| { |
| "best_metric": 0.940613155334921, |
| "best_model_checkpoint": "model_saves/roberta-large_lemon-spell_10k_1_p3/checkpoint-268", |
| "epoch": 7.0, |
| "global_step": 1876, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.940613155334921, |
| "eval_loss": 0.4339312016963959, |
| "eval_runtime": 3.4077, |
| "eval_samples_per_second": 1285.919, |
| "eval_steps_per_second": 10.271, |
| "step": 268 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.940512528091772, |
| "eval_loss": 0.4440305829048157, |
| "eval_runtime": 3.4113, |
| "eval_samples_per_second": 1284.557, |
| "eval_steps_per_second": 10.26, |
| "step": 536 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9396907389393888, |
| "eval_loss": 0.47240737080574036, |
| "eval_runtime": 3.4072, |
| "eval_samples_per_second": 1286.11, |
| "eval_steps_per_second": 10.272, |
| "step": 804 |
| }, |
| { |
| "epoch": 3.73, |
| "learning_rate": 1e-05, |
| "loss": 0.3147, |
| "step": 1000 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.9389416250181688, |
| "eval_loss": 0.5123679637908936, |
| "eval_runtime": 3.4154, |
| "eval_samples_per_second": 1283.018, |
| "eval_steps_per_second": 10.248, |
| "step": 1072 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.9388409977750198, |
| "eval_loss": 0.549247682094574, |
| "eval_runtime": 3.4089, |
| "eval_samples_per_second": 1285.444, |
| "eval_steps_per_second": 10.267, |
| "step": 1340 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.9379353525866791, |
| "eval_loss": 0.5995227694511414, |
| "eval_runtime": 3.412, |
| "eval_samples_per_second": 1284.273, |
| "eval_steps_per_second": 10.258, |
| "step": 1608 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_accuracy": 0.9379744854034593, |
| "eval_loss": 0.6558637619018555, |
| "eval_runtime": 3.4474, |
| "eval_samples_per_second": 1271.12, |
| "eval_steps_per_second": 10.153, |
| "step": 1876 |
| }, |
| { |
| "epoch": 7.0, |
| "step": 1876, |
| "total_flos": 2.467935271727923e+16, |
| "train_loss": 0.0685914208385736, |
| "train_runtime": 255.862, |
| "train_samples_per_second": 2011.084, |
| "train_steps_per_second": 15.712 |
| } |
| ], |
| "max_steps": 4020, |
| "num_train_epochs": 15, |
| "total_flos": 2.467935271727923e+16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
