| { | |
| "best_metric": 0.5450584888458252, | |
| "best_model_checkpoint": "bert-finetuned-japanese-sentiment/checkpoint-474", | |
| "epoch": 6.0, | |
| "global_step": 2844, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8157940210817349, | |
| "eval_f1": 0.7272032479349645, | |
| "eval_loss": 0.5450584888458252, | |
| "eval_precision": 0.7101173006557553, | |
| "eval_recall": 0.7530568561281469, | |
| "eval_runtime": 84.5162, | |
| "eval_samples_per_second": 68.472, | |
| "eval_steps_per_second": 2.142, | |
| "step": 474 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 1.789029535864979e-05, | |
| "loss": 0.3251, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8261620874373596, | |
| "eval_f1": 0.7413523368662124, | |
| "eval_loss": 0.5779568552970886, | |
| "eval_precision": 0.7270594811474224, | |
| "eval_recall": 0.7636775589314819, | |
| "eval_runtime": 84.8717, | |
| "eval_samples_per_second": 68.185, | |
| "eval_steps_per_second": 2.133, | |
| "step": 948 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 1.578059071729958e-05, | |
| "loss": 0.2209, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8156212199758078, | |
| "eval_f1": 0.7283195708625394, | |
| "eval_loss": 0.6474512219429016, | |
| "eval_precision": 0.7140241339852836, | |
| "eval_recall": 0.7508970192749587, | |
| "eval_runtime": 84.4623, | |
| "eval_samples_per_second": 68.516, | |
| "eval_steps_per_second": 2.143, | |
| "step": 1422 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 1.3670886075949368e-05, | |
| "loss": 0.1636, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8107827890098497, | |
| "eval_f1": 0.7287062118529598, | |
| "eval_loss": 0.8141492605209351, | |
| "eval_precision": 0.7155878847825652, | |
| "eval_recall": 0.7576050434353393, | |
| "eval_runtime": 84.7752, | |
| "eval_samples_per_second": 68.263, | |
| "eval_steps_per_second": 2.135, | |
| "step": 1896 | |
| }, | |
| { | |
| "epoch": 4.22, | |
| "learning_rate": 1.1561181434599158e-05, | |
| "loss": 0.114, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.8123379989631934, | |
| "eval_f1": 0.7293509360093955, | |
| "eval_loss": 0.9643709063529968, | |
| "eval_precision": 0.7212611749404146, | |
| "eval_recall": 0.7546179503626446, | |
| "eval_runtime": 84.2684, | |
| "eval_samples_per_second": 68.673, | |
| "eval_steps_per_second": 2.148, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 5.27, | |
| "learning_rate": 9.451476793248946e-06, | |
| "loss": 0.0876, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.8132020044928288, | |
| "eval_f1": 0.7284553808496855, | |
| "eval_loss": 1.028875708580017, | |
| "eval_precision": 0.7124400203988301, | |
| "eval_recall": 0.7560308594078071, | |
| "eval_runtime": 84.9239, | |
| "eval_samples_per_second": 68.143, | |
| "eval_steps_per_second": 2.131, | |
| "step": 2844 | |
| } | |
| ], | |
| "max_steps": 4740, | |
| "num_train_epochs": 10, | |
| "total_flos": 1.074326001547428e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |