| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 350, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 0.5477, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 0.5383, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 3e-06, | |
| "loss": 0.5464, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7685714285714286, | |
| "eval_f1": 0.8691437802907915, | |
| "eval_loss": 0.5194858312606812, | |
| "eval_runtime": 10.6792, | |
| "eval_samples_per_second": 65.548, | |
| "eval_steps_per_second": 4.12, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.5248, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5475, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 6e-06, | |
| "loss": 0.5114, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 7e-06, | |
| "loss": 0.5552, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.7685714285714286, | |
| "eval_f1": 0.8691437802907915, | |
| "eval_loss": 0.525272011756897, | |
| "eval_runtime": 15.9825, | |
| "eval_samples_per_second": 43.798, | |
| "eval_steps_per_second": 2.753, | |
| "step": 350 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 525, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 826596567613440.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |