| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.006837606837606838, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006837606837606838, | |
| "grad_norm": 1.0130343437194824, | |
| "learning_rate": 2e-05, | |
| "loss": 2.584, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006837606837606838, | |
| "eval_loss": 2.547212600708008, | |
| "eval_runtime": 36.006, | |
| "eval_samples_per_second": 17.108, | |
| "eval_steps_per_second": 8.554, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013675213675213675, | |
| "grad_norm": 1.0078518390655518, | |
| "learning_rate": 4e-05, | |
| "loss": 2.5779, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0020512820512820513, | |
| "grad_norm": 1.0306919813156128, | |
| "learning_rate": 6e-05, | |
| "loss": 2.531, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0020512820512820513, | |
| "eval_loss": 2.5370709896087646, | |
| "eval_runtime": 35.1306, | |
| "eval_samples_per_second": 17.535, | |
| "eval_steps_per_second": 8.767, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002735042735042735, | |
| "grad_norm": 0.9756653308868408, | |
| "learning_rate": 8e-05, | |
| "loss": 2.4736, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003418803418803419, | |
| "grad_norm": 1.171130895614624, | |
| "learning_rate": 0.0001, | |
| "loss": 2.5007, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0041025641025641026, | |
| "grad_norm": 1.2566697597503662, | |
| "learning_rate": 0.00012, | |
| "loss": 2.4883, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0041025641025641026, | |
| "eval_loss": 2.3956897258758545, | |
| "eval_runtime": 35.1302, | |
| "eval_samples_per_second": 17.535, | |
| "eval_steps_per_second": 8.767, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004786324786324786, | |
| "grad_norm": 0.9161843061447144, | |
| "learning_rate": 0.00014, | |
| "loss": 2.384, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00547008547008547, | |
| "grad_norm": 0.7558853626251221, | |
| "learning_rate": 0.00016, | |
| "loss": 2.256, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.006153846153846154, | |
| "grad_norm": 0.832514762878418, | |
| "learning_rate": 0.00018, | |
| "loss": 2.348, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006153846153846154, | |
| "eval_loss": 2.2804863452911377, | |
| "eval_runtime": 35.1448, | |
| "eval_samples_per_second": 17.527, | |
| "eval_steps_per_second": 8.764, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006837606837606838, | |
| "grad_norm": 1.2244415283203125, | |
| "learning_rate": 0.0002, | |
| "loss": 2.3463, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3699128496291840.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |