| { | |
| "best_metric": 1.8282623291015625, | |
| "best_model_checkpoint": "./outputs/checkpoint-1000", | |
| "epoch": 0.7285974499089253, | |
| "eval_steps": 100, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0002, | |
| "loss": 2.2671, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 2.1813676357269287, | |
| "eval_runtime": 549.6637, | |
| "eval_samples_per_second": 11.414, | |
| "eval_steps_per_second": 1.428, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0002, | |
| "loss": 2.1547, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_loss": 2.131509304046631, | |
| "eval_runtime": 549.883, | |
| "eval_samples_per_second": 11.41, | |
| "eval_steps_per_second": 1.428, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0002, | |
| "loss": 2.1088, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_loss": 2.0894575119018555, | |
| "eval_runtime": 550.3941, | |
| "eval_samples_per_second": 11.399, | |
| "eval_steps_per_second": 1.426, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.0002, | |
| "loss": 2.0681, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_loss": 2.0435657501220703, | |
| "eval_runtime": 550.6916, | |
| "eval_samples_per_second": 11.393, | |
| "eval_steps_per_second": 1.425, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0002, | |
| "loss": 2.0241, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": 2.0031208992004395, | |
| "eval_runtime": 550.5855, | |
| "eval_samples_per_second": 11.395, | |
| "eval_steps_per_second": 1.426, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9755, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 1.9635978937149048, | |
| "eval_runtime": 552.4575, | |
| "eval_samples_per_second": 11.357, | |
| "eval_steps_per_second": 1.421, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9447, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 1.9280308485031128, | |
| "eval_runtime": 552.7859, | |
| "eval_samples_per_second": 11.35, | |
| "eval_steps_per_second": 1.42, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9024, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_loss": 1.8917897939682007, | |
| "eval_runtime": 553.0559, | |
| "eval_samples_per_second": 11.344, | |
| "eval_steps_per_second": 1.419, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8626, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": 1.8584532737731934, | |
| "eval_runtime": 554.4522, | |
| "eval_samples_per_second": 11.316, | |
| "eval_steps_per_second": 1.416, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8397, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_loss": 1.8282623291015625, | |
| "eval_runtime": 554.0635, | |
| "eval_samples_per_second": 11.324, | |
| "eval_steps_per_second": 1.417, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 4116, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "total_flos": 2.6035701176578867e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |