| { | |
| "best_metric": 0.17471107840538025, | |
| "best_model_checkpoint": "xlnet-base-cased/subtaskA/0/checkpoint-23952", | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 23952, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.9860832776664444e-05, | |
| "loss": 0.5163, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.9721665553328883e-05, | |
| "loss": 0.3694, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1.9582498329993322e-05, | |
| "loss": 0.3342, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.944333110665776e-05, | |
| "loss": 0.3631, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.9304163883322203e-05, | |
| "loss": 0.2701, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1.9164996659986642e-05, | |
| "loss": 0.2449, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1.902582943665108e-05, | |
| "loss": 0.2478, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.888666221331552e-05, | |
| "loss": 0.2499, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1.8747494989979962e-05, | |
| "loss": 0.2542, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.86083277666444e-05, | |
| "loss": 0.2503, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1.8469160543308843e-05, | |
| "loss": 0.2436, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1.832999331997328e-05, | |
| "loss": 0.2492, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1.819082609663772e-05, | |
| "loss": 0.228, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 1.805165887330216e-05, | |
| "loss": 0.2293, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 1.7912491649966602e-05, | |
| "loss": 0.2179, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1.777332442663104e-05, | |
| "loss": 0.2044, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 1.763415720329548e-05, | |
| "loss": 0.1854, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 1.7494989979959922e-05, | |
| "loss": 0.1957, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1.735582275662436e-05, | |
| "loss": 0.2028, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.72166555332888e-05, | |
| "loss": 0.1937, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 1.707748830995324e-05, | |
| "loss": 0.1722, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1.693832108661768e-05, | |
| "loss": 0.1461, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1.679915386328212e-05, | |
| "loss": 0.1734, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1.6659986639946563e-05, | |
| "loss": 0.1978, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 1.6520819416611002e-05, | |
| "loss": 0.1648, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 1.638165219327544e-05, | |
| "loss": 0.1769, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 1.624248496993988e-05, | |
| "loss": 0.1984, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 1.6103317746604322e-05, | |
| "loss": 0.1515, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 1.596415052326876e-05, | |
| "loss": 0.1543, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 1.58249832999332e-05, | |
| "loss": 0.1974, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 1.5685816076597642e-05, | |
| "loss": 0.162, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 1.554664885326208e-05, | |
| "loss": 0.1493, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1.5407481629926523e-05, | |
| "loss": 0.1776, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1.5268314406590962e-05, | |
| "loss": 0.1675, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.5129147183255401e-05, | |
| "loss": 0.1587, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.498997995991984e-05, | |
| "loss": 0.1289, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.485081273658428e-05, | |
| "loss": 0.1719, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.471164551324872e-05, | |
| "loss": 0.1658, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.4572478289913162e-05, | |
| "loss": 0.1505, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 1.44333110665776e-05, | |
| "loss": 0.1898, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 1.4294143843242041e-05, | |
| "loss": 0.1813, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 1.415497661990648e-05, | |
| "loss": 0.1528, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 1.4015809396570921e-05, | |
| "loss": 0.1635, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 1.3876642173235361e-05, | |
| "loss": 0.1543, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.37374749498998e-05, | |
| "loss": 0.1539, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1.3598307726564241e-05, | |
| "loss": 0.1421, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 1.345914050322868e-05, | |
| "loss": 0.1217, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_f1": 0.9711923847695391, | |
| "eval_loss": 0.17471107840538025, | |
| "eval_runtime": 440.9341, | |
| "eval_samples_per_second": 54.321, | |
| "eval_steps_per_second": 13.58, | |
| "step": 23952 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 71856, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 2.729295518247936e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |