| { | |
| "best_metric": 0.0, | |
| "best_model_checkpoint": "/scratch/mrahma45/pixel/finetuned_models/mbert/mbert-base-finetuned-masakhaner-amh/checkpoint-1000", | |
| "epoch": 36.36363636363637, | |
| "global_step": 2000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.64, | |
| "eval_accuracy_score": 0.8425259792166268, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.7014185786247253, | |
| "eval_precision": 0.0, | |
| "eval_recall": 0.0, | |
| "eval_runtime": 3.5028, | |
| "eval_samples_per_second": 71.372, | |
| "eval_steps_per_second": 9.136, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 7.27, | |
| "eval_accuracy_score": 0.8425259792166268, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.6971796751022339, | |
| "eval_precision": 0.0, | |
| "eval_recall": 0.0, | |
| "eval_runtime": 3.4905, | |
| "eval_samples_per_second": 71.623, | |
| "eval_steps_per_second": 9.168, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 9.09, | |
| "learning_rate": 4.865771812080537e-05, | |
| "loss": 0.7264, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 10.91, | |
| "eval_accuracy_score": 0.8425259792166268, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.698952853679657, | |
| "eval_precision": 0.0, | |
| "eval_recall": 0.0, | |
| "eval_runtime": 3.4754, | |
| "eval_samples_per_second": 71.935, | |
| "eval_steps_per_second": 9.208, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 14.55, | |
| "eval_accuracy_score": 0.8425259792166268, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.708954393863678, | |
| "eval_precision": 0.0, | |
| "eval_recall": 0.0, | |
| "eval_runtime": 3.4855, | |
| "eval_samples_per_second": 71.726, | |
| "eval_steps_per_second": 9.181, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 18.18, | |
| "learning_rate": 4.697986577181208e-05, | |
| "loss": 0.6917, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 18.18, | |
| "eval_accuracy_score": 0.8425259792166268, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.6995488405227661, | |
| "eval_precision": 0.0, | |
| "eval_recall": 0.0, | |
| "eval_runtime": 3.4744, | |
| "eval_samples_per_second": 71.955, | |
| "eval_steps_per_second": 9.21, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 21.82, | |
| "eval_accuracy_score": 0.8425259792166268, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.698596179485321, | |
| "eval_precision": 0.0, | |
| "eval_recall": 0.0, | |
| "eval_runtime": 3.4893, | |
| "eval_samples_per_second": 71.648, | |
| "eval_steps_per_second": 9.171, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 25.45, | |
| "eval_accuracy_score": 0.8425259792166268, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.7002435326576233, | |
| "eval_precision": 0.0, | |
| "eval_recall": 0.0, | |
| "eval_runtime": 3.4772, | |
| "eval_samples_per_second": 71.897, | |
| "eval_steps_per_second": 9.203, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 27.27, | |
| "learning_rate": 4.530201342281879e-05, | |
| "loss": 0.6883, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 29.09, | |
| "eval_accuracy_score": 0.8425259792166268, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.7004148364067078, | |
| "eval_precision": 0.0, | |
| "eval_recall": 0.0, | |
| "eval_runtime": 3.4851, | |
| "eval_samples_per_second": 71.734, | |
| "eval_steps_per_second": 9.182, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 32.73, | |
| "eval_accuracy_score": 0.8425259792166268, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.6990127563476562, | |
| "eval_precision": 0.0, | |
| "eval_recall": 0.0, | |
| "eval_runtime": 3.4756, | |
| "eval_samples_per_second": 71.93, | |
| "eval_steps_per_second": 9.207, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 36.36, | |
| "learning_rate": 4.36241610738255e-05, | |
| "loss": 0.6889, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 36.36, | |
| "eval_accuracy_score": 0.8425259792166268, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.6986844539642334, | |
| "eval_precision": 0.0, | |
| "eval_recall": 0.0, | |
| "eval_runtime": 3.4585, | |
| "eval_samples_per_second": 72.285, | |
| "eval_steps_per_second": 9.253, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 36.36, | |
| "step": 2000, | |
| "total_flos": 8314988993187840.0, | |
| "train_loss": 0.6987884674072266, | |
| "train_runtime": 2254.7389, | |
| "train_samples_per_second": 212.885, | |
| "train_steps_per_second": 6.653 | |
| } | |
| ], | |
| "max_steps": 15000, | |
| "num_train_epochs": 273, | |
| "total_flos": 8314988993187840.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |