| { | |
| "best_metric": 0.741533273748008, | |
| "best_model_checkpoint": "trained/hebban-reviews/xlm-roberta-base/checkpoint-2000", | |
| "epoch": 4.382997370727432, | |
| "global_step": 5001, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 4.504099180163968e-05, | |
| "loss": 0.7622, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_accuracy": 0.7567800788954635, | |
| "eval_f1": 0.7729405363796663, | |
| "eval_loss": 0.626587986946106, | |
| "eval_precision": 0.8122754990827801, | |
| "eval_qwk": 0.6618145848522559, | |
| "eval_recall": 0.7567800788954635, | |
| "eval_runtime": 23.2604, | |
| "eval_samples_per_second": 697.494, | |
| "eval_steps_per_second": 5.46, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 4.0041991601679665e-05, | |
| "loss": 0.6228, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_accuracy": 0.7375493096646942, | |
| "eval_f1": 0.7560139522475998, | |
| "eval_loss": 0.592847466468811, | |
| "eval_precision": 0.8006409272816242, | |
| "eval_qwk": 0.6464780542008888, | |
| "eval_recall": 0.7375493096646942, | |
| "eval_runtime": 23.1917, | |
| "eval_samples_per_second": 699.56, | |
| "eval_steps_per_second": 5.476, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 3.504299140171966e-05, | |
| "loss": 0.5623, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "eval_accuracy": 0.7543145956607495, | |
| "eval_f1": 0.7717090298131432, | |
| "eval_loss": 0.5968530178070068, | |
| "eval_precision": 0.8134758130284254, | |
| "eval_qwk": 0.6828220433375901, | |
| "eval_recall": 0.7543145956607495, | |
| "eval_runtime": 23.2366, | |
| "eval_samples_per_second": 698.21, | |
| "eval_steps_per_second": 5.466, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 3.0043991201759648e-05, | |
| "loss": 0.5421, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "eval_accuracy": 0.8150271203155819, | |
| "eval_f1": 0.8184520029418662, | |
| "eval_loss": 0.5808575749397278, | |
| "eval_precision": 0.8233166962202109, | |
| "eval_qwk": 0.741533273748008, | |
| "eval_recall": 0.8150271203155819, | |
| "eval_runtime": 23.1787, | |
| "eval_samples_per_second": 699.952, | |
| "eval_steps_per_second": 5.479, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 2.504499100179964e-05, | |
| "loss": 0.5033, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "eval_accuracy": 0.789447731755424, | |
| "eval_f1": 0.8012347601760753, | |
| "eval_loss": 0.640012800693512, | |
| "eval_precision": 0.8269193049518779, | |
| "eval_qwk": 0.7122705559860744, | |
| "eval_recall": 0.789447731755424, | |
| "eval_runtime": 23.1944, | |
| "eval_samples_per_second": 699.48, | |
| "eval_steps_per_second": 5.475, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 2.0055988802239554e-05, | |
| "loss": 0.4493, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "eval_accuracy": 0.7778599605522682, | |
| "eval_f1": 0.7918891407245614, | |
| "eval_loss": 0.6219201683998108, | |
| "eval_precision": 0.8239935574770723, | |
| "eval_qwk": 0.7029409846056511, | |
| "eval_recall": 0.7778599605522682, | |
| "eval_runtime": 23.0915, | |
| "eval_samples_per_second": 702.598, | |
| "eval_steps_per_second": 5.5, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 1.5066986602679465e-05, | |
| "loss": 0.4391, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "eval_accuracy": 0.784948224852071, | |
| "eval_f1": 0.7976824915929677, | |
| "eval_loss": 0.6451554298400879, | |
| "eval_precision": 0.8255295840982949, | |
| "eval_qwk": 0.7107576916204621, | |
| "eval_recall": 0.784948224852071, | |
| "eval_runtime": 23.2205, | |
| "eval_samples_per_second": 698.694, | |
| "eval_steps_per_second": 5.469, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 1.0067986402719456e-05, | |
| "loss": 0.3756, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "eval_accuracy": 0.7970290927021696, | |
| "eval_f1": 0.8070579315874782, | |
| "eval_loss": 0.6958814263343811, | |
| "eval_precision": 0.8265215874136934, | |
| "eval_qwk": 0.7249078215037359, | |
| "eval_recall": 0.7970290927021696, | |
| "eval_runtime": 23.1336, | |
| "eval_samples_per_second": 701.319, | |
| "eval_steps_per_second": 5.49, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "learning_rate": 5.068986202759449e-06, | |
| "loss": 0.3633, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "eval_accuracy": 0.7962894477317555, | |
| "eval_f1": 0.8063568557789076, | |
| "eval_loss": 0.6968616247177124, | |
| "eval_precision": 0.8256437219303169, | |
| "eval_qwk": 0.7253147876480203, | |
| "eval_recall": 0.7962894477317555, | |
| "eval_runtime": 23.1633, | |
| "eval_samples_per_second": 700.418, | |
| "eval_steps_per_second": 5.483, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "learning_rate": 6.998600279944012e-08, | |
| "loss": 0.3263, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "eval_accuracy": 0.7972140039447732, | |
| "eval_f1": 0.8072907591794813, | |
| "eval_loss": 0.7634969353675842, | |
| "eval_precision": 0.826968890246297, | |
| "eval_qwk": 0.7254593503280649, | |
| "eval_recall": 0.7972140039447732, | |
| "eval_runtime": 23.3008, | |
| "eval_samples_per_second": 696.286, | |
| "eval_steps_per_second": 5.45, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "step": 5001, | |
| "total_flos": 1.6838837781764506e+17, | |
| "train_loss": 0.4945967703420051, | |
| "train_runtime": 2688.9042, | |
| "train_samples_per_second": 238.063, | |
| "train_steps_per_second": 1.86 | |
| } | |
| ], | |
| "max_steps": 5001, | |
| "num_train_epochs": 5, | |
| "total_flos": 1.6838837781764506e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |