| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.987012987012987, | |
| "eval_steps": 500, | |
| "global_step": 38, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 5e-05, | |
| "loss": 1.8487, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00019957341762950344, | |
| "loss": 1.5092, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00018502171357296144, | |
| "loss": 0.9757, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.0001526432162877356, | |
| "loss": 0.8052, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.00010922683594633021, | |
| "loss": 0.768, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 6.387583338128471e-05, | |
| "loss": 0.6994, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 2.6099108277934103e-05, | |
| "loss": 0.7122, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 3.817435682718096e-06, | |
| "loss": 0.6894, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_loss": 0.6976714730262756, | |
| "eval_runtime": 38.531, | |
| "eval_samples_per_second": 4.308, | |
| "eval_steps_per_second": 0.545, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "step": 38, | |
| "total_flos": 1.335946087759872e+16, | |
| "train_loss": 0.8748512268066406, | |
| "train_runtime": 281.6973, | |
| "train_samples_per_second": 1.09, | |
| "train_steps_per_second": 0.135 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 38, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "total_flos": 1.335946087759872e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |