| { | |
| "best_metric": 0.823045267489712, | |
| "best_model_checkpoint": "distilbert-base-multilingual-cased-hyper-matt/run-ud8wy1bz/checkpoint-200", | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 200, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 2.0627684593200684, | |
| "learning_rate": 5.8944331187986266e-05, | |
| "loss": 0.5729, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 3.5791327953338623, | |
| "learning_rate": 5.7945274727172945e-05, | |
| "loss": 0.505, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 6.052925109863281, | |
| "learning_rate": 5.694621826635961e-05, | |
| "loss": 0.507, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 1.8351855278015137, | |
| "learning_rate": 5.594716180554629e-05, | |
| "loss": 0.4524, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 6.351097583770752, | |
| "learning_rate": 5.494810534473296e-05, | |
| "loss": 0.3062, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 1.3773590326309204, | |
| "learning_rate": 5.394904888391964e-05, | |
| "loss": 0.3473, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 3.009101629257202, | |
| "learning_rate": 5.2949992423106304e-05, | |
| "loss": 0.3905, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 3.680708646774292, | |
| "learning_rate": 5.195093596229298e-05, | |
| "loss": 0.3812, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 3.7381820678710938, | |
| "learning_rate": 5.0951879501479655e-05, | |
| "loss": 0.3667, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 4.209010124206543, | |
| "learning_rate": 4.995282304066633e-05, | |
| "loss": 0.2821, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.845, | |
| "eval_f1": 0.693069306930693, | |
| "eval_loss": 0.41840919852256775, | |
| "eval_precision": 0.8860759493670886, | |
| "eval_recall": 0.5691056910569106, | |
| "eval_runtime": 1.5344, | |
| "eval_samples_per_second": 260.687, | |
| "eval_steps_per_second": 16.293, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "grad_norm": 12.662829399108887, | |
| "learning_rate": 4.8953766579853e-05, | |
| "loss": 0.2514, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 4.311421871185303, | |
| "learning_rate": 4.795471011903968e-05, | |
| "loss": 0.2339, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "grad_norm": 7.38905668258667, | |
| "learning_rate": 4.695565365822635e-05, | |
| "loss": 0.2277, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "grad_norm": 2.4141809940338135, | |
| "learning_rate": 4.595659719741303e-05, | |
| "loss": 0.306, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 2.5219364166259766, | |
| "learning_rate": 4.49575407365997e-05, | |
| "loss": 0.2245, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 2.283900499343872, | |
| "learning_rate": 4.3958484275786364e-05, | |
| "loss": 0.2222, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "grad_norm": 7.031118392944336, | |
| "learning_rate": 4.295942781497304e-05, | |
| "loss": 0.3507, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "grad_norm": 3.3153152465820312, | |
| "learning_rate": 4.1960371354159715e-05, | |
| "loss": 0.305, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "grad_norm": 5.0271315574646, | |
| "learning_rate": 4.096131489334639e-05, | |
| "loss": 0.2648, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 2.9085686206817627, | |
| "learning_rate": 3.996225843253306e-05, | |
| "loss": 0.1931, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8925, | |
| "eval_f1": 0.823045267489712, | |
| "eval_loss": 0.30675894021987915, | |
| "eval_precision": 0.8333333333333334, | |
| "eval_recall": 0.8130081300813008, | |
| "eval_runtime": 1.5679, | |
| "eval_samples_per_second": 255.111, | |
| "eval_steps_per_second": 15.944, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 600, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 6, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 423630740901888.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": { | |
| "_wandb": {}, | |
| "assignments": {}, | |
| "learning_rate": 5.9943387648799594e-05, | |
| "metric": "eval/loss", | |
| "num_train_epochs": 6, | |
| "per_device_train_batch_size": 16, | |
| "seed": 31 | |
| } | |
| } | |