': '5.249', 'learning_rate': '9.925e-06', 'epoch': '1.107'} | |
| {'loss': '0.112', 'grad_norm': '0.5568', 'learning_rate': '9.919e-06', 'epoch': '1.107'} | |
| {'loss': '0.0881', 'grad_norm': '2.11', 'learning_rate': '9.914e-06', 'epoch': '1.108'} | |
| {'loss': '0.1096', 'grad_norm': '1.995', 'learning_rate': '9.909e-06', 'epoch': '1.108'} | |
| {'loss': '0.1106', 'grad_norm': '1.411', 'learning_rate': '9.903e-06', 'epoch': '1.109'} | |
| {'loss': '0.1164', 'grad_norm': '4.978', 'learning_rate': '9.898e-06', 'epoch': '1.109'} | |
| {'loss': '0.09391', 'grad_norm': '2.785', 'learning_rate': '9.893e-06', 'epoch': '1.11'} | |
| {'loss': '0.1007', 'grad_norm': '0.7657', 'learning_rate': '9.887e-06', 'epoch': '1.11'} | |
| {'loss': '0.2269', 'grad_norm': '0.832', 'learning_rate': '9.882e-06', 'epoch': '1.111'} | |
| {'loss': '0.1034', 'grad_norm': '5.803', 'learning_rate': '9.877e-06', 'epoch': '1.111'} | |
| {'loss': '0.09748', 'grad_norm': '0.7809', 'learning_rate': '9.872e-06', 'epoch': '1.112'} | |
| {'loss': '0.1042', 'grad_norm': '1.613', 'learning_rate': '9.866e-06', 'epoch': '1.112'} | |
| {'loss': '0.1005', 'grad_norm': '2.29', 'learning_rate': '9.861e-06', 'epoch': '1.113'} | |
| {'loss': '0.1143', 'grad_norm': '4.848', 'learning_rate': '9.856e-06', 'epoch': '1.113'} | |
| {'loss': '0.09965', 'grad_norm': '0.7419', 'learning_rate': '9.85e-06', 'epoch': '1.113'} | |
| {'loss': '0.09915', 'grad_norm': '1.823', 'learning_rate': '9.845e-06', 'epoch': '1.114'} | |
| {'loss': '0.08926', 'grad_norm': '0.2598', 'learning_rate': '9.84e-06', 'epoch': '1.114'} | |
| {'loss': '0.1107', 'grad_norm': '4.37', 'learning_rate': '9.835e-06', 'epoch': '1.115'} | |
| {'eval_ms_marco_loss': '0.03066', 'eval_val-ms-marco-768_cosine_accuracy': '0.999', 'eval_val-ms-marco-512_cosine_accuracy': '0.999', 'eval_val-ms-marco-256_cosine_accuracy': '0.999', 'eval_val-ms-marco-128_cosine_accuracy': '0.999', 'eval_val-ms-marco-64_cosine_accuracy': '0.999', 'eval_sequential_score': '0.999', 'eval_ms_marco_runtime': '34.09', 'eval_ms_marco_samples_per_second': '293.4', 'eval_ms_marco_steps_per_second': '9.182', 'epoch': '1.115'} | |
| {'loss': '0.1061', 'grad_norm': '3.734', 'learning_rate': '9.829e-06', 'epoch': '1.115'} | |
| {'loss': '0.1073', 'grad_norm': '0.6095', 'learning_rate': '9.824e-06', 'epoch': '1.116'} | |
| {'loss': '0.1108', 'grad_norm': '5.941', 'learning_rate': '9.819e-06', 'epoch': '1.116'} | |
| {'loss': '0.1057', 'grad_norm': '2.801', 'learning_rate': '9.813e-06', 'epoch': '1.117'} | |
| {'loss': '0.089', 'grad_norm': '0.7363', 'learning_rate': '9.808e-06', 'epoch': '1.117'} | |
| {'loss': '0.08048', 'grad_norm': '2.874', 'learning_rate': '9.803e-06', 'epoch': '1.118'} | |
| {'loss': '0.1035', 'grad_norm': '0.8072', 'learning_rate': '9.797e-06', 'epoch': '1.118'} | |
| {'loss': '0.08826', 'grad_norm': '4.309', 'learning_rate': '9.792e-06', 'epoch': '1.119'} | |
| {'loss': '0.0945', 'grad_norm': '3.741', 'learning_rate': '9.787e-06', 'epoch': '1.119'} | |
| {'loss': '0.0934', 'grad_norm': '3.719', 'learning_rate': '9.782e-06', 'epoch': '1.12'} | |
| {'loss': '0.09663', 'grad_norm': '1.424', 'learning_rate': '9.776e-06', 'epoch': '1.12'} | |
| {'loss': '0.2275', 'grad_norm': '2.275', 'learning_rate': '9.771e-06', 'epoch': '1.121'} | |
| {'loss': '0.1905', 'grad_norm': '5.383', 'learning_rate': '9.766e-06', 'epoch': '1.121'} | |
| {'loss': '0.09699', 'grad_norm': '4.173', 'learning_rate': '9.76e-06', 'epoch': '1.122'} | |
| {'loss': '0.08816', 'grad_norm': '0.2791', 'learning_rate': '9.755e-06', 'epoch': '1.122'} | |
| {'loss': '0.08853', 'grad_norm': '2.589', 'learning_rate': '9.75e-06', 'epoch': '1.123'} | |
| {'loss': '0.204', 'grad_norm': '5.082', 'learning_rate': '9.745e-06', 'epoch': '1.123'} | |
| {'loss': '0.2704', 'grad_norm': '0.7242', 'learning_rate': '9.739e-06', 'epoch': '1.123'} | |
| {'loss': '0.1168', 'grad_norm': '1.236', 'learning_rate': '9.734e-06', 'epoch': '1.124'} | |
| {'loss': '0.13', 'grad_norm': '0.3646', 'learning_rate': '9.729e-06', 'epoch': '1.124'} | |
| {'loss': '0.1045', 'grad_norm': '1.511', 'learning_rate': '9.723e-06', 'epoch': '1.125'} | |
| {'loss': '0.1038', 'grad_norm': '0.7631', 'learning_rate': '9.718e-06', 'epoch': '1.125'} | |
| {'loss': '0.1009', 'grad_norm': '3.86', 'learning_rate': '9.713e-06', 'epoch': '1.126'} | |
| {'loss': '0.09287', 'grad_norm': '1.588', 'learning_rate': '9.707e-06', 'epoch': '1.126'} | |
| {'loss': '0.1997', 'grad_norm': '3.53', 'learning_rate': '9.702e-06', 'epoch': '1.127'} | |
| {'loss': '0.1058', 'grad_norm': '11.1', 'learning_rate': '9.697e-06', 'epoch': '1.127'} | |
| {'loss': '0.109', 'grad_norm': '5.122', 'learning_rate': '9.692e-06', 'epoch': '1.128'} | |
| {'loss': '0.08854', 'grad_norm': '1.871', 'learning_rate': '9.686e-06', 'epoch': '1.128'} | |
| {'loss': '0.09247', 'grad_norm': '1.737', 'learning_rate': '9.681e-06', 'epoch': '1.129'} | |
| {'loss': '0.0942', 'grad_norm': '0.4874', 'learning_rate': '9.676e-06', 'epoch': '1.129'} | |
| {'loss': '0.1089', 'grad_norm': '5.928', 'learning_rate': '9.67e-06', 'epoch': '1.13'} | |
| {'loss': '0.1144', 'grad_norm': '0.5369', 'learning_rate': '9.665e-06', 'epoch': '1.13'} | |
| {'loss': '0.08285', 'grad_norm': '0.2054', 'learning_rate': '9.66e-06', 'epoch': '1.131'} | |
| {'loss': '0.2029', 'grad_norm': '3.437', 'learning_rate': '9.655e-06', 'epoch': '1.131'} | |
| {'loss': '0.1012', 'grad_norm': '0.2876', 'learning_rate': '9.649e-06', 'epoch': '1.132'} | |
| {'loss': '0.1055', 'grad_norm': '3.541', 'learning_rate': '9.644e-06', 'epoch': '1.132'} | |
| {'loss': '0.08288', 'grad_norm': '3.841', 'learning_rate': '9.639e-06', 'epoch': '1.133'} | |
| {'loss': '0.1011', 'grad_norm': '0.6177', 'learning_rate': '9.633e-06', 'epoch': '1.133'} | |
| {'loss': '0.1006', 'grad_norm': '1.078', 'learning_rate': '9.628e-06', 'epoch': '1.133'} | |
| {'loss': '0.0774', 'grad_norm': '1.549', 'learning_rate': '9.623e-06', 'epoch': '1.134'} | |
| {'loss': '0.09856', 'grad_norm': '1.842', 'learning_rate': '9.618e-06', 'epoch': '1.134'} | |
| {'loss': '0.1109', 'grad_norm': '1.658', 'learning_rate': '9.612e-06', 'epoch': '1.135'} | |
| {'loss': '0.09993', 'grad_norm': '3.336', 'learning_rate': '9.607e-06', 'epoch': '1.135'} | |
| {'loss': '0.09813', 'grad_norm': '1.905', 'learning_rate': '9.602e-06', 'epoch': '1.136'} | |
| {'loss': '0.07356', 'grad_norm': '2.714', 'learning_rate': '9.596e-06', 'epoch': '1.136'} | |
| {'loss': '0.1029', 'grad_norm': '5.095', 'learning_rate': '9.591e-06', 'epoch': '1.137'} | |
| {'loss': '0.1058', 'grad_norm': '1.686', 'learning_rate': '9.586e-06', 'epoch': '1.137'} | |
| {'loss': '0.09024', 'grad_norm': '2.495', 'learning_rate': '9.58e-06', 'epoch': '1.138'} | |
| {'loss': '0.09615', 'grad_norm': '2.013', 'learning_rate': '9.575e-06', 'epoch': '1.138'} | |
| {'loss': '0.2203', 'grad_norm': '6.586', 'learning_rate': '9.57e-06', 'epoch': '1.139'} | |
| {'loss': '0.09219', 'grad_norm': '4.453', 'learning_rate': '9.565e-06', 'epoch': '1.139'} | |
| {'loss': '0.08737', 'grad_norm': '2.821', 'learning_rate': '9.559e-06', 'epoch': '1.14'} | |
| {'loss': '0.08992', 'grad_norm': '0.5445', 'learning_rate': '9.554e-06', 'epoch': '1.14'} | |
| {'loss': '0.09271', 'grad_norm': '0.3159', 'learning_rate': '9.549e-06', 'epoch': '1.141'} | |
| {'loss': '0.09734', 'grad_norm': '4.319', 'learning_rate': '9.543e-06', 'epoch': '1.141'} | |
| {'loss': '0.09551', 'grad_norm': '3.467', 'learning_rate': '9.538e-06', 'epoch': '1.142'} | |
| {'loss': '0.1007', 'grad_norm': '4.426', 'learning_rate': '9.533e-06', 'epoch': '1.142'} | |
| {'loss': '0.09821', 'grad_norm': '2.751', 'learning_rate': '9.528e-06', 'epoch': '1.143'} | |
| {'loss': '0.0946', 'grad_norm': '0.8053', 'learning_rate': '9.522e-06', 'epoch': '1.143'} | |
| {'loss': '0.08695', 'grad_norm': '3.485', 'learning_rate': '9.517e-06', 'epoch': '1.143'} | |
| {'eval_ms_marco_loss': '0.02937', 'eval_val-ms-marco-768_cosine_accuracy': '0.9993', 'eval_val-ms-marco-512_cosine_accuracy': '0.9997', 'eval_val-ms-marco-256_cosine_accuracy': '0.9997', 'eval_val-ms-marco-128_cosine_accuracy': '0.9993', 'eval_val-ms-marco-64_cosine_accuracy': '0.999', 'eval_sequential_score': '0.9993', 'eval_ms_marco_runtime': '33.94', 'eval_ms_marco_samples_per_second': '294.6', 'eval_ms_marco_steps_per_second': '9.222', 'epoch': '1.143'} | |
| {'loss': '0.08985', 'grad_norm': '0.4441', 'learning_rate': '9.512e-06', 'epoch': '1.144'} | |
| {'loss': '0.09132', 'grad_norm': '0.3741', 'learning_rate': '9.506e-06', 'epoch': '1.144'} | |
| {'loss': '0.0972', 'grad_norm': '0.3908', 'learning_rate': '9.501e-06', 'epoch': '1.145'} | |
| {'loss': '0.09427', 'grad_norm': '1.091', 'learning_rate': '9.496e-06', 'epoch': '1.145'} | |
| {'loss': '0.09496', 'grad_norm': '3.573', 'learning_rate': '9.49e-06', 'epoch': '1.146'} | |
| {'loss': '0.1068', 'grad_norm': '1.692', 'learning_rate': '9.485e-06', 'epoch': '1.146'} | |
| {'loss': '0.09879', 'grad_norm': '1.546', 'learning_rate': '9.48e-06', 'epoch': '1.147'} | |
| {'loss': '0.1969', 'grad_norm': '5.921', 'learning_rate': '9.475e-06', 'epoch': '1.147'} | |
| {'loss': '0.0967', 'grad_norm': '1.28', 'learning_rate': '9.469e-06', 'epoch': '1.148'} | |
| {'loss': '0.09034', 'grad_norm': '1.735', 'learning_rate': '9.464e-06', 'epoch': '1.148'} | |
| {'loss': '0.09361', 'grad_norm': '5.22', 'learning_rate': '9.459e-06', 'epoch': '1.149'} | |
| {'loss': '0.07997', 'grad_norm': '1.57', 'learning_rate': '9.453e-06', 'epoch': '1.149'} | |
| {'loss': '0.09259', 'grad_norm': '1.311', 'learning_rate': '9.448e-06', 'epoch': '1.15'} | |
| {'loss': '0.1146', 'grad_norm': '7.106', 'learning_rate': '9.443e-06', 'epoch': '1.15'} | |
| {'loss': '0.07921', 'grad_norm': '1.017', 'learning_rate': '9.438e-06', 'epoch': '1.151'} | |
| {'loss': '0.09874', 'grad_norm': '2.363', 'learning_rate': '9.432e-06', 'epoch': '1.151'} | |
| {'loss': '0.1009', 'grad_norm': '0.3195', 'learning_rate': '9.427e-06', 'epoch': '1.152'} | |
| {'loss': '0.08229', 'grad_norm': '0.3647', 'learning_rate': '9.422e-06', 'epoch': '1.152'} | |
| {'loss': '0.1065', 'grad_norm': '0.67', 'learning_rate': '9.416e-06', 'epoch': '1.153'} | |
| {'loss': '0.1024', 'grad_norm': '1.656', 'learning_rate': '9.411e-06', 'epoch': '1.153'} | |
| {'loss': '0.0887', 'grad_norm': '0.7883', 'learning_rate': '9.406e-06', 'epoch': '1.153'} | |
| {'loss': '0.1035', 'grad_norm': '2.298', 'learning_rate': '9.4e-06', 'epoch': '1.154'} | |
| {'loss': '0.2003', 'grad_norm': '0.1707', 'learning_rate': '9.395e-06', 'epoch': '1.154'} | |
| {'loss': '0.08582', 'grad_norm': '0.7727', 'learning_rate': '9.39e-06', 'epoch': '1.155'} | |
| {'loss': '0.08914', 'grad_norm': '3.105', 'learning_rate': '9.385e-06', 'epoch': '1.155'} | |
| {'loss': '0.09291', 'grad_norm': '3.06', 'learning_rate': '9.379e-06', 'epoch': '1.156'} | |
| {'loss': '0.2178', 'grad_norm': '2.159', 'learning_rate': '9.374e-06', 'epoch': '1.156'} | |
| {'loss': '0.09558', 'grad_norm': '6.371', 'learning_rate': '9.369e-06', 'epoch': '1.157'} | |
| {'loss': '0.1005', 'grad_norm': '0.4349', 'learning_rate': '9.363e-06', 'epoch': '1.157'} | |
| {'loss': '0.08631', 'grad_norm': '1.392', 'learning_rate': '9.358e-06', 'epoch': '1.158'} | |
| {'loss': '0.09421', 'grad_norm': '0.2167', 'learning_rate': '9.353e-06', 'epoch': '1.158'} | |
| {'loss': '0.09634', 'grad_norm': '1.484', 'learning_rate': '9.348e-06', 'epoch': '1.159'} | |
| {'loss': '0.09054', 'grad_norm': '2.127', 'learning_rate': '9.342e-06', 'epoch': '1.159'} | |
| {'loss': '0.08752', 'grad_norm': '0.1683', 'learning_rate': '9.337e-06', 'epoch': '1.16'} | |
| {'loss': '0.09956', 'grad_norm': '0.6896', 'learning_rate': '9.332e-06', 'epoch': '1.16'} | |
| {'loss': '0.08395', 'grad_norm': '0.3252', 'learning_rate': '9.326e-06', 'epoch': '1.161'} | |
| {'loss': '0.08457', 'grad_norm': '0.2082', 'learning_rate': '9.321e-06', 'epoch': '1.161'} | |
| {'loss': '0.107', 'grad_norm': '4.383', 'learning_rate': '9.316e-06', 'epoch': '1.162'} | |
| {'loss': '0.08358', 'grad_norm': '1.263', 'learning_rate': '9.31e-06', 'epoch': '1.162'} | |
| {'loss': '0.1802', 'grad_norm': '0.3221', 'learning_rate': '9.305e-06', 'epoch': '1.163'} | |
| {'loss': '0.08806', 'grad_norm': '0.4674', 'learning_rate': '9.3e-06', 'epoch': '1.163'} | |
| {'loss': '0.09045', 'grad_norm': '0.1093', 'learning_rate': '9.295e-06', 'epoch': '1.163'} | |
| {'loss': '0.09398', 'grad_norm': '1.124', 'learning_rate': '9.289e-06', 'epoch': '1.164'} | |
| {'loss': '0.1035', 'grad_norm': '4.458', 'learning_rate': '9.284e-06', 'epoch': '1.164'} | |
| {'loss': '0.09868', 'grad_norm': '1.814', 'learning_rate': '9.279e-06', 'epoch': '1.165'} | |
| {'loss': '0.2107', 'grad_norm': '3.327', 'learning_rate': '9.273e-06', 'epoch': '1.165'} | |
| {'loss': '0.09194', 'grad_norm': '2.106', 'learning_rate': '9.268e-06', 'epoch': '1.166'} | |
| {'loss': '0.08543', 'grad_norm': '1.818', 'learning_rate': '9.263e-06', 'epoch': '1.166'} | |
| {'loss': '0.0946', 'grad_norm': '0.7188', 'learning_rate': '9.258e-06', 'epoch': '1.167'} | |
| {'loss': '0.1019', 'grad_norm': '0.1272', 'learning_rate': '9.252e-06', 'epoch': '1.167'} | |
| {'loss': '0.09863', 'grad_norm': '4.564', 'learning_rate': '9.247e-06', 'epoch': '1.168'} | |
| {'loss': '0.08255', 'grad_norm': '0.8258', 'learning_rate': '9.242e-06', 'epoch': '1.168'} | |
| {'loss': '0.1131', 'grad_norm': '0.9629', 'learning_rate': '9.236e-06', 'epoch': '1.169'} | |
| {'loss': '0.0882', 'grad_norm': '0.9496', 'learning_rate': '9.231e-06', 'epoch': '1.169'} | |
| {'loss': '0.1964', 'grad_norm': '1.592', 'learning_rate': '9.226e-06', 'epoch': '1.17'} | |
| {'loss': '0.08191', 'grad_norm': '0.718', 'learning_rate': '9.22e-06', 'epoch': '1.17'} | |
| {'loss': '0.1912', 'grad_norm': '0.4277', 'learning_rate': '9.215e-06', 'epoch': '1.171'} | |
| {'loss': '0.2123', 'grad_norm': '1.631', 'learning_rate': '9.21e-06', 'epoch': '1.171'} | |
| {'loss': '0.08692', 'grad_norm': '2.018', 'learning_rate': '9.205e-06', 'epoch': '1.172'} | |
| {'loss': '0.08227', 'grad_norm': '0.9648', 'learning_rate': '9.199e-06', 'epoch': '1.172'} | |
| {'eval_ms_marco_loss': '0.02788', 'eval_val-ms-marco-768_cosine_accuracy': '1', 'eval_val-ms-marco-512_cosine_accuracy': '1', 'eval_val-ms-marco-256_cosine_accuracy': '0.9993', 'eval_val-ms-marco-128_cosine_accuracy': '0.9997', 'eval_val-ms-marco-64_cosine_accuracy': '0.999', 'eval_sequential_score': '1', 'eval_ms_marco_runtime': '33.96', 'eval_ms_marco_samples_per_second': '294.5', 'eval_ms_marco_steps_per_second': '9.217', 'epoch': '1.172'} | |
| {'loss': '0.07901', 'grad_norm': '0.9754', 'learning_rate': '9.194e-06', 'epoch': '1.173'} | |
| {'loss': '0.1897', 'grad_norm': '8.264', 'learning_rate': '9.189e-06', 'epoch': '1.173'} | |
| {'loss': '0.08389', 'grad_norm': '1.197', 'learning_rate': '9.183e-06', 'epoch': '1.173'} | |
| {'loss': '0.08413', 'grad_norm': '3.889', 'learning_rate': '9.178e-06', 'epoch': '1.174'} | |
| {'loss': '0.1805', 'grad_norm': '3.968', 'learning_rate': '9.173e-06', 'epoch': '1.174'} | |
| {'loss': '0.08363', 'grad_norm': '5.573', 'learning_rate': '9.168e-06', 'epoch': '1.175'} | |
| {'loss': '0.09429', 'grad_norm': '6.455', 'learning_rate': '9.162e-06', 'epoch': '1.175'} | |
| {'loss': '0.09996', 'grad_norm': '1.528', 'learning_rate': '9.157e-06', 'epoch': '1.176'} | |
| {'loss': '0.1008', 'grad_norm': '5.181', 'learning_rate': '9.152e-06', 'epoch': '1.176'} | |
| {'loss': '0.09043', 'grad_norm': '0.3711', 'learning_rate': '9.146e-06', 'epoch': '1.177'} | |
| {'loss': '0.09344', 'grad_norm': '0.1866', 'learning_rate': '9.141e-06', 'epoch': '1.177'} | |
| {'loss': '0.07784', 'grad_norm': '0.1348', 'learning_rate': '9.136e-06', 'epoch': '1.178'} | |
| {'loss': '0.09874', 'grad_norm': '0.1464', 'learning_rate': '9.13e-06', 'epoch': '1.178'} | |
| {'loss': '0.09191', 'grad_norm': '1.744', 'learning_rate': '9.125e-06', 'epoch': '1.179'} | |
| {'loss': '0.08751', 'grad_norm': '4.896', 'learning_rate': '9.12e-06', 'epoch': '1.179'} | |
| {'loss': '0.1005', 'grad_norm': '0.9098', 'learning_rate': '9.115e-06', 'epoch': '1.18'} | |
| {'loss': '0.09664', 'grad_norm': '0.228', 'learning_rate': '9.109e-06', 'epoch': '1.18'} | |
| {'loss': '0.1686', 'grad_norm': '1.182', 'learning_rate': '9.104e-06', 'epoch': '1.181'} | |
| {'loss': '0.103', 'grad_norm': '2.059', 'learning_rate': '9.099e-06', 'epoch': '1.181'} | |
| {'loss': '0.08491', 'grad_norm': '3.642', 'learning_rate': '9.093e-06', 'epoch': '1.182'} | |
| {'loss': '0.0768', 'grad_norm': '0.5397', 'learning_rate': '9.088e-06', 'epoch': '1.182'} | |
| {'loss': '0.09612', 'grad_norm': '3.012', 'learning_rate': '9.083e-06', 'epoch': '1.183'} | |
| {'loss': '0.07901', 'grad_norm': '3.625', 'learning_rate': '9.078e-06', 'epoch': '1.183'} | |
| {'loss': '0.07871', 'grad_norm': '0.3869', 'learning_rate': '9.072e-06', 'epoch': '1.184'} | |
| {'loss': '0.07974', 'grad_norm': '4.948', 'learning_rate': '9.067e-06', 'epoch': '1.184'} | |
| {'loss': '0.09403', 'grad_norm': '1.833', 'learning_rate': '9.062e-06', 'epoch': '1.184'} | |
| {'loss': '0.08668', 'grad_norm': '1.285', 'learning_rate': '9.056e-06', 'epoch': '1.185'} | |
| {'loss': '0.09097', 'grad_norm': '3.486', 'learning_rate': '9.051e-06', 'epoch': '1.185'} | |
| {'loss': '0.1033', 'grad_norm': '2.34', 'learning_rate': '9.046e-06', 'epoch': '1.186'} | |
| {'loss': '0.1767', 'grad_norm': '1.282', 'learning_rate': '9.04e-06', 'epoch': '1.186'} | |
| {'loss': '0.09549', 'grad_norm': '0.67', 'learning_rate': '9.035e-06', 'epoch': '1.187'} | |
| {'loss': '0.08119', 'grad_norm': '1.802', 'learning_rate': '9.03e-06', 'epoch': '1.187'} | |
| {'loss': '0.09628', 'grad_norm': '1.437', 'learning_rate': '9.025e-06', 'epoch': '1.188'} | |
| {'loss': '0.08527', 'grad_norm': '0.3958', 'learning_rate': '9.019e-06', 'epoch': '1.188'} | |
| {'loss': '0.07863', 'grad_norm': '0.8126', 'learning_rate': '9.014e-06', 'epoch': '1.189'} | |
| {'loss': '0.1716', 'grad_norm': '4.943', 'learning_rate': '9.009e-06', 'epoch': '1.189'} | |
| {'loss': '0.0876', 'grad_norm': '1.08', 'learning_rate': '9.003e-06', 'epoch': '1.19'} | |
| {'loss': '0.07947', 'grad_norm': '0.5627', 'learning_rate': '8.998e-06', 'epoch': '1.19'} | |
| {'loss': '0.1062', 'grad_norm': '0.5067', 'learning_rate': '8.993e-06', 'epoch': '1.191'} | |
| {'loss': '0.08912', 'grad_norm': '1.165', 'learning_rate': '8.988e-06', 'epoch': '1.191'} | |
| {'loss': '0.08452', 'grad_norm': '4.01', 'learning_rate': '8.982e-06', 'epoch': '1.192'} | |
| {'loss': '0.08756', 'grad_norm': '2.79', 'learning_rate': '8.977e-06', 'epoch': '1.192'} | |
| {'loss': '0.08796', 'grad_norm': '2.441', 'learning_rate': '8.972e-06', 'epoch': '1.193'} | |
| {'loss': '0.07897', 'grad_norm': '0.3486', 'learning_rate': '8.966e-06', 'epoch': '1.193'} | |
| {'loss': '0.07665', 'grad_norm': '3.448', 'learning_rate': '8.961e-06', 'epoch': '1.194'} | |
| {'loss': '0.08119', 'grad_norm': '0.6297', 'learning_rate': '8.956e-06', 'epoch': '1.194'} | |
| {'loss': '0.09297', 'grad_norm': '3.341', 'learning_rate': '8.95e-06', 'epoch': '1.194'} | |
| {'loss': '0.07819', 'grad_norm': '0.7612', 'learning_rate': '8.945e-06', 'epoch': '1.195'} | |
| {'loss': '0.08163', 'grad_norm': '2.205', 'learning_rate': '8.94e-06', 'epoch': '1.195'} | |
| {'loss': '0.08297', 'grad_norm': '0.2555', 'learning_rate': '8.935e-06', 'epoch': '1.196'} | |
| {'loss': '0.0957', 'grad_norm': '1.549', 'learning_rate': '8.929e-06', 'epoch': '1.196'} | |
| {'loss': '0.09146', 'grad_norm': '1.591', 'learning_rate': '8.924e-06', 'epoch': '1.197'} | |
| {'loss': '0.09616', 'grad_norm': '3.981', 'learning_rate': '8.919e-06', 'epoch': '1.197'} | |
| {'loss': '0.08902', 'grad_norm': '0.2184', 'learning_rate': '8.913e-06', 'epoch': '1.198'} | |
| {'loss': '0.08328', 'grad_norm': '4.172', 'learning_rate': '8.908e-06', 'epoch': '1.198'} | |
| {'loss': '0.07968', 'grad_norm': '1.134', 'learning_rate': '8.903e-06', 'epoch': '1.199'} | |
| {'loss': '0.1887', 'grad_norm': '1.241', 'learning_rate': '8.898e-06', 'epoch': '1.199'} | |
| {'loss': '0.08631', 'grad_norm': '2.193', 'learning_rate': '8.892e-06', 'epoch': '1.2'} | |
| {'loss': '0.08239', 'grad_norm': '0.7888', 'learning_rate': '8.887e-06', 'epoch': '1.2'} | |
| {'loss': '0.08705', 'grad_norm': '0.1574', 'learning_rate': '8.882e-06', 'epoch': '1.201'} | |
| {'eval_ms_marco_loss': '0.03019', 'eval_val-ms-marco-768_cosine_accuracy': '0.999', 'eval_val-ms-marco-512_cosine_accuracy': '0.999', 'eval_val-ms-marco-256_cosine_accuracy': '0.999', 'eval_val-ms-marco-128_cosine_accuracy': '0.9987', 'eval_val-ms-marco-64_cosine_accuracy': '0.9993', 'eval_sequential_score': '0.999', 'eval_ms_marco_runtime': '34.17', 'eval_ms_marco_samples_per_second': '292.7', 'eval_ms_marco_steps_per_second': '9.161', 'epoch': '1.201'} | |
| {'loss': '0.07799', 'grad_norm': '1.393', 'learning_rate': '8.876e-06', 'epoch': '1.201'} | |
| {'loss': '0.08563', 'grad_norm': '0.5866', 'learning_rate': '8.871e-06', 'epoch': '1.202'} | |
| {'loss': '0.09719', 'grad_norm': '1.106', 'learning_rate': '8.866e-06', 'epoch': '1.202'} | |
| {'loss': '0.09601', 'grad_norm': '3.949', 'learning_rate': '8.86e-06', 'epoch': '1.203'} | |
| {'loss': '0.09071', 'grad_norm': '0.5785', 'learning_rate': '8.855e-06', 'epoch': '1.203'} | |
| {'loss': '0.08362', 'grad_norm': '2.394', 'learning_rate': '8.85e-06', 'epoch': '1.204'} | |
| {'loss': '0.08284', 'grad_norm': '0.5066', 'learning_rate': '8.845e-06', 'epoch': '1.204'} | |
| {'loss': '0.09583', 'grad_norm': '0.251', 'learning_rate': '8.839e-06', 'epoch': '1.204'} | |
| {'loss': '0.09394', 'grad_norm': '7.013', 'learning_rate': '8.834e-06', 'epoch': '1.205'} | |
| {'loss': '0.08998', 'grad_norm': '3.807', 'learning_rate': '8.829e-06', 'epoch': '1.205'} | |
| {'loss': '0.1702', 'grad_norm': '5.804', 'learning_rate': '8.823e-06', 'epoch': '1.206'} | |
| {'loss': '0.08593', 'grad_norm': '0.4831', 'learning_rate': '8.818e-06', 'epoch': '1.206'} | |
| {'loss': '0.0823', 'grad_norm': '0.3806', 'learning_rate': '8.813e-06', 'epoch': '1.207'} | |
| {'loss': '0.09197', 'grad_norm': '0.7675', 'learning_rate': '8.808e-06', 'epoch': '1.207'} | |
| {'loss': '0.08257', 'grad_norm': '0.2761', 'learning_rate': '8.802e-06', 'epoch': '1.208'} | |
| {'loss': '0.1018', 'grad_norm': '0.559', 'learning_rate': '8.797e-06', 'epoch': '1.208'} | |
| {'loss': '0.08199', 'grad_norm': '1.733', 'learning_rate': '8.792e-06', 'epoch': '1.209'} | |
| {'loss': '0.08684', 'grad_norm': '1.346', 'learning_rate': '8.786e-06', 'epoch': '1.209'} | |
| {'loss': '0.06461', 'grad_norm': '1.097', 'learning_rate': '8.781e-06', 'epoch': '1.21'} | |
| {'loss': '0.08258', 'grad_norm': '3.662', 'learning_rate': '8.776e-06', 'epoch': '1.21'} | |
| {'loss': '0.09862', 'grad_norm': '6.081', 'learning_rate': '8.77e-06', 'epoch': '1.211'} | |
| {'loss': '0.07979', 'grad_norm': '1.147', 'learning_rate': '8.765e-06', 'epoch': '1.211'} | |
| {'loss': '0.2074', 'grad_norm': '3.471', 'learning_rate': '8.76e-06', 'epoch': '1.212'} | |
| {'loss': '0.09268', 'grad_norm': '4.253', 'learning_rate': '8.755e-06', 'epoch': '1.212'} | |
| {'loss': '0.07883', 'grad_norm': '1.58', 'learning_rate': '8.749e-06', 'epoch': '1.213'} | |
| {'loss': '0.08489', 'grad_norm': '0.4693', 'learning_rate': '8.744e-06', 'epoch': '1.213'} | |
| {'loss': '0.07138', 'grad_norm': '2.388', 'learning_rate': '8.739e-06', 'epoch': '1.214'} | |
| {'loss': '0.08296', 'grad_norm': '5.727', 'learning_rate': '8.733e-06', 'epoch': '1.214'} | |
| {'loss': '0.07187', 'grad_norm': '1.085', 'learning_rate': '8.728e-06', 'epoch': '1.214'} | |
| {'loss': '0.09401', 'grad_norm': '1.13', 'learning_rate': '8.723e-06', 'epoch': '1.215'} | |
| {'loss': '0.2034', 'grad_norm': '0.3451', 'learning_rate': '8.718e-06', 'epoch': '1.215'} | |
| {'loss': '0.08473', 'grad_norm': '0.7438', 'learning_rate': '8.712e-06', 'epoch': '1.216'} | |
| {'loss': '0.07758', 'grad_norm': '2.138', 'learning_rate': '8.707e-06', 'epoch': '1.216'} | |
| {'loss': '0.08453', 'grad_norm': '3.172', 'learning_rate': '8.702e-06', 'epoch': '1.217'} | |
| {'loss': '0.08324', 'grad_norm': '3.203', 'learning_rate': '8.696e-06', 'epoch': '1.217'} | |
| {'loss': '0.08558', 'grad_norm': '1.401', 'learning_rate': '8.691e-06', 'epoch': '1.218'} | |
| {'loss': '0.08924', 'grad_norm': '1.261', 'learning_rate': '8.686e-06', 'epoch': '1.218'} | |
| {'loss': '0.08246', 'grad_norm': '0.804', 'learning_rate': '8.68e-06', 'epoch': '1.219'} | |
| {'loss': '0.09809', 'grad_norm': '0.5416', 'learning_rate': '8.675e-06', 'epoch': '1.219'} | |
| {'loss': '0.08137', 'grad_norm': '1.994', 'learning_rate': '8.67e-06', 'epoch': '1.22'} | |
| {'loss': '0.08125', 'grad_norm': '6.261', 'learning_rate': '8.665e-06', 'epoch': '1.22'} | |
| {'loss': '0.07869', 'grad_norm': '2.022', 'learning_rate': '8.659e-06', 'epoch': '1.221'} | |
| {'loss': '0.079', 'grad_norm': '0.07363', 'learning_rate': '8.654e-06', 'epoch': '1.221'} | |
| {'loss': '0.09446', 'grad_norm': '0.6779', 'learning_rate': '8.649e-06', 'epoch': '1.222'} | |
| {'loss': '0.07342', 'grad_norm': '1.358', 'learning_rate': '8.643e-06', 'epoch': '1.222'} | |
| {'loss': '0.07396', 'grad_norm': '5.563', 'learning_rate': '8.638e-06', 'epoch': '1.223'} | |
| {'loss': '0.08748', 'grad_norm': '5.332', 'learning_rate': '8.633e-06', 'epoch': '1.223'} | |
| {'loss': '0.08427', 'grad_norm': '1.474', 'learning_rate': '8.628e-06', 'epoch': '1.224'} | |
| {'loss': '0.0861', 'grad_norm': '5.224', 'learning_rate': '8.622e-06', 'epoch': '1.224'} | |
| {'loss': '0.0799', 'grad_norm': '3.161', 'learning_rate': '8.617e-06', 'epoch': '1.224'} | |
| {'loss': '0.07689', 'grad_norm': '2.048', 'learning_rate': '8.612e-06', 'epoch': '1.225'} | |
| {'loss': '0.08683', 'grad_norm': '0.2557', 'learning_rate': '8.606e-06', 'epoch': '1.225'} | |
| {'loss': '0.089', 'grad_norm': '5.809', 'learning_rate': '8.601e-06', 'epoch': '1.226'} | |
| {'loss': '0.06246', 'grad_norm': '2.861', 'learning_rate': '8.596e-06', 'epoch': '1.226'} | |
| {'loss': '0.07908', 'grad_norm': '2.042', 'learning_rate': '8.59e-06', 'epoch': '1.227'} | |
| {'loss': '0.09404', 'grad_norm': '2.531', 'learning_rate': '8.585e-06', 'epoch': '1.227'} | |
| {'loss': '0.086', 'grad_norm': '2.948', 'learning_rate': '8.58e-06', 'epoch': '1.228'} | |
| {'loss': '0.08605', 'grad_norm': '4.32', 'learning_rate': '8.575e-06', 'epoch': '1.228'} | |
| {'loss': '0.08335', 'grad_norm': '0.7442', 'learning_rate': '8.569e-06', 'epoch': '1.229'} | |
| {'loss': '0.09066', 'grad_norm': '1.156', 'learning_rate': '8.564e-06', 'epoch': '1.229'} | |
| {'eval_ms_marco_loss': '0.02598', 'eval_val-ms-marco-768_cosine_accuracy': '0.9997', 'eval_val-ms-marco-512_cosine_accuracy': '0.9997', 'eval_val-ms-marco-256_cosine_accuracy': '0.9997', 'eval_val-ms-marco-128_cosine_accuracy': '0.9997', 'eval_val-ms-marco-64_cosine_accuracy': '0.9997', 'eval_sequential_score': '0.9997', 'eval_ms_marco_runtime': '34.01', 'eval_ms_marco_samples_per_second': '294.1', 'eval_ms_marco_steps_per_second': '9.204', 'epoch': '1.229'} | |
| {'loss': '0.2068', 'grad_norm': '2.898', 'learning_rate': '8.559e-06', 'epoch': '1.23'} | |
| {'loss': '0.08963', 'grad_norm': '1.254', 'learning_rate': '8.553e-06', 'epoch': '1.23'} | |
| {'loss': '0.08297', 'grad_norm': '2.109', 'learning_rate': '8.548e-06', 'epoch': '1.231'} | |
| {'loss': '0.09572', 'grad_norm': '1.716', 'learning_rate': '8.543e-06', 'epoch': '1.231'} | |
| {'loss': '0.09061', 'grad_norm': '1.23', 'learning_rate': '8.538e-06', 'epoch': '1.232'} | |
| {'loss': '0.07571', 'grad_norm': '0.2024', 'learning_rate': '8.532e-06', 'epoch': '1.232'} | |
| {'loss': '0.07866', 'grad_norm': '0.5132', 'learning_rate': '8.527e-06', 'epoch': '1.233'} | |
| {'loss': '0.0688', 'grad_norm': '1.566', 'learning_rate': '8.522e-06', 'epoch': '1.233'} | |
| {'loss': '0.2356', 'grad_norm': '0.7271', 'learning_rate': '8.516e-06', 'epoch': '1.234'} | |
| {'loss': '0.1744', 'grad_norm': '0.7258', 'learning_rate': '8.511e-06', 'epoch': '1.234'} | |
| {'loss': '0.07021', 'grad_norm': '1.398', 'learning_rate': '8.506e-06', 'epoch': '1.234'} | |
| {'loss': '0.09067', 'grad_norm': '1.215', 'learning_rate': '8.5e-06', 'epoch': '1.235'} | |
| {'loss': '0.08208', 'grad_norm': '5.266', 'learning_rate': '8.495e-06', 'epoch': '1.235'} | |
| {'loss': '0.08167', 'grad_norm': '4.499', 'learning_rate': '8.49e-06', 'epoch': '1.236'} | |
| {'loss': '0.06638', 'grad_norm': '0.8301', 'learning_rate': '8.485e-06', 'epoch': '1.236'} | |
| {'loss': '0.08912', 'grad_norm': '0.2796', 'learning_rate': '8.479e-06', 'epoch': '1.237'} | |
| {'loss': '0.08868', 'grad_norm': '4.837', 'learning_rate': '8.474e-06', 'epoch': '1.237'} | |
| {'loss': '0.07976', 'grad_norm': '1.965', 'learning_rate': '8.469e-06', 'epoch': '1.238'} | |
| {'loss': '0.06857', 'grad_norm': '6.719', 'learning_rate': '8.463e-06', 'epoch': '1.238'} | |
| {'loss': '0.09342', 'grad_norm': '4.126', 'learning_rate': '8.458e-06', 'epoch': '1.239'} | |
| {'loss': '0.17', 'grad_norm': '0.1263', 'learning_rate': '8.453e-06', 'epoch': '1.239'} | |
| {'loss': '0.08055', 'grad_norm': '0.5272', 'learning_rate': '8.448e-06', 'epoch': '1.24'} | |
| {'loss': '0.08631', 'grad_norm': '0.2144', 'learning_rate': '8.442e-06', 'epoch': '1.24'} | |
| {'loss': '0.0894', 'grad_norm': '0.4165', 'learning_rate': '8.437e-06', 'epoch': '1.241'} | |
| {'loss': '0.08184', 'grad_norm': '1.242', 'learning_rate': '8.432e-06', 'epoch': '1.241'} | |
| {'loss': '0.09935', 'grad_norm': '1.992', 'learning_rate': '8.426e-06', 'epoch': '1.242'} | |
| {'loss': '0.1691', 'grad_norm': '1.133', 'learning_rate': '8.421e-06', 'epoch': '1.242'} | |
| {'loss': '0.08106', 'grad_norm': '0.2354', 'learning_rate': '8.416e-06', 'epoch': '1.243'} | |
| {'loss': '0.09585', 'grad_norm': '0.1648', 'learning_rate': '8.41e-06', 'epoch': '1.243'} | |
| {'loss': '0.08188', 'grad_norm': '1.045', 'learning_rate': '8.405e-06', 'epoch': '1.244'} | |
| {'loss': '0.08063', 'grad_norm': '3.463', 'learning_rate': '8.4e-06', 'epoch': '1.244'} | |
| {'loss': '0.0751', 'grad_norm': '0.1253', 'learning_rate': '8.395e-06', 'epoch': '1.244'} | |
| {'loss': '0.07892', 'grad_norm': '1.36', 'learning_rate': '8.389e-06', 'epoch': '1.245'} | |
| {'loss': '0.08835', 'grad_norm': '6.249', 'learning_rate': '8.384e-06', 'epoch': '1.245'} | |
| {'loss': '0.08036', 'grad_norm': '0.5841', 'learning_rate': '8.379e-06', 'epoch': '1.246'} | |
| {'loss': '0.1882', 'grad_norm': '0.9161', 'learning_rate': '8.373e-06', 'epoch': '1.246'} | |
| {'loss': '0.07372', 'grad_norm': '2.324', 'learning_rate': '8.368e-06', 'epoch': '1.247'} | |
| {'loss': '0.2162', 'grad_norm': '1.813', 'learning_rate': '8.363e-06', 'epoch': '1.247'} | |
| {'loss': '0.06803', 'grad_norm': '0.4133', 'learning_rate': '8.358e-06', 'epoch': '1.248'} | |
| {'loss': '0.07013', 'grad_norm': '1.787', 'learning_rate': '8.352e-06', 'epoch': '1.248'} | |
| {'loss': '0.07187', 'grad_norm': '3.647', 'learning_rate': '8.347e-06', 'epoch': '1.249'} | |
| {'loss': '0.09026', 'grad_norm': '2.311', 'learning_rate': '8.342e-06', 'epoch': '1.249'} | |
| {'loss': '0.08086', 'grad_norm': '5.994', 'learning_rate': '8.336e-06', 'epoch': '1.25'} | |
| {'loss': '0.0657', 'grad_norm': '3.994', 'learning_rate': '8.331e-06', 'epoch': '1.25'} | |
| {'loss': '0.08311', 'grad_norm': '1.002', 'learning_rate': '8.326e-06', 'epoch': '1.251'} | |
| {'loss': '0.08276', 'grad_norm': '1.898', 'learning_rate': '8.32e-06', 'epoch': '1.251'} | |
| {'loss': '0.07797', 'grad_norm': '1.057', 'learning_rate': '8.315e-06', 'epoch': '1.252'} | |
| {'loss': '0.07858', 'grad_norm': '2.009', 'learning_rate': '8.31e-06', 'epoch': '1.252'} | |
| {'loss': '0.09765', 'grad_norm': '1.416', 'learning_rate': '8.305e-06', 'epoch': '1.253'} | |
| {'loss': '0.07863', 'grad_norm': '1.219', 'learning_rate': '8.299e-06', 'epoch': '1.253'} | |
| {'loss': '0.08494', 'grad_norm': '2.339', 'learning_rate': '8.294e-06', 'epoch': '1.254'} | |
| {'loss': '0.1759', 'grad_norm': '2.225', 'learning_rate': '8.289e-06', 'epoch': '1.254'} | |
| {'loss': '0.07998', 'grad_norm': '0.5006', 'learning_rate': '8.283e-06', 'epoch': '1.254'} | |
| {'loss': '0.3144', 'grad_norm': '0.2471', 'learning_rate': '8.278e-06', 'epoch': '1.255'} | |
| {'loss': '0.08735', 'grad_norm': '0.7437', 'learning_rate': '8.273e-06', 'epoch': '1.255'} | |
| {'loss': '0.09624', 'grad_norm': '0.7118', 'learning_rate': '8.268e-06', 'epoch': '1.256'} | |
| {'loss': '0.07078', 'grad_norm': '0.3375', 'learning_rate': '8.262e-06', 'epoch': '1.256'} | |
| {'loss': '0.1875', 'grad_norm': '2.479', 'learning_rate': '8.257e-06', 'epoch': '1.257'} | |
| {'loss': '0.07463', 'grad_norm': '2.218', 'learning_rate': '8.252e-06', 'epoch': '1.257'} | |
| {'loss': '0.09397', 'grad_norm': '2.537', 'learning_rate': '8.246e-06', 'epoch': '1.258'} | |
| {'eval_ms_marco_loss': '0.02585', 'eval_val-ms-marco-768_cosine_accuracy': '0.9997', 'eval_val-ms-marco-512_cosine_accuracy': '0.9993', 'eval_val-ms-marco-256_cosine_accuracy': '0.9997', 'eval_val-ms-marco-128_cosine_accuracy': '0.9997', 'eval_val-ms-marco-64_cosine_accuracy': '0.9997', 'eval_sequential_score': '0.9997', 'eval_ms_marco_runtime': '33.92', 'eval_ms_marco_samples_per_second': '294.9', 'eval_ms_marco_steps_per_second': '9.229', 'epoch': '1.258'} | |
| {'loss': '0.07179', 'grad_norm': '2.424', 'learning_rate': '8.241e-06', 'epoch': '1.258'} | |
| {'loss': '0.1001', 'grad_norm': '7.421', 'learning_rate': '8.236e-06', 'epoch': '1.259'} | |
| {'loss': '0.07366', 'grad_norm': '0.3592', 'learning_rate': '8.231e-06', 'epoch': '1.259'} | |
| {'loss': '0.07374', 'grad_norm': '0.4787', 'learning_rate': '8.225e-06', 'epoch': '1.26'} | |
| {'loss': '0.2075', 'grad_norm': '0.5596', 'learning_rate': '8.22e-06', 'epoch': '1.26'} | |
| {'loss': '0.0749', 'grad_norm': '1.278', 'learning_rate': '8.215e-06', 'epoch': '1.261'} | |
| {'loss': '0.06458', 'grad_norm': '2.284', 'learning_rate': '8.209e-06', 'epoch': '1.261'} | |
| {'loss': '0.07734', 'grad_norm': '4.544', 'learning_rate': '8.204e-06', 'epoch': '1.262'} | |
| {'loss': '0.08656', 'grad_norm': '0.3471', 'learning_rate': '8.199e-06', 'epoch': '1.262'} | |
| {'loss': '0.1786', 'grad_norm': '0.6253', 'learning_rate': '8.193e-06', 'epoch': '1.263'} | |
| {'loss': '0.06828', 'grad_norm': '0.7939', 'learning_rate': '8.188e-06', 'epoch': '1.263'} | |
| {'loss': '0.07812', 'grad_norm': '0.4277', 'learning_rate': '8.183e-06', 'epoch': '1.264'} | |
| {'loss': '0.08519', 'grad_norm': '1.186', 'learning_rate': '8.178e-06', 'epoch': '1.264'} | |
| {'loss': '0.08213', 'grad_norm': '2.086', 'learning_rate': '8.172e-06', 'epoch': '1.264'} | |
| {'loss': '0.07858', 'grad_norm': '0.1502', 'learning_rate': '8.167e-06', 'epoch': '1.265'} | |
| {'loss': '0.07591', 'grad_norm': '0.9786', 'learning_rate': '8.162e-06', 'epoch': '1.265'} | |
| {'loss': '0.07876', 'grad_norm': '0.262', 'learning_rate': '8.156e-06', 'epoch': '1.266'} | |
| {'loss': '0.0776', 'grad_norm': '2.222', 'learning_rate': '8.151e-06', 'epoch': '1.266'} | |
| {'loss': '0.07553', 'grad_norm': '1.213', 'learning_rate': '8.146e-06', 'epoch': '1.267'} | |
| {'loss': '0.07413', 'grad_norm': '1.226', 'learning_rate': '8.141e-06', 'epoch': '1.267'} | |
| {'loss': '0.07212', 'grad_norm': '1.755', 'learning_rate': '8.135e-06', 'epoch': '1.268'} | |
| {'loss': '0.08284', 'grad_norm': '4.786', 'learning_rate': '8.13e-06', 'epoch': '1.268'} | |
| {'loss': '0.06311', 'grad_norm': '0.4839', 'learning_rate': '8.125e-06', 'epoch': '1.269'} | |
| {'loss': '0.169', 'grad_norm': '0.9799', 'learning_rate': '8.119e-06', 'epoch': '1.269'} | |
| {'loss': '0.08327', 'grad_norm': '2.016', 'learning_rate': '8.114e-06', 'epoch': '1.27'} | |
| {'loss': '0.1911', 'grad_norm': '2.318', 'learning_rate': '8.109e-06', 'epoch': '1.27'} | |
| {'loss': '0.07114', 'grad_norm': '2.739', 'learning_rate': '8.103e-06', 'epoch': '1.271'} | |
| {'loss': '0.09121', 'grad_norm': '3.559', 'learning_rate': '8.098e-06', 'epoch': '1.271'} | |
| {'loss': '0.07284', 'grad_norm': '0.2887', 'learning_rate': '8.093e-06', 'epoch': '1.272'} | |
| {'loss': '0.07257', 'grad_norm': '3.91', 'learning_rate': '8.088e-06', 'epoch': '1.272'} | |
| {'loss': '0.07745', 'grad_norm': '0.708', 'learning_rate': '8.082e-06', 'epoch': '1.273'} | |
| {'loss': '0.08667', 'grad_norm': '0.313', 'learning_rate': '8.077e-06', 'epoch': '1.273'} | |
| {'loss': '0.06971', 'grad_norm': '5.871', 'learning_rate': '8.072e-06', 'epoch': '1.274'} | |
| {'loss': '0.07813', 'grad_norm': '0.7103', 'learning_rate': '8.066e-06', 'epoch': '1.274'} | |
| {'loss': '0.07478', 'grad_norm': '2.16', 'learning_rate': '8.061e-06', 'epoch': '1.275'} | |
| {'loss': '0.0749', 'grad_norm': '0.9667', 'learning_rate': '8.056e-06', 'epoch': '1.275'} | |
| {'loss': '0.08589', 'grad_norm': '0.5126', 'learning_rate': '8.051e-06', 'epoch': '1.275'} | |
| {'loss': '0.07193', 'grad_norm': '1.092', 'learning_rate': '8.045e-06', 'epoch': '1.276'} | |
| {'loss': '0.07487', 'grad_norm': '3.718', 'learning_rate': '8.04e-06', 'epoch': '1.276'} | |
| {'loss': '0.173', 'grad_norm': '5.198', 'learning_rate': '8.035e-06', 'epoch': '1.277'} | |
| {'loss': '0.08273', 'grad_norm': '2.367', 'learning_rate': '8.029e-06', 'epoch': '1.277'} | |
| {'loss': '0.07321', 'grad_norm': '4.745', 'learning_rate': '8.024e-06', 'epoch': '1.278'} | |
| {'loss': '0.07806', 'grad_norm': '1.009', 'learning_rate': '8.019e-06', 'epoch': '1.278'} | |
| {'loss': '0.08897', 'grad_norm': '4.862', 'learning_rate': '8.013e-06', 'epoch': '1.279'} | |
| {'loss': '0.07365', 'grad_norm': '0.5103', 'learning_rate': '8.008e-06', 'epoch': '1.279'} | |
| {'loss': '0.159', 'grad_norm': '0.5276', 'learning_rate': '8.003e-06', 'epoch': '1.28'} | |
| {'loss': '0.06384', 'grad_norm': '2.782', 'learning_rate': '7.998e-06', 'epoch': '1.28'} | |
| {'loss': '0.07828', 'grad_norm': '2.924', 'learning_rate': '7.992e-06', 'epoch': '1.281'} | |
| {'loss': '0.0837', 'grad_norm': '3.099', 'learning_rate': '7.987e-06', 'epoch': '1.281'} | |
| {'loss': '0.07845', 'grad_norm': '1.302', 'learning_rate': '7.982e-06', 'epoch': '1.282'} | |
| {'loss': '0.06442', 'grad_norm': '0.3695', 'learning_rate': '7.976e-06', 'epoch': '1.282'} | |
| {'loss': '0.07541', 'grad_norm': '0.1598', 'learning_rate': '7.971e-06', 'epoch': '1.283'} | |
| {'loss': '0.07442', 'grad_norm': '0.2363', 'learning_rate': '7.966e-06', 'epoch': '1.283'} | |
| {'loss': '0.07022', 'grad_norm': '0.4732', 'learning_rate': '7.961e-06', 'epoch': '1.284'} | |
| {'loss': '0.0788', 'grad_norm': '0.1735', 'learning_rate': '7.955e-06', 'epoch': '1.284'} | |
| {'loss': '0.1881', 'grad_norm': '5.304', 'learning_rate': '7.95e-06', 'epoch': '1.285'} | |
| {'loss': '0.07733', 'grad_norm': '0.06522', 'learning_rate': '7.945e-06', 'epoch': '1.285'} | |
| {'loss': '0.07223', 'grad_norm': '0.4597', 'learning_rate': '7.939e-06', 'epoch': '1.285'} | |
| {'loss': '0.08679', 'grad_norm': '3.367', 'learning_rate': '7.934e-06', 'epoch': '1.286'} | |
| {'loss': '0.08052', 'grad_norm': '1.104', 'learning_rate': '7.929e-06', 'epoch': '1.286'} | |
| {'eval_ms_marco_loss': '0.02412', 'eval_val-ms-marco-768_cosine_accuracy': '0.9993', 'eval_val-ms-marco-512_cosine_accuracy': '0.9993', 'eval_val-ms-marco-256_cosine_accuracy': '0.9993', 'eval_val-ms-marco-128_cosine_accuracy': '0.9993', 'eval_val-ms-marco-64_cosine_accuracy': '0.9993', 'eval_sequential_score': '0.9993', 'eval_ms_marco_runtime': '34.06', 'eval_ms_marco_samples_per_second': '293.6', 'eval_ms_marco_steps_per_second': '9.189', 'epoch': '1.286'} | |
| {'loss': '0.08154', 'grad_norm': '4.186', 'learning_rate': '7.923e-06', 'epoch': '1.287'} | |
| {'loss': '0.07475', 'grad_norm': '0.4348', 'learning_rate': '7.918e-06', 'epoch': '1.287'} | |
| {'loss': '0.06922', 'grad_norm': '0.06681', 'learning_rate': '7.913e-06', 'epoch': '1.288'} | |
| {'loss': '0.0788', 'grad_norm': '3.682', 'learning_rate': '7.908e-06', 'epoch': '1.288'} | |
| {'loss': '0.0822', 'grad_norm': '1.196', 'learning_rate': '7.902e-06', 'epoch': '1.289'} | |
| {'loss': '0.07424', 'grad_norm': '0.7284', 'learning_rate': '7.897e-06', 'epoch': '1.289'} | |
| {'loss': '0.07933', 'grad_norm': '1.95', 'learning_rate': '7.892e-06', 'epoch': '1.29'} | |
| {'loss': '0.1784', 'grad_norm': '1.513', 'learning_rate': '7.886e-06', 'epoch': '1.29'} | |
| {'loss': '0.07398', 'grad_norm': '0.1015', 'learning_rate': '7.881e-06', 'epoch': '1.291'} | |
| {'loss': '0.08055', 'grad_norm': '2.419', 'learning_rate': '7.876e-06', 'epoch': '1.291'} | |
| {'loss': '0.07991', 'grad_norm': '1.372', 'learning_rate': '7.871e-06', 'epoch': '1.292'} | |
| {'loss': '0.06819', 'grad_norm': '0.2693', 'learning_rate': '7.865e-06', 'epoch': '1.292'} | |
| {'loss': '0.08447', 'grad_norm': '6.469', 'learning_rate': '7.86e-06', 'epoch': '1.293'} | |
| {'loss': '0.06587', 'grad_norm': '0.8333', 'learning_rate': '7.855e-06', 'epoch': '1.293'} | |
| {'loss': '0.07576', 'grad_norm': '1.241', 'learning_rate': '7.849e-06', 'epoch': '1.294'} | |
| {'loss': '0.07123', 'grad_norm': '0.4124', 'learning_rate': '7.844e-06', 'epoch': '1.294'} | |
| {'loss': '0.08429', 'grad_norm': '2.085', 'learning_rate': '7.839e-06', 'epoch': '1.295'} | |
| {'loss': '0.08962', 'grad_norm': '0.5485', 'learning_rate': '7.833e-06', 'epoch': '1.295'} | |
| {'loss': '0.07114', 'grad_norm': '2.309', 'learning_rate': '7.828e-06', 'epoch': '1.295'} | |
| {'loss': '0.06875', 'grad_norm': '0.2902', 'learning_rate': '7.823e-06', 'epoch': '1.296'} | |
| {'loss': '0.07026', 'grad_norm': '1.373', 'learning_rate': '7.818e-06', 'epoch': '1.296'} | |
| {'loss': '0.0751', 'grad_norm': '2.214', 'learning_rate': '7.812e-06', 'epoch': '1.297'} | |
| {'loss': '0.08778', 'grad_norm': '1.104', 'learning_rate': '7.807e-06', 'epoch': '1.297'} | |
| {'loss': '0.07702', 'grad_norm': '1.367', 'learning_rate': '7.802e-06', 'epoch': '1.298'} | |
| {'loss': '0.07593', 'grad_norm': '7.301', 'learning_rate': '7.796e-06', 'epoch': '1.298'} | |
| {'loss': '0.0642', 'grad_norm': '0.2471', 'learning_rate': '7.791e-06', 'epoch': '1.299'} | |
| {'loss': '0.06708', 'grad_norm': '0.6393', 'learning_rate': '7.786e-06', 'epoch': '1.299'} | |
| {'loss': '0.07007', 'grad_norm': '0.1983', 'learning_rate': '7.781e-06', 'epoch': '1.3'} | |
| {'loss': '0.06523', 'grad_norm': '1.091', 'learning_rate': '7.775e-06', 'epoch': '1.3'} | |
| {'loss': '0.08986', 'grad_norm': '0.9111', 'learning_rate': '7.77e-06', 'epoch': '1.301'} | |
| {'loss': '0.08664', 'grad_norm': '1.081', 'learning_rate': '7.765e-06', 'epoch': '1.301'} | |
| {'loss': '0.08603', 'grad_norm': '4.763', 'learning_rate': '7.759e-06', 'epoch': '1.302'} | |
| {'loss': '0.08449', 'grad_norm': '0.3963', 'learning_rate': '7.754e-06', 'epoch': '1.302'} | |
| {'loss': '0.07284', 'grad_norm': '0.08671', 'learning_rate': '7.749e-06', 'epoch': '1.303'} | |
| {'loss': '0.07519', 'grad_norm': '3.622', 'learning_rate': '7.743e-06', 'epoch': '1.303'} | |
| {'loss': '0.0769', 'grad_norm': '0.5956', 'learning_rate': '7.738e-06', 'epoch': '1.304'} | |
| {'loss': '0.06265', 'grad_norm': '1.38', 'learning_rate': '7.733e-06', 'epoch': '1.304'} | |
| {'loss': '0.06528', 'grad_norm': '1.684', 'learning_rate': '7.728e-06', 'epoch': '1.305'} | |
| {'loss': '0.0834', 'grad_norm': '0.3609', 'learning_rate': '7.722e-06', 'epoch': '1.305'} | |
| {'loss': '0.1739', 'grad_norm': '4.735', 'learning_rate': '7.717e-06', 'epoch': '1.305'} | |
| {'loss': '0.07601', 'grad_norm': '1.908', 'learning_rate': '7.712e-06', 'epoch': '1.306'} | |
| {'loss': '0.07395', 'grad_norm': '0.09011', 'learning_rate': '7.706e-06', 'epoch': '1.306'} | |
| {'loss': '0.07586', 'grad_norm': '0.0854', 'learning_rate': '7.701e-06', 'epoch': '1.307'} | |
| {'loss': '0.07544', 'grad_norm': '0.2425', 'learning_rate': '7.696e-06', 'epoch': '1.307'} | |
| {'loss': '0.07624', 'grad_norm': '0.1931', 'learning_rate': '7.691e-06', 'epoch': '1.308'} | |
| {'loss': '0.08371', 'grad_norm': '0.7396', 'learning_rate': '7.685e-06', 'epoch': '1.308'} | |
| {'loss': '0.08535', 'grad_norm': '1.149', 'learning_rate': '7.68e-06', 'epoch': '1.309'} | |
| {'loss': '0.07417', 'grad_norm': '6.247', 'learning_rate': '7.675e-06', 'epoch': '1.309'} | |
| {'loss': '0.0743', 'grad_norm': '1.137', 'learning_rate': '7.669e-06', 'epoch': '1.31'} | |
| {'loss': '0.08413', 'grad_norm': '0.9467', 'learning_rate': '7.664e-06', 'epoch': '1.31'} | |
| {'loss': '0.08097', 'grad_norm': '2.822', 'learning_rate': '7.659e-06', 'epoch': '1.311'} | |
| {'loss': '0.07909', 'grad_norm': '0.394', 'learning_rate': '7.653e-06', 'epoch': '1.311'} | |
| {'loss': '0.2152', 'grad_norm': '1.218', 'learning_rate': '7.648e-06', 'epoch': '1.312'} | |
| {'loss': '0.07361', 'grad_norm': '4.459', 'learning_rate': '7.643e-06', 'epoch': '1.312'} | |
| {'loss': '0.07175', 'grad_norm': '0.2381', 'learning_rate': '7.638e-06', 'epoch': '1.313'} | |
| {'loss': '0.1549', 'grad_norm': '0.6932', 'learning_rate': '7.632e-06', 'epoch': '1.313'} | |
| {'loss': '0.08605', 'grad_norm': '0.4696', 'learning_rate': '7.627e-06', 'epoch': '1.314'} | |
| {'loss': '0.07427', 'grad_norm': '0.342', 'learning_rate': '7.622e-06', 'epoch': '1.314'} | |
| {'loss': '0.07623', 'grad_norm': '0.8394', 'learning_rate': '7.616e-06', 'epoch': '1.315'} | |
| {'loss': '0.09013', 'grad_norm': '0.3038', 'learning_rate': '7.611e-06', 'epoch': '1.315'} | |
| {'eval_ms_marco_loss': '0.02401', 'eval_val-ms-marco-768_cosine_accuracy': '0.9993', 'eval_val-ms-marco-512_cosine_accuracy': '0.9993', 'eval_val-ms-marco-256_cosine_accuracy': '0.9993', 'eval_val-ms-marco-128_cosine_accuracy': '0.9993', 'eval_val-ms-marco-64_cosine_accuracy': '0.9993', 'eval_sequential_score': '0.9993', 'eval_ms_marco_runtime': '33.92', 'eval_ms_marco_samples_per_second': '294.8', 'eval_ms_marco_steps_per_second': '9.226', 'epoch': '1.315'} | |
| {'loss': '0.08209', 'grad_norm': '2.722', 'learning_rate': '7.606e-06', 'epoch': '1.315'} | |
| {'loss': '0.07893', 'grad_norm': '0.3186', 'learning_rate': '7.601e-06', 'epoch': '1.316'} | |
| {'loss': '0.1623', 'grad_norm': '1.618', 'learning_rate': '7.595e-06', 'epoch': '1.316'} | |
| {'loss': '0.07397', 'grad_norm': '2.422', 'learning_rate': '7.59e-06', 'epoch': '1.317'} | |
| {'loss': '0.08382', 'grad_norm': '1.431', 'learning_rate': '7.585e-06', 'epoch': '1.317'} | |
| {'loss': '0.07758', 'grad_norm': '0.2063', 'learning_rate': '7.579e-06', 'epoch': '1.318'} | |
| {'loss': '0.08064', 'grad_norm': '0.632', 'learning_rate': '7.574e-06', 'epoch': '1.318'} | |
| {'loss': '0.07621', 'grad_norm': '2.958', 'learning_rate': '7.569e-06', 'epoch': '1.319'} | |
| {'loss': '0.07917', 'grad_norm': '1.186', 'learning_rate': '7.563e-06', 'epoch': '1.319'} | |
| {'loss': '0.06864', 'grad_norm': '4.521', 'learning_rate': '7.558e-06', 'epoch': '1.32'} | |
| {'loss': '0.1861', 'grad_norm': '0.08005', 'learning_rate': '7.553e-06', 'epoch': '1.32'} | |
| {'loss': '0.0784', 'grad_norm': '1.244', 'learning_rate': '7.548e-06', 'epoch': '1.321'} | |
| {'loss': '0.07486', 'grad_norm': '4.144', 'learning_rate': '7.542e-06', 'epoch': '1.321'} | |
| {'loss': '0.07348', 'grad_norm': '1.33', 'learning_rate': '7.537e-06', 'epoch': '1.322'} | |
| {'loss': '0.07872', 'grad_norm': '3.27', 'learning_rate': '7.532e-06', 'epoch': '1.322'} | |
| {'loss': '0.071', 'grad_norm': '6.96', 'learning_rate': '7.526e-06', 'epoch': '1.323'} | |
| {'loss': '0.07478', 'grad_norm': '6.508', 'learning_rate': '7.521e-06', 'epoch': '1.323'} | |
| {'loss': '0.06593', 'grad_norm': '2.059', 'learning_rate': '7.516e-06', 'epoch': '1.324'} | |
| {'loss': '0.0723', 'grad_norm': '0.5186', 'learning_rate': '7.511e-06', 'epoch': '1.324'} | |
| {'loss': '0.2004', 'grad_norm': '1.797', 'learning_rate': '7.505e-06', 'epoch': '1.325'} | |
| {'loss': '0.08821', 'grad_norm': '2.226', 'learning_rate': '7.5e-06', 'epoch': '1.325'} | |
| {'loss': '0.06895', 'grad_norm': '2.31', 'learning_rate': '7.495e-06', 'epoch': '1.325'} | |
| {'loss': '0.05983', 'grad_norm': '1.029', 'learning_rate': '7.489e-06', 'epoch': '1.326'} | |
| {'loss': '0.08353', 'grad_norm': '0.4934', 'learning_rate': '7.484e-06', 'epoch': '1.326'} | |
| {'loss': '0.08424', 'grad_norm': '1.785', 'learning_rate': '7.479e-06', 'epoch': '1.327'} | |
| {'loss': '0.06651', 'grad_norm': '2.124', 'learning_rate': '7.473e-06', 'epoch': '1.327'} | |
| {'loss': '0.165', 'grad_norm': '4.684', 'learning_rate': '7.468e-06', 'epoch': '1.328'} | |
| {'loss': '0.0872', 'grad_norm': '1.517', 'learning_rate': '7.463e-06', 'epoch': '1.328'} | |
| {'loss': '0.06445', 'grad_norm': '1.165', 'learning_rate': '7.458e-06', 'epoch': '1.329'} | |
| {'loss': '0.1739', 'grad_norm': '4.696', 'learning_rate': '7.452e-06', 'epoch': '1.329'} | |
| {'loss': '0.07615', 'grad_norm': '3.308', 'learning_rate': '7.447e-06', 'epoch': '1.33'} | |
| {'loss': '0.07166', 'grad_norm': '0.2193', 'learning_rate': '7.442e-06', 'epoch': '1.33'} | |
| {'loss': '0.06517', 'grad_norm': '0.7214', 'learning_rate': '7.436e-06', 'epoch': '1.331'} | |
| {'loss': '0.07532', 'grad_norm': '2.411', 'learning_rate': '7.431e-06', 'epoch': '1.331'} | |
| {'loss': '0.07', 'grad_norm': '5.839', 'learning_rate': '7.426e-06', 'epoch': '1.332'} | |
| {'loss': '0.07721', 'grad_norm': '1.067', 'learning_rate': '7.421e-06', 'epoch': '1.332'} | |
| {'loss': '0.07051', 'grad_norm': '0.612', 'learning_rate': '7.415e-06', 'epoch': '1.333'} | |
| {'loss': '0.08683', 'grad_norm': '1.379', 'learning_rate': '7.41e-06', 'epoch': '1.333'} | |
| {'loss': '0.1898', 'grad_norm': '1.321', 'learning_rate': '7.405e-06', 'epoch': '1.334'} | |
| {'loss': '0.06587', 'grad_norm': '1.021', 'learning_rate': '7.399e-06', 'epoch': '1.334'} | |
| {'loss': '0.06571', 'grad_norm': '0.4096', 'learning_rate': '7.394e-06', 'epoch': '1.335'} | |
| {'loss': '0.06014', 'grad_norm': '1.507', 'learning_rate': '7.389e-06', 'epoch': '1.335'} | |
| {'loss': '0.07355', 'grad_norm': '5.622', 'learning_rate': '7.383e-06', 'epoch': '1.335'} | |
| {'loss': '0.06213', 'grad_norm': '0.2228', 'learning_rate': '7.378e-06', 'epoch': '1.336'} | |
| {'loss': '0.07968', 'grad_norm': '1.042', 'learning_rate': '7.373e-06', 'epoch': '1.336'} | |
| {'loss': '0.09189', 'grad_norm': '0.2686', 'learning_rate': '7.368e-06', 'epoch': '1.337'} | |
| {'loss': '0.06824', 'grad_norm': '6.412', 'learning_rate': '7.362e-06', 'epoch': '1.337'} | |
| {'loss': '0.06662', 'grad_norm': '1.231', 'learning_rate': '7.357e-06', 'epoch': '1.338'} | |
| {'loss': '0.07732', 'grad_norm': '1.555', 'learning_rate': '7.352e-06', 'epoch': '1.338'} | |
| {'loss': '0.06878', 'grad_norm': '1.355', 'learning_rate': '7.346e-06', 'epoch': '1.339'} | |
| {'loss': '0.07396', 'grad_norm': '3.692', 'learning_rate': '7.341e-06', 'epoch': '1.339'} | |
| {'loss': '0.07495', 'grad_norm': '0.5519', 'learning_rate': '7.336e-06', 'epoch': '1.34'} | |
| {'loss': '0.07101', 'grad_norm': '3.342', 'learning_rate': '7.331e-06', 'epoch': '1.34'} | |
| {'loss': '0.08694', 'grad_norm': '0.6689', 'learning_rate': '7.325e-06', 'epoch': '1.341'} | |
| {'loss': '0.06231', 'grad_norm': '0.8861', 'learning_rate': '7.32e-06', 'epoch': '1.341'} | |
| {'loss': '0.07512', 'grad_norm': '0.4965', 'learning_rate': '7.315e-06', 'epoch': '1.342'} | |
| {'loss': '0.07102', 'grad_norm': '0.3332', 'learning_rate': '7.309e-06', 'epoch': '1.342'} | |
| {'loss': '0.07944', 'grad_norm': '0.154', 'learning_rate': '7.304e-06', 'epoch': '1.343'} | |
| {'loss': '0.07304', 'grad_norm': '4.773', 'learning_rate': '7.299e-06', 'epoch': '1.343'} | |
| {'loss': '0.07497', 'grad_norm': '1.686', 'learning_rate': '7.293e-06', 'epoch': '1.344'} | |
| {'eval_ms_marco_loss': '0.0228', 'eval_val-ms-marco-768_cosine_accuracy': '0.9993', 'eval_val-ms-marco-512_cosine_accuracy': '0.9993', 'eval_val-ms-marco-256_cosine_accuracy': '0.9993', 'eval_val-ms-marco-128_cosine_accuracy': '0.9993', 'eval_val-ms-marco-64_cosine_accuracy': '0.9993', 'eval_sequential_score': '0.9993', 'eval_ms_marco_runtime': '33.79', 'eval_ms_marco_samples_per_second': '295.9', 'eval_ms_marco_steps_per_second': '9.263', 'epoch': '1.344'} | |
| {'loss': '0.2085', 'grad_norm': '1.311', 'learning_rate': '7.288e-06', 'epoch': '1.344'} | |
| {'loss': '0.07605', 'grad_norm': '1.316', 'learning_rate': '7.283e-06', 'epoch': '1.345'} | |
| {'loss': '0.06861', 'grad_norm': '1.922', 'learning_rate': '7.278e-06', 'epoch': '1.345'} | |
| {'loss': '0.1793', 'grad_norm': '7.456', 'learning_rate': '7.272e-06', 'epoch': '1.345'} | |
| {'loss': '0.08002', 'grad_norm': '0.252', 'learning_rate': '7.267e-06', 'epoch': '1.346'} | |
| {'loss': '0.08251', 'grad_norm': '0.1042', 'learning_rate': '7.262e-06', 'epoch': '1.346'} | |
| {'loss': '0.1843', 'grad_norm': '0.6605', 'learning_rate': '7.256e-06', 'epoch': '1.347'} | |
| {'loss': '0.07206', 'grad_norm': '0.2784', 'learning_rate': '7.251e-06', 'epoch': '1.347'} | |
| {'loss': '0.0555', 'grad_norm': '0.7894', 'learning_rate': '7.246e-06', 'epoch': '1.348'} | |
| {'loss': '0.08226', 'grad_norm': '5.347', 'learning_rate': '7.241e-06', 'epoch': '1.348'} | |
| {'loss': '0.0753', 'grad_norm': '1.012', 'learning_rate': '7.235e-06', 'epoch': '1.349'} | |
| {'loss': '0.1685', 'grad_norm': '4.583', 'learning_rate': '7.23e-06', 'epoch': '1.349'} | |
| {'loss': '0.05721', 'grad_norm': '0.3316', 'learning_rate': '7.225e-06', 'epoch': '1.35'} | |
| {'loss': '0.1402', 'grad_norm': '0.1027', 'learning_rate': '7.219e-06', 'epoch': '1.35'} | |
| {'loss': '0.07247', 'grad_norm': '1.462', 'learning_rate': '7.214e-06', 'epoch': '1.351'} | |
| {'loss': '0.08091', 'grad_norm': '6.11', 'learning_rate': '7.209e-06', 'epoch': '1.351'} | |
| {'loss': '0.0639', 'grad_norm': '0.5151', 'learning_rate': '7.203e-06', 'epoch': '1.352'} | |
| {'loss': '0.07521', 'grad_norm': '3.518', 'learning_rate': '7.198e-06', 'epoch': '1.352'} | |
| {'loss': '0.07234', 'grad_norm': '0.2217', 'learning_rate': '7.193e-06', 'epoch': '1.353'} | |
| {'loss': '0.08008', 'grad_norm': '3.226', 'learning_rate': '7.188e-06', 'epoch': '1.353'} | |
| {'loss': '0.08209', 'grad_norm': '0.1414', 'learning_rate': '7.182e-06', 'epoch': '1.354'} | |
| {'loss': '0.07534', 'grad_norm': '3.778', 'learning_rate': '7.177e-06', 'epoch': '1.354'} | |
| {'loss': '0.08046', 'grad_norm': '2.657', 'learning_rate': '7.172e-06', 'epoch': '1.355'} | |
| {'loss': '0.07571', 'grad_norm': '0.7198', 'learning_rate': '7.166e-06', 'epoch': '1.355'} | |
| {'loss': '0.07849', 'grad_norm': '1.943', 'learning_rate': '7.161e-06', 'epoch': '1.356'} | |
| {'loss': '0.2103', 'grad_norm': '1.871', 'learning_rate': '7.156e-06', 'epoch': '1.356'} | |
| {'loss': '0.05931', 'grad_norm': '0.5641', 'learning_rate': '7.151e-06', 'epoch': '1.356'} | |
| {'loss': '0.05695', 'grad_norm': '6.211', 'learning_rate': '7.145e-06', 'epoch': '1.357'} | |
| {'loss': '0.2079', 'grad_norm': '1.391', 'learning_rate': '7.14e-06', 'epoch': '1.357'} | |
| {'loss': '0.06483', 'grad_norm': '3.177', 'learning_rate': '7.135e-06', 'epoch': '1.358'} | |
| {'loss': '0.07312', 'grad_norm': '0.1217', 'learning_rate': '7.129e-06', 'epoch': '1.358'} | |
| {'loss': '0.06331', 'grad_norm': '2.275', 'learning_rate': '7.124e-06', 'epoch': '1.359'} | |
| {'loss': '0.07327', 'grad_norm': '1.568', 'learning_rate': '7.119e-06', 'epoch': '1.359'} | |
| {'loss': '0.1971', 'grad_norm': '5.1', 'learning_rate': '7.113e-06', 'epoch': '1.36'} | |
| {'loss': '0.0713', 'grad_norm': '2.372', 'learning_rate': '7.108e-06', 'epoch': '1.36'} | |
| {'loss': '0.07282', 'grad_norm': '5.032', 'learning_rate': '7.103e-06', 'epoch': '1.361'} | |
| {'loss': '0.0699', 'grad_norm': '0.9573', 'learning_rate': '7.098e-06', 'epoch': '1.361'} | |
| {'loss': '0.08196', 'grad_norm': '3.87', 'learning_rate': '7.092e-06', 'epoch': '1.362'} | |
| {'loss': '0.06685', 'grad_norm': '3.251', 'learning_rate': '7.087e-06', 'epoch': '1.362'} | |
| {'loss': '0.06435', 'grad_norm': '1.117', 'learning_rate': '7.082e-06', 'epoch': '1.363'} | |
| {'loss': '0.1957', 'grad_norm': '1.158', 'learning_rate': '7.076e-06', 'epoch': '1.363'} | |
| {'loss': '0.0685', 'grad_norm': '1.798', 'learning_rate': '7.071e-06', 'epoch': '1.364'} | |
| {'loss': '0.06695', 'grad_norm': '0.3644', 'learning_rate': '7.066e-06', 'epoch': '1.364'} | |
| {'loss': '0.0935', 'grad_norm': '0.1187', 'learning_rate': '7.061e-06', 'epoch': '1.365'} | |
| {'loss': '0.182', 'grad_norm': '3.396', 'learning_rate': '7.055e-06', 'epoch': '1.365'} | |
| {'loss': '0.06995', 'grad_norm': '0.3624', 'learning_rate': '7.05e-06', 'epoch': '1.366'} | |
| {'loss': '0.07162', 'grad_norm': '2.649', 'learning_rate': '7.045e-06', 'epoch': '1.366'} | |
| {'loss': '0.07213', 'grad_norm': '0.4143', 'learning_rate': '7.039e-06', 'epoch': '1.366'} | |
| {'loss': '0.06477', 'grad_norm': '0.4932', 'learning_rate': '7.034e-06', 'epoch': '1.367'} | |
| {'loss': '0.1713', 'grad_norm': '3.522', 'learning_rate': '7.029e-06', 'epoch': '1.367'} | |
| {'loss': '0.07542', 'grad_norm': '6.282', 'learning_rate': '7.023e-06', 'epoch': '1.368'} | |
| {'loss': '0.06746', 'grad_norm': '0.2258', 'learning_rate': '7.018e-06', 'epoch': '1.368'} | |
| {'loss': '0.06204', 'grad_norm': '0.423', 'learning_rate': '7.013e-06', 'epoch': '1.369'} | |
| {'loss': '0.07864', 'grad_norm': '2.756', 'learning_rate': '7.008e-06', 'epoch': '1.369'} | |
| {'loss': '0.06305', 'grad_norm': '5.89', 'learning_rate': '7.002e-06', 'epoch': '1.37'} | |
| {'loss': '0.06171', 'grad_norm': '2.453', 'learning_rate': '6.997e-06', 'epoch': '1.37'} | |
| {'loss': '0.07022', 'grad_norm': '1.943', 'learning_rate': '6.992e-06', 'epoch': '1.371'} | |
| {'loss': '0.07187', 'grad_norm': '2.09', 'learning_rate': '6.986e-06', 'epoch': '1.371'} | |
| {'loss': '0.06968', 'grad_norm': '2.495', 'learning_rate': '6.981e-06', 'epoch': '1.372'} | |
| {'loss': '0.06595', 'grad_norm': '4.022', 'learning_rate': '6.976e-06', 'epoch': '1.372'} | |
| {'eval_ms_marco_loss': '0.0223', 'eval_val-ms-marco-768_cosine_accuracy': '0.9993', 'eval_val-ms-marco-512_cosine_accuracy': '0.9993', 'eval_val-ms-marco-256_cosine_accuracy': '0.9993', 'eval_val-ms-marco-128_cosine_accuracy': '0.999', 'eval_val-ms-marco-64_cosine_accuracy': '0.999', 'eval_sequential_score': '0.9993', 'eval_ms_marco_runtime': '33.91', 'eval_ms_marco_samples_per_second': '294.9', 'eval_ms_marco_steps_per_second': '9.231', 'epoch': '1.372'} | |
| {'loss': '0.08119', 'grad_norm': '0.9997', 'learning_rate': '6.971e-06', 'epoch': '1.373'} | |
| {'loss': '0.08131', 'grad_norm': '0.2208', 'learning_rate': '6.965e-06', 'epoch': '1.373'} | |
| {'loss': '0.06158', 'grad_norm': '2.777', 'learning_rate': '6.96e-06', 'epoch': '1.374'} | |
| {'loss': '0.0713', 'grad_norm': '5.404', 'learning_rate': '6.955e-06', 'epoch': '1.374'} | |
| {'loss': '0.06924', 'grad_norm': '2.891', 'learning_rate': '6.949e-06', 'epoch': '1.375'} | |
| {'loss': '0.06868', 'grad_norm': '0.4025', 'learning_rate': '6.944e-06', 'epoch': '1.375'} | |
| {'loss': '0.06434', 'grad_norm': '1.426', 'learning_rate': '6.939e-06', 'epoch': '1.376'} | |
| {'loss': '0.07403', 'grad_norm': '0.4306', 'learning_rate': '6.933e-06', 'epoch': '1.376'} | |
| {'loss': '0.06898', 'grad_norm': '1.625', 'learning_rate': '6.928e-06', 'epoch': '1.376'} | |
| {'loss': '0.06513', 'grad_norm': '1.084', 'learning_rate': '6.923e-06', 'epoch': '1.377'} | |
| {'loss': '0.05991', 'grad_norm': '7.095', 'learning_rate': '6.918e-06', 'epoch': '1.377'} | |
| {'loss': '0.07573', 'grad_norm': '0.4645', 'learning_rate': '6.912e-06', 'epoch': '1.378'} | |
| {'loss': '0.1694', 'grad_norm': '2.907', 'learning_rate': '6.907e-06', 'epoch': '1.378'} | |
| {'loss': '0.06658', 'grad_norm': '0.6612', 'learning_rate': '6.902e-06', 'epoch': '1.379'} | |
| {'loss': '0.06148', 'grad_norm': '0.7449', 'learning_rate': '6.896e-06', 'epoch': '1.379'} | |
| {'loss': '0.07183', 'grad_norm': '0.7905', 'learning_rate': '6.891e-06', 'epoch': '1.38'} | |
| {'loss': '0.05945', 'grad_norm': '0.4809', 'learning_rate': '6.886e-06', 'epoch': '1.38'} | |
| {'loss': '0.07559', 'grad_norm': '0.4029', 'learning_rate': '6.881e-06', 'epoch': '1.381'} | |
| {'loss': '0.06842', 'grad_norm': '1.257', 'learning_rate': '6.875e-06', 'epoch': '1.381'} | |
| {'loss': '0.1801', 'grad_norm': '6.203', 'learning_rate': '6.87e-06', 'epoch': '1.382'} | |
| {'loss': '0.06468', 'grad_norm': '0.4121', 'learning_rate': '6.865e-06', 'epoch': '1.382'} | |
| {'loss': '0.07451', 'grad_norm': '6.727', 'learning_rate': '6.859e-06', 'epoch': '1.383'} | |
| {'loss': '0.07032', 'grad_norm': '0.508', 'learning_rate': '6.854e-06', 'epoch': '1.383'} | |
| {'loss': '0.0758', 'grad_norm': '0.4325', 'learning_rate': '6.849e-06', 'epoch': '1.384'} | |
| {'loss': '0.06328', 'grad_norm': '3.7', 'learning_rate': '6.844e-06', 'epoch': '1.384'} | |
| {'loss': '0.07495', 'grad_norm': '4.649', 'learning_rate': '6.838e-06', 'epoch': '1.385'} | |
| {'loss': '0.07565', 'grad_norm': '0.2385', 'learning_rate': '6.833e-06', 'epoch': '1.385'} | |
| {'loss': '0.06093', 'grad_norm': '3.455', 'learning_rate': '6.828e-06', 'epoch': '1.386'} | |
| {'loss': '0.06478', 'grad_norm': '0.2356', 'learning_rate': '6.822e-06', 'epoch': '1.386'} | |
| {'loss': '0.06461', 'grad_norm': '0.2403', 'learning_rate': '6.817e-06', 'epoch': '1.386'} | |
| {'loss': '0.08123', 'grad_norm': '0.4481', 'learning_rate': '6.812e-06', 'epoch': '1.387'} | |
| {'loss': '0.1784', 'grad_norm': '4.928', 'learning_rate': '6.806e-06', 'epoch': '1.387'} | |
| {'loss': '0.06753', 'grad_norm': '1.898', 'learning_rate': '6.801e-06', 'epoch': '1.388'} | |
| {'loss': '0.07243', 'grad_norm': '0.8118', 'learning_rate': '6.796e-06', 'epoch': '1.388'} | |
| {'loss': '0.06825', 'grad_norm': '3.577', 'learning_rate': '6.791e-06', 'epoch': '1.389'} | |
| {'loss': '0.06334', 'grad_norm': '3.067', 'learning_rate': '6.785e-06', 'epoch': '1.389'} | |
| {'loss': '0.07011', 'grad_norm': '0.1792', 'learning_rate': '6.78e-06', 'epoch': '1.39'} | |
| {'loss': '0.07421', 'grad_norm': '0.1946', 'learning_rate': '6.775e-06', 'epoch': '1.39'} | |
| {'loss': '0.07354', 'grad_norm': '0.2838', 'learning_rate': '6.769e-06', 'epoch': '1.391'} | |
| {'loss': '0.07838', 'grad_norm': '1.688', 'learning_rate': '6.764e-06', 'epoch': '1.391'} | |
| {'loss': '0.07055', 'grad_norm': '3.268', 'learning_rate': '6.759e-06', 'epoch': '1.392'} | |
| {'loss': '0.1994', 'grad_norm': '1.098', 'learning_rate': '6.754e-06', 'epoch': '1.392'} | |
| {'loss': '0.06714', 'grad_norm': '0.5892', 'learning_rate': '6.748e-06', 'epoch': '1.393'} | |
| {'loss': '0.06585', 'grad_norm': '0.2516', 'learning_rate': '6.743e-06', 'epoch': '1.393'} | |
| {'loss': '0.06358', 'grad_norm': '2.305', 'learning_rate': '6.738e-06', 'epoch': '1.394'} | |
| {'loss': '0.0706', 'grad_norm': '0.9325', 'learning_rate': '6.732e-06', 'epoch': '1.394'} | |
| {'loss': '0.06269', 'grad_norm': '0.1587', 'learning_rate': '6.727e-06', 'epoch': '1.395'} | |
| {'loss': '0.1783', 'grad_norm': '2.616', 'learning_rate': '6.722e-06', 'epoch': '1.395'} | |
| {'loss': '0.07921', 'grad_norm': '0.2057', 'learning_rate': '6.716e-06', 'epoch': '1.396'} | |
| {'loss': '0.06526', 'grad_norm': '0.3703', 'learning_rate': '6.711e-06', 'epoch': '1.396'} | |
| {'loss': '0.07816', 'grad_norm': '0.2255', 'learning_rate': '6.706e-06', 'epoch': '1.396'} | |
| {'loss': '0.06392', 'grad_norm': '1.435', 'learning_rate': '6.701e-06', 'epoch': '1.397'} | |
| {'loss': '0.04961', 'grad_norm': '0.08075', 'learning_rate': '6.695e-06', 'epoch': '1.397'} | |
| {'loss': '0.07469', 'grad_norm': '3.483', 'learning_rate': '6.69e-06', 'epoch': '1.398'} | |
| {'loss': '0.06627', 'grad_norm': '1.685', 'learning_rate': '6.685e-06', 'epoch': '1.398'} | |
| {'loss': '0.0643', 'grad_norm': '5.068', 'learning_rate': '6.679e-06', 'epoch': '1.399'} | |
| {'loss': '0.0748', 'grad_norm': '0.9578', 'learning_rate': '6.674e-06', 'epoch': '1.399'} | |
| {'loss': '0.07223', 'grad_norm': '2.674', 'learning_rate': '6.669e-06', 'epoch': '1.4'} | |
| {'loss': '0.07248', 'grad_norm': '3.849', 'learning_rate': '6.664e-06', 'epoch': '1.4'} | |
| {'loss': '0.06167', 'grad_norm': '1.287', 'learning_rate': '6.658e-06', 'epoch': '1.401'} | |
| {'eval_ms_marco_loss': '0.02046', 'eval_val-ms-marco-768_cosine_accuracy': '0.999', 'eval_val-ms-marco-512_cosine_accuracy': '0.999', 'eval_val-ms-marco-256_cosine_accuracy': '0.999', 'eval_val-ms-marco-128_cosine_accuracy': '0.999', 'eval_val-ms-marco-64_cosine_accuracy': '0.9987', 'eval_sequential_score': '0.999', 'eval_ms_marco_runtime': '34.02', 'eval_ms_marco_samples_per_second': '293.9', 'eval_ms_marco_steps_per_second': '9.2', 'epoch': '1.401'} | |
| {'loss': '0.06259', 'grad_norm': '0.3058', 'learning_rate': '6.653e-06', 'epoch': '1.401'} | |
| {'loss': '0.07076', 'grad_norm': '0.4823', 'learning_rate': '6.648e-06', 'epoch': '1.402'} | |
| {'loss': '0.07175', 'grad_norm': '0.5014', 'learning_rate': '6.642e-06', 'epoch': '1.402'} | |
| {'loss': '0.06988', 'grad_norm': '0.1167', 'learning_rate': '6.637e-06', 'epoch': '1.403'} | |
| {'loss': '0.05839', 'grad_norm': '0.8651', 'learning_rate': '6.632e-06', 'epoch': '1.403'} | |
| {'loss': '0.06694', 'grad_norm': '0.5194', 'learning_rate': '6.626e-06', 'epoch': '1.404'} | |
| {'loss': '0.07507', 'grad_norm': '6.157', 'learning_rate': '6.621e-06', 'epoch': '1.404'} | |
| {'loss': '0.07232', 'grad_norm': '2.486', 'learning_rate': '6.616e-06', 'epoch': '1.405'} | |
| {'loss': '0.07021', 'grad_norm': '0.6643', 'learning_rate': '6.611e-06', 'epoch': '1.405'} | |
| {'loss': '0.06332', 'grad_norm': '1.556', 'learning_rate': '6.605e-06', 'epoch': '1.406'} | |
| {'loss': '0.06292', 'grad_norm': '0.6265', 'learning_rate': '6.6e-06', 'epoch': '1.406'} | |
| {'loss': '0.06525', 'grad_norm': '0.7865', 'learning_rate': '6.595e-06', 'epoch': '1.406'} | |
| {'loss': '0.06897', 'grad_norm': '2.26', 'learning_rate': '6.589e-06', 'epoch': '1.407'} | |
| {'loss': '0.06187', 'grad_norm': '3.186', 'learning_rate': '6.584e-06', 'epoch': '1.407'} | |
| {'loss': '0.06965', 'grad_norm': '0.7727', 'learning_rate': '6.579e-06', 'epoch': '1.408'} | |
| {'loss': '0.06446', 'grad_norm': '2.933', 'learning_rate': '6.574e-06', 'epoch': '1.408'} | |
| {'loss': '0.07101', 'grad_norm': '4.366', 'learning_rate': '6.568e-06', 'epoch': '1.409'} | |
| {'loss': '0.06149', 'grad_norm': '0.2045', 'learning_rate': '6.563e-06', 'epoch': '1.409'} | |
| {'loss': '0.0769', 'grad_norm': '1.859', 'learning_rate': '6.558e-06', 'epoch': '1.41'} | |
| {'loss': '0.06771', 'grad_norm': '0.1458', 'learning_rate': '6.552e-06', 'epoch': '1.41'} | |
| {'loss': '0.07045', 'grad_norm': '1.506', 'learning_rate': '6.547e-06', 'epoch': '1.411'} | |
| {'loss': '0.06396', 'grad_norm': '0.2208', 'learning_rate': '6.542e-06', 'epoch': '1.411'} | |
| {'loss': '0.07239', 'grad_norm': '0.2352', 'learning_rate': '6.536e-06', 'epoch': '1.412'} | |
| {'loss': '0.05413', 'grad_norm': '1.925', 'learning_rate': '6.531e-06', 'epoch': '1.412'} | |
| {'loss': '0.1656', 'grad_norm': '0.8655', 'learning_rate': '6.526e-06', 'epoch': '1.413'} | |
| {'loss': '0.07135', 'grad_norm': '1.689', 'learning_rate': '6.521e-06', 'epoch': '1.413'} | |
| {'loss': '0.1586', 'grad_norm': '1.308', 'learning_rate': '6.515e-06', 'epoch': '1.414'} | |
| {'loss': '0.05385', 'grad_norm': '0.9572', 'learning_rate': '6.51e-06', 'epoch': '1.414'} | |
| {'loss': '0.06236', 'grad_norm': '3.404', 'learning_rate': '6.505e-06', 'epoch': '1.415'} | |
| {'loss': '0.1675', 'grad_norm': '0.1628', 'learning_rate': '6.499e-06', 'epoch': '1.415'} | |
| {'loss': '0.06872', 'grad_norm': '2.101', 'learning_rate': '6.494e-06', 'epoch': '1.416'} | |
| {'loss': '0.07065', 'grad_norm': '1.827', 'learning_rate': '6.489e-06', 'epoch': '1.416'} | |
| {'loss': '0.08419', 'grad_norm': '1.421', 'learning_rate': '6.484e-06', 'epoch': '1.416'} | |
| {'loss': '0.07281', 'grad_norm': '1.534', 'learning_rate': '6.478e-06', 'epoch': '1.417'} | |
| {'loss': '0.08427', 'grad_norm': '5.376', 'learning_rate': '6.473e-06', 'epoch': '1.417'} | |
| {'loss': '0.07024', 'grad_norm': '0.3546', 'learning_rate': '6.468e-06', 'epoch': '1.418'} | |
| {'loss': '0.06393', 'grad_norm': '0.215', 'learning_rate': '6.462e-06', 'epoch': '1.418'} | |
| {'loss': '0.05869', 'grad_norm': '3.702', 'learning_rate': '6.457e-06', 'epoch': '1.419'} | |
| {'loss': '0.07593', 'grad_norm': '2.414', 'learning_rate': '6.452e-06', 'epoch': '1.419'} | |
| {'loss': '0.06134', 'grad_norm': '5.051', 'learning_rate': '6.446e-06', 'epoch': '1.42'} | |
| {'loss': '0.06721', 'grad_norm': '3.229', 'learning_rate': '6.441e-06', 'epoch': '1.42'} | |
| {'loss': '0.07729', 'grad_norm': '1.102', 'learning_rate': '6.436e-06', 'epoch': '1.421'} | |
| {'loss': '0.05924', 'grad_norm': '3.162', 'learning_rate': '6.431e-06', 'epoch': '1.421'} | |
| {'loss': '0.06975', 'grad_norm': '1.152', 'learning_rate': '6.425e-06', 'epoch': '1.422'} | |
| {'loss': '0.07135', 'grad_norm': '0.3478', 'learning_rate': '6.42e-06', 'epoch': '1.422'} | |
| {'loss': '0.08369', 'grad_norm': '0.7439', 'learning_rate': '6.415e-06', 'epoch': '1.423'} | |
| {'loss': '0.08144', 'grad_norm': '0.5524', 'learning_rate': '6.409e-06', 'epoch': '1.423'} | |
| {'loss': '0.06847', 'grad_norm': '0.04581', 'learning_rate': '6.404e-06', 'epoch': '1.424'} | |
| {'loss': '0.1716', 'grad_norm': '0.8499', 'learning_rate': '6.399e-06', 'epoch': '1.424'} | |
| {'loss': '0.1584', 'grad_norm': '0.6489', 'learning_rate': '6.394e-06', 'epoch': '1.425'} | |
| {'loss': '0.169', 'grad_norm': '1.254', 'learning_rate': '6.388e-06', 'epoch': '1.425'} | |
| {'loss': '0.06264', 'grad_norm': '2.106', 'learning_rate': '6.383e-06', 'epoch': '1.426'} | |
| {'loss': '0.07856', 'grad_norm': '0.191', 'learning_rate': '6.378e-06', 'epoch': '1.426'} | |
| {'loss': '0.07432', 'grad_norm': '0.5085', 'learning_rate': '6.372e-06', 'epoch': '1.426'} | |
| {'loss': '0.0624', 'grad_norm': '0.07828', 'learning_rate': '6.367e-06', 'epoch': '1.427'} | |
| {'loss': '0.06202', 'grad_norm': '1.629', 'learning_rate': '6.362e-06', 'epoch': '1.427'} | |
| {'loss': '0.0736', 'grad_norm': '0.6944', 'learning_rate': '6.356e-06', 'epoch': '1.428'} | |
| {'loss': '0.07542', 'grad_norm': '0.3539', 'learning_rate': '6.351e-06', 'epoch': '1.428'} | |
| {'loss': '0.06456', 'grad_norm': '5.697', 'learning_rate': '6.346e-06', 'epoch': '1.429'} | |
| {'loss': '0.06757', 'grad_norm': '0.2125', 'learning_rate': '6.341e-06', 'epoch': '1.429'} | |
| {'eval_ms_marco_loss': '0.0203', 'eval_val-ms-marco-768_cosine_accuracy': '0.9993', 'eval_val-ms-marco-512_cosine_accuracy': '0.9993', 'eval_val-ms-marco-256_cosine_accuracy': '0.9993', 'eval_val-ms-marco-128_cosine_accuracy': '0.999', 'eval_val-ms-marco-64_cosine_accuracy': '0.999', 'eval_sequential_score': '0.9993', 'eval_ms_marco_runtime': '33.99', 'eval_ms_marco_samples_per_second': '294.2', 'eval_ms_marco_steps_per_second': '9.209', 'epoch': '1.429'} | |
| {'loss': '0.06181', 'grad_norm': '0.3892', 'learning_rate': '6.335e-06', 'epoch': '1.43'} | |
| {'loss': '0.06729', 'grad_norm': '3.005', 'learning_rate': '6.33e-06', 'epoch': '1.43'} | |
| {'loss': '0.1601', 'grad_norm': '2.637', 'learning_rate': '6.325e-06', 'epoch': '1.431'} | |
| {'loss': '0.1449', 'grad_norm': '4.98', 'learning_rate': '6.319e-06', 'epoch': '1.431'} | |
| {'loss': '0.07424', 'grad_norm': '3.026', 'learning_rate': '6.314e-06', 'epoch': '1.432'} | |
| {'loss': '0.05711', 'grad_norm': '0.4461', 'learning_rate': '6.309e-06', 'epoch': '1.432'} | |
| {'loss': '0.178', 'grad_norm': '0.2757', 'learning_rate': '6.304e-06', 'epoch': '1.433'} | |
| {'loss': '0.06589', 'grad_norm': '0.4701', 'learning_rate': '6.298e-06', 'epoch': '1.433'} | |
| {'loss': '0.06894', 'grad_norm': '0.6013', 'learning_rate': '6.293e-06', 'epoch': '1.434'} | |
| {'loss': '0.06178', 'grad_norm': '1.171', 'learning_rate': '6.288e-06', 'epoch': '1.434'} | |
| {'loss': '0.07502', 'grad_norm': '0.648', 'learning_rate': '6.282e-06', 'epoch': '1.435'} | |
| {'loss': '0.06706', 'grad_norm': '0.2183', 'learning_rate': '6.277e-06', 'epoch': '1.435'} | |
| {'loss': '0.06939', 'grad_norm': '0.6525', 'learning_rate': '6.272e-06', 'epoch': '1.436'} | |
| {'loss': '0.08022', 'grad_norm': '1.184', 'learning_rate': '6.266e-06', 'epoch': '1.436'} | |
| {'loss': '0.06444', 'grad_norm': '0.714', 'learning_rate': '6.261e-06', 'epoch': '1.436'} | |
| {'loss': '0.06519', 'grad_norm': '0.1067', 'learning_rate': '6.256e-06', 'epoch': '1.437'} | |
| {'loss': '0.0627', 'grad_norm': '0.4161', 'learning_rate': '6.251e-06', 'epoch': '1.437'} | |
| {'loss': '0.06812', 'grad_norm': '1.87', 'learning_rate': '6.245e-06', 'epoch': '1.438'} | |
| {'loss': '0.06522', 'grad_norm': '1.968', 'learning_rate': '6.24e-06', 'epoch': '1.438'} | |
| {'loss': '0.0644', 'grad_norm': '1.114', 'learning_rate': '6.235e-06', 'epoch': '1.439'} | |
| {'loss': '0.06509', 'grad_norm': '1.838', 'learning_rate': '6.229e-06', 'epoch': '1.439'} | |
| {'loss': '0.07043', 'grad_norm': '3.975', 'learning_rate': '6.224e-06', 'epoch': '1.44'} | |
| {'loss': '0.05879', 'grad_norm': '0.105', 'learning_rate': '6.219e-06', 'epoch': '1.44'} | |
| {'loss': '0.1632', 'grad_norm': '2.976', 'learning_rate': '6.214e-06', 'epoch': '1.441'} | |
| {'loss': '0.06908', 'grad_norm': '1.224', 'learning_rate': '6.208e-06', 'epoch': '1.441'} | |
| {'loss': '0.06508', 'grad_norm': '0.7286', 'learning_rate': '6.203e-06', 'epoch': '1.442'} | |
| {'loss': '0.07458', 'grad_norm': '5.114', 'learning_rate': '6.198e-06', 'epoch': '1.442'} | |
| {'loss': '0.06386', 'grad_norm': '0.1647', 'learning_rate': '6.192e-06', 'epoch': '1.443'} | |
| {'loss': '0.06843', 'grad_norm': '3.839', 'learning_rate': '6.187e-06', 'epoch': '1.443'} | |
| {'loss': '0.06987', 'grad_norm': '2.476', 'learning_rate': '6.182e-06', 'epoch': '1.444'} | |
| {'loss': '0.06363', 'grad_norm': '0.2715', 'learning_rate': '6.176e-06', 'epoch': '1.444'} | |
| {'loss': '0.06753', 'grad_norm': '4.184', 'learning_rate': '6.171e-06', 'epoch': '1.445'} | |
| {'loss': '0.07687', 'grad_norm': '0.7797', 'learning_rate': '6.166e-06', 'epoch': '1.445'} | |
| {'loss': '0.06681', 'grad_norm': '3.296', 'learning_rate': '6.161e-06', 'epoch': '1.446'} | |
| {'loss': '0.07644', 'grad_norm': '0.7374', 'learning_rate': '6.155e-06', 'epoch': '1.446'} | |
| {'loss': '0.06222', 'grad_norm': '0.7899', 'learning_rate': '6.15e-06', 'epoch': '1.447'} | |
| {'loss': '0.06514', 'grad_norm': '0.5541', 'learning_rate': '6.145e-06', 'epoch': '1.447'} | |
| {'loss': '0.07681', 'grad_norm': '1.684', 'learning_rate': '6.139e-06', 'epoch': '1.447'} | |
| {'loss': '0.07398', 'grad_norm': '4.186', 'learning_rate': '6.134e-06', 'epoch': '1.448'} | |
| {'loss': '0.04888', 'grad_norm': '0.4402', 'learning_rate': '6.129e-06', 'epoch': '1.448'} | |
| {'loss': '0.07158', 'grad_norm': '4.014', 'learning_rate': '6.124e-06', 'epoch': '1.449'} | |
| {'loss': '0.06208', 'grad_norm': '0.8706', 'learning_rate': '6.118e-06', 'epoch': '1.449'} | |
| {'loss': '0.0829', 'grad_norm': '1.208', 'learning_rate': '6.113e-06', 'epoch': '1.45'} | |
| {'loss': '0.05332', 'grad_norm': '0.07605', 'learning_rate': '6.108e-06', 'epoch': '1.45'} | |
| {'loss': '0.07559', 'grad_norm': '2.723', 'learning_rate': '6.102e-06', 'epoch': '1.451'} | |
| {'loss': '0.05756', 'grad_norm': '0.08781', 'learning_rate': '6.097e-06', 'epoch': '1.451'} | |
| {'loss': '0.07096', 'grad_norm': '3.105', 'learning_rate': '6.092e-06', 'epoch': '1.452'} | |
| {'loss': '0.0617', 'grad_norm': '1.301', 'learning_rate': '6.086e-06', 'epoch': '1.452'} | |
| {'loss': '0.06648', 'grad_norm': '0.2089', 'learning_rate': '6.081e-06', 'epoch': '1.453'} | |
| {'loss': '0.06531', 'grad_norm': '2.399', 'learning_rate': '6.076e-06', 'epoch': '1.453'} | |
| {'loss': '0.06669', 'grad_norm': '0.3182', 'learning_rate': '6.071e-06', 'epoch': '1.454'} | |
| {'loss': '0.06063', 'grad_norm': '0.8473', 'learning_rate': '6.065e-06', 'epoch': '1.454'} | |
| {'loss': '0.0743', 'grad_norm': '0.8937', 'learning_rate': '6.06e-06', 'epoch': '1.455'} | |
| {'loss': '0.07442', 'grad_norm': '2.306', 'learning_rate': '6.055e-06', 'epoch': '1.455'} | |
| {'loss': '0.1822', 'grad_norm': '0.6459', 'learning_rate': '6.049e-06', 'epoch': '1.456'} | |
| {'loss': '0.05663', 'grad_norm': '1.015', 'learning_rate': '6.044e-06', 'epoch': '1.456'} | |
| {'loss': '0.06446', 'grad_norm': '5.003', 'learning_rate': '6.039e-06', 'epoch': '1.457'} | |
| {'loss': '0.1893', 'grad_norm': '0.2905', 'learning_rate': '6.034e-06', 'epoch': '1.457'} | |
| {'loss': '0.05388', 'grad_norm': '2.551', 'learning_rate': '6.028e-06', 'epoch': '1.457'} | |
| {'loss': '0.06255', 'grad_norm': '0.3422', 'learning_rate': '6.023e-06', 'epoch': '1.458'} | |
| {'eval_ms_marco_loss': '0.01884', 'eval_val-ms-marco-768_cosine_accuracy': '0.9993', 'eval_val-ms-marco-512_cosine_accuracy': '0.9993', 'eval_val-ms-marco-256_cosine_accuracy': '0.9993', 'eval_val-ms-marco-128_cosine_accuracy': '0.9993', 'eval_val-ms-marco-64_cosine_accuracy': '0.999', 'eval_sequential_score': '0.9993', 'eval_ms_marco_runtime': '34.03', 'eval_ms_marco_samples_per_second': '293.8', 'eval_ms_marco_steps_per_second': '9.197', 'epoch': '1.458'} | |
| {'loss': '0.06564', 'grad_norm': '1.667', 'learning_rate': '6.018e-06', 'epoch': '1.458'} | |
| {'loss': '0.1657', 'grad_norm': '5.081', 'learning_rate': '6.012e-06', 'epoch': '1.459'} | |
| {'loss': '0.07136', 'grad_norm': '1.709', 'learning_rate': '6.007e-06', 'epoch': '1.459'} | |
| {'loss': '0.06834', 'grad_norm': '3.294', 'learning_rate': '6.002e-06', 'epoch': '1.46'} | |
| {'loss': '0.06185', 'grad_norm': '1.167', 'learning_rate': '5.996e-06', 'epoch': '1.46'} | |
| {'loss': '0.07284', 'grad_norm': '3.596', 'learning_rate': '5.991e-06', 'epoch': '1.461'} | |
| {'loss': '0.06736', 'grad_norm': '2.297', 'learning_rate': '5.986e-06', 'epoch': '1.461'} | |
| {'loss': '0.07729', 'grad_norm': '5.345', 'learning_rate': '5.981e-06', 'epoch': '1.462'} | |
| {'loss': '0.05844', 'grad_norm': '4.396', 'learning_rate': '5.975e-06', 'epoch': '1.462'} | |
| {'loss': '0.06533', 'grad_norm': '4.648', 'learning_rate': '5.97e-06', 'epoch': '1.463'} | |
| {'loss': '0.07371', 'grad_norm': '2.717', 'learning_rate': '5.965e-06', 'epoch': '1.463'} | |
| {'loss': '0.1603', 'grad_norm': '8.045', 'learning_rate': '5.959e-06', 'epoch': '1.464'} | |
| {'loss': '0.1822', 'grad_norm': '3.351', 'learning_rate': '5.954e-06', 'epoch': '1.464'} | |
| {'loss': '0.06979', 'grad_norm': '0.4319', 'learning_rate': '5.949e-06', 'epoch': '1.465'} | |
| {'loss': '0.07256', 'grad_norm': '1.972', 'learning_rate': '5.944e-06', 'epoch': '1.465'} | |
| {'loss': '0.06268', 'grad_norm': '0.1176', 'learning_rate': '5.938e-06', 'epoch': '1.466'} | |
| {'loss': '0.06631', 'grad_norm': '0.1254', 'learning_rate': '5.933e-06', 'epoch': '1.466'} | |
| {'loss': '0.06429', 'grad_norm': '0.1678', 'learning_rate': '5.928e-06', 'epoch': '1.467'} | |
| {'loss': '0.06699', 'grad_norm': '0.2714', 'learning_rate': '5.922e-06', 'epoch': '1.467'} | |
| {'loss': '0.06809', 'grad_norm': '0.975', 'learning_rate': '5.917e-06', 'epoch': '1.467'} | |
| {'loss': '0.06099', 'grad_norm': '0.4892', 'learning_rate': '5.912e-06', 'epoch': '1.468'} | |
| {'loss': '0.06257', 'grad_norm': '3.791', 'learning_rate': '5.906e-06', 'epoch': '1.468'} | |
| {'loss': '0.07179', 'grad_norm': '2.139', 'learning_rate': '5.901e-06', 'epoch': '1.469'} | |
| {'loss': '0.06218', 'grad_norm': '1.289', 'learning_rate': '5.896e-06', 'epoch': '1.469'} | |
| {'loss': '0.0719', 'grad_norm': '4.65', 'learning_rate': '5.891e-06', 'epoch': '1.47'} | |
| {'loss': '0.06135', 'grad_norm': '0.8339', 'learning_rate': '5.885e-06', 'epoch': '1.47'} | |
| {'loss': '0.0723', 'grad_norm': '0.1526', 'learning_rate': '5.88e-06', 'epoch': '1.471'} | |
| {'loss': '0.05565', 'grad_norm': '0.05241', 'learning_rate': '5.875e-06', 'epoch': '1.471'} | |
| {'loss': '0.06291', 'grad_norm': '0.8525', 'learning_rate': '5.869e-06', 'epoch': '1.472'} | |
| {'loss': '0.05969', 'grad_norm': '1.73', 'learning_rate': '5.864e-06', 'epoch': '1.472'} | |
| {'loss': '0.06357', 'grad_norm': '0.1324', 'learning_rate': '5.859e-06', 'epoch': '1.473'} | |
| {'loss': '0.06317', 'grad_norm': '0.07747', 'learning_rate': '5.854e-06', 'epoch': '1.473'} | |
| {'loss': '0.06292', 'grad_norm': '0.1206', 'learning_rate': '5.848e-06', 'epoch': '1.474'} | |
| {'loss': '0.06306', 'grad_norm': '1.284', 'learning_rate': '5.843e-06', 'epoch': '1.474'} | |
| {'loss': '0.0604', 'grad_norm': '0.2309', 'learning_rate': '5.838e-06', 'epoch': '1.475'} | |
| {'loss': '0.06211', 'grad_norm': '5.613', 'learning_rate': '5.832e-06', 'epoch': '1.475'} | |
| {'loss': '0.1452', 'grad_norm': '4.509', 'learning_rate': '5.827e-06', 'epoch': '1.476'} | |
| {'loss': '0.0626', 'grad_norm': '0.8515', 'learning_rate': '5.822e-06', 'epoch': '1.476'} | |
| {'loss': '0.06148', 'grad_norm': '2.211', 'learning_rate': '5.816e-06', 'epoch': '1.477'} | |
| {'loss': '0.06333', 'grad_norm': '0.1905', 'learning_rate': '5.811e-06', 'epoch': '1.477'} | |
| {'loss': '0.17', 'grad_norm': '15.43', 'learning_rate': '5.806e-06', 'epoch': '1.477'} | |
| {'loss': '0.1559', 'grad_norm': '1.189', 'learning_rate': '5.801e-06', 'epoch': '1.478'} | |
| {'loss': '0.07625', 'grad_norm': '0.1848', 'learning_rate': '5.795e-06', 'epoch': '1.478'} | |
| {'loss': '0.06206', 'grad_norm': '1.565', 'learning_rate': '5.79e-06', 'epoch': '1.479'} | |
| {'loss': '0.05077', 'grad_norm': '0.3281', 'learning_rate': '5.785e-06', 'epoch': '1.479'} | |
| {'loss': '0.05777', 'grad_norm': '3.012', 'learning_rate': '5.779e-06', 'epoch': '1.48'} | |
| {'loss': '0.07017', 'grad_norm': '0.3221', 'learning_rate': '5.774e-06', 'epoch': '1.48'} | |
| {'loss': '0.05686', 'grad_norm': '3.51', 'learning_rate': '5.769e-06', 'epoch': '1.481'} | |
| {'loss': '0.06396', 'grad_norm': '0.1256', 'learning_rate': '5.764e-06', 'epoch': '1.481'} | |
| {'loss': '0.05525', 'grad_norm': '0.1246', 'learning_rate': '5.758e-06', 'epoch': '1.482'} | |
| {'loss': '0.1546', 'grad_norm': '1.804', 'learning_rate': '5.753e-06', 'epoch': '1.482'} | |
| {'loss': '0.06188', 'grad_norm': '0.1199', 'learning_rate': '5.748e-06', 'epoch': '1.483'} | |
| {'loss': '0.06457', 'grad_norm': '0.9485', 'learning_rate': '5.742e-06', 'epoch': '1.483'} | |
| {'loss': '0.06186', 'grad_norm': '1.808', 'learning_rate': '5.737e-06', 'epoch': '1.484'} | |
| {'loss': '0.1521', 'grad_norm': '0.5434', 'learning_rate': '5.732e-06', 'epoch': '1.484'} | |
| {'loss': '0.07332', 'grad_norm': '1.773', 'learning_rate': '5.726e-06', 'epoch': '1.485'} | |
| {'loss': '0.05343', 'grad_norm': '1.718', 'learning_rate': '5.721e-06', 'epoch': '1.485'} | |
| {'loss': '0.154', 'grad_norm': '0.1703', 'learning_rate': '5.716e-06', 'epoch': '1.486'} | |
| {'loss': '0.06672', 'grad_norm': '1.688', 'learning_rate': '5.711e-06', 'epoch': '1.486'} | |
| {'loss': '0.06013', 'grad_norm': '0.1248', 'learning_rate': '5.705e-06', 'epoch': '1.487'} | |
| {'eval_ms_marco_loss': '0.01846', 'eval_val-ms-marco-768_cosine_accuracy': '0.9993', 'eval_val-ms-marco-512_cosine_accuracy': '0.9993', 'eval_val-ms-marco-256_cosine_accuracy': '0.9993', 'eval_val-ms-marco-128_cosine_accuracy': '0.999', 'eval_val-ms-marco-64_cosine_accuracy': '0.9987', 'eval_sequential_score': '0.9993', 'eval_ms_marco_runtime': '33.91', 'eval_ms_marco_samples_per_second': '294.9', 'eval_ms_marco_steps_per_second': '9.232', 'epoch': '1.487'} | |
| {'loss': '0.0613', 'grad_norm': '2.162', 'learning_rate': '5.7e-06', 'epoch': '1.487'} | |
| {'loss': '0.06881', 'grad_norm': '3.68', 'learning_rate': '5.695e-06', 'epoch': '1.487'} | |
| {'loss': '0.05764', 'grad_norm': '0.709', 'learning_rate': '5.689e-06', 'epoch': '1.488'} | |
| {'loss': '0.06153', 'grad_norm': '0.08565', 'learning_rate': '5.684e-06', 'epoch': '1.488'} | |
| {'loss': '0.06371', 'grad_norm': '0.1671', 'learning_rate': '5.679e-06', 'epoch': '1.489'} | |
| {'loss': '0.1521', 'grad_norm': '7.749', 'learning_rate': '5.674e-06', 'epoch': '1.489'} | |
| {'loss': '0.05305', 'grad_norm': '0.7092', 'learning_rate': '5.668e-06', 'epoch': '1.49'} | |
| {'loss': '0.06789', 'grad_norm': '0.2868', 'learning_rate': '5.663e-06', 'epoch': '1.49'} | |
| {'loss': '0.05917', 'grad_norm': '10.97', 'learning_rate': '5.658e-06', 'epoch': '1.491'} | |
| {'loss': '0.06655', 'grad_norm': '6.529', 'learning_rate': '5.652e-06', 'epoch': '1.491'} | |
| {'loss': '0.05715', 'grad_norm': '0.2323', 'learning_rate': '5.647e-06', 'epoch': '1.492'} | |
| {'loss': '0.1822', 'grad_norm': '0.5333', 'learning_rate': '5.642e-06', 'epoch': '1.492'} | |
| {'loss': '0.06494', 'grad_norm': '0.4665', 'learning_rate': '5.636e-06', 'epoch': '1.493'} | |
| {'loss': '0.0555', 'grad_norm': '0.2717', 'learning_rate': '5.631e-06', 'epoch': '1.493'} | |
| {'loss': '0.1534', 'grad_norm': '1.622', 'learning_rate': '5.626e-06', 'epoch': '1.494'} | |
| {'loss': '0.05697', 'grad_norm': '0.9888', 'learning_rate': '5.621e-06', 'epoch': '1.494'} | |
| {'loss': '0.04946', 'grad_norm': '0.5934', 'learning_rate': '5.615e-06', 'epoch': '1.495'} | |
| {'loss': '0.06106', 'grad_norm': '0.424', 'learning_rate': '5.61e-06', 'epoch': '1.495'} | |
| {'loss': '0.149', 'grad_norm': '3.04', 'learning_rate': '5.605e-06', 'epoch': '1.496'} | |
| {'loss': '0.06345', 'grad_norm': '0.03768', 'learning_rate': '5.599e-06', 'epoch': '1.496'} | |
| {'loss': '0.07303', 'grad_norm': '0.95', 'learning_rate': '5.594e-06', 'epoch': '1.497'} | |
| {'loss': '0.07179', 'grad_norm': '1.92', 'learning_rate': '5.589e-06', 'epoch': '1.497'} | |
| {'loss': '0.1447', 'grad_norm': '4.572', 'learning_rate': '5.584e-06', 'epoch': '1.497'} | |
| {'loss': '0.06678', 'grad_norm': '0.5926', 'learning_rate': '5.578e-06', 'epoch': '1.498'} | |
| {'loss': '0.06263', 'grad_norm': '0.1181', 'learning_rate': '5.573e-06', 'epoch': '1.498'} | |
| {'loss': '0.07186', 'grad_norm': '2.826', 'learning_rate': '5.568e-06', 'epoch': '1.499'} | |
| {'loss': '0.1748', 'grad_norm': '0.2007', 'learning_rate': '5.562e-06', 'epoch': '1.499'} | |
| {'loss': '0.06552', 'grad_norm': '0.2401', 'learning_rate': '5.557e-06', 'epoch': '1.5'} | |
| {'loss': '0.05921', 'grad_norm': '0.554', 'learning_rate': '5.552e-06', 'epoch': '1.5'} | |
| {'loss': '0.05487', 'grad_norm': '0.4975', 'learning_rate': '5.546e-06', 'epoch': '1.501'} | |
| {'loss': '0.05207', 'grad_norm': '0.9576', 'learning_rate': '5.541e-06', 'epoch': '1.501'} | |
| {'loss': '0.05541', 'grad_norm': '1.198', 'learning_rate': '5.536e-06', 'epoch': '1.502'} | |
| {'loss': '0.0554', 'grad_norm': '0.7839', 'learning_rate': '5.531e-06', 'epoch': '1.502'} | |
| {'loss': '0.1953', 'grad_norm': '3.311', 'learning_rate': '5.525e-06', 'epoch': '1.503'} | |
| {'loss': '0.07309', 'grad_norm': '0.5019', 'learning_rate': '5.52e-06', 'epoch': '1.503'} | |
| {'loss': '0.07629', 'grad_norm': '5.568', 'learning_rate': '5.515e-06', 'epoch': '1.504'} | |
| {'loss': '0.1593', 'grad_norm': '0.196', 'learning_rate': '5.509e-06', 'epoch': '1.504'} | |
| {'loss': '0.0616', 'grad_norm': '2.9', 'learning_rate': '5.504e-06', 'epoch': '1.505'} | |
| {'loss': '0.06638', 'grad_norm': '0.2907', 'learning_rate': '5.499e-06', 'epoch': '1.505'} | |
| {'loss': '0.06209', 'grad_norm': '0.2833', 'learning_rate': '5.494e-06', 'epoch': '1.506'} | |
| {'loss': '0.06319', 'grad_norm': '1.79', 'learning_rate': '5.488e-06', 'epoch': '1.506'} | |
| {'loss': '0.06508', 'grad_norm': '0.5216', 'learning_rate': '5.483e-06', 'epoch': '1.507'} | |
| {'loss': '0.0641', 'grad_norm': '0.289', 'learning_rate': '5.478e-06', 'epoch': '1.507'} | |
| {'loss': '0.05488', 'grad_norm': '0.5811', 'learning_rate': '5.472e-06', 'epoch': '1.507'} | |
| {'loss': '0.06199', 'grad_norm': '1.416', 'learning_rate': '5.467e-06', 'epoch': '1.508'} | |
| {'loss': '0.07181', 'grad_norm': '0.9703', 'learning_rate': '5.462e-06', 'epoch': '1.508'} | |
| {'loss': '0.07037', 'grad_norm': '1.749', 'learning_rate': '5.456e-06', 'epoch': '1.509'} | |
| {'loss': '0.06614', 'grad_norm': '0.2992', 'learning_rate': '5.451e-06', 'epoch': '1.509'} | |
| {'loss': '0.06157', 'grad_norm': '0.1738', 'learning_rate': '5.446e-06', 'epoch': '1.51'} | |
| {'loss': '0.07023', 'grad_norm': '3.373', 'learning_rate': '5.441e-06', 'epoch': '1.51'} | |
| {'loss': '0.05967', 'grad_norm': '0.1523', 'learning_rate': '5.435e-06', 'epoch': '1.511'} | |
| {'loss': '0.1777', 'grad_norm': '1.327', 'learning_rate': '5.43e-06', 'epoch': '1.511'} | |
| {'loss': '0.0828', 'grad_norm': '0.03801', 'learning_rate': '5.425e-06', 'epoch': '1.512'} | |
| {'loss': '0.06282', 'grad_norm': '6.173', 'learning_rate': '5.419e-06', 'epoch': '1.512'} | |
| {'loss': '0.05994', 'grad_norm': '0.2638', 'learning_rate': '5.414e-06', 'epoch': '1.513'} | |
| {'loss': '0.05584', 'grad_norm': '3.29', 'learning_rate': '5.409e-06', 'epoch': '1.513'} | |
| {'loss': '0.06133', 'grad_norm': '0.3704', 'learning_rate': '5.404e-06', 'epoch': '1.514'} | |
| {'loss': '0.06034', 'grad_norm': '6.332', 'learning_rate': '5.398e-06', 'epoch': '1.514'} | |
| {'loss': '0.05978', 'grad_norm': '0.1354', 'learning_rate': '5.393e-06', 'epoch': '1.515'} | |
| {'loss': '0.05464', 'grad_norm': '1.757', 'learning_rate': '5.388e-06', 'epoch': '1.515'} | |
| {'eval_ms_marco_loss': '0.01883', 'eval_val-ms-marco-768_cosine_accuracy': '0.9993', 'eval_val-ms-marco-512_cosine_accuracy': '0.999', 'eval_val-ms-marco-256_cosine_accuracy': '0.999', 'eval_val-ms-marco-128_cosine_accuracy': '0.999', 'eval_val-ms-marco-64_cosine_accuracy': '0.9987', 'eval_sequential_score': '0.9993', 'eval_ms_marco_runtime': '33.76', 'eval_ms_marco_samples_per_second': '296.2', 'eval_ms_marco_steps_per_second': '9.271', 'epoch': '1.515'} | |
| {'loss': '0.05931', 'grad_norm': '1.933', 'learning_rate': '5.382e-06', 'epoch': '1.516'} | |
| {'loss': '0.05384', 'grad_norm': '0.7918', 'learning_rate': '5.377e-06', 'epoch': '1.516'} | |
| {'loss': '0.05793', 'grad_norm': '2.952', 'learning_rate': '5.372e-06', 'epoch': '1.517'} | |
| {'loss': '0.05853', 'grad_norm': '0.5657', 'learning_rate': '5.367e-06', 'epoch': '1.517'} | |
| {'loss': '0.0664', 'grad_norm': '0.2056', 'learning_rate': '5.361e-06', 'epoch': '1.517'} | |
| {'loss': '0.04729', 'grad_norm': '2.394', 'learning_rate': '5.356e-06', 'epoch': '1.518'} | |
| {'loss': '0.06', 'grad_norm': '2.34', 'learning_rate': '5.351e-06', 'epoch': '1.518'} | |
| {'loss': '0.06653', 'grad_norm': '2.088', 'learning_rate': '5.345e-06', 'epoch': '1.519'} | |
| {'loss': '0.04815', 'grad_norm': '1.851', 'learning_rate': '5.34e-06', 'epoch': '1.519'} | |
| {'loss': '0.0616', 'grad_norm': '0.1278', 'learning_rate': '5.335e-06', 'epoch': '1.52'} | |
| {'loss': '0.05381', 'grad_norm': '0.221', 'learning_rate': '5.329e-06', 'epoch': '1.52'} | |
| {'loss': '0.06253', 'grad_norm': '1.268', 'learning_rate': '5.324e-06', 'epoch': '1.521'} | |
| {'loss': '0.05455', 'grad_norm': '0.1437', 'learning_rate': '5.319e-06', 'epoch': '1.521'} | |
| {'loss': '0.06963', 'grad_norm': '1.964', 'learning_rate': '5.314e-06', 'epoch': '1.522'} | |
| {'loss': '0.1544', 'grad_norm': '0.1358', 'learning_rate': '5.308e-06', 'epoch': '1.522'} | |
| {'loss': '0.06524', 'grad_norm': '0.8184', 'learning_rate': '5.303e-06', 'epoch': '1.523'} | |
| {'loss': '0.06212', 'grad_norm': '5.751', 'learning_rate': '5.298e-06', 'epoch': '1.523'} | |
| {'loss': '0.06557', 'grad_norm': '2.865', 'learning_rate': '5.292e-06', 'epoch': '1.524'} | |
| {'loss': '0.04836', 'grad_norm': '0.4566', 'learning_rate': '5.287e-06', 'epoch': '1.524'} | |
| {'loss': '0.0679', 'grad_norm': '3.731', 'learning_rate': '5.282e-06', 'epoch': '1.525'} | |
| {'loss': '0.05557', 'grad_norm': '0.1769', 'learning_rate': '5.277e-06', 'epoch': '1.525'} | |
| {'loss': '0.06255', 'grad_norm': '1.854', 'learning_rate': '5.271e-06', 'epoch': '1.526'} | |
| {'loss': '0.05111', 'grad_norm': '5.554', 'learning_rate': '5.266e-06', 'epoch': '1.526'} | |
| {'loss': '0.06164', 'grad_norm': '0.6985', 'learning_rate': '5.261e-06', 'epoch': '1.527'} | |
| {'loss': '0.06152', 'grad_norm': '1.182', 'learning_rate': '5.255e-06', 'epoch': '1.527'} | |
| {'loss': '0.06064', 'grad_norm': '0.2447', 'learning_rate': '5.25e-06', 'epoch': '1.527'} | |
| {'loss': '0.06', 'grad_norm': '0.3068', 'learning_rate': '5.245e-06', 'epoch': '1.528'} | |
| {'loss': '0.06647', 'grad_norm': '2.061', 'learning_rate': '5.239e-06', 'epoch': '1.528'} | |
| {'loss': '0.1603', 'grad_norm': '1.148', 'learning_rate': '5.234e-06', 'epoch': '1.529'} | |
| {'loss': '0.05232', 'grad_norm': '0.9911', 'learning_rate': '5.229e-06', 'epoch': '1.529'} | |
| {'loss': '0.05568', 'grad_norm': '1.308', 'learning_rate': '5.224e-06', 'epoch': '1.53'} | |
| {'loss': '0.05295', 'grad_norm': '0.3183', 'learning_rate': '5.218e-06', 'epoch': '1.53'} | |
| {'loss': '0.06536', 'grad_norm': '1.854', 'learning_rate': '5.213e-06', 'epoch': '1.531'} | |
| {'loss': '0.05958', 'grad_norm': '0.9563', 'learning_rate': '5.208e-06', 'epoch': '1.531'} | |
| {'loss': '0.06238', 'grad_norm': '0.2286', 'learning_rate': '5.202e-06', 'epoch': '1.532'} | |
| {'loss': '0.05918', 'grad_norm': '0.9824', 'learning_rate': '5.197e-06', 'epoch': '1.532'} | |
| {'loss': '0.06598', 'grad_norm': '3.281', 'learning_rate': '5.192e-06', 'epoch': '1.533'} | |
| {'loss': '0.04559', 'grad_norm': '0.472', 'learning_rate': '5.187e-06', 'epoch': '1.533'} | |
| {'loss': '0.04003', 'grad_norm': '2.194', 'learning_rate': '5.181e-06', 'epoch': '1.534'} | |
| {'loss': '0.06445', 'grad_norm': '2.225', 'learning_rate': '5.176e-06', 'epoch': '1.534'} | |
| {'loss': '0.0587', 'grad_norm': '1.243', 'learning_rate': '5.171e-06', 'epoch': '1.535'} | |
| {'loss': '0.06506', 'grad_norm': '5.345', 'learning_rate': '5.165e-06', 'epoch': '1.535'} | |
| {'loss': '0.05879', 'grad_norm': '1.527', 'learning_rate': '5.16e-06', 'epoch': '1.536'} | |
| {'loss': '0.06206', 'grad_norm': '1.525', 'learning_rate': '5.155e-06', 'epoch': '1.536'} | |
| {'loss': '0.05753', 'grad_norm': '0.8362', 'learning_rate': '5.149e-06', 'epoch': '1.537'} | |
| {'loss': '0.05956', 'grad_norm': '0.8354', 'learning_rate': '5.144e-06', 'epoch': '1.537'} | |
| {'loss': '0.05963', 'grad_norm': '1.048', 'learning_rate': '5.139e-06', 'epoch': '1.538'} | |
| {'loss': '0.06199', 'grad_norm': '4.755', 'learning_rate': '5.134e-06', 'epoch': '1.538'} | |
| {'loss': '0.06586', 'grad_norm': '3.627', 'learning_rate': '5.128e-06', 'epoch': '1.538'} | |
| {'loss': '0.1679', 'grad_norm': '2.199', 'learning_rate': '5.123e-06', 'epoch': '1.539'} | |
| {'loss': '0.05811', 'grad_norm': '0.9338', 'learning_rate': '5.118e-06', 'epoch': '1.539'} | |
| {'loss': '0.05578', 'grad_norm': '1.337', 'learning_rate': '5.112e-06', 'epoch': '1.54'} | |
| {'loss': '0.07295', 'grad_norm': '0.6358', 'learning_rate': '5.107e-06', 'epoch': '1.54'} | |
| {'loss': '0.06876', 'grad_norm': '1.34', 'learning_rate': '5.102e-06', 'epoch': '1.541'} | |
| {'loss': '0.06584', 'grad_norm': '0.3789', 'learning_rate': '5.097e-06', 'epoch': '1.541'} | |
| {'loss': '0.05599', 'grad_norm': '2.777', 'learning_rate': '5.091e-06', 'epoch': '1.542'} | |
| {'loss': '0.05208', 'grad_norm': '0.2256', 'learning_rate': '5.086e-06', 'epoch': '1.542'} | |
| {'loss': '0.06041', 'grad_norm': '0.4861', 'learning_rate': '5.081e-06', 'epoch': '1.543'} | |
| {'loss': '0.05644', 'grad_norm': '1.056', 'learning_rate': '5.075e-06', 'epoch': '1.543'} | |
| {'loss': '0.06018', 'grad_norm': '0.9172', 'learning_rate': '5.07e-06', 'epoch': '1.544'} | |
| {'eval_ms_marco_loss': '0.01833', 'eval_val-ms-marco-768_cosine_accuracy': '0.9993', 'eval_val-ms-marco-512_cosine_accuracy': '0.9993', 'eval_val-ms-marco-256_cosine_accuracy': '0.9993', 'eval_val-ms-marco-128_cosine_accuracy': '0.999', 'eval_val-ms-marco-64_cosine_accuracy': '0.9987', 'eval_sequential_score': '0.9993', 'eval_ms_marco_runtime': '34.11', 'eval_ms_marco_samples_per_second': '293.1', 'eval_ms_marco_steps_per_second': '9.175', 'epoch': '1.544'} | |
| {'loss': '0.05032', 'grad_norm': '3.789', 'learning_rate': '5.065e-06', 'epoch': '1.544'} | |
| {'loss': '0.0657', 'grad_norm': '0.1196', 'learning_rate': '5.059e-06', 'epoch': '1.545'} | |
| {'loss': '0.05492', 'grad_norm': '3.23', 'learning_rate': '5.054e-06', 'epoch': '1.545'} | |
| {'loss': '0.04831', 'grad_norm': '1.02', 'learning_rate': '5.049e-06', 'epoch': '1.546'} | |
| {'loss': '0.06414', 'grad_norm': '0.1641', 'learning_rate': '5.044e-06', 'epoch': '1.546'} | |
| {'loss': '0.06359', 'grad_norm': '0.74', 'learning_rate': '5.038e-06', 'epoch': '1.547'} | |
| {'loss': '0.06041', 'grad_norm': '0.1225', 'learning_rate': '5.033e-06', 'epoch': '1.547'} | |
| {'loss': '0.05892', 'grad_norm': '3.438', 'learning_rate': '5.028e-06', 'epoch': '1.548'} | |
| {'loss': '0.06264', 'grad_norm': '0.4798', 'learning_rate': '5.022e-06', 'epoch': '1.548'} | |
| {'loss': '0.05217', 'grad_norm': '0.3564', 'learning_rate': '5.017e-06', 'epoch': '1.548'} | |
| {'loss': '0.07352', 'grad_norm': '1.418', 'learning_rate': '5.012e-06', 'epoch': '1.549'} | |
| {'loss': '0.06611', 'grad_norm': '1.144', 'learning_rate': '5.007e-06', 'epoch': '1.549'} | |
| {'loss': '0.05449', 'grad_norm': '0.4747', 'learning_rate': '5.001e-06', 'epoch': '1.55'} | |
| {'loss': '0.05816', 'grad_norm': '0.09771', 'learning_rate': '4.996e-06', 'epoch': '1.55'} | |
| {'loss': '0.05816', 'grad_norm': '0.3347', 'learning_rate': '4.991e-06', 'epoch': '1.551'} | |
| {'loss': '0.05554', 'grad_norm': '0.1814', 'learning_rate': '4.985e-06', 'epoch': '1.551'} | |
| {'loss': '0.05842', 'grad_norm': '0.2508', 'learning_rate': '4.98e-06', 'epoch': '1.552'} | |
| {'loss': '0.161', 'grad_norm': '4.2', 'learning_rate': '4.975e-06', 'epoch': '1.552'} | |
| {'loss': '0.05502', 'grad_norm': '0.02851', 'learning_rate': '4.969e-06', 'epoch': '1.553'} | |
| {'loss': '0.06869', 'grad_norm': '0.1412', 'learning_rate': '4.964e-06', 'epoch': '1.553'} | |
| {'loss': '0.06119', 'grad_norm': '3.953', 'learning_rate': '4.959e-06', 'epoch': '1.554'} | |
| {'loss': '0.05919', 'grad_norm': '0.4051', 'learning_rate': '4.954e-06', 'epoch': '1.554'} | |
| {'loss': '0.05876', 'grad_norm': '0.08219', 'learning_rate': '4.948e-06', 'epoch': '1.555'} | |
| {'loss': '0.067', 'grad_norm': '4.864', 'learning_rate': '4.943e-06', 'epoch': '1.555'} | |
| {'loss': '0.1524', 'grad_norm': '6.415', 'learning_rate': '4.938e-06', 'epoch': '1.556'} | |
| {'loss': '0.05504', 'grad_norm': '0.6755', 'learning_rate': '4.932e-06', 'epoch': '1.556'} | |
| {'loss': '0.06197', 'grad_norm': '0.1385', 'learning_rate': '4.927e-06', 'epoch': '1.557'} | |
| {'loss': '0.05443', 'grad_norm': '6.01', 'learning_rate': '4.922e-06', 'epoch': '1.557'} | |
| {'loss': '0.06033', 'grad_norm': '2.127', 'learning_rate': '4.917e-06', 'epoch': '1.558'} | |
| {'loss': '0.05556', 'grad_norm': '2.036', 'learning_rate': '4.911e-06', 'epoch': '1.558'} | |
| {'loss': '0.06117', 'grad_norm': '1.42', 'learning_rate': '4.906e-06', 'epoch': '1.558'} | |
| {'loss': '0.05017', 'grad_norm': '2.743', 'learning_rate': '4.901e-06', 'epoch': '1.559'} | |
| {'loss': '0.06457', 'grad_norm': '2.084', 'learning_rate': '4.895e-06', 'epoch': '1.559'} | |
| {'loss': '0.05828', 'grad_norm': '0.7497', 'learning_rate': '4.89e-06', 'epoch': '1.56'} | |
| {'loss': '0.05039', 'grad_norm': '2.412', 'learning_rate': '4.885e-06', 'epoch': '1.56'} | |
| {'loss': '0.05768', 'grad_norm': '3.908', 'learning_rate': '4.879e-06', 'epoch': '1.561'} | |
| {'loss': '0.05198', 'grad_norm': '0.1718', 'learning_rate': '4.874e-06', 'epoch': '1.561'} | |
| {'loss': '0.06148', 'grad_norm': '2.371', 'learning_rate': '4.869e-06', 'epoch': '1.562'} | |
| {'loss': '0.04772', 'grad_norm': '1.797', 'learning_rate': '4.864e-06', 'epoch': '1.562'} | |
| {'loss': '0.06246', 'grad_norm': '1.935', 'learning_rate': '4.858e-06', 'epoch': '1.563'} | |
| {'loss': '0.05842', 'grad_norm': '5.343', 'learning_rate': '4.853e-06', 'epoch': '1.563'} | |
| {'loss': '0.06736', 'grad_norm': '0.9585', 'learning_rate': '4.848e-06', 'epoch': '1.564'} | |
| {'loss': '0.2204', 'grad_norm': '2.097', 'learning_rate': '4.842e-06', 'epoch': '1.564'} | |
| {'loss': '0.05199', 'grad_norm': '0.03854', 'learning_rate': '4.837e-06', 'epoch': '1.565'} | |
| {'loss': '0.06052', 'grad_norm': '0.982', 'learning_rate': '4.832e-06', 'epoch': '1.565'} | |
| {'loss': '0.05366', 'grad_norm': '5.44', 'learning_rate': '4.827e-06', 'epoch': '1.566'} | |
| {'loss': '0.06671', 'grad_norm': '5.411', 'learning_rate': '4.821e-06', 'epoch': '1.566'} | |
| {'loss': '0.1698', 'grad_norm': '0.4936', 'learning_rate': '4.816e-06', 'epoch': '1.567'} | |
| {'loss': '0.054', 'grad_norm': '0.3099', 'learning_rate': '4.811e-06', 'epoch': '1.567'} | |
| {'loss': '0.05315', 'grad_norm': '0.6798', 'learning_rate': '4.805e-06', 'epoch': '1.568'} | |
| {'loss': '0.05845', 'grad_norm': '2.652', 'learning_rate': '4.8e-06', 'epoch': '1.568'} | |
| {'loss': '0.1594', 'grad_norm': '2.078', 'learning_rate': '4.795e-06', 'epoch': '1.568'} | |
| {'loss': '0.05716', 'grad_norm': '1.249', 'learning_rate': '4.789e-06', 'epoch': '1.569'} | |
| {'loss': '0.06111', 'grad_norm': '4.914', 'learning_rate': '4.784e-06', 'epoch': '1.569'} | |
| {'loss': '0.05388', 'grad_norm': '0.24', 'learning_rate': '4.779e-06', 'epoch': '1.57'} | |
| {'loss': '0.0587', 'grad_norm': '0.4863', 'learning_rate': '4.774e-06', 'epoch': '1.57'} | |
| {'loss': '0.07255', 'grad_norm': '0.09327', 'learning_rate': '4.768e-06', 'epoch': '1.571'} | |
| {'loss': '0.06211', 'grad_norm': '1.84', 'learning_rate': '4.763e-06', 'epoch': '1.571'} | |
| {'loss': '0.05596', 'grad_norm': '0.3163', 'learning_rate': '4.758e-06', 'epoch': '1.572'} | |
| {'loss': '0.04541', 'grad_norm': '1.099', 'learning_rate': '4.752e-06', 'epoch': '1.572'} | |
| {'eval_ms_marco_loss': '0.01734', 'eval_val-ms-marco-768_cosine_accuracy': '0.9993', 'eval_val-ms-marco-512_cosine_accuracy': '0.9993', 'eval_val-ms-marco-256_cosine_accuracy': '0.9993', 'eval_val-ms-marco-128_cosine_accuracy': '0.999', 'eval_val-ms-marco-64_cosine_accuracy': '0.999', 'eval_sequential_score': '0.9993', 'eval_ms_marco_runtime': '33.8', 'eval_ms_marco_samples_per_second': '295.8', 'eval_ms_marco_steps_per_second': '9.259', 'epoch': '1.572'} | |
| {'loss': '0.05838', 'grad_norm': '1.07', 'learning_rate': '4.747e-06', 'epoch': '1.573'} | |
| {'loss': '0.05493', 'grad_norm': '0.8682', 'learning_rate': '4.742e-06', 'epoch': '1.573'} | |
| {'loss': '0.1428', 'grad_norm': '1.089', 'learning_rate': '4.737e-06', 'epoch': '1.574'} | |
| {'loss': '0.05245', 'grad_norm': '0.7817', 'learning_rate': '4.731e-06', 'epoch': '1.574'} | |
| {'loss': '0.05597', 'grad_norm': '2.773', 'learning_rate': '4.726e-06', 'epoch': '1.575'} | |
| {'loss': '0.1526', 'grad_norm': '0.1797', 'learning_rate': '4.721e-06', 'epoch': '1.575'} | |
| {'loss': '0.05464', 'grad_norm': '3.862', 'learning_rate': '4.715e-06', 'epoch': '1.576'} | |
| {'loss': '0.05339', 'grad_norm': '0.08057', 'learning_rate': '4.71e-06', 'epoch': '1.576'} | |
| {'loss': '0.05878', 'grad_norm': '0.4388', 'learning_rate': '4.705e-06', 'epoch': '1.577'} | |
| {'loss': '0.05503', 'grad_norm': '2.16', 'learning_rate': '4.699e-06', 'epoch': '1.577'} | |
| {'loss': '0.05439', 'grad_norm': '2.878', 'learning_rate': '4.694e-06', 'epoch': '1.578'} | |
| {'loss': '0.05773', 'grad_norm': '3.807', 'learning_rate': '4.689e-06', 'epoch': '1.578'} | |
| {'loss': '0.06215', 'grad_norm': '3.483', 'learning_rate': '4.684e-06', 'epoch': '1.578'} | |
| {'loss': '0.1713', 'grad_norm': '1.461', 'learning_rate': '4.678e-06', 'epoch': '1.579'} | |
| {'loss': '0.1732', 'grad_norm': '2.277', 'learning_rate': '4.673e-06', 'epoch': '1.579'} | |
| {'loss': '0.04768', 'grad_norm': '5.483', 'learning_rate': '4.668e-06', 'epoch': '1.58'} | |
| {'loss': '0.04937', 'grad_norm': '0.1808', 'learning_rate': '4.662e-06', 'epoch': '1.58'} | |
| {'loss': '0.06658', 'grad_norm': '0.4174', 'learning_rate': '4.657e-06', 'epoch': '1.581'} | |
| {'loss': '0.05097', 'grad_norm': '1.167', 'learning_rate': '4.652e-06', 'epoch': '1.581'} | |
| {'loss': '0.06133', 'grad_norm': '0.1732', 'learning_rate': '4.647e-06', 'epoch': '1.582'} | |
| {'loss': '0.164', 'grad_norm': '0.08883', 'learning_rate': '4.641e-06', 'epoch': '1.582'} | |
| {'loss': '0.0478', 'grad_norm': '0.5503', 'learning_rate': '4.636e-06', 'epoch': '1.583'} | |
| {'loss': '0.05848', 'grad_norm': '1.362', 'learning_rate': '4.631e-06', 'epoch': '1.583'} | |
| {'loss': '0.05558', 'grad_norm': '0.3915', 'learning_rate': '4.625e-06', 'epoch': '1.584'} | |
| {'loss': '0.06288', 'grad_norm': '1.961', 'learning_rate': '4.62e-06', 'epoch': '1.584'} | |
| {'loss': '0.05837', 'grad_norm': '0.4937', 'learning_rate': '4.615e-06', 'epoch': '1.585'} | |
| {'loss': '0.06975', 'grad_norm': '0.259', 'learning_rate': '4.609e-06', 'epoch': '1.585'} | |
| {'loss': '0.05541', 'grad_norm': '0.4749', 'learning_rate': '4.604e-06', 'epoch': '1.586'} | |
| {'loss': '0.06144', 'grad_norm': '0.1892', 'learning_rate': '4.599e-06', 'epoch': '1.586'} | |
| {'loss': '0.1445', 'grad_norm': '1.617', 'learning_rate': '4.594e-06', 'epoch': '1.587'} | |
| {'loss': '0.05677', 'grad_norm': '0.07523', 'learning_rate': '4.588e-06', 'epoch': '1.587'} | |
| {'loss': '0.06641', 'grad_norm': '1.072', 'learning_rate': '4.583e-06', 'epoch': '1.588'} | |
| {'loss': '0.04538', 'grad_norm': '2.655', 'learning_rate': '4.578e-06', 'epoch': '1.588'} | |
| {'loss': '0.0628', 'grad_norm': '1.704', 'learning_rate': '4.572e-06', 'epoch': '1.588'} | |
| {'loss': '0.05492', 'grad_norm': '0.4666', 'learning_rate': '4.567e-06', 'epoch': '1.589'} | |
| {'loss': '0.05129', 'grad_norm': '0.1785', 'learning_rate': '4.562e-06', 'epoch': '1.589'} | |
| {'loss': '0.06342', 'grad_norm': '0.3696', 'learning_rate': '4.557e-06', 'epoch': '1.59'} | |
| {'loss': '0.05256', 'grad_norm': '0.224', 'learning_rate': '4.551e-06', 'epoch': '1.59'} | |
| {'loss': '0.04853', 'grad_norm': '0.459', 'learning_rate': '4.546e-06', 'epoch': '1.591'} | |
| {'loss': '0.05957', 'grad_norm': '4.456', 'learning_rate': '4.541e-06', 'epoch': '1.591'} | |
| {'loss': '0.1513', 'grad_norm': '0.6919', 'learning_rate': '4.535e-06', 'epoch': '1.592'} | |
| {'loss': '0.06737', 'grad_norm': '3.318', 'learning_rate': '4.53e-06', 'epoch': '1.592'} | |
| {'loss': '0.0676', 'grad_norm': '0.6914', 'learning_rate': '4.525e-06', 'epoch': '1.593'} | |
| {'loss': '0.05934', 'grad_norm': '1.55', 'learning_rate': '4.519e-06', 'epoch': '1.593'} | |
| {'loss': '0.06407', 'grad_norm': '1.434', 'learning_rate': '4.514e-06', 'epoch': '1.594'} | |
| {'loss': '0.0596', 'grad_norm': '0.5034', 'learning_rate': '4.509e-06', 'epoch': '1.594'} | |
| {'loss': '0.05061', 'grad_norm': '0.1348', 'learning_rate': '4.504e-06', 'epoch': '1.595'} | |
| {'loss': '0.05849', 'grad_norm': '3.237', 'learning_rate': '4.498e-06', 'epoch': '1.595'} | |
| {'loss': '0.06172', 'grad_norm': '1.581', 'learning_rate': '4.493e-06', 'epoch': '1.596'} | |
| {'loss': '0.05774', 'grad_norm': '0.8768', 'learning_rate': '4.488e-06', 'epoch': '1.596'} | |
| {'loss': '0.05756', 'grad_norm': '1.009', 'learning_rate': '4.482e-06', 'epoch': '1.597'} | |
| {'loss': '0.05268', 'grad_norm': '1.759', 'learning_rate': '4.477e-06', 'epoch': '1.597'} | |
| {'loss': '0.04507', 'grad_norm': '0.4227', 'learning_rate': '4.472e-06', 'epoch': '1.598'} | |
| {'loss': '0.05795', 'grad_norm': '0.6905', 'learning_rate': '4.467e-06', 'epoch': '1.598'} | |
| {'loss': '0.05528', 'grad_norm': '7.443', 'learning_rate': '4.461e-06', 'epoch': '1.598'} | |
| {'loss': '0.05979', 'grad_norm': '1.767', 'learning_rate': '4.456e-06', 'epoch': '1.599'} | |
| {'loss': '0.06111', 'grad_norm': '0.1583', 'learning_rate': '4.451e-06', 'epoch': '1.599'} | |
| {'loss': '0.07129', 'grad_norm': '1.273', 'learning_rate': '4.445e-06', 'epoch': '1.6'} | |
| {'loss': '0.05791', 'grad_norm': '0.06586', 'learning_rate': '4.44e-06', 'epoch': '1.6'} | |
| {'loss': '0.1699', 'grad_norm': '1.677', 'learning_rate': '4.435e-06', 'epoch': '1.601'} | |
| {'eval_ms_marco_loss': '0.01826', 'eval_val-ms-marco-768_cosine_accuracy': '0.9993', 'eval_val-ms-marco-512_cosine_accuracy': '0.9993', 'eval_val-ms-marco-256_cosine_accuracy': '0.9993', 'eval_val-ms-marco-128_cosine_accuracy': '0.9993', 'eval_val-ms-marco-64_cosine_accuracy': '0.999', 'eval_sequential_score': '0.9993', 'eval_ms_marco_runtime': '33.96', 'eval_ms_marco_samples_per_second': '294.4', 'eval_ms_marco_steps_per_second': '9.216', 'epoch': '1.601'} | |
| {'loss': '0.0548', 'grad_norm': '0.344', 'learning_rate': '4.429e-06', 'epoch': '1.601'} | |
| {'loss': '0.06038', 'grad_norm': '0.2566', 'learning_rate': '4.424e-06', 'epoch': '1.602'} | |
| {'loss': '0.145', 'grad_norm': '5.06', 'learning_rate': '4.419e-06', 'epoch': '1.602'} | |
| {'loss': '0.1781', 'grad_norm': '1.746', 'learning_rate': '4.414e-06', 'epoch': '1.603'} | |
| {'loss': '0.04696', 'grad_norm': '1.574', 'learning_rate': '4.408e-06', 'epoch': '1.603'} | |
| {'loss': '0.05062', 'grad_norm': '0.4792', 'learning_rate': '4.403e-06', 'epoch': '1.604'} | |
| {'loss': '0.05977', 'grad_norm': '0.8724', 'learning_rate': '4.398e-06', 'epoch': '1.604'} | |
| {'loss': '0.05428', 'grad_norm': '0.09955', 'learning_rate': '4.392e-06', 'epoch': '1.605'} | |
| {'loss': '0.05237', 'grad_norm': '6.826', 'learning_rate': '4.387e-06', 'epoch': '1.605'} | |
| {'loss': '0.04516', 'grad_norm': '0.752', 'learning_rate': '4.382e-06', 'epoch': '1.606'} | |
| {'loss': '0.07008', 'grad_norm': '0.1081', 'learning_rate': '4.377e-06', 'epoch': '1.606'} | |
| {'loss': '0.06259', 'grad_norm': '0.08992', 'learning_rate': '4.371e-06', 'epoch': '1.607'} | |
| {'loss': '0.2615', 'grad_norm': '1.784', 'learning_rate': '4.366e-06', 'epoch': '1.607'} | |
| {'loss': '0.05134', 'grad_norm': '0.698', 'learning_rate': '4.361e-06', 'epoch': '1.608'} | |
| {'loss': '0.06427', 'grad_norm': '0.1188', 'learning_rate': '4.355e-06', 'epoch': '1.608'} | |
| {'loss': '0.05365', 'grad_norm': '1.695', 'learning_rate': '4.35e-06', 'epoch': '1.608'} | |
| {'loss': '0.05325', 'grad_norm': '0.1916', 'learning_rate': '4.345e-06', 'epoch': '1.609'} | |
| {'loss': '0.05478', 'grad_norm': '4.2', 'learning_rate': '4.339e-06', 'epoch': '1.609'} | |
| {'loss': '0.04628', 'grad_norm': '3.833', 'learning_rate': '4.334e-06', 'epoch': '1.61'} | |
| {'loss': '0.04841', 'grad_norm': '0.293', 'learning_rate': '4.329e-06', 'epoch': '1.61'} | |
| {'loss': '0.04455', 'grad_norm': '0.6407', 'learning_rate': '4.324e-06', 'epoch': '1.611'} | |
| {'loss': '0.04837', 'grad_norm': '1.556', 'learning_rate': '4.318e-06', 'epoch': '1.611'} | |
| {'loss': '0.05249', 'grad_norm': '1.954', 'learning_rate': '4.313e-06', 'epoch': '1.612'} | |
| {'loss': '0.06683', 'grad_norm': '2.326', 'learning_rate': '4.308e-06', 'epoch': '1.612'} | |
| {'loss': '0.06004', 'grad_norm': '0.811', 'learning_rate': '4.302e-06', 'epoch': '1.613'} | |
| {'loss': '0.05564', 'grad_norm': '3.489', 'learning_rate': '4.297e-06', 'epoch': '1.613'} | |
| {'loss': '0.04984', 'grad_norm': '1.129', 'learning_rate': '4.292e-06', 'epoch': '1.614'} | |
| {'loss': '0.06546', 'grad_norm': '6.243', 'learning_rate': '4.287e-06', 'epoch': '1.614'} | |
| {'loss': '0.06119', 'grad_norm': '0.09195', 'learning_rate': '4.281e-06', 'epoch': '1.615'} | |
| {'loss': '0.05128', 'grad_norm': '0.149', 'learning_rate': '4.276e-06', 'epoch': '1.615'} | |
| {'loss': '0.04984', 'grad_norm': '0.1581', 'learning_rate': '4.271e-06', 'epoch': '1.616'} | |
| {'loss': '0.05538', 'grad_norm': '1.432', 'learning_rate': '4.265e-06', 'epoch': '1.616'} | |
| {'loss': '0.04826', 'grad_norm': '2.206', 'learning_rate': '4.26e-06', 'epoch': '1.617'} | |
| {'loss': '0.05783', 'grad_norm': '2.89', 'learning_rate': '4.255e-06', 'epoch': '1.617'} | |
| {'loss': '0.05679', 'grad_norm': '0.1003', 'learning_rate': '4.249e-06', 'epoch': '1.618'} | |
| {'loss': '0.06274', 'grad_norm': '0.7888', 'learning_rate': '4.244e-06', 'epoch': '1.618'} | |
| {'loss': '0.05539', 'grad_norm': '1.067', 'learning_rate': '4.239e-06', 'epoch': '1.619'} | |
| {'loss': '0.1726', 'grad_norm': '0.4448', 'learning_rate': '4.234e-06', 'epoch': '1.619'} | |
| {'loss': '0.05924', 'grad_norm': '0.09998', 'learning_rate': '4.228e-06', 'epoch': '1.619'} | |
| {'loss': '0.05045', 'grad_norm': '8.12', 'learning_rate': '4.223e-06', 'epoch': '1.62'} | |
| {'loss': '0.04764', 'grad_norm': '1.353', 'learning_rate': '4.218e-06', 'epoch': '1.62'} | |
| {'loss': '0.1748', 'grad_norm': '4.994', 'learning_rate': '4.212e-06', 'epoch': '1.621'} | |
| {'loss': '0.1441', 'grad_norm': '0.04709', 'learning_rate': '4.207e-06', 'epoch': '1.621'} | |
| {'loss': '0.04964', 'grad_norm': '1.529', 'learning_rate': '4.202e-06', 'epoch': '1.622'} | |
| {'loss': '0.2417', 'grad_norm': '0.1722', 'learning_rate': '4.197e-06', 'epoch': '1.622'} | |
| {'loss': '0.0573', 'grad_norm': '4.33', 'learning_rate': '4.191e-06', 'epoch': '1.623'} | |
| {'loss': '0.06541', 'grad_norm': '4.375', 'learning_rate': '4.186e-06', 'epoch': '1.623'} | |
| {'loss': '0.05069', 'grad_norm': '0.5797', 'learning_rate': '4.181e-06', 'epoch': '1.624'} | |
| {'loss': '0.05671', 'grad_norm': '1.446', 'learning_rate': '4.175e-06', 'epoch': '1.624'} | |
| {'loss': '0.05099', 'grad_norm': '3.197', 'learning_rate': '4.17e-06', 'epoch': '1.625'} | |
| {'loss': '0.195', 'grad_norm': '0.5707', 'learning_rate': '4.165e-06', 'epoch': '1.625'} | |
| {'loss': '0.1497', 'grad_norm': '2.597', 'learning_rate': '4.159e-06', 'epoch': '1.626'} | |
| {'loss': '0.05789', 'grad_norm': '0.8342', 'learning_rate': '4.154e-06', 'epoch': '1.626'} | |
| {'loss': '0.06777', 'grad_norm': '3.305', 'learning_rate': '4.149e-06', 'epoch': '1.627'} | |
| {'loss': '0.05439', 'grad_norm': '1.66', 'learning_rate': '4.144e-06', 'epoch': '1.627'} | |
| {'loss': '0.05475', 'grad_norm': '5.293', 'learning_rate': '4.138e-06', 'epoch': '1.628'} | |
| {'loss': '0.05308', 'grad_norm': '2.859', 'learning_rate': '4.133e-06', 'epoch': '1.628'} | |
| {'loss': '0.06449', 'grad_norm': '0.4534', 'learning_rate': '4.128e-06', 'epoch': '1.629'} | |
| {'loss': '0.06503', 'grad_norm': '0.9443', 'learning_rate': '4.122e-06', 'epoch': '1.629'} | |
| {'loss': '0.06152', 'grad_norm': '0.2035', 'learning_rate': '4.117e-06', 'epoch': '1.629'} | |
| {'eval_ms_marco_loss': '0.01714', 'eval_val-ms-marco-768_cosine_accuracy': '0.9993', 'eval_val-ms-marco-512_cosine_accuracy': '0.9993', 'eval_val-ms-marco-256_cosine_accuracy': '0.9993', 'eval_val-ms-marco-128_cosine_accuracy': '0.9993', 'eval_val-ms-marco-64_cosine_accuracy': '0.9993', 'eval_sequential_score': '0.9993', 'eval_ms_marco_runtime': '34.02', 'eval_ms_marco_samples_per_second': '293.9', 'eval_ms_marco_steps_per_second': '9.2', 'epoch': '1.629'} | |
| {'loss': '0.05063', 'grad_norm': '1.204', 'learning_rate': '4.112e-06', 'epoch': '1.63'} | |
| {'loss': '0.04841', 'grad_norm': '0.3062', 'learning_rate': '4.107e-06', 'epoch': '1.63'} | |
| {'loss': '0.07391', 'grad_norm': '0.1622', 'learning_rate': '4.101e-06', 'epoch': '1.631'} | |
| {'loss': '0.05127', 'grad_norm': '1.111', 'learning_rate': '4.096e-06', 'epoch': '1.631'} | |
| {'loss': '0.1433', 'grad_norm': '1.311', 'learning_rate': '4.091e-06', 'epoch': '1.632'} | |
| {'loss': '0.04509', 'grad_norm': '0.5154', 'learning_rate': '4.085e-06', 'epoch': '1.632'} | |
| {'loss': '0.05698', 'grad_norm': '0.5525', 'learning_rate': '4.08e-06', 'epoch': '1.633'} | |
| {'loss': '0.05706', 'grad_norm': '5.408', 'learning_rate': '4.075e-06', 'epoch': '1.633'} | |
| {'loss': '0.0552', 'grad_norm': '2.455', 'learning_rate': '4.069e-06', 'epoch': '1.634'} | |
| {'loss': '0.04768', 'grad_norm': '0.7161', 'learning_rate': '4.064e-06', 'epoch': '1.634'} | |
| {'loss': '0.05363', 'grad_norm': '0.1032', 'learning_rate': '4.059e-06', 'epoch': '1.635'} | |
| {'loss': '0.05425', 'grad_norm': '0.355', 'learning_rate': '4.054e-06', 'epoch': '1.635'} | |
| {'loss': '0.1559', 'grad_norm': '111.9', 'learning_rate': '4.048e-06', 'epoch': '1.636'} | |
| {'loss': '0.06404', 'grad_norm': '0.163', 'learning_rate': '4.043e-06', 'epoch': '1.636'} | |
| {'loss': '0.04756', 'grad_norm': '1.214', 'learning_rate': '4.038e-06', 'epoch': '1.637'} | |
| {'loss': '0.05501', 'grad_norm': '4.775', 'learning_rate': '4.032e-06', 'epoch': '1.637'} | |
| {'loss': '0.1622', 'grad_norm': '1.762', 'learning_rate': '4.027e-06', 'epoch': '1.638'} | |
| {'loss': '0.05066', 'grad_norm': '0.6713', 'learning_rate': '4.022e-06', 'epoch': '1.638'} | |
| {'loss': '0.06029', 'grad_norm': '2.941', 'learning_rate': '4.017e-06', 'epoch': '1.639'} | |
| {'loss': '0.05125', 'grad_norm': '0.05313', 'learning_rate': '4.011e-06', 'epoch': '1.639'} | |
| {'loss': '0.05903', 'grad_norm': '0.8338', 'learning_rate': '4.006e-06', 'epoch': '1.639'} | |
| {'loss': '0.06257', 'grad_norm': '0.04498', 'learning_rate': '4.001e-06', 'epoch': '1.64'} | |
| {'loss': '0.139', 'grad_norm': '1.214', 'learning_rate': '3.995e-06', 'epoch': '1.64'} | |
| {'loss': '0.0512', 'grad_norm': '0.2586', 'learning_rate': '3.99e-06', 'epoch': '1.641'} | |
| {'loss': '0.0578', 'grad_norm': '0.4862', 'learning_rate': '3.985e-06', 'epoch': '1.641'} | |
| {'loss': '0.1475', 'grad_norm': '0.7821', 'learning_rate': '3.98e-06', 'epoch': '1.642'} | |
| {'loss': '0.05159', 'grad_norm': '3.26', 'learning_rate': '3.974e-06', 'epoch': '1.642'} | |
| {'loss': '0.05676', 'grad_norm': '2.846', 'learning_rate': '3.969e-06', 'epoch': '1.643'} | |
| {'loss': '0.0548', 'grad_norm': '0.2648', 'learning_rate': '3.964e-06', 'epoch': '1.643'} | |
| {'loss': '0.05456', 'grad_norm': '1.41', 'learning_rate': '3.958e-06', 'epoch': '1.644'} | |
| {'loss': '0.06415', 'grad_norm': '0.24', 'learning_rate': '3.953e-06', 'epoch': '1.644'} | |
| {'loss': '0.04811', 'grad_norm': '1.485', 'learning_rate': '3.948e-06', 'epoch': '1.645'} | |
| {'loss': '0.05464', 'grad_norm': '1.86', 'learning_rate': '3.942e-06', 'epoch': '1.645'} | |
| {'loss': '0.06198', 'grad_norm': '0.676', 'learning_rate': '3.937e-06', 'epoch': '1.646'} | |
| {'loss': '0.05197', 'grad_norm': '0.1095', 'learning_rate': '3.932e-06', 'epoch': '1.646'} | |
| {'loss': '0.051', 'grad_norm': '0.3238', 'learning_rate': '3.927e-06', 'epoch': '1.647'} | |
| {'loss': '0.06522', 'grad_norm': '2.142', 'learning_rate': '3.921e-06', 'epoch': '1.647'} | |
| {'loss': '0.05554', 'grad_norm': '0.05208', 'learning_rate': '3.916e-06', 'epoch': '1.648'} | |
| {'loss': '0.04702', 'grad_norm': '0.7257', 'learning_rate': '3.911e-06', 'epoch': '1.648'} | |
| {'loss': '0.06452', 'grad_norm': '2.824', 'learning_rate': '3.905e-06', 'epoch': '1.649'} | |
| {'loss': '0.05591', 'grad_norm': '1.647', 'learning_rate': '3.9e-06', 'epoch': '1.649'} | |
| {'loss': '0.06008', 'grad_norm': '1.039', 'learning_rate': '3.895e-06', 'epoch': '1.649'} | |
| {'loss': '0.05102', 'grad_norm': '0.6654', 'learning_rate': '3.89e-06', 'epoch': '1.65'} | |
| {'loss': '0.05599', 'grad_norm': '1.114', 'learning_rate': '3.884e-06', 'epoch': '1.65'} | |
| {'loss': '0.04777', 'grad_norm': '0.7107', 'learning_rate': '3.879e-06', 'epoch': '1.651'} | |
| {'loss': '0.05194', 'grad_norm': '4.722', 'learning_rate': '3.874e-06', 'epoch': '1.651'} | |
| {'loss': '0.05312', 'grad_norm': '3.458', 'learning_rate': '3.868e-06', 'epoch': '1.652'} | |
| {'loss': '0.1469', 'grad_norm': '4.437', 'learning_rate': '3.863e-06', 'epoch': '1.652'} | |
| {'loss': '0.05201', 'grad_norm': '1.381', 'learning_rate': '3.858e-06', 'epoch': '1.653'} | |
| {'loss': '0.0612', 'grad_norm': '1.851', 'learning_rate': '3.852e-06', 'epoch': '1.653'} | |
| {'loss': '0.0622', 'grad_norm': '0.7882', 'learning_rate': '3.847e-06', 'epoch': '1.654'} | |
| {'loss': '0.06129', 'grad_norm': '3.656', 'learning_rate': '3.842e-06', 'epoch': '1.654'} | |
| {'loss': '0.1421', 'grad_norm': '1.935', 'learning_rate': '3.837e-06', 'epoch': '1.655'} | |
| {'loss': '0.05446', 'grad_norm': '0.08204', 'learning_rate': '3.831e-06', 'epoch': '1.655'} | |
| {'loss': '0.06451', 'grad_norm': '6.42', 'learning_rate': '3.826e-06', 'epoch': '1.656'} | |
| {'loss': '0.1555', 'grad_norm': '4.3', 'learning_rate': '3.821e-06', 'epoch': '1.656'} | |
| {'loss': '0.04492', 'grad_norm': '0.3183', 'learning_rate': '3.815e-06', 'epoch': '1.657'} | |
| {'loss': '0.05756', 'grad_norm': '1.746', 'learning_rate': '3.81e-06', 'epoch': '1.657'} | |
| {'loss': '0.05499', 'grad_norm': '2.34', 'learning_rate': '3.805e-06', 'epoch': '1.658'} | |
| {'loss': '0.06794', 'grad_norm': '0.4575', 'learning_rate': '3.8e-06', 'epoch': '1.658'} | |
| {'eval_ms_marco_loss': '0.01672', 'eval_val-ms-marco-768_cosine_accuracy': '0.9997', 'eval_val-ms-marco-512_cosine_accuracy': '0.9993', 'eval_val-ms-marco-256_cosine_accuracy': '0.9993', 'eval_val-ms-marco-128_cosine_accuracy': '0.9993', 'eval_val-ms-marco-64_cosine_accuracy': '0.999', 'eval_sequential_score': '0.9997', 'eval_ms_marco_runtime': '33.77', 'eval_ms_marco_samples_per_second': '296.1', 'eval_ms_marco_steps_per_second': '9.269', 'epoch': '1.658'} | |
| {'loss': '0.1417', 'grad_norm': '1.154', 'learning_rate': '3.794e-06', 'epoch': '1.659'} | |
| {'loss': '0.05814', 'grad_norm': '3.687', 'learning_rate': '3.789e-06', 'epoch': '1.659'} | |
| {'loss': '0.05705', 'grad_norm': '0.6806', 'learning_rate': '3.784e-06', 'epoch': '1.659'} | |
| {'loss': '0.05177', 'grad_norm': '2.107', 'learning_rate': '3.778e-06', 'epoch': '1.66'} | |
| {'loss': '0.0475', 'grad_norm': '2.528', 'learning_rate': '3.773e-06', 'epoch': '1.66'} | |
| {'loss': '0.1718', 'grad_norm': '2.212', 'learning_rate': '3.768e-06', 'epoch': '1.661'} | |
| {'loss': '0.06644', 'grad_norm': '1.104', 'learning_rate': '3.762e-06', 'epoch': '1.661'} | |
| {'loss': '0.04928', 'grad_norm': '0.6434', 'learning_rate': '3.757e-06', 'epoch': '1.662'} | |
| {'loss': '0.04752', 'grad_norm': '0.3668', 'learning_rate': '3.752e-06', 'epoch': '1.662'} | |
| {'loss': '0.06384', 'grad_norm': '0.2868', 'learning_rate': '3.747e-06', 'epoch': '1.663'} | |
| {'loss': '0.04978', 'grad_norm': '0.09889', 'learning_rate': '3.741e-06', 'epoch': '1.663'} | |
| {'loss': '0.05885', 'grad_norm': '1.32', 'learning_rate': '3.736e-06', 'epoch': '1.664'} | |
| {'loss': '0.04699', 'grad_norm': '0.2635', 'learning_rate': '3.731e-06', 'epoch': '1.664'} | |
| {'loss': '0.1405', 'grad_norm': '0.2635', 'learning_rate': '3.725e-06', 'epoch': '1.665'} | |
| {'loss': '0.05202', 'grad_norm': '1.497', 'learning_rate': '3.72e-06', 'epoch': '1.665'} | |
| {'loss': '0.05174', 'grad_norm': '0.2616', 'learning_rate': '3.715e-06', 'epoch': '1.666'} | |
| {'loss': '0.05864', 'grad_norm': '0.6191', 'learning_rate': '3.71e-06', 'epoch': '1.666'} | |
| {'loss': '0.04783', 'grad_norm': '2.103', 'learning_rate': '3.704e-06', 'epoch': '1.667'} | |
| {'loss': '0.0509', 'grad_norm': '0.5015', 'learning_rate': '3.699e-06', 'epoch': '1.667'} | |
| {'loss': '0.06102', 'grad_norm': '0.1464', 'learning_rate': '3.694e-06', 'epoch': '1.668'} | |
| {'loss': '0.05456', 'grad_norm': '0.2549', 'learning_rate': '3.688e-06', 'epoch': '1.668'} | |
| {'loss': '0.1435', 'grad_norm': '2.111', 'learning_rate': '3.683e-06', 'epoch': '1.669'} | |
| {'loss': '0.05139', 'grad_norm': '5.295', 'learning_rate': '3.678e-06', 'epoch': '1.669'} | |
| {'loss': '0.03827', 'grad_norm': '3.179', 'learning_rate': '3.672e-06', 'epoch': '1.669'} | |
| {'loss': '0.06114', 'grad_norm': '2.664', 'learning_rate': '3.667e-06', 'epoch': '1.67'} | |
| {'loss': '0.05303', 'grad_norm': '2.489', 'learning_rate': '3.662e-06', 'epoch': '1.67'} | |
| {'loss': '0.3063', 'grad_norm': '0.337', 'learning_rate': '3.657e-06', 'epoch': '1.671'} | |
| {'loss': '0.05724', 'grad_norm': '0.4427', 'learning_rate': '3.651e-06', 'epoch': '1.671'} | |
| {'loss': '0.04714', 'grad_norm': '0.6596', 'learning_rate': '3.646e-06', 'epoch': '1.672'} | |
| {'loss': '0.04497', 'grad_norm': '4.348', 'learning_rate': '3.641e-06', 'epoch': '1.672'} | |
| {'loss': '0.05042', 'grad_norm': '2.11', 'learning_rate': '3.635e-06', 'epoch': '1.673'} | |
| {'loss': '0.05002', 'grad_norm': '1.268', 'learning_rate': '3.63e-06', 'epoch': '1.673'} | |
| {'loss': '0.04993', 'grad_norm': '0.2632', 'learning_rate': '3.625e-06', 'epoch': '1.674'} | |
| {'loss': '0.05386', 'grad_norm': '0.3695', 'learning_rate': '3.62e-06', 'epoch': '1.674'} | |
| {'loss': '0.05286', 'grad_norm': '0.8267', 'learning_rate': '3.614e-06', 'epoch': '1.675'} | |
| {'loss': '0.04559', 'grad_norm': '0.4304', 'learning_rate': '3.609e-06', 'epoch': '1.675'} | |
| {'loss': '0.05541', 'grad_norm': '1.413', 'learning_rate': '3.604e-06', 'epoch': '1.676'} | |
| {'loss': '0.04662', 'grad_norm': '0.9398', 'learning_rate': '3.598e-06', 'epoch': '1.676'} | |
| {'loss': '0.05909', 'grad_norm': '0.8004', 'learning_rate': '3.593e-06', 'epoch': '1.677'} | |
| {'loss': '0.1303', 'grad_norm': '0.2499', 'learning_rate': '3.588e-06', 'epoch': '1.677'} | |
| {'loss': '0.05718', 'grad_norm': '2.324', 'learning_rate': '3.582e-06', 'epoch': '1.678'} | |
| {'loss': '0.05958', 'grad_norm': '2.912', 'learning_rate': '3.577e-06', 'epoch': '1.678'} | |
| {'loss': '0.05859', 'grad_norm': '1.8', 'learning_rate': '3.572e-06', 'epoch': '1.679'} | |
| {'loss': '0.05998', 'grad_norm': '0.2089', 'learning_rate': '3.567e-06', 'epoch': '1.679'} | |
| {'loss': '0.1612', 'grad_norm': '1.188', 'learning_rate': '3.561e-06', 'epoch': '1.679'} | |
| {'loss': '0.05166', 'grad_norm': '0.1534', 'learning_rate': '3.556e-06', 'epoch': '1.68'} | |
| {'loss': '0.05', 'grad_norm': '2.243', 'learning_rate': '3.551e-06', 'epoch': '1.68'} | |
| {'loss': '0.05066', 'grad_norm': '0.6609', 'learning_rate': '3.545e-06', 'epoch': '1.681'} | |
| {'loss': '0.1364', 'grad_norm': '0.697', 'learning_rate': '3.54e-06', 'epoch': '1.681'} | |
| {'loss': '0.05622', 'grad_norm': '0.8691', 'learning_rate': '3.535e-06', 'epoch': '1.682'} | |
| {'loss': '0.04618', 'grad_norm': '0.0614', 'learning_rate': '3.53e-06', 'epoch': '1.682'} | |
| {'loss': '0.04654', 'grad_norm': '0.1651', 'learning_rate': '3.524e-06', 'epoch': '1.683'} | |
| {'loss': '0.05251', 'grad_norm': '0.5375', 'learning_rate': '3.519e-06', 'epoch': '1.683'} | |
| {'loss': '0.1622', 'grad_norm': '0.4139', 'learning_rate': '3.514e-06', 'epoch': '1.684'} | |
| {'loss': '0.05136', 'grad_norm': '0.4331', 'learning_rate': '3.508e-06', 'epoch': '1.684'} | |
| {'loss': '0.06601', 'grad_norm': '4.255', 'learning_rate': '3.503e-06', 'epoch': '1.685'} | |
| {'loss': '0.04804', 'grad_norm': '0.2241', 'learning_rate': '3.498e-06', 'epoch': '1.685'} | |
| {'loss': '0.06142', 'grad_norm': '0.1535', 'learning_rate': '3.492e-06', 'epoch': '1.686'} | |
| {'loss': '0.04947', 'grad_norm': '0.1726', 'learning_rate': '3.487e-06', 'epoch': '1.686'} | |
| {'loss': '0.0498', 'grad_norm': '1.066', 'learning_rate': '3.482e-06', 'epoch': '1.687'} | |
| {'eval_ms_marco_loss': '0.01697', 'eval_val-ms-marco-768_cosine_accuracy': '0.9993', 'eval_val-ms-marco-512_cosine_accuracy': '0.9993', 'eval_val-ms-marco-256_cosine_accuracy': '0.9993', 'eval_val-ms-marco-128_cosine_accuracy': '0.9993', 'eval_val-ms-marco-64_cosine_accuracy': '0.9993', 'eval_sequential_score': '0.9993', 'eval_ms_marco_runtime': '33.98', 'eval_ms_marco_samples_per_second': '294.3', 'eval_ms_marco_steps_per_second': '9.211', 'epoch': '1.687'} | |
| {'loss': '0.04854', 'grad_norm': '8.585', 'learning_rate': '3.477e-06', 'epoch': '1.687'} | |
| {'loss': '0.05712', 'grad_norm': '4.033', 'learning_rate': '3.471e-06', 'epoch': '1.688'} | |
| {'loss': '0.04584', 'grad_norm': '2.445', 'learning_rate': '3.466e-06', 'epoch': '1.688'} | |
| {'loss': '0.04935', 'grad_norm': '0.1365', 'learning_rate': '3.461e-06', 'epoch': '1.689'} | |
| {'loss': '0.04968', 'grad_norm': '0.1487', 'learning_rate': '3.455e-06', 'epoch': '1.689'} | |
| {'loss': '0.05677', 'grad_norm': '0.3102', 'learning_rate': '3.45e-06', 'epoch': '1.689'} | |
| {'loss': '0.05371', 'grad_norm': '0.5666', 'learning_rate': '3.445e-06', 'epoch': '1.69'} | |
| {'loss': '0.04816', 'grad_norm': '3.758', 'learning_rate': '3.44e-06', 'epoch': '1.69'} | |
| {'loss': '0.04619', 'grad_norm': '0.8526', 'learning_rate': '3.434e-06', 'epoch': '1.691'} | |
| {'loss': '0.05332', 'grad_norm': '0.1718', 'learning_rate': '3.429e-06', 'epoch': '1.691'} | |
| {'loss': '0.05455', 'grad_norm': '2.022', 'learning_rate': '3.424e-06', 'epoch': '1.692'} | |
| {'loss': '0.05739', 'grad_norm': '1.287', 'learning_rate': '3.418e-06', 'epoch': '1.692'} | |
| {'loss': '0.04609', 'grad_norm': '0.5176', 'learning_rate': '3.413e-06', 'epoch': '1.693'} | |
| {'loss': '0.05733', 'grad_norm': '3.742', 'learning_rate': '3.408e-06', 'epoch': '1.693'} | |
| {'loss': '0.05016', 'grad_norm': '3.286', 'learning_rate': '3.402e-06', 'epoch': '1.694'} | |
| {'loss': '0.03923', 'grad_norm': '0.905', 'learning_rate': '3.397e-06', 'epoch': '1.694'} | |
| {'loss': '0.05801', 'grad_norm': '1.238', 'learning_rate': '3.392e-06', 'epoch': '1.695'} | |
| {'loss': '0.05768', 'grad_norm': '0.255', 'learning_rate': '3.387e-06', 'epoch': '1.695'} | |
| {'loss': '0.05748', 'grad_norm': '3.13', 'learning_rate': '3.381e-06', 'epoch': '1.696'} | |
| {'loss': '0.05719', 'grad_norm': '0.9251', 'learning_rate': '3.376e-06', 'epoch': '1.696'} | |
| {'loss': '0.05456', 'grad_norm': '2.472', 'learning_rate': '3.371e-06', 'epoch': '1.697'} | |
| {'loss': '0.05119', 'grad_norm': '5.66', 'learning_rate': '3.365e-06', 'epoch': '1.697'} | |
| {'loss': '0.04458', 'grad_norm': '0.05791', 'learning_rate': '3.36e-06', 'epoch': '1.698'} | |
| {'loss': '0.04006', 'grad_norm': '0.8276', 'learning_rate': '3.355e-06', 'epoch': '1.698'} | |
| {'loss': '0.0511', 'grad_norm': '0.6094', 'learning_rate': '3.35e-06', 'epoch': '1.699'} | |
| {'loss': '0.04702', 'grad_norm': '1.613', 'learning_rate': '3.344e-06', 'epoch': '1.699'} | |
| {'loss': '0.05401', 'grad_norm': '3.956', 'learning_rate': '3.339e-06', 'epoch': '1.699'} | |
| {'loss': '0.04892', 'grad_norm': '4.459', 'learning_rate': '3.334e-06', 'epoch': '1.7'} | |
| {'loss': '0.05966', 'grad_norm': '3.835', 'learning_rate': '3.328e-06', 'epoch': '1.7'} | |
| {'loss': '0.05081', 'grad_norm': '0.1044', 'learning_rate': '3.323e-06', 'epoch': '1.701'} | |
| {'loss': '0.1743', 'grad_norm': '1.354', 'learning_rate': '3.318e-06', 'epoch': '1.701'} | |
| {'loss': '0.04246', 'grad_norm': '0.09843', 'learning_rate': '3.312e-06', 'epoch': '1.702'} | |
| {'loss': '0.0501', 'grad_norm': '0.9345', 'learning_rate': '3.307e-06', 'epoch': '1.702'} | |
| {'loss': '0.05735', 'grad_norm': '5.448', 'learning_rate': '3.302e-06', 'epoch': '1.703'} | |
| {'loss': '0.05322', 'grad_norm': '5.559', 'learning_rate': '3.297e-06', 'epoch': '1.703'} | |
| {'loss': '0.05275', 'grad_norm': '0.1555', 'learning_rate': '3.291e-06', 'epoch': '1.704'} | |
| {'loss': '0.0593', 'grad_norm': '7.182', 'learning_rate': '3.286e-06', 'epoch': '1.704'} | |
| {'loss': '0.04437', 'grad_norm': '0.3817', 'learning_rate': '3.281e-06', 'epoch': '1.705'} | |
| {'loss': '0.0574', 'grad_norm': '0.06879', 'learning_rate': '3.275e-06', 'epoch': '1.705'} | |
| {'loss': '0.05454', 'grad_norm': '0.2939', 'learning_rate': '3.27e-06', 'epoch': '1.706'} | |
| {'loss': '0.0525', 'grad_norm': '0.05482', 'learning_rate': '3.265e-06', 'epoch': '1.706'} | |
| {'loss': '0.04728', 'grad_norm': '5.179', 'learning_rate': '3.26e-06', 'epoch': '1.707'} | |
| {'loss': '0.07084', 'grad_norm': '0.538', 'learning_rate': '3.254e-06', 'epoch': '1.707'} | |
| {'loss': '0.0491', 'grad_norm': '5.556', 'learning_rate': '3.249e-06', 'epoch': '1.708'} | |
| {'loss': '0.05321', 'grad_norm': '2.997', 'learning_rate': '3.244e-06', 'epoch': '1.708'} | |
| {'loss': '0.04554', 'grad_norm': '1.628', 'learning_rate': '3.238e-06', 'epoch': '1.709'} | |
| {'loss': '0.05302', 'grad_norm': '0.6783', 'learning_rate': '3.233e-06', 'epoch': '1.709'} | |
| {'loss': '0.05003', 'grad_norm': '0.05728', 'learning_rate': '3.228e-06', 'epoch': '1.71'} | |
| {'loss': '0.05489', 'grad_norm': '0.2125', 'learning_rate': '3.222e-06', 'epoch': '1.71'} | |
| {'loss': '0.05337', 'grad_norm': '0.4077', 'learning_rate': '3.217e-06', 'epoch': '1.71'} | |
| {'loss': '0.05542', 'grad_norm': '0.8471', 'learning_rate': '3.212e-06', 'epoch': '1.711'} | |
| {'loss': '0.05203', 'grad_norm': '0.1762', 'learning_rate': '3.207e-06', 'epoch': '1.711'} | |
| {'loss': '0.05094', 'grad_norm': '0.9535', 'learning_rate': '3.201e-06', 'epoch': '1.712'} | |
| {'loss': '0.042', 'grad_norm': '1.006', 'learning_rate': '3.196e-06', 'epoch': '1.712'} | |
| {'loss': '0.0573', 'grad_norm': '1.606', 'learning_rate': '3.191e-06', 'epoch': '1.713'} | |
| {'loss': '0.04549', 'grad_norm': '0.9213', 'learning_rate': '3.185e-06', 'epoch': '1.713'} | |
| {'loss': '0.05648', 'grad_norm': '0.08144', 'learning_rate': '3.18e-06', 'epoch': '1.714'} | |
| {'loss': '0.05266', 'grad_norm': '0.1312', 'learning_rate': '3.175e-06', 'epoch': '1.714'} | |
| {'loss': '0.05192', 'grad_norm': '0.1169', 'learning_rate': '3.17e-06', 'epoch': '1.715'} | |
| {'loss': '0.04887', 'grad_norm': '2.631', 'learning_rate': '3.164e-06', 'epoch': '1.715'} | |
| {'eval_ms_marco_loss': '0.0167', 'eval_val-ms-marco-768_cosine_accuracy': '0.9993', 'eval_val-ms-marco-512_cosine_accuracy': '0.9993', 'eval_val-ms-marco-256_cosine_accuracy': '0.9993', 'eval_val-ms-marco-128_cosine_accuracy': '0.9993', 'eval_val-ms-marco-64_cosine_accuracy': '0.999', 'eval_sequential_score': '0.9993', 'eval_ms_marco_runtime': '33.81', 'eval_ms_marco_samples_per_second': '295.8', 'eval_ms_marco_steps_per_second': '9.259', 'epoch': '1.715'} | |
| {'loss': '0.06475', 'grad_norm': '4.275', 'learning_rate': '3.159e-06', 'epoch': '1.716'} | |
| {'loss': '0.05858', 'grad_norm': '0.3678', 'learning_rate': '3.154e-06', 'epoch': '1.716'} | |
| {'loss': '0.1212', 'grad_norm': '0.5196', 'learning_rate': '3.148e-06', 'epoch': '1.717'} | |
| {'loss': '0.03767', 'grad_norm': '1.408', 'learning_rate': '3.143e-06', 'epoch': '1.717'} | |
| {'loss': '0.0536', 'grad_norm': '0.07929', 'learning_rate': '3.138e-06', 'epoch': '1.718'} | |
| {'loss': '0.04887', 'grad_norm': '0.07851', 'learning_rate': '3.132e-06', 'epoch': '1.718'} | |
| {'loss': '0.04583', 'grad_norm': '0.7768', 'learning_rate': '3.127e-06', 'epoch': '1.719'} | |
| {'loss': '0.159', 'grad_norm': '0.4919', 'learning_rate': '3.122e-06', 'epoch': '1.719'} | |
| {'loss': '0.0461', 'grad_norm': '0.2712', 'learning_rate': '3.117e-06', 'epoch': '1.72'} | |
| {'loss': '0.0548', 'grad_norm': '4.467', 'learning_rate': '3.111e-06', 'epoch': '1.72'} | |
| {'loss': '0.05169', 'grad_norm': '0.1415', 'learning_rate': '3.106e-06', 'epoch': '1.72'} | |
| {'loss': '0.05195', 'grad_norm': '0.08947', 'learning_rate': '3.101e-06', 'epoch': '1.721'} | |
| {'loss': '0.04741', 'grad_norm': '1.508', 'learning_rate': '3.095e-06', 'epoch': '1.721'} | |
| {'loss': '0.04805', 'grad_norm': '1.307', 'learning_rate': '3.09e-06', 'epoch': '1.722'} | |
| {'loss': '0.05455', 'grad_norm': '0.2813', 'learning_rate': '3.085e-06', 'epoch': '1.722'} | |
| {'loss': '0.05934', 'grad_norm': '0.6254', 'learning_rate': '3.08e-06', 'epoch': '1.723'} | |
| {'loss': '0.06551', 'grad_norm': '0.09593', 'learning_rate': '3.074e-06', 'epoch': '1.723'} | |
| {'loss': '0.06673', 'grad_norm': '2.867', 'learning_rate': '3.069e-06', 'epoch': '1.724'} | |
| {'loss': '0.04741', 'grad_norm': '0.2651', 'learning_rate': '3.064e-06', 'epoch': '1.724'} | |
| {'loss': '0.05618', 'grad_norm': '0.06876', 'learning_rate': '3.058e-06', 'epoch': '1.725'} | |
| {'loss': '0.05737', 'grad_norm': '0.1515', 'learning_rate': '3.053e-06', 'epoch': '1.725'} | |
| {'loss': '0.05381', 'grad_norm': '0.07802', 'learning_rate': '3.048e-06', 'epoch': '1.726'} | |
| {'loss': '0.0504', 'grad_norm': '0.8411', 'learning_rate': '3.042e-06', 'epoch': '1.726'} | |
| {'loss': '0.1321', 'grad_norm': '0.3334', 'learning_rate': '3.037e-06', 'epoch': '1.727'} | |
| {'loss': '0.05524', 'grad_norm': '2.091', 'learning_rate': '3.032e-06', 'epoch': '1.727'} | |
| {'loss': '0.04481', 'grad_norm': '4.089', 'learning_rate': '3.027e-06', 'epoch': '1.728'} | |
| {'loss': '0.0531', 'grad_norm': '2.136', 'learning_rate': '3.021e-06', 'epoch': '1.728'} | |
| {'loss': '0.04384', 'grad_norm': '0.3143', 'learning_rate': '3.016e-06', 'epoch': '1.729'} | |
| {'loss': '0.04803', 'grad_norm': '1.128', 'learning_rate': '3.011e-06', 'epoch': '1.729'} | |
| {'loss': '0.04873', 'grad_norm': '0.2743', 'learning_rate': '3.005e-06', 'epoch': '1.73'} | |
| {'loss': '0.0562', 'grad_norm': '1.813', 'learning_rate': '3e-06', 'epoch': '1.73'} | |
| {'loss': '0.05574', 'grad_norm': '1.642', 'learning_rate': '2.995e-06', 'epoch': '1.73'} | |
| {'loss': '0.06548', 'grad_norm': '1.388', 'learning_rate': '2.99e-06', 'epoch': '1.731'} | |
| {'loss': '0.06012', 'grad_norm': '2.098', 'learning_rate': '2.984e-06', 'epoch': '1.731'} | |
| {'loss': '0.05957', 'grad_norm': '0.3825', 'learning_rate': '2.979e-06', 'epoch': '1.732'} | |
| {'loss': '0.04749', 'grad_norm': '1.35', 'learning_rate': '2.974e-06', 'epoch': '1.732'} | |
| {'loss': '0.05581', 'grad_norm': '4.856', 'learning_rate': '2.968e-06', 'epoch': '1.733'} | |
| {'loss': '0.05433', 'grad_norm': '0.04843', 'learning_rate': '2.963e-06', 'epoch': '1.733'} | |
| {'loss': '0.04498', 'grad_norm': '3.223', 'learning_rate': '2.958e-06', 'epoch': '1.734'} | |
| {'loss': '0.05178', 'grad_norm': '0.8328', 'learning_rate': '2.952e-06', 'epoch': '1.734'} | |
| {'loss': '0.05443', 'grad_norm': '0.8791', 'learning_rate': '2.947e-06', 'epoch': '1.735'} | |
| {'loss': '0.03888', 'grad_norm': '1.355', 'learning_rate': '2.942e-06', 'epoch': '1.735'} | |
| {'loss': '0.05149', 'grad_norm': '1.645', 'learning_rate': '2.937e-06', 'epoch': '1.736'} | |
| {'loss': '0.05922', 'grad_norm': '0.03903', 'learning_rate': '2.931e-06', 'epoch': '1.736'} | |
| {'loss': '0.04908', 'grad_norm': '0.3396', 'learning_rate': '2.926e-06', 'epoch': '1.737'} | |
| {'loss': '0.04853', 'grad_norm': '1.522', 'learning_rate': '2.921e-06', 'epoch': '1.737'} | |
| {'loss': '0.05089', 'grad_norm': '2.974', 'learning_rate': '2.915e-06', 'epoch': '1.738'} | |
| {'loss': '0.04051', 'grad_norm': '0.5383', 'learning_rate': '2.91e-06', 'epoch': '1.738'} | |
| {'loss': '0.0531', 'grad_norm': '3.027', 'learning_rate': '2.905e-06', 'epoch': '1.739'} | |
| {'loss': '0.04827', 'grad_norm': '0.6446', 'learning_rate': '2.9e-06', 'epoch': '1.739'} | |
| {'loss': '0.0445', 'grad_norm': '0.3142', 'learning_rate': '2.894e-06', 'epoch': '1.74'} | |
| {'loss': '0.05057', 'grad_norm': '1.228', 'learning_rate': '2.889e-06', 'epoch': '1.74'} | |
| {'loss': '0.06218', 'grad_norm': '1.735', 'learning_rate': '2.884e-06', 'epoch': '1.74'} | |
| {'loss': '0.05198', 'grad_norm': '1.817', 'learning_rate': '2.878e-06', 'epoch': '1.741'} | |
| {'loss': '0.04478', 'grad_norm': '0.4038', 'learning_rate': '2.873e-06', 'epoch': '1.741'} | |
| {'loss': '0.0513', 'grad_norm': '2.339', 'learning_rate': '2.868e-06', 'epoch': '1.742'} | |
| {'loss': '0.04736', 'grad_norm': '1.682', 'learning_rate': '2.862e-06', 'epoch': '1.742'} | |
| {'loss': '0.05984', 'grad_norm': '0.6474', 'learning_rate': '2.857e-06', 'epoch': '1.743'} | |
| {'loss': '0.06487', 'grad_norm': '1.34', 'learning_rate': '2.852e-06', 'epoch': '1.743'} | |
| {'loss': '0.1404', 'grad_norm': '0.1582', 'learning_rate': '2.847e-06', 'epoch': '1.744'} | |
| {'eval_ms_marco_loss': '0.01693', 'eval_val-ms-marco-768_cosine_accuracy': '0.999', 'eval_val-ms-marco-512_cosine_accuracy': '0.999', 'eval_val-ms-marco-256_cosine_accuracy': '0.999', 'eval_val-ms-marco-128_cosine_accuracy': '0.999', 'eval_val-ms-marco-64_cosine_accuracy': '0.999', 'eval_sequential_score': '0.999', 'eval_ms_marco_runtime': '33.93', 'eval_ms_marco_samples_per_second': '294.7', 'eval_ms_marco_steps_per_second': '9.224', 'epoch': '1.744'} | |
| {'loss': '0.05556', 'grad_norm': '3.365', 'learning_rate': '2.841e-06', 'epoch': '1.744'} | |
| {'loss': '0.05122', 'grad_norm': '3.873', 'learning_rate': '2.836e-06', 'epoch': '1.745'} | |
| {'loss': '0.04325', 'grad_norm': '0.1207', 'learning_rate': '2.831e-06', 'epoch': '1.745'} | |
| {'loss': '0.04678', 'grad_norm': '0.2219', 'learning_rate': '2.825e-06', 'epoch': '1.746'} | |
| {'loss': '0.05928', 'grad_norm': '9.303', 'learning_rate': '2.82e-06', 'epoch': '1.746'} | |
| {'loss': '0.2577', 'grad_norm': '4.444', 'learning_rate': '2.815e-06', 'epoch': '1.747'} | |
| {'loss': '0.1494', 'grad_norm': '1.613', 'learning_rate': '2.81e-06', 'epoch': '1.747'} | |
| {'loss': '0.04683', 'grad_norm': '1.306', 'learning_rate': '2.804e-06', 'epoch': '1.748'} | |
| {'loss': '0.04584', 'grad_norm': '2.88', 'learning_rate': '2.799e-06', 'epoch': '1.748'} | |
| {'loss': '0.2412', 'grad_norm': '2.368', 'learning_rate': '2.794e-06', 'epoch': '1.749'} | |
| {'loss': '0.06371', 'grad_norm': '0.1442', 'learning_rate': '2.788e-06', 'epoch': '1.749'} | |
| {'loss': '0.04664', 'grad_norm': '2.759', 'learning_rate': '2.783e-06', 'epoch': '1.75'} | |
| {'loss': '0.04347', 'grad_norm': '1.351', 'learning_rate': '2.778e-06', 'epoch': '1.75'} | |
| {'loss': '0.1403', 'grad_norm': '1.154', 'learning_rate': '2.772e-06', 'epoch': '1.75'} | |
| {'loss': '0.04981', 'grad_norm': '1.267', 'learning_rate': '2.767e-06', 'epoch': '1.751'} | |
| {'loss': '0.04565', 'grad_norm': '0.4595', 'learning_rate': '2.762e-06', 'epoch': '1.751'} | |
| {'loss': '0.06047', 'grad_norm': '1.378', 'learning_rate': '2.757e-06', 'epoch': '1.752'} | |
| {'loss': '0.04408', 'grad_norm': '1.691', 'learning_rate': '2.751e-06', 'epoch': '1.752'} | |
| {'loss': '0.04509', 'grad_norm': '0.3233', 'learning_rate': '2.746e-06', 'epoch': '1.753'} | |
| {'loss': '0.04678', 'grad_norm': '2.461', 'learning_rate': '2.741e-06', 'epoch': '1.753'} | |
| {'loss': '0.05937', 'grad_norm': '3.721', 'learning_rate': '2.735e-06', 'epoch': '1.754'} | |
| {'loss': '0.1307', 'grad_norm': '0.4398', 'learning_rate': '2.73e-06', 'epoch': '1.754'} | |
| {'loss': '0.04463', 'grad_norm': '5.155', 'learning_rate': '2.725e-06', 'epoch': '1.755'} | |
| {'loss': '0.04551', 'grad_norm': '0.3232', 'learning_rate': '2.72e-06', 'epoch': '1.755'} | |
| {'loss': '0.04372', 'grad_norm': '0.347', 'learning_rate': '2.714e-06', 'epoch': '1.756'} | |
| {'loss': '0.05091', 'grad_norm': '0.2433', 'learning_rate': '2.709e-06', 'epoch': '1.756'} | |
| {'loss': '0.05222', 'grad_norm': '0.3224', 'learning_rate': '2.704e-06', 'epoch': '1.757'} | |
| {'loss': '0.1354', 'grad_norm': '2.344', 'learning_rate': '2.698e-06', 'epoch': '1.757'} | |
| {'loss': '0.04898', 'grad_norm': '0.7834', 'learning_rate': '2.693e-06', 'epoch': '1.758'} | |
| {'loss': '0.04964', 'grad_norm': '0.1563', 'learning_rate': '2.688e-06', 'epoch': '1.758'} | |
| {'loss': '0.04652', 'grad_norm': '3.361', 'learning_rate': '2.682e-06', 'epoch': '1.759'} | |
| {'loss': '0.05149', 'grad_norm': '0.2638', 'learning_rate': '2.677e-06', 'epoch': '1.759'} | |
| {'loss': '0.04127', 'grad_norm': '4.816', 'learning_rate': '2.672e-06', 'epoch': '1.76'} | |
| {'loss': '0.05246', 'grad_norm': '1.496', 'learning_rate': '2.667e-06', 'epoch': '1.76'} | |
| {'loss': '0.04304', 'grad_norm': '1.389', 'learning_rate': '2.661e-06', 'epoch': '1.76'} | |
| {'loss': '0.0421', 'grad_norm': '0.3584', 'learning_rate': '2.656e-06', 'epoch': '1.761'} | |
| {'loss': '0.05233', 'grad_norm': '1.425', 'learning_rate': '2.651e-06', 'epoch': '1.761'} | |
| {'loss': '0.04728', 'grad_norm': '0.391', 'learning_rate': '2.645e-06', 'epoch': '1.762'} | |
| {'loss': '0.05308', 'grad_norm': '0.3359', 'learning_rate': '2.64e-06', 'epoch': '1.762'} | |
| {'loss': '0.04498', 'grad_norm': '3.708', 'learning_rate': '2.635e-06', 'epoch': '1.763'} | |
| {'loss': '0.04228', 'grad_norm': '0.2499', 'learning_rate': '2.63e-06', 'epoch': '1.763'} | |
| {'loss': '0.054', 'grad_norm': '4.913', 'learning_rate': '2.624e-06', 'epoch': '1.764'} | |
| {'loss': '0.04681', 'grad_norm': '0.2361', 'learning_rate': '2.619e-06', 'epoch': '1.764'} | |
| {'loss': '0.04841', 'grad_norm': '0.7551', 'learning_rate': '2.614e-06', 'epoch': '1.765'} | |
| {'loss': '0.04995', 'grad_norm': '0.6519', 'learning_rate': '2.608e-06', 'epoch': '1.765'} | |
| {'loss': '0.05201', 'grad_norm': '1.126', 'learning_rate': '2.603e-06', 'epoch': '1.766'} | |
| {'loss': '0.05566', 'grad_norm': '0.5374', 'learning_rate': '2.598e-06', 'epoch': '1.766'} | |
| {'loss': '0.04213', 'grad_norm': '0.05563', 'learning_rate': '2.593e-06', 'epoch': '1.767'} | |
| {'loss': '0.1509', 'grad_norm': '0.5853', 'learning_rate': '2.587e-06', 'epoch': '1.767'} | |
| {'loss': '0.04745', 'grad_norm': '0.09846', 'learning_rate': '2.582e-06', 'epoch': '1.768'} | |
| {'loss': '0.04081', 'grad_norm': '0.2922', 'learning_rate': '2.577e-06', 'epoch': '1.768'} | |
| {'loss': '0.04158', 'grad_norm': '0.4013', 'learning_rate': '2.571e-06', 'epoch': '1.769'} | |
| {'loss': '0.04858', 'grad_norm': '0.2193', 'learning_rate': '2.566e-06', 'epoch': '1.769'} | |
| {'loss': '0.1479', 'grad_norm': '1.68', 'learning_rate': '2.561e-06', 'epoch': '1.77'} | |
| {'loss': '0.04129', 'grad_norm': '1.926', 'learning_rate': '2.555e-06', 'epoch': '1.77'} | |
| {'loss': '0.04492', 'grad_norm': '0.07381', 'learning_rate': '2.55e-06', 'epoch': '1.77'} | |
| {'loss': '0.05583', 'grad_norm': '1.98', 'learning_rate': '2.545e-06', 'epoch': '1.771'} | |
| {'loss': '0.0459', 'grad_norm': '2.767', 'learning_rate': '2.54e-06', 'epoch': '1.771'} | |
| {'loss': '0.04631', 'grad_norm': '0.9453', 'learning_rate': '2.534e-06', 'epoch': '1.772'} | |
| {'loss': '0.04175', 'grad_norm': '0.5843', 'learning_rate': '2.529e-06', 'epoch': '1.772'} | |
| {'eval_ms_marco_loss': '0.01579', 'eval_val-ms-marco-768_cosine_accuracy': '0.9993', 'eval_val-ms-marco-512_cosine_accuracy': '0.9993', 'eval_val-ms-marco-256_cosine_accuracy': '0.9993', 'eval_val-ms-marco-128_cosine_accuracy': '0.9993', 'eval_val-ms-marco-64_cosine_accuracy': '0.999', 'eval_sequential_score': '0.9993', 'eval_ms_marco_runtime': '34.33', 'eval_ms_marco_samples_per_second': '291.3', 'eval_ms_marco_steps_per_second': '9.117', 'epoch': '1.772'} | |
| {'loss': '0.1271', 'grad_norm': '3.608', 'learning_rate': '2.524e-06', 'epoch': '1.773'} | |
| {'loss': '0.04512', 'grad_norm': '3.464', 'learning_rate': '2.518e-06', 'epoch': '1.773'} | |
| {'loss': '0.1497', 'grad_norm': '0.5898', 'learning_rate': '2.513e-06', 'epoch': '1.774'} | |
| {'loss': '0.05548', 'grad_norm': '1.552', 'learning_rate': '2.508e-06', 'epoch': '1.774'} | |
| {'loss': '0.05796', 'grad_norm': '3.045', 'learning_rate': '2.503e-06', 'epoch': '1.775'} | |
| {'loss': '0.04843', 'grad_norm': '0.335', 'learning_rate': '2.497e-06', 'epoch': '1.775'} | |
| {'loss': '0.1576', 'grad_norm': '0.7184', 'learning_rate': '2.492e-06', 'epoch': '1.776'} | |
| {'loss': '0.0553', 'grad_norm': '0.05305', 'learning_rate': '2.487e-06', 'epoch': '1.776'} | |
| {'loss': '0.05427', 'grad_norm': '0.463', 'learning_rate': '2.481e-06', 'epoch': '1.777'} | |
| {'loss': '0.04067', 'grad_norm': '2.424', 'learning_rate': '2.476e-06', 'epoch': '1.777'} | |
| {'loss': '0.05621', 'grad_norm': '0.2761', 'learning_rate': '2.471e-06', 'epoch': '1.778'} | |
| {'loss': '0.05036', 'grad_norm': '0.1726', 'learning_rate': '2.465e-06', 'epoch': '1.778'} | |
| {'loss': '0.04703', 'grad_norm': '2.359', 'learning_rate': '2.46e-06', 'epoch': '1.779'} | |
| {'loss': '0.04612', 'grad_norm': '1.156', 'learning_rate': '2.455e-06', 'epoch': '1.779'} | |
| {'loss': '0.04242', 'grad_norm': '0.1499', 'learning_rate': '2.45e-06', 'epoch': '1.78'} | |
| {'loss': '0.04147', 'grad_norm': '1.995', 'learning_rate': '2.444e-06', 'epoch': '1.78'} | |
| {'loss': '0.04821', 'grad_norm': '0.2004', 'learning_rate': '2.439e-06', 'epoch': '1.78'} | |
| {'loss': '0.05503', 'grad_norm': '7.653', 'learning_rate': '2.434e-06', 'epoch': '1.781'} | |
| {'loss': '0.04835', 'grad_norm': '1.366', 'learning_rate': '2.428e-06', 'epoch': '1.781'} | |
| {'loss': '0.04905', 'grad_norm': '0.1634', 'learning_rate': '2.423e-06', 'epoch': '1.782'} | |
| {'loss': '0.05479', 'grad_norm': '1.871', 'learning_rate': '2.418e-06', 'epoch': '1.782'} | |
| {'loss': '0.05069', 'grad_norm': '0.5492', 'learning_rate': '2.413e-06', 'epoch': '1.783'} | |
| {'loss': '0.1282', 'grad_norm': '0.4893', 'learning_rate': '2.407e-06', 'epoch': '1.783'} | |
| {'loss': '0.05074', 'grad_norm': '0.1925', 'learning_rate': '2.402e-06', 'epoch': '1.784'} | |
| {'loss': '0.05813', 'grad_norm': '0.1246', 'learning_rate': '2.397e-06', 'epoch': '1.784'} | |
| {'loss': '0.04544', 'grad_norm': '1.261', 'learning_rate': '2.391e-06', 'epoch': '1.785'} | |
| {'loss': '0.04394', 'grad_norm': '0.2873', 'learning_rate': '2.386e-06', 'epoch': '1.785'} | |
| {'loss': '0.1503', 'grad_norm': '0.6856', 'learning_rate': '2.381e-06', 'epoch': '1.786'} | |
| {'loss': '0.05782', 'grad_norm': '0.8046', 'learning_rate': '2.375e-06', 'epoch': '1.786'} | |
| {'loss': '0.04721', 'grad_norm': '0.4772', 'learning_rate': '2.37e-06', 'epoch': '1.787'} | |
| {'loss': '0.05133', 'grad_norm': '0.09898', 'learning_rate': '2.365e-06', 'epoch': '1.787'} | |
| {'loss': '0.05401', 'grad_norm': '0.2253', 'learning_rate': '2.36e-06', 'epoch': '1.788'} | |
| {'loss': '0.04817', 'grad_norm': '0.2431', 'learning_rate': '2.354e-06', 'epoch': '1.788'} | |
| {'loss': '0.05526', 'grad_norm': '0.8642', 'learning_rate': '2.349e-06', 'epoch': '1.789'} | |
| {'loss': '0.06451', 'grad_norm': '1.171', 'learning_rate': '2.344e-06', 'epoch': '1.789'} | |
| {'loss': '0.04333', 'grad_norm': '0.1696', 'learning_rate': '2.338e-06', 'epoch': '1.79'} | |
| {'loss': '0.04229', 'grad_norm': '0.07819', 'learning_rate': '2.333e-06', 'epoch': '1.79'} | |
| {'loss': '0.04671', 'grad_norm': '5.458', 'learning_rate': '2.328e-06', 'epoch': '1.791'} | |
| {'loss': '0.04651', 'grad_norm': '0.9929', 'learning_rate': '2.323e-06', 'epoch': '1.791'} | |
| {'loss': '0.1739', 'grad_norm': '3.392', 'learning_rate': '2.317e-06', 'epoch': '1.791'} | |
| {'loss': '0.04972', 'grad_norm': '0.3147', 'learning_rate': '2.312e-06', 'epoch': '1.792'} | |
| {'loss': '0.05184', 'grad_norm': '0.09956', 'learning_rate': '2.307e-06', 'epoch': '1.792'} | |
| {'loss': '0.05808', 'grad_norm': '2.2', 'learning_rate': '2.301e-06', 'epoch': '1.793'} | |
| {'loss': '0.05617', 'grad_norm': '5.321', 'learning_rate': '2.296e-06', 'epoch': '1.793'} | |
| {'loss': '0.04371', 'grad_norm': '3.256', 'learning_rate': '2.291e-06', 'epoch': '1.794'} | |
| {'loss': '0.05668', 'grad_norm': '0.3637', 'learning_rate': '2.285e-06', 'epoch': '1.794'} | |
| {'loss': '0.04495', 'grad_norm': '0.4752', 'learning_rate': '2.28e-06', 'epoch': '1.795'} | |
| {'loss': '0.05449', 'grad_norm': '2.51', 'learning_rate': '2.275e-06', 'epoch': '1.795'} | |
| {'loss': '0.1483', 'grad_norm': '0.6732', 'learning_rate': '2.27e-06', 'epoch': '1.796'} | |
| {'loss': '0.05229', 'grad_norm': '1.253', 'learning_rate': '2.264e-06', 'epoch': '1.796'} | |
| {'loss': '0.04856', 'grad_norm': '2.542', 'learning_rate': '2.259e-06', 'epoch': '1.797'} | |
| {'loss': '0.04798', 'grad_norm': '0.05745', 'learning_rate': '2.254e-06', 'epoch': '1.797'} | |
| {'loss': '0.172', 'grad_norm': '1.502', 'learning_rate': '2.248e-06', 'epoch': '1.798'} | |
| {'loss': '0.03607', 'grad_norm': '0.2297', 'learning_rate': '2.243e-06', 'epoch': '1.798'} | |
| {'loss': '0.04044', 'grad_norm': '0.08014', 'learning_rate': '2.238e-06', 'epoch': '1.799'} | |
| {'loss': '0.04963', 'grad_norm': '0.3325', 'learning_rate': '2.233e-06', 'epoch': '1.799'} | |
| {'loss': '0.05382', 'grad_norm': '0.09467', 'learning_rate': '2.227e-06', 'epoch': '1.8'} | |
| {'loss': '0.04349', 'grad_norm': '0.4187', 'learning_rate': '2.222e-06', 'epoch': '1.8'} | |
| {'loss': '0.05416', 'grad_norm': '0.2931', 'learning_rate': '2.217e-06', 'epoch': '1.801'} | |
| {'loss': '0.04435', 'grad_norm': '0.8902', 'learning_rate': '2.211e-06', 'epoch': '1.801'} | |
| {'eval_ms_marco_loss': '0.01424', 'eval_val-ms-marco-768_cosine_accuracy': '0.9997', 'eval_val-ms-marco-512_cosine_accuracy': '0.9997', 'eval_val-ms-marco-256_cosine_accuracy': '0.9997', 'eval_val-ms-marco-128_cosine_accuracy': '0.9997', 'eval_val-ms-marco-64_cosine_accuracy': '0.9997', 'eval_sequential_score': '0.9997', 'eval_ms_marco_runtime': '33.94', 'eval_ms_marco_samples_per_second': '294.6', 'eval_ms_marco_steps_per_second': '9.222', 'epoch': '1.801'} | |
| {'loss': '0.04447', 'grad_norm': '1.377', 'learning_rate': '2.206e-06', 'epoch': '1.801'} | |
| {'loss': '0.05416', 'grad_norm': '0.3089', 'learning_rate': '2.201e-06', 'epoch': '1.802'} | |
| {'loss': '0.0498', 'grad_norm': '2.948', 'learning_rate': '2.195e-06', 'epoch': '1.802'} | |
| {'loss': '0.05035', 'grad_norm': '1.672', 'learning_rate': '2.19e-06', 'epoch': '1.803'} | |
| {'loss': '0.04766', 'grad_norm': '2.656', 'learning_rate': '2.185e-06', 'epoch': '1.803'} | |
| {'loss': '0.04272', 'grad_norm': '0.9156', 'learning_rate': '2.18e-06', 'epoch': '1.804'} | |
| {'loss': '0.1565', 'grad_norm': '1.133', 'learning_rate': '2.174e-06', 'epoch': '1.804'} | |
| {'loss': '0.0426', 'grad_norm': '1.448', 'learning_rate': '2.169e-06', 'epoch': '1.805'} | |
| {'loss': '0.05733', 'grad_norm': '0.1856', 'learning_rate': '2.164e-06', 'epoch': '1.805'} | |
| {'loss': '0.05339', 'grad_norm': '0.27', 'learning_rate': '2.158e-06', 'epoch': '1.806'} | |
| {'loss': '0.04483', 'grad_norm': '0.861', 'learning_rate': '2.153e-06', 'epoch': '1.806'} | |
| {'loss': '0.04422', 'grad_norm': '0.2222', 'learning_rate': '2.148e-06', 'epoch': '1.807'} | |
| {'loss': '0.1455', 'grad_norm': '0.1989', 'learning_rate': '2.143e-06', 'epoch': '1.807'} | |
| {'loss': '0.05373', 'grad_norm': '0.9697', 'learning_rate': '2.137e-06', 'epoch': '1.808'} | |
| {'loss': '0.04539', 'grad_norm': '0.1127', 'learning_rate': '2.132e-06', 'epoch': '1.808'} | |
| {'loss': '0.0501', 'grad_norm': '0.677', 'learning_rate': '2.127e-06', 'epoch': '1.809'} | |
| {'loss': '0.04646', 'grad_norm': '1.824', 'learning_rate': '2.121e-06', 'epoch': '1.809'} | |
| {'loss': '0.05214', 'grad_norm': '0.03867', 'learning_rate': '2.116e-06', 'epoch': '1.81'} | |
| {'loss': '0.1417', 'grad_norm': '3.142', 'learning_rate': '2.111e-06', 'epoch': '1.81'} | |
| {'loss': '0.04098', 'grad_norm': '2.535', 'learning_rate': '2.105e-06', 'epoch': '1.811'} | |
| {'loss': '0.06422', 'grad_norm': '3.698', 'learning_rate': '2.1e-06', 'epoch': '1.811'} | |
| {'loss': '0.1648', 'grad_norm': '0.4225', 'learning_rate': '2.095e-06', 'epoch': '1.811'} | |
| {'loss': '0.1424', 'grad_norm': '6.429', 'learning_rate': '2.09e-06', 'epoch': '1.812'} | |
| {'loss': '0.04035', 'grad_norm': '6.451', 'learning_rate': '2.084e-06', 'epoch': '1.812'} | |
| {'loss': '0.05065', 'grad_norm': '0.7217', 'learning_rate': '2.079e-06', 'epoch': '1.813'} | |
| {'loss': '0.04089', 'grad_norm': '0.5391', 'learning_rate': '2.074e-06', 'epoch': '1.813'} | |
| {'loss': '0.06063', 'grad_norm': '2.418', 'learning_rate': '2.068e-06', 'epoch': '1.814'} | |
| {'loss': '0.04809', 'grad_norm': '1.51', 'learning_rate': '2.063e-06', 'epoch': '1.814'} | |
| {'loss': '0.04407', 'grad_norm': '2.16', 'learning_rate': '2.058e-06', 'epoch': '1.815'} | |
| {'loss': '0.0511', 'grad_norm': '0.2727', 'learning_rate': '2.053e-06', 'epoch': '1.815'} | |
| {'loss': '0.1553', 'grad_norm': '0.2512', 'learning_rate': '2.047e-06', 'epoch': '1.816'} | |
| {'loss': '0.04152', 'grad_norm': '1.938', 'learning_rate': '2.042e-06', 'epoch': '1.816'} | |
| {'loss': '0.04989', 'grad_norm': '0.05465', 'learning_rate': '2.037e-06', 'epoch': '1.817'} | |
| {'loss': '0.05572', 'grad_norm': '0.1113', 'learning_rate': '2.031e-06', 'epoch': '1.817'} | |
| {'loss': '0.04007', 'grad_norm': '2.945', 'learning_rate': '2.026e-06', 'epoch': '1.818'} | |
| {'loss': '0.0496', 'grad_norm': '3.087', 'learning_rate': '2.021e-06', 'epoch': '1.818'} | |
| {'loss': '0.04755', 'grad_norm': '0.3998', 'learning_rate': '2.015e-06', 'epoch': '1.819'} | |
| {'loss': '0.04869', 'grad_norm': '1.802', 'learning_rate': '2.01e-06', 'epoch': '1.819'} | |
| {'loss': '0.05232', 'grad_norm': '0.6002', 'learning_rate': '2.005e-06', 'epoch': '1.82'} | |
| {'loss': '0.05087', 'grad_norm': '0.2635', 'learning_rate': '2e-06', 'epoch': '1.82'} | |
| {'loss': '0.05499', 'grad_norm': '0.2701', 'learning_rate': '1.994e-06', 'epoch': '1.821'} | |
| {'loss': '0.04351', 'grad_norm': '0.2445', 'learning_rate': '1.989e-06', 'epoch': '1.821'} | |
| {'loss': '0.05457', 'grad_norm': '0.2939', 'learning_rate': '1.984e-06', 'epoch': '1.821'} | |
| {'loss': '0.05651', 'grad_norm': '0.05733', 'learning_rate': '1.978e-06', 'epoch': '1.822'} | |
| {'loss': '0.0417', 'grad_norm': '0.6475', 'learning_rate': '1.973e-06', 'epoch': '1.822'} | |
| {'loss': '0.04142', 'grad_norm': '3.66', 'learning_rate': '1.968e-06', 'epoch': '1.823'} | |
| {'loss': '0.04868', 'grad_norm': '4.573', 'learning_rate': '1.963e-06', 'epoch': '1.823'} | |
| {'loss': '0.05599', 'grad_norm': '2.08', 'learning_rate': '1.957e-06', 'epoch': '1.824'} | |
| {'loss': '0.04626', 'grad_norm': '2.817', 'learning_rate': '1.952e-06', 'epoch': '1.824'} | |
| {'loss': '0.04596', 'grad_norm': '1.093', 'learning_rate': '1.947e-06', 'epoch': '1.825'} | |
| {'loss': '0.05071', 'grad_norm': '1.727', 'learning_rate': '1.941e-06', 'epoch': '1.825'} | |
| {'loss': '0.04758', 'grad_norm': '0.245', 'learning_rate': '1.936e-06', 'epoch': '1.826'} | |
| {'loss': '0.1637', 'grad_norm': '0.2851', 'learning_rate': '1.931e-06', 'epoch': '1.826'} | |
| {'loss': '0.05044', 'grad_norm': '0.8624', 'learning_rate': '1.925e-06', 'epoch': '1.827'} | |
| {'loss': '0.04327', 'grad_norm': '0.2354', 'learning_rate': '1.92e-06', 'epoch': '1.827'} | |
| {'loss': '0.05395', 'grad_norm': '3.705', 'learning_rate': '1.915e-06', 'epoch': '1.828'} | |
| {'loss': '0.1388', 'grad_norm': '1.36', 'learning_rate': '1.91e-06', 'epoch': '1.828'} | |
| {'loss': '0.05433', 'grad_norm': '0.9225', 'learning_rate': '1.904e-06', 'epoch': '1.829'} | |
| {'loss': '0.0501', 'grad_norm': '0.7722', 'learning_rate': '1.899e-06', 'epoch': '1.829'} | |
| {'loss': '0.1306', 'grad_norm': '0.3667', 'learning_rate': '1.894e-06', 'epoch': '1.83'} | |
| {'eval_ms_marco_loss': '0.0147', 'eval_val-ms-marco-768_cosine_accuracy': '0.9997', 'eval_val-ms-marco-512_cosine_accuracy': '0.9997', 'eval_val-ms-marco-256_cosine_accuracy': '0.9997', 'eval_val-ms-marco-128_cosine_accuracy': '0.9997', 'eval_val-ms-marco-64_cosine_accuracy': '0.9993', 'eval_sequential_score': '0.9997', 'eval_ms_marco_runtime': '33.89', 'eval_ms_marco_samples_per_second': '295.1', 'eval_ms_marco_steps_per_second': '9.236', 'epoch': '1.83'} | |
| {'loss': '0.1331', 'grad_norm': '2.304', 'learning_rate': '1.888e-06', 'epoch': '1.83'} | |
| {'loss': '0.0561', 'grad_norm': '0.8422', 'learning_rate': '1.883e-06', 'epoch': '1.831'} | |
| {'loss': '0.04745', 'grad_norm': '0.3697', 'learning_rate': '1.878e-06', 'epoch': '1.831'} | |
| {'loss': '0.05279', 'grad_norm': '0.8463', 'learning_rate': '1.873e-06', 'epoch': '1.831'} | |
| {'loss': '0.04956', 'grad_norm': '0.2758', 'learning_rate': '1.867e-06', 'epoch': '1.832'} | |
| {'loss': '0.04675', 'grad_norm': '0.32', 'learning_rate': '1.862e-06', 'epoch': '1.832'} | |
| {'loss': '0.0447', 'grad_norm': '2.461', 'learning_rate': '1.857e-06', 'epoch': '1.833'} | |
| {'loss': '0.0396', 'grad_norm': '0.3079', 'learning_rate': '1.851e-06', 'epoch': '1.833'} | |
| {'loss': '0.03974', 'grad_norm': '0.1023', 'learning_rate': '1.846e-06', 'epoch': '1.834'} | |
| {'loss': '0.1396', 'grad_norm': '0.951', 'learning_rate': '1.841e-06', 'epoch': '1.834'} | |
| {'loss': '0.04496', 'grad_norm': '0.1794', 'learning_rate': '1.835e-06', 'epoch': '1.835'} | |
| {'loss': '0.0522', 'grad_norm': '0.2591', 'learning_rate': '1.83e-06', 'epoch': '1.835'} | |
| {'loss': '0.04038', 'grad_norm': '0.1968', 'learning_rate': '1.825e-06', 'epoch': '1.836'} | |
| {'loss': '0.04229', 'grad_norm': '3.988', 'learning_rate': '1.82e-06', 'epoch': '1.836'} | |
| {'loss': '0.1325', 'grad_norm': '0.4513', 'learning_rate': '1.814e-06', 'epoch': '1.837'} | |
| {'loss': '0.176', 'grad_norm': '3.445', 'learning_rate': '1.809e-06', 'epoch': '1.837'} | |
| {'loss': '0.04495', 'grad_norm': '0.5678', 'learning_rate': '1.804e-06', 'epoch': '1.838'} | |
| {'loss': '0.1574', 'grad_norm': '1.492', 'learning_rate': '1.798e-06', 'epoch': '1.838'} | |
| {'loss': '0.04215', 'grad_norm': '0.06437', 'learning_rate': '1.793e-06', 'epoch': '1.839'} | |
| {'loss': '0.1587', 'grad_norm': '1.233', 'learning_rate': '1.788e-06', 'epoch': '1.839'} | |
| {'loss': '0.04476', 'grad_norm': '0.222', 'learning_rate': '1.783e-06', 'epoch': '1.84'} | |
| {'loss': '0.03938', 'grad_norm': '0.1428', 'learning_rate': '1.777e-06', 'epoch': '1.84'} | |
| {'loss': '0.0488', 'grad_norm': '1.125', 'learning_rate': '1.772e-06', 'epoch': '1.841'} | |
| {'loss': '0.05513', 'grad_norm': '0.1082', 'learning_rate': '1.767e-06', 'epoch': '1.841'} | |
| {'loss': '0.1552', 'grad_norm': '0.1858', 'learning_rate': '1.761e-06', 'epoch': '1.841'} | |
| {'loss': '0.05034', 'grad_norm': '0.486', 'learning_rate': '1.756e-06', 'epoch': '1.842'} | |
| {'loss': '0.0472', 'grad_norm': '1.128', 'learning_rate': '1.751e-06', 'epoch': '1.842'} | |
| {'loss': '0.04767', 'grad_norm': '0.1633', 'learning_rate': '1.745e-06', 'epoch': '1.843'} | |
| {'loss': '0.04864', 'grad_norm': '3.306', 'learning_rate': '1.74e-06', 'epoch': '1.843'} | |
| {'loss': '0.0373', 'grad_norm': '1.567', 'learning_rate': '1.735e-06', 'epoch': '1.844'} | |
| {'loss': '0.04468', 'grad_norm': '0.0347', 'learning_rate': '1.73e-06', 'epoch': '1.844'} | |
| {'loss': '0.04617', 'grad_norm': '2.897', 'learning_rate': '1.724e-06', 'epoch': '1.845'} | |
| {'loss': '0.063', 'grad_norm': '0.9048', 'learning_rate': '1.719e-06', 'epoch': '1.845'} | |
| {'loss': '0.04453', 'grad_norm': '1.741', 'learning_rate': '1.714e-06', 'epoch': '1.846'} | |
| {'loss': '0.05663', 'grad_norm': '0.04382', 'learning_rate': '1.708e-06', 'epoch': '1.846'} | |
| {'loss': '0.05643', 'grad_norm': '2.261', 'learning_rate': '1.703e-06', 'epoch': '1.847'} | |
| {'loss': '0.05062', 'grad_norm': '2.085', 'learning_rate': '1.698e-06', 'epoch': '1.847'} | |
| {'loss': '0.1493', 'grad_norm': '1.991', 'learning_rate': '1.693e-06', 'epoch': '1.848'} | |
| {'loss': '0.04841', 'grad_norm': '0.321', 'learning_rate': '1.687e-06', 'epoch': '1.848'} | |
| {'loss': '0.04655', 'grad_norm': '1.034', 'learning_rate': '1.682e-06', 'epoch': '1.849'} | |
| {'loss': '0.05534', 'grad_norm': '2.092', 'learning_rate': '1.677e-06', 'epoch': '1.849'} | |
| {'loss': '0.056', 'grad_norm': '0.1173', 'learning_rate': '1.671e-06', 'epoch': '1.85'} | |
| {'loss': '0.05349', 'grad_norm': '0.1678', 'learning_rate': '1.666e-06', 'epoch': '1.85'} | |
| {'loss': '0.04465', 'grad_norm': '0.1886', 'learning_rate': '1.661e-06', 'epoch': '1.851'} | |
| {'loss': '0.04501', 'grad_norm': '5.219', 'learning_rate': '1.655e-06', 'epoch': '1.851'} | |
| {'loss': '0.04881', 'grad_norm': '3.869', 'learning_rate': '1.65e-06', 'epoch': '1.851'} | |
| {'loss': '0.04407', 'grad_norm': '1.86', 'learning_rate': '1.645e-06', 'epoch': '1.852'} | |
| {'loss': '0.1293', 'grad_norm': '5.059', 'learning_rate': '1.64e-06', 'epoch': '1.852'} | |
| {'loss': '0.03716', 'grad_norm': '0.1851', 'learning_rate': '1.634e-06', 'epoch': '1.853'} | |
| {'loss': '0.05003', 'grad_norm': '0.1263', 'learning_rate': '1.629e-06', 'epoch': '1.853'} | |
| {'loss': '0.04848', 'grad_norm': '0.1387', 'learning_rate': '1.624e-06', 'epoch': '1.854'} | |
| {'loss': '0.1374', 'grad_norm': '2.122', 'learning_rate': '1.618e-06', 'epoch': '1.854'} | |
| {'loss': '0.03928', 'grad_norm': '0.2171', 'learning_rate': '1.613e-06', 'epoch': '1.855'} | |
| {'loss': '0.05103', 'grad_norm': '0.5294', 'learning_rate': '1.608e-06', 'epoch': '1.855'} | |
| {'loss': '0.05414', 'grad_norm': '0.04698', 'learning_rate': '1.603e-06', 'epoch': '1.856'} | |
| {'loss': '0.05562', 'grad_norm': '0.2696', 'learning_rate': '1.597e-06', 'epoch': '1.856'} | |
| {'loss': '0.052', 'grad_norm': '0.3445', 'learning_rate': '1.592e-06', 'epoch': '1.857'} | |
| {'loss': '0.04209', 'grad_norm': '0.4102', 'learning_rate': '1.587e-06', 'epoch': '1.857'} | |
| {'loss': '0.04079', 'grad_norm': '0.717', 'learning_rate': '1.581e-06', 'epoch': '1.858'} | |
| {'loss': '0.05336', 'grad_norm': '0.7867', 'learning_rate': '1.576e-06', 'epoch': '1.858'} | |
| {'eval_ms_marco_loss': '0.01511', 'eval_val-ms-marco-768_cosine_accuracy': '0.9997', 'eval_val-ms-marco-512_cosine_accuracy': '0.9997', 'eval_val-ms-marco-256_cosine_accuracy': '0.9997', 'eval_val-ms-marco-128_cosine_accuracy': '0.9997', 'eval_val-ms-marco-64_cosine_accuracy': '0.9993', 'eval_sequential_score': '0.9997', 'eval_ms_marco_runtime': '34.1', 'eval_ms_marco_samples_per_second': '293.3', 'eval_ms_marco_steps_per_second': '9.179', 'epoch': '1.858'} | |
| {'loss': '0.05123', 'grad_norm': '0.8126', 'learning_rate': '1.571e-06', 'epoch': '1.859'} | |
| {'loss': '0.05472', 'grad_norm': '0.1258', 'learning_rate': '1.565e-06', 'epoch': '1.859'} | |
| {'loss': '0.04116', 'grad_norm': '0.1895', 'learning_rate': '1.56e-06', 'epoch': '1.86'} | |
| {'loss': '0.04169', 'grad_norm': '0.1509', 'learning_rate': '1.555e-06', 'epoch': '1.86'} | |
| {'loss': '0.05528', 'grad_norm': '4.852', 'learning_rate': '1.55e-06', 'epoch': '1.861'} | |
| {'loss': '0.04903', 'grad_norm': '5.772', 'learning_rate': '1.544e-06', 'epoch': '1.861'} | |
| {'loss': '0.0439', 'grad_norm': '2.756', 'learning_rate': '1.539e-06', 'epoch': '1.861'} | |
| {'loss': '0.05399', 'grad_norm': '0.2322', 'learning_rate': '1.534e-06', 'epoch': '1.862'} | |
| {'loss': '0.03693', 'grad_norm': '1.055', 'learning_rate': '1.528e-06', 'epoch': '1.862'} | |
| {'loss': '0.03783', 'grad_norm': '0.6974', 'learning_rate': '1.523e-06', 'epoch': '1.863'} | |
| {'loss': '0.05618', 'grad_norm': '3.544', 'learning_rate': '1.518e-06', 'epoch': '1.863'} | |
| {'loss': '0.05833', 'grad_norm': '4.296', 'learning_rate': '1.513e-06', 'epoch': '1.864'} | |
| {'loss': '0.04941', 'grad_norm': '0.09987', 'learning_rate': '1.507e-06', 'epoch': '1.864'} | |
| {'loss': '0.1723', 'grad_norm': '2.925', 'learning_rate': '1.502e-06', 'epoch': '1.865'} | |
| {'loss': '0.04836', 'grad_norm': '0.7777', 'learning_rate': '1.497e-06', 'epoch': '1.865'} | |
| {'loss': '0.04466', 'grad_norm': '4.531', 'learning_rate': '1.491e-06', 'epoch': '1.866'} | |
| {'loss': '0.05744', 'grad_norm': '1.62', 'learning_rate': '1.486e-06', 'epoch': '1.866'} | |
| {'loss': '0.1522', 'grad_norm': '1.294', 'learning_rate': '1.481e-06', 'epoch': '1.867'} | |
| {'loss': '0.1512', 'grad_norm': '1.052', 'learning_rate': '1.475e-06', 'epoch': '1.867'} | |
| {'loss': '0.04073', 'grad_norm': '1.634', 'learning_rate': '1.47e-06', 'epoch': '1.868'} | |
| {'loss': '0.04478', 'grad_norm': '0.242', 'learning_rate': '1.465e-06', 'epoch': '1.868'} | |
| {'loss': '0.03992', 'grad_norm': '0.7399', 'learning_rate': '1.46e-06', 'epoch': '1.869'} | |
| {'loss': '0.0509', 'grad_norm': '2.447', 'learning_rate': '1.454e-06', 'epoch': '1.869'} | |
| {'loss': '0.04005', 'grad_norm': '2.302', 'learning_rate': '1.449e-06', 'epoch': '1.87'} | |
| {'loss': '0.04728', 'grad_norm': '0.12', 'learning_rate': '1.444e-06', 'epoch': '1.87'} | |
| {'loss': '0.0425', 'grad_norm': '0.1418', 'learning_rate': '1.438e-06', 'epoch': '1.871'} | |
| {'loss': '0.04095', 'grad_norm': '5.605', 'learning_rate': '1.433e-06', 'epoch': '1.871'} | |
| {'loss': '0.051', 'grad_norm': '2.052', 'learning_rate': '1.428e-06', 'epoch': '1.871'} | |
| {'loss': '0.04615', 'grad_norm': '5.947', 'learning_rate': '1.423e-06', 'epoch': '1.872'} | |
| {'loss': '0.04632', 'grad_norm': '0.9691', 'learning_rate': '1.417e-06', 'epoch': '1.872'} | |
| {'loss': '0.2158', 'grad_norm': '1.468', 'learning_rate': '1.412e-06', 'epoch': '1.873'} | |
| {'loss': '0.04552', 'grad_norm': '1.415', 'learning_rate': '1.407e-06', 'epoch': '1.873'} | |
| {'loss': '0.04385', 'grad_norm': '4.498', 'learning_rate': '1.401e-06', 'epoch': '1.874'} | |
| {'loss': '0.1583', 'grad_norm': '1.345', 'learning_rate': '1.396e-06', 'epoch': '1.874'} | |
| {'loss': '0.04899', 'grad_norm': '0.9058', 'learning_rate': '1.391e-06', 'epoch': '1.875'} | |
| {'loss': '0.04274', 'grad_norm': '0.5131', 'learning_rate': '1.385e-06', 'epoch': '1.875'} | |
| {'loss': '0.04822', 'grad_norm': '0.6315', 'learning_rate': '1.38e-06', 'epoch': '1.876'} | |
| {'loss': '0.1591', 'grad_norm': '0.5827', 'learning_rate': '1.375e-06', 'epoch': '1.876'} | |
| {'loss': '0.046', 'grad_norm': '0.1475', 'learning_rate': '1.37e-06', 'epoch': '1.877'} | |
| {'loss': '0.0382', 'grad_norm': '4.953', 'learning_rate': '1.364e-06', 'epoch': '1.877'} | |
| {'loss': '0.1447', 'grad_norm': '1.896', 'learning_rate': '1.359e-06', 'epoch': '1.878'} | |
| {'loss': '0.05646', 'grad_norm': '0.5152', 'learning_rate': '1.354e-06', 'epoch': '1.878'} | |
| {'loss': '0.03775', 'grad_norm': '1.481', 'learning_rate': '1.348e-06', 'epoch': '1.879'} | |
| {'loss': '0.0525', 'grad_norm': '1.293', 'learning_rate': '1.343e-06', 'epoch': '1.879'} | |
| {'loss': '0.03921', 'grad_norm': '0.6941', 'learning_rate': '1.338e-06', 'epoch': '1.88'} | |
| {'loss': '0.0407', 'grad_norm': '0.2335', 'learning_rate': '1.333e-06', 'epoch': '1.88'} | |
| {'loss': '0.03947', 'grad_norm': '0.0845', 'learning_rate': '1.327e-06', 'epoch': '1.881'} | |
| {'loss': '0.04456', 'grad_norm': '0.2788', 'learning_rate': '1.322e-06', 'epoch': '1.881'} | |
| {'loss': '0.04264', 'grad_norm': '0.1711', 'learning_rate': '1.317e-06', 'epoch': '1.882'} | |
| {'loss': '0.04269', 'grad_norm': '0.06945', 'learning_rate': '1.311e-06', 'epoch': '1.882'} | |
| {'loss': '0.04773', 'grad_norm': '0.1657', 'learning_rate': '1.306e-06', 'epoch': '1.882'} | |
| {'loss': '0.05218', 'grad_norm': '0.2929', 'learning_rate': '1.301e-06', 'epoch': '1.883'} | |
| {'loss': '0.05447', 'grad_norm': '0.5411', 'learning_rate': '1.295e-06', 'epoch': '1.883'} | |
| {'loss': '0.04332', 'grad_norm': '6.045', 'learning_rate': '1.29e-06', 'epoch': '1.884'} | |
| {'loss': '0.05057', 'grad_norm': '4.2', 'learning_rate': '1.285e-06', 'epoch': '1.884'} | |
| {'loss': '0.04455', 'grad_norm': '0.07677', 'learning_rate': '1.28e-06', 'epoch': '1.885'} | |
| {'loss': '0.1488', 'grad_norm': '0.4499', 'learning_rate': '1.274e-06', 'epoch': '1.885'} | |
| {'loss': '0.0481', 'grad_norm': '0.8655', 'learning_rate': '1.269e-06', 'epoch': '1.886'} | |
| {'loss': '0.04576', 'grad_norm': '0.09383', 'learning_rate': '1.264e-06', 'epoch': '1.886'} | |
| {'loss': '0.04997', 'grad_norm': '1.118', 'learning_rate': '1.258e-06', 'epoch': '1.887'} | |
| {'eval_ms_marco_loss': '0.01491', 'eval_val-ms-marco-768_cosine_accuracy': '0.9997', 'eval_val-ms-marco-512_cosine_accuracy': '0.9997', 'eval_val-ms-marco-256_cosine_accuracy': '0.9997', 'eval_val-ms-marco-128_cosine_accuracy': '0.9997', 'eval_val-ms-marco-64_cosine_accuracy': '0.9997', 'eval_sequential_score': '0.9997', 'eval_ms_marco_runtime': '33.76', 'eval_ms_marco_samples_per_second': '296.2', 'eval_ms_marco_steps_per_second': '9.272', 'epoch': '1.887'} | |
| {'loss': '0.04123', 'grad_norm': '0.2867', 'learning_rate': '1.253e-06', 'epoch': '1.887'} | |
| {'loss': '0.05941', 'grad_norm': '1.386', 'learning_rate': '1.248e-06', 'epoch': '1.888'} | |
| {'loss': '0.05126', 'grad_norm': '0.2597', 'learning_rate': '1.243e-06', 'epoch': '1.888'} | |
| {'loss': '0.04542', 'grad_norm': '0.3502', 'learning_rate': '1.237e-06', 'epoch': '1.889'} | |
| {'loss': '0.06088', 'grad_norm': '0.2015', 'learning_rate': '1.232e-06', 'epoch': '1.889'} | |
| {'loss': '0.04179', 'grad_norm': '0.6408', 'learning_rate': '1.227e-06', 'epoch': '1.89'} | |
| {'loss': '0.04006', 'grad_norm': '5.445', 'learning_rate': '1.221e-06', 'epoch': '1.89'} | |
| {'loss': '0.04391', 'grad_norm': '3.637', 'learning_rate': '1.216e-06', 'epoch': '1.891'} | |
| {'loss': '0.05213', 'grad_norm': '5.152', 'learning_rate': '1.211e-06', 'epoch': '1.891'} | |
| {'loss': '0.04042', 'grad_norm': '0.9804', 'learning_rate': '1.205e-06', 'epoch': '1.892'} | |
| {'loss': '0.05717', 'grad_norm': '2.268', 'learning_rate': '1.2e-06', 'epoch': '1.892'} | |
| {'loss': '0.04472', 'grad_norm': '4.299', 'learning_rate': '1.195e-06', 'epoch': '1.892'} | |
| {'loss': '0.04287', 'grad_norm': '0.1556', 'learning_rate': '1.19e-06', 'epoch': '1.893'} | |
| {'loss': '0.05089', 'grad_norm': '0.1182', 'learning_rate': '1.184e-06', 'epoch': '1.893'} | |
| {'loss': '0.05058', 'grad_norm': '0.18', 'learning_rate': '1.179e-06', 'epoch': '1.894'} | |
| {'loss': '0.05302', 'grad_norm': '6.493', 'learning_rate': '1.174e-06', 'epoch': '1.894'} | |
| {'loss': '0.04657', 'grad_norm': '0.6322', 'learning_rate': '1.168e-06', 'epoch': '1.895'} | |
| {'loss': '0.04799', 'grad_norm': '0.1656', 'learning_rate': '1.163e-06', 'epoch': '1.895'} | |
| {'loss': '0.05334', 'grad_norm': '0.2659', 'learning_rate': '1.158e-06', 'epoch': '1.896'} | |
| {'loss': '0.0458', 'grad_norm': '5.91', 'learning_rate': '1.153e-06', 'epoch': '1.896'} | |
| {'loss': '0.04041', 'grad_norm': '2.307', 'learning_rate': '1.147e-06', 'epoch': '1.897'} | |
| {'loss': '0.1459', 'grad_norm': '0.7924', 'learning_rate': '1.142e-06', 'epoch': '1.897'} | |
| {'loss': '0.04939', 'grad_norm': '1.881', 'learning_rate': '1.137e-06', 'epoch': '1.898'} | |
| {'loss': '0.05031', 'grad_norm': '0.1399', 'learning_rate': '1.131e-06', 'epoch': '1.898'} | |
| {'loss': '0.0434', 'grad_norm': '1.479', 'learning_rate': '1.126e-06', 'epoch': '1.899'} | |
| {'loss': '0.04438', 'grad_norm': '0.6392', 'learning_rate': '1.121e-06', 'epoch': '1.899'} | |
| {'loss': '0.04328', 'grad_norm': '0.04356', 'learning_rate': '1.116e-06', 'epoch': '1.9'} | |
| {'loss': '0.04989', 'grad_norm': '0.2074', 'learning_rate': '1.11e-06', 'epoch': '1.9'} | |
| {'loss': '0.04316', 'grad_norm': '0.878', 'learning_rate': '1.105e-06', 'epoch': '1.901'} | |
| {'loss': '0.04548', 'grad_norm': '1.496', 'learning_rate': '1.1e-06', 'epoch': '1.901'} | |
| {'loss': '0.04775', 'grad_norm': '0.3414', 'learning_rate': '1.094e-06', 'epoch': '1.902'} | |
| {'loss': '0.04067', 'grad_norm': '0.3658', 'learning_rate': '1.089e-06', 'epoch': '1.902'} | |
| {'loss': '0.04151', 'grad_norm': '0.1074', 'learning_rate': '1.084e-06', 'epoch': '1.902'} | |
| {'loss': '0.04345', 'grad_norm': '0.5899', 'learning_rate': '1.078e-06', 'epoch': '1.903'} | |
| {'loss': '0.04197', 'grad_norm': '0.3859', 'learning_rate': '1.073e-06', 'epoch': '1.903'} | |
| {'loss': '0.04557', 'grad_norm': '1.111', 'learning_rate': '1.068e-06', 'epoch': '1.904'} | |
| {'loss': '0.04518', 'grad_norm': '2.226', 'learning_rate': '1.063e-06', 'epoch': '1.904'} | |
| {'loss': '0.1477', 'grad_norm': '4.991', 'learning_rate': '1.057e-06', 'epoch': '1.905'} | |
| {'loss': '0.04976', 'grad_norm': '0.08021', 'learning_rate': '1.052e-06', 'epoch': '1.905'} | |
| {'loss': '0.1332', 'grad_norm': '1.451', 'learning_rate': '1.047e-06', 'epoch': '1.906'} | |
| {'loss': '0.03886', 'grad_norm': '0.2451', 'learning_rate': '1.041e-06', 'epoch': '1.906'} | |
| {'loss': '0.04467', 'grad_norm': '0.3856', 'learning_rate': '1.036e-06', 'epoch': '1.907'} | |
| {'loss': '0.04817', 'grad_norm': '0.5322', 'learning_rate': '1.031e-06', 'epoch': '1.907'} | |
| {'loss': '0.03869', 'grad_norm': '0.5235', 'learning_rate': '1.026e-06', 'epoch': '1.908'} | |
| {'loss': '0.0534', 'grad_norm': '1.7', 'learning_rate': '1.02e-06', 'epoch': '1.908'} | |
| {'loss': '0.05045', 'grad_norm': '1.477', 'learning_rate': '1.015e-06', 'epoch': '1.909'} | |
| {'loss': '0.04574', 'grad_norm': '2.673', 'learning_rate': '1.01e-06', 'epoch': '1.909'} | |
| {'loss': '0.04736', 'grad_norm': '2.729', 'learning_rate': '1.004e-06', 'epoch': '1.91'} | |
| {'loss': '0.04165', 'grad_norm': '2.554', 'learning_rate': '9.99e-07', 'epoch': '1.91'} | |
| {'loss': '0.1387', 'grad_norm': '6.848', 'learning_rate': '9.937e-07', 'epoch': '1.911'} | |
| {'loss': '0.03952', 'grad_norm': '1.048', 'learning_rate': '9.885e-07', 'epoch': '1.911'} | |
| {'loss': '0.03929', 'grad_norm': '0.3886', 'learning_rate': '9.832e-07', 'epoch': '1.912'} | |
| {'loss': '0.1371', 'grad_norm': '3.663', 'learning_rate': '9.779e-07', 'epoch': '1.912'} | |
| {'loss': '0.05074', 'grad_norm': '1.101', 'learning_rate': '9.726e-07', 'epoch': '1.912'} | |
| {'loss': '0.04566', 'grad_norm': '0.056', 'learning_rate': '9.673e-07', 'epoch': '1.913'} | |
| {'loss': '0.04996', 'grad_norm': '1.63', 'learning_rate': '9.62e-07', 'epoch': '1.913'} | |
| {'loss': '0.04619', 'grad_norm': '3.148', 'learning_rate': '9.567e-07', 'epoch': '1.914'} | |
| {'loss': '0.0426', 'grad_norm': '1.062', 'learning_rate': '9.514e-07', 'epoch': '1.914'} | |
| {'loss': '0.04509', 'grad_norm': '0.3644', 'learning_rate': '9.461e-07', 'epoch': '1.915'} | |
| {'loss': '0.05789', 'grad_norm': '0.616', 'learning_rate': '9.408e-07', 'epoch': '1.915'} | |
| {'eval_ms_marco_loss': '0.01466', 'eval_val-ms-marco-768_cosine_accuracy': '0.9997', 'eval_val-ms-marco-512_cosine_accuracy': '0.9997', 'eval_val-ms-marco-256_cosine_accuracy': '0.9997', 'eval_val-ms-marco-128_cosine_accuracy': '0.9997', 'eval_val-ms-marco-64_cosine_accuracy': '0.9993', 'eval_sequential_score': '0.9997', 'eval_ms_marco_runtime': '33.94', 'eval_ms_marco_samples_per_second': '294.6', 'eval_ms_marco_steps_per_second': '9.222', 'epoch': '1.915'} | |
| {'loss': '0.04819', 'grad_norm': '0.08739', 'learning_rate': '9.355e-07', 'epoch': '1.916'} | |
| {'loss': '0.1552', 'grad_norm': '9.683', 'learning_rate': '9.302e-07', 'epoch': '1.916'} | |
| {'loss': '0.04429', 'grad_norm': '1.694', 'learning_rate': '9.249e-07', 'epoch': '1.917'} | |
| {'loss': '0.04535', 'grad_norm': '1.35', 'learning_rate': '9.196e-07', 'epoch': '1.917'} | |
| {'loss': '0.04854', 'grad_norm': '2.037', 'learning_rate': '9.143e-07', 'epoch': '1.918'} | |
| {'loss': '0.04741', 'grad_norm': '1.368', 'learning_rate': '9.09e-07', 'epoch': '1.918'} | |
| {'loss': '0.03893', 'grad_norm': '1.276', 'learning_rate': '9.037e-07', 'epoch': '1.919'} | |
| {'loss': '0.04209', 'grad_norm': '0.1457', 'learning_rate': '8.985e-07', 'epoch': '1.919'} | |
| {'loss': '0.04871', 'grad_norm': '0.121', 'learning_rate': '8.932e-07', 'epoch': '1.92'} | |
| {'loss': '0.03734', 'grad_norm': '0.2831', 'learning_rate': '8.879e-07', 'epoch': '1.92'} | |
| {'loss': '0.04772', 'grad_norm': '0.2896', 'learning_rate': '8.826e-07', 'epoch': '1.921'} | |
| {'loss': '0.05255', 'grad_norm': '3.259', 'learning_rate': '8.773e-07', 'epoch': '1.921'} | |
| {'loss': '0.04453', 'grad_norm': '4.098', 'learning_rate': '8.72e-07', 'epoch': '1.922'} | |
| {'loss': '0.04373', 'grad_norm': '3.155', 'learning_rate': '8.667e-07', 'epoch': '1.922'} | |
| {'loss': '0.05144', 'grad_norm': '0.9121', 'learning_rate': '8.614e-07', 'epoch': '1.922'} | |
| {'loss': '0.04593', 'grad_norm': '1.755', 'learning_rate': '8.561e-07', 'epoch': '1.923'} | |
| {'loss': '0.04826', 'grad_norm': '4.332', 'learning_rate': '8.508e-07', 'epoch': '1.923'} | |
| {'loss': '0.04603', 'grad_norm': '1.447', 'learning_rate': '8.455e-07', 'epoch': '1.924'} | |
| {'loss': '0.04647', 'grad_norm': '3.143', 'learning_rate': '8.402e-07', 'epoch': '1.924'} | |
| {'loss': '0.1576', 'grad_norm': '3.178', 'learning_rate': '8.349e-07', 'epoch': '1.925'} | |
| {'loss': '0.1307', 'grad_norm': '0.8748', 'learning_rate': '8.296e-07', 'epoch': '1.925'} | |
| {'loss': '0.04348', 'grad_norm': '0.3937', 'learning_rate': '8.243e-07', 'epoch': '1.926'} | |
| {'loss': '0.04692', 'grad_norm': '0.3109', 'learning_rate': '8.19e-07', 'epoch': '1.926'} | |
| {'loss': '0.04124', 'grad_norm': '0.1309', 'learning_rate': '8.138e-07', 'epoch': '1.927'} | |
| {'loss': '0.1455', 'grad_norm': '5.861', 'learning_rate': '8.085e-07', 'epoch': '1.927'} | |
| {'loss': '0.05259', 'grad_norm': '0.673', 'learning_rate': '8.032e-07', 'epoch': '1.928'} | |
| {'loss': '0.04882', 'grad_norm': '1.273', 'learning_rate': '7.979e-07', 'epoch': '1.928'} | |
| {'loss': '0.1456', 'grad_norm': '0.2147', 'learning_rate': '7.926e-07', 'epoch': '1.929'} | |
| {'loss': '0.04924', 'grad_norm': '1.879', 'learning_rate': '7.873e-07', 'epoch': '1.929'} | |
| {'loss': '0.04159', 'grad_norm': '1.029', 'learning_rate': '7.82e-07', 'epoch': '1.93'} | |
| {'loss': '0.04296', 'grad_norm': '0.06983', 'learning_rate': '7.767e-07', 'epoch': '1.93'} | |
| {'loss': '0.04447', 'grad_norm': '0.3283', 'learning_rate': '7.714e-07', 'epoch': '1.931'} | |
| {'loss': '0.04415', 'grad_norm': '1.167', 'learning_rate': '7.661e-07', 'epoch': '1.931'} | |
| {'loss': '0.04621', 'grad_norm': '1.534', 'learning_rate': '7.608e-07', 'epoch': '1.932'} | |
| {'loss': '0.05352', 'grad_norm': '1.713', 'learning_rate': '7.555e-07', 'epoch': '1.932'} | |
| {'loss': '0.04213', 'grad_norm': '3.376', 'learning_rate': '7.502e-07', 'epoch': '1.932'} | |
| {'loss': '0.03761', 'grad_norm': '4.34', 'learning_rate': '7.449e-07', 'epoch': '1.933'} | |
| {'loss': '0.05012', 'grad_norm': '0.3598', 'learning_rate': '7.396e-07', 'epoch': '1.933'} | |
| {'loss': '0.04673', 'grad_norm': '4.235', 'learning_rate': '7.343e-07', 'epoch': '1.934'} | |
| {'loss': '0.03904', 'grad_norm': '0.2119', 'learning_rate': '7.29e-07', 'epoch': '1.934'} | |
| {'loss': '0.03552', 'grad_norm': '1.541', 'learning_rate': '7.238e-07', 'epoch': '1.935'} | |
| {'loss': '0.1656', 'grad_norm': '0.5263', 'learning_rate': '7.185e-07', 'epoch': '1.935'} | |
| {'loss': '0.1481', 'grad_norm': '0.8864', 'learning_rate': '7.132e-07', 'epoch': '1.936'} | |
| {'loss': '0.1357', 'grad_norm': '0.5588', 'learning_rate': '7.079e-07', 'epoch': '1.936'} | |
| {'loss': '0.04667', 'grad_norm': '0.4341', 'learning_rate': '7.026e-07', 'epoch': '1.937'} | |
| {'loss': '0.04211', 'grad_norm': '4.593', 'learning_rate': '6.973e-07', 'epoch': '1.937'} | |
| {'loss': '0.04653', 'grad_norm': '0.4385', 'learning_rate': '6.92e-07', 'epoch': '1.938'} | |
| {'loss': '0.03578', 'grad_norm': '1.466', 'learning_rate': '6.867e-07', 'epoch': '1.938'} | |
| {'loss': '0.0489', 'grad_norm': '1.355', 'learning_rate': '6.814e-07', 'epoch': '1.939'} | |
| {'loss': '0.04468', 'grad_norm': '0.1496', 'learning_rate': '6.761e-07', 'epoch': '1.939'} | |
| {'loss': '0.1588', 'grad_norm': '1.671', 'learning_rate': '6.708e-07', 'epoch': '1.94'} | |
| {'loss': '0.03974', 'grad_norm': '2.524', 'learning_rate': '6.655e-07', 'epoch': '1.94'} | |
| {'loss': '0.04436', 'grad_norm': '3.828', 'learning_rate': '6.602e-07', 'epoch': '1.941'} | |
| {'loss': '0.04371', 'grad_norm': '0.2301', 'learning_rate': '6.549e-07', 'epoch': '1.941'} | |
| {'loss': '0.04337', 'grad_norm': '0.152', 'learning_rate': '6.496e-07', 'epoch': '1.942'} | |
| {'loss': '0.04947', 'grad_norm': '1.741', 'learning_rate': '6.443e-07', 'epoch': '1.942'} | |
| {'loss': '0.05105', 'grad_norm': '1.006', 'learning_rate': '6.391e-07', 'epoch': '1.942'} | |
| {'loss': '0.0458', 'grad_norm': '0.589', 'learning_rate': '6.338e-07', 'epoch': '1.943'} | |
| {'loss': '0.03765', 'grad_norm': '1.869', 'learning_rate': '6.285e-07', 'epoch': '1.943'} | |
| {'loss': '0.03646', 'grad_norm': '0.9365', 'learning_rate': '6.232e-07', 'epoch': '1.944'} | |
| {'eval_ms_marco_loss': '0.01461', 'eval_val-ms-marco-768_cosine_accuracy': '0.9997', 'eval_val-ms-marco-512_cosine_accuracy': '0.9997', 'eval_val-ms-marco-256_cosine_accuracy': '0.9997', 'eval_val-ms-marco-128_cosine_accuracy': '0.9997', 'eval_val-ms-marco-64_cosine_accuracy': '0.9993', 'eval_sequential_score': '0.9997', 'eval_ms_marco_runtime': '33.84', 'eval_ms_marco_samples_per_second': '295.5', 'eval_ms_marco_steps_per_second': '9.25', 'epoch': '1.944'} | |
| {'loss': '0.1272', 'grad_norm': '0.2255', 'learning_rate': '6.179e-07', 'epoch': '1.944'} | |
| {'loss': '0.03847', 'grad_norm': '0.1473', 'learning_rate': '6.126e-07', 'epoch': '1.945'} | |
| {'loss': '0.04791', 'grad_norm': '0.2967', 'learning_rate': '6.073e-07', 'epoch': '1.945'} | |
| {'loss': '0.04369', 'grad_norm': '0.5087', 'learning_rate': '6.02e-07', 'epoch': '1.946'} | |
| {'loss': '0.03796', 'grad_norm': '0.7981', 'learning_rate': '5.967e-07', 'epoch': '1.946'} | |
| {'loss': '0.04573', 'grad_norm': '0.4673', 'learning_rate': '5.914e-07', 'epoch': '1.947'} | |
| {'loss': '0.05166', 'grad_norm': '0.5551', 'learning_rate': '5.861e-07', 'epoch': '1.947'} | |
| {'loss': '0.04408', 'grad_norm': '4.66', 'learning_rate': '5.808e-07', 'epoch': '1.948'} | |
| {'loss': '0.04087', 'grad_norm': '0.2018', 'learning_rate': '5.755e-07', 'epoch': '1.948'} | |
| {'loss': '0.03988', 'grad_norm': '0.8576', 'learning_rate': '5.702e-07', 'epoch': '1.949'} | |
| {'loss': '0.04613', 'grad_norm': '0.1273', 'learning_rate': '5.649e-07', 'epoch': '1.949'} | |
| {'loss': '0.0456', 'grad_norm': '0.9679', 'learning_rate': '5.596e-07', 'epoch': '1.95'} | |
| {'loss': '0.04548', 'grad_norm': '0.1523', 'learning_rate': '5.544e-07', 'epoch': '1.95'} | |
| {'loss': '0.05117', 'grad_norm': '0.08392', 'learning_rate': '5.491e-07', 'epoch': '1.951'} | |
| {'loss': '0.04689', 'grad_norm': '1.518', 'learning_rate': '5.438e-07', 'epoch': '1.951'} | |
| {'loss': '0.03283', 'grad_norm': '1.298', 'learning_rate': '5.385e-07', 'epoch': '1.952'} | |
| {'loss': '0.04617', 'grad_norm': '0.2392', 'learning_rate': '5.332e-07', 'epoch': '1.952'} | |
| {'loss': '0.0368', 'grad_norm': '2.649', 'learning_rate': '5.279e-07', 'epoch': '1.952'} | |
| {'loss': '0.05027', 'grad_norm': '0.1325', 'learning_rate': '5.226e-07', 'epoch': '1.953'} | |
| {'loss': '0.04955', 'grad_norm': '0.5483', 'learning_rate': '5.173e-07', 'epoch': '1.953'} | |
| {'loss': '0.0455', 'grad_norm': '0.1019', 'learning_rate': '5.12e-07', 'epoch': '1.954'} | |
| {'loss': '0.05324', 'grad_norm': '0.8549', 'learning_rate': '5.067e-07', 'epoch': '1.954'} | |
| {'loss': '0.03357', 'grad_norm': '2.234', 'learning_rate': '5.014e-07', 'epoch': '1.955'} | |
| {'loss': '0.04779', 'grad_norm': '0.1489', 'learning_rate': '4.961e-07', 'epoch': '1.955'} | |
| {'loss': '0.1523', 'grad_norm': '0.2711', 'learning_rate': '4.908e-07', 'epoch': '1.956'} | |
| {'loss': '0.05426', 'grad_norm': '0.08483', 'learning_rate': '4.855e-07', 'epoch': '1.956'} | |
| {'loss': '0.05103', 'grad_norm': '1.432', 'learning_rate': '4.802e-07', 'epoch': '1.957'} | |
| {'loss': '0.04321', 'grad_norm': '0.2559', 'learning_rate': '4.749e-07', 'epoch': '1.957'} | |
| {'loss': '0.0396', 'grad_norm': '0.05477', 'learning_rate': '4.696e-07', 'epoch': '1.958'} | |
| {'loss': '0.04247', 'grad_norm': '11.42', 'learning_rate': '4.644e-07', 'epoch': '1.958'} | |
| {'loss': '0.1377', 'grad_norm': '0.1795', 'learning_rate': '4.591e-07', 'epoch': '1.959'} | |
| {'loss': '0.04965', 'grad_norm': '0.5854', 'learning_rate': '4.538e-07', 'epoch': '1.959'} | |
| {'loss': '0.03988', 'grad_norm': '2.573', 'learning_rate': '4.485e-07', 'epoch': '1.96'} | |
| {'loss': '0.03612', 'grad_norm': '3.367', 'learning_rate': '4.432e-07', 'epoch': '1.96'} | |
| {'loss': '0.04436', 'grad_norm': '7.296', 'learning_rate': '4.379e-07', 'epoch': '1.961'} | |
| {'loss': '0.03127', 'grad_norm': '6.919', 'learning_rate': '4.326e-07', 'epoch': '1.961'} | |
| {'loss': '0.04451', 'grad_norm': '0.5584', 'learning_rate': '4.273e-07', 'epoch': '1.962'} | |
| {'loss': '0.03996', 'grad_norm': '1.063', 'learning_rate': '4.22e-07', 'epoch': '1.962'} | |
| {'loss': '0.1255', 'grad_norm': '0.9586', 'learning_rate': '4.167e-07', 'epoch': '1.962'} | |
| {'loss': '0.03835', 'grad_norm': '0.8179', 'learning_rate': '4.114e-07', 'epoch': '1.963'} | |
| {'loss': '0.03908', 'grad_norm': '3.018', 'learning_rate': '4.061e-07', 'epoch': '1.963'} | |
| {'loss': '0.056', 'grad_norm': '2.889', 'learning_rate': '4.008e-07', 'epoch': '1.964'} | |
| {'loss': '0.1324', 'grad_norm': '0.07593', 'learning_rate': '3.955e-07', 'epoch': '1.964'} | |
| {'loss': '0.04549', 'grad_norm': '0.9513', 'learning_rate': '3.902e-07', 'epoch': '1.965'} | |
| {'loss': '0.05011', 'grad_norm': '0.8216', 'learning_rate': '3.849e-07', 'epoch': '1.965'} | |
| {'loss': '0.04936', 'grad_norm': '0.3447', 'learning_rate': '3.797e-07', 'epoch': '1.966'} | |
| {'loss': '0.04712', 'grad_norm': '4.362', 'learning_rate': '3.744e-07', 'epoch': '1.966'} | |
| {'loss': '0.04165', 'grad_norm': '0.05664', 'learning_rate': '3.691e-07', 'epoch': '1.967'} | |
| {'loss': '0.04011', 'grad_norm': '1.013', 'learning_rate': '3.638e-07', 'epoch': '1.967'} | |
| {'loss': '0.04469', 'grad_norm': '1.744', 'learning_rate': '3.585e-07', 'epoch': '1.968'} | |
| {'loss': '0.04503', 'grad_norm': '5.004', 'learning_rate': '3.532e-07', 'epoch': '1.968'} | |
| {'loss': '0.04504', 'grad_norm': '1.428', 'learning_rate': '3.479e-07', 'epoch': '1.969'} | |
| {'loss': '0.03507', 'grad_norm': '0.3071', 'learning_rate': '3.426e-07', 'epoch': '1.969'} | |
| {'loss': '0.04075', 'grad_norm': '0.7387', 'learning_rate': '3.373e-07', 'epoch': '1.97'} | |
| {'loss': '0.04266', 'grad_norm': '0.7534', 'learning_rate': '3.32e-07', 'epoch': '1.97'} | |
| {'loss': '0.04063', 'grad_norm': '1.805', 'learning_rate': '3.267e-07', 'epoch': '1.971'} | |
| {'loss': '0.04171', 'grad_norm': '1.321', 'learning_rate': '3.214e-07', 'epoch': '1.971'} | |
| {'loss': '0.04459', 'grad_norm': '1.862', 'learning_rate': '3.161e-07', 'epoch': '1.972'} | |
| {'loss': '0.03618', 'grad_norm': '0.666', 'learning_rate': '3.108e-07', 'epoch': '1.972'} | |
| {'loss': '0.04225', 'grad_norm': '1.444', 'learning_rate': '3.055e-07', 'epoch': '1.973'} | |
| {'eval_ms_marco_loss': '0.01428', 'eval_val-ms-marco-768_cosine_accuracy': '0.9997', 'eval_val-ms-marco-512_cosine_accuracy': '0.9997', 'eval_val-ms-marco-256_cosine_accuracy': '0.9997', 'eval_val-ms-marco-128_cosine_accuracy': '0.9997', 'eval_val-ms-marco-64_cosine_accuracy': '0.9993', 'eval_sequential_score': '0.9997', 'eval_ms_marco_runtime': '33.81', 'eval_ms_marco_samples_per_second': '295.7', 'eval_ms_marco_steps_per_second': '9.257', 'epoch': '1.973'} | |
| {'loss': '0.1408', 'grad_norm': '1.095', 'learning_rate': '3.002e-07', 'epoch': '1.973'} | |
| {'loss': '0.03795', 'grad_norm': '3.112', 'learning_rate': '2.949e-07', 'epoch': '1.973'} | |
| {'loss': '0.13', 'grad_norm': '4.002', 'learning_rate': '2.897e-07', 'epoch': '1.974'} | |
| {'loss': '0.04499', 'grad_norm': '2.38', 'learning_rate': '2.844e-07', 'epoch': '1.974'} | |
| {'loss': '0.04836', 'grad_norm': '1.943', 'learning_rate': '2.791e-07', 'epoch': '1.975'} | |
| {'loss': '0.0431', 'grad_norm': '0.1494', 'learning_rate': '2.738e-07', 'epoch': '1.975'} | |
| {'loss': '0.04664', 'grad_norm': '7.176', 'learning_rate': '2.685e-07', 'epoch': '1.976'} | |
| {'loss': '0.04394', 'grad_norm': '5.588', 'learning_rate': '2.632e-07', 'epoch': '1.976'} | |
| {'loss': '0.04646', 'grad_norm': '2.967', 'learning_rate': '2.579e-07', 'epoch': '1.977'} | |
| {'loss': '0.03849', 'grad_norm': '0.1599', 'learning_rate': '2.526e-07', 'epoch': '1.977'} | |
| {'loss': '0.03411', 'grad_norm': '0.1124', 'learning_rate': '2.473e-07', 'epoch': '1.978'} | |
| {'loss': '0.1405', 'grad_norm': '0.1426', 'learning_rate': '2.42e-07', 'epoch': '1.978'} | |
| {'loss': '0.04139', 'grad_norm': '4.349', 'learning_rate': '2.367e-07', 'epoch': '1.979'} | |
| {'loss': '0.03977', 'grad_norm': '0.4622', 'learning_rate': '2.314e-07', 'epoch': '1.979'} | |
| {'loss': '0.03413', 'grad_norm': '0.1811', 'learning_rate': '2.261e-07', 'epoch': '1.98'} | |
| {'loss': '0.04375', 'grad_norm': '0.5068', 'learning_rate': '2.208e-07', 'epoch': '1.98'} | |
| {'loss': '0.1913', 'grad_norm': '2.004', 'learning_rate': '2.155e-07', 'epoch': '1.981'} | |
| {'loss': '0.0427', 'grad_norm': '1.383', 'learning_rate': '2.102e-07', 'epoch': '1.981'} | |
| {'loss': '0.04279', 'grad_norm': '0.3793', 'learning_rate': '2.05e-07', 'epoch': '1.982'} | |
| {'loss': '0.04846', 'grad_norm': '5.044', 'learning_rate': '1.997e-07', 'epoch': '1.982'} | |
| {'loss': '0.0361', 'grad_norm': '0.1521', 'learning_rate': '1.944e-07', 'epoch': '1.983'} | |
| {'loss': '0.0473', 'grad_norm': '4.233', 'learning_rate': '1.891e-07', 'epoch': '1.983'} | |
| {'loss': '0.04824', 'grad_norm': '3.059', 'learning_rate': '1.838e-07', 'epoch': '1.983'} | |
| {'loss': '0.04692', 'grad_norm': '0.1569', 'learning_rate': '1.785e-07', 'epoch': '1.984'} | |
| {'loss': '0.1495', 'grad_norm': '0.4943', 'learning_rate': '1.732e-07', 'epoch': '1.984'} | |
| {'loss': '0.03739', 'grad_norm': '0.8721', 'learning_rate': '1.679e-07', 'epoch': '1.985'} | |
| {'loss': '0.04978', 'grad_norm': '0.8615', 'learning_rate': '1.626e-07', 'epoch': '1.985'} | |
| {'loss': '0.04099', 'grad_norm': '0.9866', 'learning_rate': '1.573e-07', 'epoch': '1.986'} | |
| {'loss': '0.03931', 'grad_norm': '0.3839', 'learning_rate': '1.52e-07', 'epoch': '1.986'} | |
| {'loss': '0.04747', 'grad_norm': '1.98', 'learning_rate': '1.467e-07', 'epoch': '1.987'} | |
| {'loss': '0.04298', 'grad_norm': '0.1485', 'learning_rate': '1.414e-07', 'epoch': '1.987'} | |
| {'loss': '0.05136', 'grad_norm': '6.327', 'learning_rate': '1.361e-07', 'epoch': '1.988'} | |
| {'loss': '0.03864', 'grad_norm': '0.07771', 'learning_rate': '1.308e-07', 'epoch': '1.988'} | |
| {'loss': '0.04812', 'grad_norm': '2.056', 'learning_rate': '1.255e-07', 'epoch': '1.989'} | |
| {'loss': '0.04627', 'grad_norm': '6.799', 'learning_rate': '1.203e-07', 'epoch': '1.989'} | |
| {'loss': '0.04309', 'grad_norm': '1.373', 'learning_rate': '1.15e-07', 'epoch': '1.99'} | |
| {'loss': '0.04746', 'grad_norm': '1.758', 'learning_rate': '1.097e-07', 'epoch': '1.99'} | |
| {'loss': '0.05072', 'grad_norm': '0.07799', 'learning_rate': '1.044e-07', 'epoch': '1.991'} | |
| {'loss': '0.03673', 'grad_norm': '0.7068', 'learning_rate': '9.908e-08', 'epoch': '1.991'} | |
| {'loss': '0.03874', 'grad_norm': '0.5105', 'learning_rate': '9.378e-08', 'epoch': '1.992'} | |
| {'loss': '0.05065', 'grad_norm': '3.684', 'learning_rate': '8.849e-08', 'epoch': '1.992'} | |
| {'loss': '0.04891', 'grad_norm': '0.4475', 'learning_rate': '8.319e-08', 'epoch': '1.993'} | |
| {'loss': '0.04701', 'grad_norm': '0.1658', 'learning_rate': '7.79e-08', 'epoch': '1.993'} | |
| {'loss': '0.04447', 'grad_norm': '1.686', 'learning_rate': '7.261e-08', 'epoch': '1.993'} | |
| {'loss': '0.04665', 'grad_norm': '0.1621', 'learning_rate': '6.731e-08', 'epoch': '1.994'} | |
| {'loss': '0.03952', 'grad_norm': '0.09613', 'learning_rate': '6.202e-08', 'epoch': '1.994'} | |
| {'loss': '0.05408', 'grad_norm': '1.459', 'learning_rate': '5.672e-08', 'epoch': '1.995'} | |
| {'loss': '0.04361', 'grad_norm': '2.07', 'learning_rate': '5.143e-08', 'epoch': '1.995'} | |
| {'loss': '0.04786', 'grad_norm': '0.1201', 'learning_rate': '4.614e-08', 'epoch': '1.996'} | |
| {'loss': '0.04192', 'grad_norm': '0.8552', 'learning_rate': '4.084e-08', 'epoch': '1.996'} | |
| {'loss': '0.05168', 'grad_norm': '4.036', 'learning_rate': '3.555e-08', 'epoch': '1.997'} | |
| {'loss': '0.04661', 'grad_norm': '0.1818', 'learning_rate': '3.025e-08', 'epoch': '1.997'} | |
| {'loss': '0.04089', 'grad_norm': '1.493', 'learning_rate': '2.496e-08', 'epoch': '1.998'} | |
| {'loss': '0.04603', 'grad_norm': '0.3944', 'learning_rate': '1.967e-08', 'epoch': '1.998'} | |
| {'loss': '0.04663', 'grad_norm': '3.714', 'learning_rate': '1.437e-08', 'epoch': '1.999'} | |
| {'loss': '0.0342', 'grad_norm': '0.0761', 'learning_rate': '9.079e-09', 'epoch': '1.999'} | |
| {'loss': '0.03921', 'grad_norm': '0.1658', 'learning_rate': '3.785e-09', 'epoch': '2'} | |
| {'train_runtime': '1.969e+05', 'train_samples_per_second': '272.9', 'train_steps_per_second': '4.265', 'train_loss': '0.231', 'epoch': '2'} | |
| finished | |
| Model saved to output/arabert_20260326_1254/final | |