| { | |
| "best_metric": 0.9335728010062837, | |
| "best_model_checkpoint": "/scicore/home/lauerg/cerque0000/models/nlp-job-ads/gbert-base-ft-edu-redux/checkpoint-1400", | |
| "epoch": 9.0, | |
| "global_step": 2664, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": 0.31717467308044434, | |
| "eval_lrap": 0.575480030593511, | |
| "eval_runtime": 8.2282, | |
| "eval_samples_per_second": 81.671, | |
| "eval_steps_per_second": 10.209, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 0.27608808875083923, | |
| "eval_lrap": 0.7146675513885474, | |
| "eval_runtime": 8.1478, | |
| "eval_samples_per_second": 82.476, | |
| "eval_steps_per_second": 10.31, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "eval_loss": 0.24148814380168915, | |
| "eval_lrap": 0.8075810415317497, | |
| "eval_runtime": 8.0351, | |
| "eval_samples_per_second": 83.633, | |
| "eval_steps_per_second": 10.454, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "eval_loss": 0.2186277061700821, | |
| "eval_lrap": 0.825712521334449, | |
| "eval_runtime": 8.0683, | |
| "eval_samples_per_second": 83.289, | |
| "eval_steps_per_second": 10.411, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 2.193243243243243e-05, | |
| "loss": 0.2693, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "eval_loss": 0.21280047297477722, | |
| "eval_lrap": 0.8625814785205315, | |
| "eval_runtime": 8.196, | |
| "eval_samples_per_second": 81.991, | |
| "eval_steps_per_second": 10.249, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "eval_loss": 0.20358851552009583, | |
| "eval_lrap": 0.8505382989284863, | |
| "eval_runtime": 8.1912, | |
| "eval_samples_per_second": 82.039, | |
| "eval_steps_per_second": 10.255, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "eval_loss": 0.21679966151714325, | |
| "eval_lrap": 0.8932179201649483, | |
| "eval_runtime": 8.0797, | |
| "eval_samples_per_second": 83.172, | |
| "eval_steps_per_second": 10.396, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "eval_loss": 0.18326468765735626, | |
| "eval_lrap": 0.903219248223994, | |
| "eval_runtime": 8.1375, | |
| "eval_samples_per_second": 82.58, | |
| "eval_steps_per_second": 10.323, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "eval_loss": 0.18310672044754028, | |
| "eval_lrap": 0.8821981117114492, | |
| "eval_runtime": 8.0697, | |
| "eval_samples_per_second": 83.274, | |
| "eval_steps_per_second": 10.409, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 1.6864864864864864e-05, | |
| "loss": 0.1665, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "eval_loss": 0.1836722493171692, | |
| "eval_lrap": 0.9224537287097426, | |
| "eval_runtime": 8.1462, | |
| "eval_samples_per_second": 82.493, | |
| "eval_steps_per_second": 10.312, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "eval_loss": 0.1867215484380722, | |
| "eval_lrap": 0.9292872160328117, | |
| "eval_runtime": 8.1758, | |
| "eval_samples_per_second": 82.194, | |
| "eval_steps_per_second": 10.274, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "eval_loss": 0.17954795062541962, | |
| "eval_lrap": 0.9233198336105406, | |
| "eval_runtime": 8.1628, | |
| "eval_samples_per_second": 82.325, | |
| "eval_steps_per_second": 10.291, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 4.39, | |
| "eval_loss": 0.1790640652179718, | |
| "eval_lrap": 0.9050188553107904, | |
| "eval_runtime": 8.1622, | |
| "eval_samples_per_second": 82.331, | |
| "eval_steps_per_second": 10.291, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "eval_loss": 0.18696065247058868, | |
| "eval_lrap": 0.9335728010062837, | |
| "eval_runtime": 8.1263, | |
| "eval_samples_per_second": 82.694, | |
| "eval_steps_per_second": 10.337, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 5.07, | |
| "learning_rate": 1.1797297297297297e-05, | |
| "loss": 0.1146, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 5.07, | |
| "eval_loss": 0.1917356699705124, | |
| "eval_lrap": 0.9100622279217009, | |
| "eval_runtime": 8.1497, | |
| "eval_samples_per_second": 82.457, | |
| "eval_steps_per_second": 10.307, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 5.41, | |
| "eval_loss": 0.17960630357265472, | |
| "eval_lrap": 0.9317027532386741, | |
| "eval_runtime": 8.1448, | |
| "eval_samples_per_second": 82.507, | |
| "eval_steps_per_second": 10.313, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 5.74, | |
| "eval_loss": 0.18476144969463348, | |
| "eval_lrap": 0.9179141722192571, | |
| "eval_runtime": 8.0555, | |
| "eval_samples_per_second": 83.422, | |
| "eval_steps_per_second": 10.428, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 6.08, | |
| "eval_loss": 0.18720324337482452, | |
| "eval_lrap": 0.9076720128841897, | |
| "eval_runtime": 8.1385, | |
| "eval_samples_per_second": 82.571, | |
| "eval_steps_per_second": 10.321, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 6.42, | |
| "eval_loss": 0.18699432909488678, | |
| "eval_lrap": 0.924198462000043, | |
| "eval_runtime": 8.1746, | |
| "eval_samples_per_second": 82.206, | |
| "eval_steps_per_second": 10.276, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 6.76, | |
| "learning_rate": 6.729729729729729e-06, | |
| "loss": 0.0813, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 6.76, | |
| "eval_loss": 0.17621222138404846, | |
| "eval_lrap": 0.915026297261488, | |
| "eval_runtime": 8.0568, | |
| "eval_samples_per_second": 83.408, | |
| "eval_steps_per_second": 10.426, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 7.09, | |
| "eval_loss": 0.18799513578414917, | |
| "eval_lrap": 0.9157933801078312, | |
| "eval_runtime": 8.2, | |
| "eval_samples_per_second": 81.951, | |
| "eval_steps_per_second": 10.244, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 7.43, | |
| "eval_loss": 0.1881764978170395, | |
| "eval_lrap": 0.9201832052904669, | |
| "eval_runtime": 8.1918, | |
| "eval_samples_per_second": 82.034, | |
| "eval_steps_per_second": 10.254, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 7.77, | |
| "eval_loss": 0.1911892592906952, | |
| "eval_lrap": 0.9248369082537248, | |
| "eval_runtime": 8.0575, | |
| "eval_samples_per_second": 83.401, | |
| "eval_steps_per_second": 10.425, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 8.11, | |
| "eval_loss": 0.18784251809120178, | |
| "eval_lrap": 0.9253503927004727, | |
| "eval_runtime": 8.1128, | |
| "eval_samples_per_second": 82.832, | |
| "eval_steps_per_second": 10.354, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 8.45, | |
| "learning_rate": 1.662162162162162e-06, | |
| "loss": 0.0624, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 8.45, | |
| "eval_loss": 0.19267971813678741, | |
| "eval_lrap": 0.9211606593694309, | |
| "eval_runtime": 8.201, | |
| "eval_samples_per_second": 81.942, | |
| "eval_steps_per_second": 10.243, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 8.78, | |
| "eval_loss": 0.1919146031141281, | |
| "eval_lrap": 0.9207750746085017, | |
| "eval_runtime": 8.267, | |
| "eval_samples_per_second": 81.287, | |
| "eval_steps_per_second": 10.161, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "step": 2664, | |
| "total_flos": 5605306439961600.0, | |
| "train_loss": 0.1333099156170636, | |
| "train_runtime": 980.3632, | |
| "train_samples_per_second": 21.73, | |
| "train_steps_per_second": 2.717 | |
| } | |
| ], | |
| "max_steps": 2664, | |
| "num_train_epochs": 9, | |
| "total_flos": 5605306439961600.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |