| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0392156862745098, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00392156862745098, | |
| "grad_norm": 0.5314080715179443, | |
| "learning_rate": 2e-05, | |
| "loss": 2.5509, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00392156862745098, | |
| "eval_loss": 3.2287890911102295, | |
| "eval_runtime": 4.4903, | |
| "eval_samples_per_second": 24.052, | |
| "eval_steps_per_second": 12.026, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00784313725490196, | |
| "grad_norm": 0.647420346736908, | |
| "learning_rate": 4e-05, | |
| "loss": 3.0168, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.011764705882352941, | |
| "grad_norm": 0.6892508268356323, | |
| "learning_rate": 6e-05, | |
| "loss": 3.2917, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.011764705882352941, | |
| "eval_loss": 3.221489429473877, | |
| "eval_runtime": 3.3195, | |
| "eval_samples_per_second": 32.535, | |
| "eval_steps_per_second": 16.268, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01568627450980392, | |
| "grad_norm": 0.7024323344230652, | |
| "learning_rate": 8e-05, | |
| "loss": 3.1428, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0196078431372549, | |
| "grad_norm": 0.8515894412994385, | |
| "learning_rate": 0.0001, | |
| "loss": 3.3058, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.023529411764705882, | |
| "grad_norm": 0.9109193086624146, | |
| "learning_rate": 0.00012, | |
| "loss": 3.2435, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.023529411764705882, | |
| "eval_loss": 3.137112617492676, | |
| "eval_runtime": 3.3297, | |
| "eval_samples_per_second": 32.436, | |
| "eval_steps_per_second": 16.218, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.027450980392156862, | |
| "grad_norm": 1.1132946014404297, | |
| "learning_rate": 0.00014, | |
| "loss": 3.0566, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.03137254901960784, | |
| "grad_norm": 0.756723165512085, | |
| "learning_rate": 0.00016, | |
| "loss": 3.0836, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03529411764705882, | |
| "grad_norm": 0.6867743730545044, | |
| "learning_rate": 0.00018, | |
| "loss": 3.1108, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03529411764705882, | |
| "eval_loss": 2.9235777854919434, | |
| "eval_runtime": 3.3689, | |
| "eval_samples_per_second": 32.058, | |
| "eval_steps_per_second": 16.029, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0392156862745098, | |
| "grad_norm": 0.8533226251602173, | |
| "learning_rate": 0.0002, | |
| "loss": 2.8134, | |
| "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": 1647822923366400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |