| { | |
| "best_metric": 0.6859038472175598, | |
| "best_model_checkpoint": "deberta_v3_finetuned_predicting_effective_arguments/checkpoint-2000", | |
| "epoch": 4.835287009063444, | |
| "global_step": 10000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 9.518375241779499e-06, | |
| "loss": 0.8315, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 0.7444673180580139, | |
| "eval_runtime": 29.7252, | |
| "eval_samples_per_second": 123.33, | |
| "eval_steps_per_second": 30.849, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 9.034816247582205e-06, | |
| "loss": 0.7232, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": 0.7441162467002869, | |
| "eval_runtime": 29.4226, | |
| "eval_samples_per_second": 124.598, | |
| "eval_steps_per_second": 31.167, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 8.552224371373308e-06, | |
| "loss": 0.7269, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_loss": 0.7453668117523193, | |
| "eval_runtime": 29.5754, | |
| "eval_samples_per_second": 123.955, | |
| "eval_steps_per_second": 31.006, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 8.068665377176016e-06, | |
| "loss": 0.7185, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_loss": 0.6859038472175598, | |
| "eval_runtime": 29.569, | |
| "eval_samples_per_second": 123.981, | |
| "eval_steps_per_second": 31.012, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 7.585106382978724e-06, | |
| "loss": 0.6611, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "eval_loss": 0.6883463263511658, | |
| "eval_runtime": 29.5377, | |
| "eval_samples_per_second": 124.113, | |
| "eval_steps_per_second": 31.045, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 7.101547388781432e-06, | |
| "loss": 0.6516, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "eval_loss": 0.7088809013366699, | |
| "eval_runtime": 29.1585, | |
| "eval_samples_per_second": 125.727, | |
| "eval_steps_per_second": 31.449, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 6.617988394584139e-06, | |
| "loss": 0.6386, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "eval_loss": 0.6939310431480408, | |
| "eval_runtime": 29.2346, | |
| "eval_samples_per_second": 125.399, | |
| "eval_steps_per_second": 31.367, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 6.134429400386848e-06, | |
| "loss": 0.6435, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "eval_loss": 0.6942200064659119, | |
| "eval_runtime": 30.0324, | |
| "eval_samples_per_second": 122.068, | |
| "eval_steps_per_second": 30.534, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 5.650870406189556e-06, | |
| "loss": 0.5823, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "eval_loss": 0.771172821521759, | |
| "eval_runtime": 29.4927, | |
| "eval_samples_per_second": 124.302, | |
| "eval_steps_per_second": 31.092, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 5.167311411992263e-06, | |
| "loss": 0.5652, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "eval_loss": 0.7315438985824585, | |
| "eval_runtime": 28.9938, | |
| "eval_samples_per_second": 126.441, | |
| "eval_steps_per_second": 31.627, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 4.683752417794971e-06, | |
| "loss": 0.5701, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "eval_loss": 0.7429590225219727, | |
| "eval_runtime": 29.2482, | |
| "eval_samples_per_second": 125.341, | |
| "eval_steps_per_second": 31.352, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 4.20019342359768e-06, | |
| "loss": 0.5583, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "eval_loss": 0.74286949634552, | |
| "eval_runtime": 28.9549, | |
| "eval_samples_per_second": 126.611, | |
| "eval_steps_per_second": 31.67, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 3.7176015473887818e-06, | |
| "loss": 0.5145, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "eval_loss": 0.8086823225021362, | |
| "eval_runtime": 29.0547, | |
| "eval_samples_per_second": 126.176, | |
| "eval_steps_per_second": 31.561, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 3.23404255319149e-06, | |
| "loss": 0.4795, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "eval_loss": 0.8026116490364075, | |
| "eval_runtime": 28.8514, | |
| "eval_samples_per_second": 127.065, | |
| "eval_steps_per_second": 31.784, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 3.63, | |
| "learning_rate": 2.7504835589941973e-06, | |
| "loss": 0.4784, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 3.63, | |
| "eval_loss": 0.7970021963119507, | |
| "eval_runtime": 28.8445, | |
| "eval_samples_per_second": 127.095, | |
| "eval_steps_per_second": 31.791, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "learning_rate": 2.2669245647969055e-06, | |
| "loss": 0.4793, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "eval_loss": 0.7971013784408569, | |
| "eval_runtime": 29.079, | |
| "eval_samples_per_second": 126.07, | |
| "eval_steps_per_second": 31.535, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "learning_rate": 1.784332688588008e-06, | |
| "loss": 0.4544, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "eval_loss": 0.8546438813209534, | |
| "eval_runtime": 29.1238, | |
| "eval_samples_per_second": 125.877, | |
| "eval_steps_per_second": 31.486, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "learning_rate": 1.3007736943907157e-06, | |
| "loss": 0.4115, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "eval_loss": 0.8430052995681763, | |
| "eval_runtime": 29.3455, | |
| "eval_samples_per_second": 124.926, | |
| "eval_steps_per_second": 31.248, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 4.59, | |
| "learning_rate": 8.172147001934237e-07, | |
| "loss": 0.4192, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 4.59, | |
| "eval_loss": 0.8553691506385803, | |
| "eval_runtime": 30.0888, | |
| "eval_samples_per_second": 121.839, | |
| "eval_steps_per_second": 30.476, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 4.84, | |
| "learning_rate": 3.3365570599613157e-07, | |
| "loss": 0.4101, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 4.84, | |
| "eval_loss": 0.863072395324707, | |
| "eval_runtime": 29.1167, | |
| "eval_samples_per_second": 125.907, | |
| "eval_steps_per_second": 31.494, | |
| "step": 10000 | |
| } | |
| ], | |
| "max_steps": 10340, | |
| "num_train_epochs": 5, | |
| "total_flos": 9148295382909930.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |