| { | |
| "best_metric": 0.9083333333333333, | |
| "best_model_checkpoint": "deverta_60k_fillna_val100/checkpoint-7600", | |
| "epoch": 1.9984551415846303, | |
| "eval_steps": 100, | |
| "global_step": 7600, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.717791411042945e-06, | |
| "loss": 1.615, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 1.6094433069229126, | |
| "eval_map@3": 0.36999999999999994, | |
| "eval_runtime": 3.9269, | |
| "eval_samples_per_second": 25.465, | |
| "eval_steps_per_second": 25.465, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 3.470639789658195e-06, | |
| "loss": 1.615, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 1.6090234518051147, | |
| "eval_map@3": 0.5433333333333333, | |
| "eval_runtime": 3.9569, | |
| "eval_samples_per_second": 25.272, | |
| "eval_steps_per_second": 25.272, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 5.2234881682734454e-06, | |
| "loss": 1.6106, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 1.6112011671066284, | |
| "eval_map@3": 0.6250000000000001, | |
| "eval_runtime": 4.2374, | |
| "eval_samples_per_second": 23.6, | |
| "eval_steps_per_second": 23.6, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 6.976336546888695e-06, | |
| "loss": 1.4954, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": 1.2830108404159546, | |
| "eval_map@3": 0.755, | |
| "eval_runtime": 4.1043, | |
| "eval_samples_per_second": 24.364, | |
| "eval_steps_per_second": 24.364, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 8.729184925503945e-06, | |
| "loss": 1.0519, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 0.8515128493309021, | |
| "eval_map@3": 0.8183333333333335, | |
| "eval_runtime": 4.0929, | |
| "eval_samples_per_second": 24.432, | |
| "eval_steps_per_second": 24.432, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.0482033304119195e-05, | |
| "loss": 0.8846, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 0.7408291101455688, | |
| "eval_map@3": 0.8366666666666667, | |
| "eval_runtime": 4.1086, | |
| "eval_samples_per_second": 24.339, | |
| "eval_steps_per_second": 24.339, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1.2234881682734446e-05, | |
| "loss": 0.8651, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_loss": 0.7649513483047485, | |
| "eval_map@3": 0.8633333333333334, | |
| "eval_runtime": 4.0899, | |
| "eval_samples_per_second": 24.45, | |
| "eval_steps_per_second": 24.45, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.3987730061349694e-05, | |
| "loss": 0.8166, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_loss": 0.7141894698143005, | |
| "eval_map@3": 0.8583333333333334, | |
| "eval_runtime": 4.1369, | |
| "eval_samples_per_second": 24.173, | |
| "eval_steps_per_second": 24.173, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1.5740578439964945e-05, | |
| "loss": 0.8283, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 0.6661826968193054, | |
| "eval_map@3": 0.845, | |
| "eval_runtime": 4.1543, | |
| "eval_samples_per_second": 24.071, | |
| "eval_steps_per_second": 24.071, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 1.7493426818580194e-05, | |
| "loss": 0.7593, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_loss": 0.6564372181892395, | |
| "eval_map@3": 0.8483333333333334, | |
| "eval_runtime": 4.076, | |
| "eval_samples_per_second": 24.534, | |
| "eval_steps_per_second": 24.534, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 1.9246275197195444e-05, | |
| "loss": 0.7401, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_loss": 0.6686395406723022, | |
| "eval_map@3": 0.85, | |
| "eval_runtime": 4.0963, | |
| "eval_samples_per_second": 24.412, | |
| "eval_steps_per_second": 24.412, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1.9998531353530498e-05, | |
| "loss": 0.7791, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": 0.608403742313385, | |
| "eval_map@3": 0.875, | |
| "eval_runtime": 4.1272, | |
| "eval_samples_per_second": 24.229, | |
| "eval_steps_per_second": 24.229, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 1.998860488949288e-05, | |
| "loss": 0.7868, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": 0.6702239513397217, | |
| "eval_map@3": 0.87, | |
| "eval_runtime": 4.0746, | |
| "eval_samples_per_second": 24.542, | |
| "eval_steps_per_second": 24.542, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 1.9969323231985812e-05, | |
| "loss": 0.7567, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_loss": 0.6087381839752197, | |
| "eval_map@3": 0.8683333333333334, | |
| "eval_runtime": 3.8341, | |
| "eval_samples_per_second": 26.081, | |
| "eval_steps_per_second": 26.081, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 1.994070443995129e-05, | |
| "loss": 0.7488, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_loss": 0.6629943251609802, | |
| "eval_map@3": 0.8616666666666667, | |
| "eval_runtime": 4.0681, | |
| "eval_samples_per_second": 24.581, | |
| "eval_steps_per_second": 24.581, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.990277531736638e-05, | |
| "loss": 0.7833, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_loss": 0.592115581035614, | |
| "eval_map@3": 0.8566666666666667, | |
| "eval_runtime": 4.0797, | |
| "eval_samples_per_second": 24.512, | |
| "eval_steps_per_second": 24.512, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1.9855571388138954e-05, | |
| "loss": 0.7706, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_loss": 0.6199390888214111, | |
| "eval_map@3": 0.8733333333333333, | |
| "eval_runtime": 3.9265, | |
| "eval_samples_per_second": 25.468, | |
| "eval_steps_per_second": 25.468, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1.979913686283649e-05, | |
| "loss": 0.7422, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": 0.6019750237464905, | |
| "eval_map@3": 0.8833333333333334, | |
| "eval_runtime": 3.9986, | |
| "eval_samples_per_second": 25.009, | |
| "eval_steps_per_second": 25.009, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1.9733524597279037e-05, | |
| "loss": 0.7129, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": 0.5683853626251221, | |
| "eval_map@3": 0.8766666666666666, | |
| "eval_runtime": 4.0628, | |
| "eval_samples_per_second": 24.613, | |
| "eval_steps_per_second": 24.613, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 1.965879604303516e-05, | |
| "loss": 0.753, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 0.536411464214325, | |
| "eval_map@3": 0.8733333333333333, | |
| "eval_runtime": 3.989, | |
| "eval_samples_per_second": 25.069, | |
| "eval_steps_per_second": 25.069, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 1.957502118986723e-05, | |
| "loss": 0.7057, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 0.5491364002227783, | |
| "eval_map@3": 0.8583333333333333, | |
| "eval_runtime": 3.9154, | |
| "eval_samples_per_second": 25.54, | |
| "eval_steps_per_second": 25.54, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 1.9482278500179953e-05, | |
| "loss": 0.73, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_loss": 0.5584819316864014, | |
| "eval_map@3": 0.8766666666666667, | |
| "eval_runtime": 3.9164, | |
| "eval_samples_per_second": 25.534, | |
| "eval_steps_per_second": 25.534, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 1.9380654835533523e-05, | |
| "loss": 0.6898, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 0.5588586330413818, | |
| "eval_map@3": 0.88, | |
| "eval_runtime": 3.8846, | |
| "eval_samples_per_second": 25.743, | |
| "eval_steps_per_second": 25.743, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 1.9270245375290263e-05, | |
| "loss": 0.6842, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_loss": 0.573777437210083, | |
| "eval_map@3": 0.8683333333333334, | |
| "eval_runtime": 4.0374, | |
| "eval_samples_per_second": 24.768, | |
| "eval_steps_per_second": 24.768, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 1.9151153527470895e-05, | |
| "loss": 0.728, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": 0.5937029123306274, | |
| "eval_map@3": 0.8866666666666666, | |
| "eval_runtime": 3.9109, | |
| "eval_samples_per_second": 25.57, | |
| "eval_steps_per_second": 25.57, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 1.902349083190399e-05, | |
| "loss": 0.7047, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 0.5620361566543579, | |
| "eval_map@3": 0.885, | |
| "eval_runtime": 3.9171, | |
| "eval_samples_per_second": 25.529, | |
| "eval_steps_per_second": 25.529, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1.888737685575924e-05, | |
| "loss": 0.7554, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_loss": 0.5551219582557678, | |
| "eval_map@3": 0.8883333333333333, | |
| "eval_runtime": 3.9451, | |
| "eval_samples_per_second": 25.348, | |
| "eval_steps_per_second": 25.348, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.874293908156247e-05, | |
| "loss": 0.7252, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_loss": 0.5565034747123718, | |
| "eval_map@3": 0.8983333333333331, | |
| "eval_runtime": 4.1016, | |
| "eval_samples_per_second": 24.381, | |
| "eval_steps_per_second": 24.381, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.8590312787797196e-05, | |
| "loss": 0.7245, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": 0.5758660435676575, | |
| "eval_map@3": 0.8816666666666667, | |
| "eval_runtime": 3.9367, | |
| "eval_samples_per_second": 25.402, | |
| "eval_steps_per_second": 25.402, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.8429640922204614e-05, | |
| "loss": 0.725, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_loss": 0.5699021816253662, | |
| "eval_map@3": 0.8883333333333333, | |
| "eval_runtime": 3.8274, | |
| "eval_samples_per_second": 26.128, | |
| "eval_steps_per_second": 26.128, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 1.8261073967900676e-05, | |
| "loss": 0.6983, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "eval_loss": 0.5696993470191956, | |
| "eval_map@3": 0.8883333333333333, | |
| "eval_runtime": 3.8632, | |
| "eval_samples_per_second": 25.885, | |
| "eval_steps_per_second": 25.885, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 1.80847698024356e-05, | |
| "loss": 0.7055, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_loss": 0.5589382648468018, | |
| "eval_map@3": 0.8933333333333333, | |
| "eval_runtime": 4.205, | |
| "eval_samples_per_second": 23.781, | |
| "eval_steps_per_second": 23.781, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 1.790089354992788e-05, | |
| "loss": 0.7091, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "eval_loss": 0.5517598986625671, | |
| "eval_map@3": 0.8883333333333333, | |
| "eval_runtime": 4.2776, | |
| "eval_samples_per_second": 23.378, | |
| "eval_steps_per_second": 23.378, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 1.7711566234443824e-05, | |
| "loss": 0.7128, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "eval_loss": 0.5628377795219421, | |
| "eval_map@3": 0.8866666666666667, | |
| "eval_runtime": 4.1647, | |
| "eval_samples_per_second": 24.011, | |
| "eval_steps_per_second": 24.011, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 1.751314068469163e-05, | |
| "loss": 0.7465, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "eval_loss": 0.5919340252876282, | |
| "eval_map@3": 0.8833333333333333, | |
| "eval_runtime": 4.0418, | |
| "eval_samples_per_second": 24.742, | |
| "eval_steps_per_second": 24.742, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1.730767842806733e-05, | |
| "loss": 0.708, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "eval_loss": 0.554470419883728, | |
| "eval_map@3": 0.895, | |
| "eval_runtime": 4.0703, | |
| "eval_samples_per_second": 24.568, | |
| "eval_steps_per_second": 24.568, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 1.709537189776684e-05, | |
| "loss": 0.7017, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_loss": 0.5175462365150452, | |
| "eval_map@3": 0.895, | |
| "eval_runtime": 4.1999, | |
| "eval_samples_per_second": 23.81, | |
| "eval_steps_per_second": 23.81, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.6876419937241033e-05, | |
| "loss": 0.7, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.5037916302680969, | |
| "eval_map@3": 0.8916666666666667, | |
| "eval_runtime": 4.1774, | |
| "eval_samples_per_second": 23.938, | |
| "eval_steps_per_second": 23.938, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 1.665102761396169e-05, | |
| "loss": 0.5923, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "eval_loss": 0.48426902294158936, | |
| "eval_map@3": 0.8916666666666667, | |
| "eval_runtime": 4.139, | |
| "eval_samples_per_second": 24.16, | |
| "eval_steps_per_second": 24.16, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 1.641940602735802e-05, | |
| "loss": 0.594, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "eval_loss": 0.48445701599121094, | |
| "eval_map@3": 0.895, | |
| "eval_runtime": 4.2445, | |
| "eval_samples_per_second": 23.56, | |
| "eval_steps_per_second": 23.56, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 1.6181772111103775e-05, | |
| "loss": 0.6075, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "eval_loss": 0.5103535652160645, | |
| "eval_map@3": 0.8899999999999999, | |
| "eval_runtime": 4.059, | |
| "eval_samples_per_second": 24.636, | |
| "eval_steps_per_second": 24.636, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 1.5938348429940095e-05, | |
| "loss": 0.5226, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "eval_loss": 0.5009714961051941, | |
| "eval_map@3": 0.8883333333333333, | |
| "eval_runtime": 4.0879, | |
| "eval_samples_per_second": 24.463, | |
| "eval_steps_per_second": 24.463, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 1.568936297122432e-05, | |
| "loss": 0.5886, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "eval_loss": 0.49200114607810974, | |
| "eval_map@3": 0.9033333333333333, | |
| "eval_runtime": 4.1867, | |
| "eval_samples_per_second": 23.885, | |
| "eval_steps_per_second": 23.885, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 1.543504893140011e-05, | |
| "loss": 0.5619, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "eval_loss": 0.49913597106933594, | |
| "eval_map@3": 0.89, | |
| "eval_runtime": 4.0492, | |
| "eval_samples_per_second": 24.696, | |
| "eval_steps_per_second": 24.696, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 1.517564449758878e-05, | |
| "loss": 0.6017, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "eval_loss": 0.4905971586704254, | |
| "eval_map@3": 0.9033333333333333, | |
| "eval_runtime": 4.0275, | |
| "eval_samples_per_second": 24.83, | |
| "eval_steps_per_second": 24.83, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 1.4911392624506427e-05, | |
| "loss": 0.534, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "eval_loss": 0.4901256263256073, | |
| "eval_map@3": 0.89, | |
| "eval_runtime": 5.205, | |
| "eval_samples_per_second": 19.212, | |
| "eval_steps_per_second": 19.212, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 1.4642540806915802e-05, | |
| "loss": 0.5914, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "eval_loss": 0.4857093095779419, | |
| "eval_map@3": 0.8916666666666666, | |
| "eval_runtime": 4.357, | |
| "eval_samples_per_second": 22.952, | |
| "eval_steps_per_second": 22.952, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 1.4369340847826037e-05, | |
| "loss": 0.6155, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "eval_loss": 0.49262702465057373, | |
| "eval_map@3": 0.8849999999999999, | |
| "eval_runtime": 4.3241, | |
| "eval_samples_per_second": 23.126, | |
| "eval_steps_per_second": 23.126, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 1.4092048622657309e-05, | |
| "loss": 0.5779, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "eval_loss": 0.4796687960624695, | |
| "eval_map@3": 0.8849999999999999, | |
| "eval_runtime": 4.3677, | |
| "eval_samples_per_second": 22.895, | |
| "eval_steps_per_second": 22.895, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 1.3810923839591368e-05, | |
| "loss": 0.6144, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "eval_loss": 0.4864266514778137, | |
| "eval_map@3": 0.8916666666666666, | |
| "eval_runtime": 4.1788, | |
| "eval_samples_per_second": 23.93, | |
| "eval_steps_per_second": 23.93, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 1.3526229796332322e-05, | |
| "loss": 0.5532, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "eval_loss": 0.5059311389923096, | |
| "eval_map@3": 0.9033333333333334, | |
| "eval_runtime": 4.1314, | |
| "eval_samples_per_second": 24.205, | |
| "eval_steps_per_second": 24.205, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 1.3238233133505538e-05, | |
| "loss": 0.5238, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "eval_loss": 0.5035010576248169, | |
| "eval_map@3": 0.8933333333333334, | |
| "eval_runtime": 4.0704, | |
| "eval_samples_per_second": 24.568, | |
| "eval_steps_per_second": 24.568, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 1.2947203584925607e-05, | |
| "loss": 0.5993, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "eval_loss": 0.5209221839904785, | |
| "eval_map@3": 0.8983333333333334, | |
| "eval_runtime": 4.0192, | |
| "eval_samples_per_second": 24.881, | |
| "eval_steps_per_second": 24.881, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 1.2653413724967272e-05, | |
| "loss": 0.5443, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "eval_loss": 0.5166578888893127, | |
| "eval_map@3": 0.8883333333333334, | |
| "eval_runtime": 4.0162, | |
| "eval_samples_per_second": 24.899, | |
| "eval_steps_per_second": 24.899, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 1.2357138713275916e-05, | |
| "loss": 0.5564, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "eval_loss": 0.50209641456604, | |
| "eval_map@3": 0.8883333333333334, | |
| "eval_runtime": 4.0769, | |
| "eval_samples_per_second": 24.529, | |
| "eval_steps_per_second": 24.529, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 1.2058656037056733e-05, | |
| "loss": 0.5962, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "eval_loss": 0.5111860632896423, | |
| "eval_map@3": 0.8933333333333334, | |
| "eval_runtime": 4.1245, | |
| "eval_samples_per_second": 24.245, | |
| "eval_steps_per_second": 24.245, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 1.1758245251183917e-05, | |
| "loss": 0.5824, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "eval_loss": 0.5007131695747375, | |
| "eval_map@3": 0.8966666666666666, | |
| "eval_runtime": 4.0577, | |
| "eval_samples_per_second": 24.644, | |
| "eval_steps_per_second": 24.644, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 1.1456187716373334e-05, | |
| "loss": 0.5327, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "eval_loss": 0.5062887072563171, | |
| "eval_map@3": 0.8883333333333334, | |
| "eval_runtime": 3.9467, | |
| "eval_samples_per_second": 25.337, | |
| "eval_steps_per_second": 25.337, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 1.1152766335663825e-05, | |
| "loss": 0.5649, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "eval_loss": 0.5016913414001465, | |
| "eval_map@3": 0.8883333333333334, | |
| "eval_runtime": 4.1523, | |
| "eval_samples_per_second": 24.083, | |
| "eval_steps_per_second": 24.083, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 1.0848265289454028e-05, | |
| "loss": 0.5717, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "eval_loss": 0.4974103271961212, | |
| "eval_map@3": 0.9033333333333334, | |
| "eval_runtime": 4.0909, | |
| "eval_samples_per_second": 24.444, | |
| "eval_steps_per_second": 24.444, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 1.054296976934281e-05, | |
| "loss": 0.5737, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "eval_loss": 0.49186939001083374, | |
| "eval_map@3": 0.8933333333333334, | |
| "eval_runtime": 4.2135, | |
| "eval_samples_per_second": 23.733, | |
| "eval_steps_per_second": 23.733, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 1.0237165711022661e-05, | |
| "loss": 0.5351, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "eval_loss": 0.4999094009399414, | |
| "eval_map@3": 0.895, | |
| "eval_runtime": 3.9962, | |
| "eval_samples_per_second": 25.024, | |
| "eval_steps_per_second": 25.024, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 9.934199946768965e-06, | |
| "loss": 0.5341, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "eval_loss": 0.4991361200809479, | |
| "eval_map@3": 0.9016666666666667, | |
| "eval_runtime": 4.1686, | |
| "eval_samples_per_second": 23.989, | |
| "eval_steps_per_second": 23.989, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 9.628236192287725e-06, | |
| "loss": 0.5501, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "eval_loss": 0.5340888500213623, | |
| "eval_map@3": 0.8866666666666667, | |
| "eval_runtime": 4.1621, | |
| "eval_samples_per_second": 24.027, | |
| "eval_steps_per_second": 24.027, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 9.32262062680631e-06, | |
| "loss": 0.5552, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "eval_loss": 0.4900314211845398, | |
| "eval_map@3": 0.9016666666666667, | |
| "eval_runtime": 4.0101, | |
| "eval_samples_per_second": 24.937, | |
| "eval_steps_per_second": 24.937, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 9.017639485767398e-06, | |
| "loss": 0.5362, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "eval_loss": 0.5052759647369385, | |
| "eval_map@3": 0.905, | |
| "eval_runtime": 4.083, | |
| "eval_samples_per_second": 24.492, | |
| "eval_steps_per_second": 24.492, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 8.713578410420254e-06, | |
| "loss": 0.5474, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "eval_loss": 0.5121599435806274, | |
| "eval_map@3": 0.905, | |
| "eval_runtime": 3.9444, | |
| "eval_samples_per_second": 25.352, | |
| "eval_steps_per_second": 25.352, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 8.41072218029293e-06, | |
| "loss": 0.5134, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "eval_loss": 0.510312020778656, | |
| "eval_map@3": 0.8983333333333334, | |
| "eval_runtime": 4.0574, | |
| "eval_samples_per_second": 24.647, | |
| "eval_steps_per_second": 24.647, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 8.1093544464716e-06, | |
| "loss": 0.5454, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "eval_loss": 0.5062999725341797, | |
| "eval_map@3": 0.9, | |
| "eval_runtime": 4.0245, | |
| "eval_samples_per_second": 24.848, | |
| "eval_steps_per_second": 24.848, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 7.809757465936754e-06, | |
| "loss": 0.5726, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "eval_loss": 0.5135546326637268, | |
| "eval_map@3": 0.905, | |
| "eval_runtime": 4.053, | |
| "eval_samples_per_second": 24.673, | |
| "eval_steps_per_second": 24.673, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 7.512211837205075e-06, | |
| "loss": 0.5173, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "eval_loss": 0.49537014961242676, | |
| "eval_map@3": 0.9, | |
| "eval_runtime": 4.1604, | |
| "eval_samples_per_second": 24.036, | |
| "eval_steps_per_second": 24.036, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 7.216996237524646e-06, | |
| "loss": 0.5118, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "eval_loss": 0.5108374357223511, | |
| "eval_map@3": 0.9066666666666667, | |
| "eval_runtime": 4.0629, | |
| "eval_samples_per_second": 24.613, | |
| "eval_steps_per_second": 24.613, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 6.924387161869565e-06, | |
| "loss": 0.5372, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "eval_loss": 0.5062543749809265, | |
| "eval_map@3": 0.8866666666666666, | |
| "eval_runtime": 3.9525, | |
| "eval_samples_per_second": 25.3, | |
| "eval_steps_per_second": 25.3, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 6.634658663978463e-06, | |
| "loss": 0.4689, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "eval_loss": 0.5014258623123169, | |
| "eval_map@3": 0.8933333333333333, | |
| "eval_runtime": 4.084, | |
| "eval_samples_per_second": 24.486, | |
| "eval_steps_per_second": 24.486, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 6.348082099679445e-06, | |
| "loss": 0.5096, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "eval_loss": 0.5079813003540039, | |
| "eval_map@3": 0.905, | |
| "eval_runtime": 4.207, | |
| "eval_samples_per_second": 23.77, | |
| "eval_steps_per_second": 23.77, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 6.0649258727418535e-06, | |
| "loss": 0.5272, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.4955463409423828, | |
| "eval_map@3": 0.9083333333333333, | |
| "eval_runtime": 4.0938, | |
| "eval_samples_per_second": 24.427, | |
| "eval_steps_per_second": 24.427, | |
| "step": 7600 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 11406, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "total_flos": 3.996618693693601e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |