| { | |
| "best_metric": 0.736704788874575, | |
| "best_model_checkpoint": "trained/hebban-reviews5/bert-base-dutch-cased/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": 4.502099580083983e-05, | |
| "loss": 1.0628, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_accuracy": 0.5249013806706114, | |
| "eval_f1": 0.5054676750370117, | |
| "eval_loss": 0.972381055355072, | |
| "eval_precision": 0.5814795813726913, | |
| "eval_qwk": 0.675301288961484, | |
| "eval_recall": 0.5249013806706114, | |
| "eval_runtime": 23.7597, | |
| "eval_samples_per_second": 682.838, | |
| "eval_steps_per_second": 5.345, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 4.003199360127974e-05, | |
| "loss": 0.9275, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_accuracy": 0.5803747534516766, | |
| "eval_f1": 0.5800698497775874, | |
| "eval_loss": 0.9043073654174805, | |
| "eval_precision": 0.5998353070803661, | |
| "eval_qwk": 0.6907240399456925, | |
| "eval_recall": 0.5803747534516766, | |
| "eval_runtime": 23.5439, | |
| "eval_samples_per_second": 689.096, | |
| "eval_steps_per_second": 5.394, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 3.5032993401319734e-05, | |
| "loss": 0.7905, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "eval_accuracy": 0.5796351084812623, | |
| "eval_f1": 0.5676464095326524, | |
| "eval_loss": 1.034230351448059, | |
| "eval_precision": 0.6112897936486814, | |
| "eval_qwk": 0.7101436512464515, | |
| "eval_recall": 0.5796351084812623, | |
| "eval_runtime": 23.4901, | |
| "eval_samples_per_second": 690.673, | |
| "eval_steps_per_second": 5.407, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 3.0033993201359727e-05, | |
| "loss": 0.752, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "eval_accuracy": 0.6031188362919132, | |
| "eval_f1": 0.6016431505000863, | |
| "eval_loss": 0.9555270671844482, | |
| "eval_precision": 0.6136242524571098, | |
| "eval_qwk": 0.736704788874575, | |
| "eval_recall": 0.6031188362919132, | |
| "eval_runtime": 23.517, | |
| "eval_samples_per_second": 689.883, | |
| "eval_steps_per_second": 5.4, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 2.503499300139972e-05, | |
| "loss": 0.6586, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "eval_accuracy": 0.6086661735700197, | |
| "eval_f1": 0.6013743918352756, | |
| "eval_loss": 1.2705243825912476, | |
| "eval_precision": 0.6225560419622415, | |
| "eval_qwk": 0.729031471959436, | |
| "eval_recall": 0.6086661735700197, | |
| "eval_runtime": 23.6098, | |
| "eval_samples_per_second": 687.171, | |
| "eval_steps_per_second": 5.379, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 2.0035992801439712e-05, | |
| "loss": 0.553, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "eval_accuracy": 0.6136587771203156, | |
| "eval_f1": 0.6146337033967545, | |
| "eval_loss": 1.228061556816101, | |
| "eval_precision": 0.6211825781857317, | |
| "eval_qwk": 0.7324255391770746, | |
| "eval_recall": 0.6136587771203156, | |
| "eval_runtime": 23.6608, | |
| "eval_samples_per_second": 685.691, | |
| "eval_steps_per_second": 5.368, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 1.5036992601479705e-05, | |
| "loss": 0.5431, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "eval_accuracy": 0.621733234714004, | |
| "eval_f1": 0.6208966398212863, | |
| "eval_loss": 1.3134678602218628, | |
| "eval_precision": 0.6258367808640274, | |
| "eval_qwk": 0.735849167037898, | |
| "eval_recall": 0.621733234714004, | |
| "eval_runtime": 23.6119, | |
| "eval_samples_per_second": 687.111, | |
| "eval_steps_per_second": 5.379, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 1.0037992401519696e-05, | |
| "loss": 0.4393, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "eval_accuracy": 0.6137820512820513, | |
| "eval_f1": 0.6131333532641816, | |
| "eval_loss": 1.4117528200149536, | |
| "eval_precision": 0.6232629307358518, | |
| "eval_qwk": 0.7288962630201523, | |
| "eval_recall": 0.6137820512820513, | |
| "eval_runtime": 23.5573, | |
| "eval_samples_per_second": 688.704, | |
| "eval_steps_per_second": 5.391, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "learning_rate": 5.038992201559688e-06, | |
| "loss": 0.4343, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "eval_accuracy": 0.6222263313609467, | |
| "eval_f1": 0.621745253450685, | |
| "eval_loss": 1.4303702116012573, | |
| "eval_precision": 0.6274850559871306, | |
| "eval_qwk": 0.7324157916744618, | |
| "eval_recall": 0.6222263313609467, | |
| "eval_runtime": 23.6811, | |
| "eval_samples_per_second": 685.102, | |
| "eval_steps_per_second": 5.363, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "learning_rate": 3.9992001599680065e-08, | |
| "loss": 0.3742, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "eval_accuracy": 0.6243836291913215, | |
| "eval_f1": 0.6243487767060615, | |
| "eval_loss": 1.5099977254867554, | |
| "eval_precision": 0.6284527038156085, | |
| "eval_qwk": 0.7324197971005459, | |
| "eval_recall": 0.6243836291913215, | |
| "eval_runtime": 23.6109, | |
| "eval_samples_per_second": 687.14, | |
| "eval_steps_per_second": 5.379, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "step": 5001, | |
| "total_flos": 1.6839139993111757e+17, | |
| "train_loss": 0.6534907585846093, | |
| "train_runtime": 2624.2686, | |
| "train_samples_per_second": 243.926, | |
| "train_steps_per_second": 1.906 | |
| } | |
| ], | |
| "max_steps": 5001, | |
| "num_train_epochs": 5, | |
| "total_flos": 1.6839139993111757e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |