| { | |
| "best_metric": 0.9595484477892756, | |
| "best_model_checkpoint": "/content/drive/MyDrive/SODUCO/article_das_2022/43-camembert_pretrained_finetuned_pero/checkpoint-1500", | |
| "epoch": 3.9893617021276597, | |
| "global_step": 1500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.27, | |
| "eval_accuracy": 0.9711394302848576, | |
| "eval_f1": 0.9418582912693962, | |
| "eval_loss": 0.24740596115589142, | |
| "eval_precision": 0.9343471810089021, | |
| "eval_recall": 0.9494911421032793, | |
| "eval_runtime": 2.7876, | |
| "eval_samples_per_second": 239.631, | |
| "eval_steps_per_second": 15.067, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_accuracy": 0.9741379310344828, | |
| "eval_f1": 0.950751879699248, | |
| "eval_loss": 0.15050481259822845, | |
| "eval_precision": 0.9482564679415073, | |
| "eval_recall": 0.9532604598567659, | |
| "eval_runtime": 2.5926, | |
| "eval_samples_per_second": 257.656, | |
| "eval_steps_per_second": 16.2, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_accuracy": 0.9730134932533733, | |
| "eval_f1": 0.9475262368815591, | |
| "eval_loss": 0.12827223539352417, | |
| "eval_precision": 0.9422288483041371, | |
| "eval_recall": 0.9528835280814173, | |
| "eval_runtime": 2.73, | |
| "eval_samples_per_second": 244.686, | |
| "eval_steps_per_second": 15.384, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "eval_accuracy": 0.9710144927536232, | |
| "eval_f1": 0.9431689875799775, | |
| "eval_loss": 0.1230660155415535, | |
| "eval_precision": 0.9417512213453589, | |
| "eval_recall": 0.9445910290237467, | |
| "eval_runtime": 2.7678, | |
| "eval_samples_per_second": 241.348, | |
| "eval_steps_per_second": 15.175, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 9e-05, | |
| "loss": 0.2505, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "eval_accuracy": 0.9786356821589205, | |
| "eval_f1": 0.9521306551529942, | |
| "eval_loss": 0.08949972689151764, | |
| "eval_precision": 0.9483919222139118, | |
| "eval_recall": 0.9558989822842066, | |
| "eval_runtime": 2.9407, | |
| "eval_samples_per_second": 227.154, | |
| "eval_steps_per_second": 14.282, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "eval_accuracy": 0.9768865567216392, | |
| "eval_f1": 0.9537420082737871, | |
| "eval_loss": 0.09133146703243256, | |
| "eval_precision": 0.951594746716698, | |
| "eval_recall": 0.9558989822842066, | |
| "eval_runtime": 2.8849, | |
| "eval_samples_per_second": 231.55, | |
| "eval_steps_per_second": 14.559, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "eval_accuracy": 0.9765117441279361, | |
| "eval_f1": 0.9579800263802524, | |
| "eval_loss": 0.09044157713651657, | |
| "eval_precision": 0.9577995478522984, | |
| "eval_recall": 0.9581605729362985, | |
| "eval_runtime": 2.8752, | |
| "eval_samples_per_second": 232.332, | |
| "eval_steps_per_second": 14.608, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "eval_accuracy": 0.9801349325337332, | |
| "eval_f1": 0.9586621570838031, | |
| "eval_loss": 0.07938132435083389, | |
| "eval_precision": 0.9557886849007119, | |
| "eval_recall": 0.9615529589144365, | |
| "eval_runtime": 2.8692, | |
| "eval_samples_per_second": 232.816, | |
| "eval_steps_per_second": 14.638, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "eval_accuracy": 0.9771364317841079, | |
| "eval_f1": 0.9548872180451128, | |
| "eval_loss": 0.09603337943553925, | |
| "eval_precision": 0.9523809523809523, | |
| "eval_recall": 0.9574067093856012, | |
| "eval_runtime": 2.8538, | |
| "eval_samples_per_second": 234.072, | |
| "eval_steps_per_second": 14.717, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0748, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "eval_accuracy": 0.9761369315342329, | |
| "eval_f1": 0.9575871819038644, | |
| "eval_loss": 0.09003584831953049, | |
| "eval_precision": 0.9577677224736049, | |
| "eval_recall": 0.9574067093856012, | |
| "eval_runtime": 2.9061, | |
| "eval_samples_per_second": 229.858, | |
| "eval_steps_per_second": 14.452, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "eval_accuracy": 0.9730134932533733, | |
| "eval_f1": 0.954383330204618, | |
| "eval_loss": 0.10545289516448975, | |
| "eval_precision": 0.9506357516828721, | |
| "eval_recall": 0.9581605729362985, | |
| "eval_runtime": 2.9384, | |
| "eval_samples_per_second": 227.334, | |
| "eval_steps_per_second": 14.293, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "eval_accuracy": 0.9761369315342329, | |
| "eval_f1": 0.9593220338983051, | |
| "eval_loss": 0.099028080701828, | |
| "eval_precision": 0.9585999247271358, | |
| "eval_recall": 0.9600452318130418, | |
| "eval_runtime": 3.0033, | |
| "eval_samples_per_second": 222.419, | |
| "eval_steps_per_second": 13.984, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 3.46, | |
| "eval_accuracy": 0.9752623688155923, | |
| "eval_f1": 0.9561782960315968, | |
| "eval_loss": 0.09300831705331802, | |
| "eval_precision": 0.9542042042042042, | |
| "eval_recall": 0.9581605729362985, | |
| "eval_runtime": 2.8431, | |
| "eval_samples_per_second": 234.956, | |
| "eval_steps_per_second": 14.773, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "eval_accuracy": 0.9775112443778111, | |
| "eval_f1": 0.9578471960858111, | |
| "eval_loss": 0.0967017412185669, | |
| "eval_precision": 0.9564073656520106, | |
| "eval_recall": 0.9592913682623445, | |
| "eval_runtime": 2.8669, | |
| "eval_samples_per_second": 233.003, | |
| "eval_steps_per_second": 14.65, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "learning_rate": 7e-05, | |
| "loss": 0.0497, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "eval_accuracy": 0.9776361819090454, | |
| "eval_f1": 0.9595484477892756, | |
| "eval_loss": 0.0839652568101883, | |
| "eval_precision": 0.9579263711495116, | |
| "eval_recall": 0.9611760271390878, | |
| "eval_runtime": 2.8628, | |
| "eval_samples_per_second": 233.335, | |
| "eval_steps_per_second": 14.671, | |
| "step": 1500 | |
| } | |
| ], | |
| "max_steps": 5000, | |
| "num_train_epochs": 14, | |
| "total_flos": 592464605771736.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |