| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.4529900550842285, | |
| "eval_runtime": 3.9942, | |
| "eval_samples_per_second": 50.073, | |
| "eval_steps_per_second": 6.259, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 2.183900833129883, | |
| "eval_runtime": 4.5703, | |
| "eval_samples_per_second": 43.761, | |
| "eval_steps_per_second": 5.47, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 2.071335554122925, | |
| "eval_runtime": 3.8996, | |
| "eval_samples_per_second": 51.287, | |
| "eval_steps_per_second": 6.411, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 2.011983871459961, | |
| "eval_runtime": 6.9041, | |
| "eval_samples_per_second": 28.968, | |
| "eval_steps_per_second": 3.621, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 28.10818099975586, | |
| "learning_rate": 1e-05, | |
| "loss": 2.123, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 1.9926012754440308, | |
| "eval_runtime": 10.0553, | |
| "eval_samples_per_second": 19.89, | |
| "eval_steps_per_second": 2.486, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 1.9686007499694824, | |
| "eval_runtime": 4.4521, | |
| "eval_samples_per_second": 44.922, | |
| "eval_steps_per_second": 5.615, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 1.9791488647460938, | |
| "eval_runtime": 2.9406, | |
| "eval_samples_per_second": 68.014, | |
| "eval_steps_per_second": 8.502, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 1.9794409275054932, | |
| "eval_runtime": 2.4017, | |
| "eval_samples_per_second": 83.276, | |
| "eval_steps_per_second": 10.409, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 2.0054731369018555, | |
| "eval_runtime": 9.7036, | |
| "eval_samples_per_second": 20.611, | |
| "eval_steps_per_second": 2.576, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 27.559810638427734, | |
| "learning_rate": 0.0, | |
| "loss": 1.2718, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "total_flos": 248093683974144.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |