| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.8453333333333335, | |
| "eval_steps": 100, | |
| "global_step": 1600, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2192, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_runtime": 1408.0486, | |
| "eval_samples_per_second": 1.776, | |
| "eval_steps_per_second": 0.222, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0001, | |
| "loss": 0.6611, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_runtime": 1407.4105, | |
| "eval_samples_per_second": 1.776, | |
| "eval_steps_per_second": 0.222, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0001, | |
| "loss": 0.6207, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_runtime": 1405.0607, | |
| "eval_samples_per_second": 1.779, | |
| "eval_steps_per_second": 0.223, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.0001, | |
| "loss": 0.6162, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_runtime": 1408.649, | |
| "eval_samples_per_second": 1.775, | |
| "eval_steps_per_second": 0.222, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.0001, | |
| "loss": 0.6019, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "eval_runtime": 1403.5405, | |
| "eval_samples_per_second": 1.781, | |
| "eval_steps_per_second": 0.223, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.0001, | |
| "loss": 0.5993, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "eval_runtime": 1401.9739, | |
| "eval_samples_per_second": 1.783, | |
| "eval_steps_per_second": 0.223, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 0.0001, | |
| "loss": 0.5692, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "eval_runtime": 1404.1983, | |
| "eval_samples_per_second": 1.78, | |
| "eval_steps_per_second": 0.223, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 0.0001, | |
| "loss": 0.5709, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "eval_runtime": 1405.1361, | |
| "eval_samples_per_second": 1.779, | |
| "eval_steps_per_second": 0.223, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.0001, | |
| "loss": 0.5724, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "eval_runtime": 1402.9928, | |
| "eval_samples_per_second": 1.782, | |
| "eval_steps_per_second": 0.223, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 4.5352669742913644e-05, | |
| "loss": 0.5422, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "eval_runtime": 1405.4811, | |
| "eval_samples_per_second": 1.779, | |
| "eval_steps_per_second": 0.223, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 3.8760711931443636e-05, | |
| "loss": 0.5561, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "eval_runtime": 1406.3866, | |
| "eval_samples_per_second": 1.778, | |
| "eval_steps_per_second": 0.223, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 3.2168754119973635e-05, | |
| "loss": 0.5347, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "eval_runtime": 1399.3753, | |
| "eval_samples_per_second": 1.787, | |
| "eval_steps_per_second": 0.224, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 2.5576796308503624e-05, | |
| "loss": 0.5479, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "eval_runtime": 1405.5826, | |
| "eval_samples_per_second": 1.779, | |
| "eval_steps_per_second": 0.223, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 1.898483849703362e-05, | |
| "loss": 0.5417, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "eval_runtime": 1403.4926, | |
| "eval_samples_per_second": 1.781, | |
| "eval_steps_per_second": 0.223, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 1.2392880685563612e-05, | |
| "loss": 0.5481, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "eval_runtime": 1405.6755, | |
| "eval_samples_per_second": 1.779, | |
| "eval_steps_per_second": 0.223, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 5.800922874093606e-06, | |
| "loss": 0.5459, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "eval_runtime": 1404.9366, | |
| "eval_samples_per_second": 1.779, | |
| "eval_steps_per_second": 0.223, | |
| "step": 1600 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 1686, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "total_flos": 6.166502675841024e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |