| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.02433682161109759, | |
| "eval_steps": 13, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004867364322219518, | |
| "eval_loss": 0.4373247027397156, | |
| "eval_runtime": 16.8029, | |
| "eval_samples_per_second": 51.479, | |
| "eval_steps_per_second": 25.769, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004867364322219518, | |
| "grad_norm": 0.5877466797828674, | |
| "learning_rate": 0.00019396926207859084, | |
| "loss": 0.3337, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006327573618885374, | |
| "eval_loss": 0.3863282799720764, | |
| "eval_runtime": 15.2093, | |
| "eval_samples_per_second": 56.873, | |
| "eval_steps_per_second": 28.469, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.009734728644439037, | |
| "grad_norm": 0.3252217471599579, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.3332, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.012655147237770748, | |
| "eval_loss": 0.38014551997184753, | |
| "eval_runtime": 15.2871, | |
| "eval_samples_per_second": 56.584, | |
| "eval_steps_per_second": 28.325, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.014602092966658554, | |
| "grad_norm": 1.1123405694961548, | |
| "learning_rate": 8.263518223330697e-05, | |
| "loss": 0.3309, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01898272085665612, | |
| "eval_loss": 0.37899667024612427, | |
| "eval_runtime": 15.1994, | |
| "eval_samples_per_second": 56.91, | |
| "eval_steps_per_second": 28.488, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.019469457288878073, | |
| "grad_norm": 0.4495070278644562, | |
| "learning_rate": 2.339555568810221e-05, | |
| "loss": 0.3451, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02433682161109759, | |
| "grad_norm": 0.503346860408783, | |
| "learning_rate": 0.0, | |
| "loss": 0.2631, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2467969653276672.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |