| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9926289926289926, | |
| "eval_steps": 500, | |
| "global_step": 101, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00015, | |
| "loss": 3.3956, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0004, | |
| "loss": 1.8859, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.0004932612176449559, | |
| "loss": 1.1419, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.0004533880175657419, | |
| "loss": 1.0646, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.00038330110820042286, | |
| "loss": 1.0495, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.00029341204441673266, | |
| "loss": 1.0399, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.00019707403194264738, | |
| "loss": 1.0655, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.0001085982811283654, | |
| "loss": 1.037, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 4.112804714676593e-05, | |
| "loss": 1.028, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 4.686172343153827e-06, | |
| "loss": 1.0416, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "step": 101, | |
| "total_flos": 9.277589981180723e+16, | |
| "train_loss": 1.3724445730152697, | |
| "train_runtime": 997.8371, | |
| "train_samples_per_second": 3.26, | |
| "train_steps_per_second": 0.101 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 101, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "total_flos": 9.277589981180723e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |