| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.02328830926874709, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004657661853749418, | |
| "eval_loss": 4.151027679443359, | |
| "eval_runtime": 56.7914, | |
| "eval_samples_per_second": 15.936, | |
| "eval_steps_per_second": 7.977, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002328830926874709, | |
| "grad_norm": 25.35050392150879, | |
| "learning_rate": 5e-05, | |
| "loss": 15.257, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004657661853749418, | |
| "grad_norm": 46.72882843017578, | |
| "learning_rate": 0.0001, | |
| "loss": 15.4873, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004657661853749418, | |
| "eval_loss": 3.0870630741119385, | |
| "eval_runtime": 57.6938, | |
| "eval_samples_per_second": 15.686, | |
| "eval_steps_per_second": 7.852, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0069864927806241265, | |
| "grad_norm": 36.1671028137207, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 12.1358, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.009315323707498836, | |
| "grad_norm": 34.362125396728516, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 11.3998, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.009315323707498836, | |
| "eval_loss": 2.732847213745117, | |
| "eval_runtime": 57.8298, | |
| "eval_samples_per_second": 15.649, | |
| "eval_steps_per_second": 7.833, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.011644154634373545, | |
| "grad_norm": 24.70348358154297, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 10.9537, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.013972985561248253, | |
| "grad_norm": 39.36613464355469, | |
| "learning_rate": 5e-05, | |
| "loss": 11.1584, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.013972985561248253, | |
| "eval_loss": 2.6284070014953613, | |
| "eval_runtime": 57.9092, | |
| "eval_samples_per_second": 15.628, | |
| "eval_steps_per_second": 7.823, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.016301816488122962, | |
| "grad_norm": 40.228370666503906, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 9.9753, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.018630647414997672, | |
| "grad_norm": 36.44306182861328, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 10.6079, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.018630647414997672, | |
| "eval_loss": 2.5764482021331787, | |
| "eval_runtime": 57.7996, | |
| "eval_samples_per_second": 15.658, | |
| "eval_steps_per_second": 7.837, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02095947834187238, | |
| "grad_norm": 36.49095153808594, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 10.6934, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.02328830926874709, | |
| "grad_norm": 39.59294128417969, | |
| "learning_rate": 0.0, | |
| "loss": 9.9457, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02328830926874709, | |
| "eval_loss": 2.5675735473632812, | |
| "eval_runtime": 57.7456, | |
| "eval_samples_per_second": 15.672, | |
| "eval_steps_per_second": 7.845, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "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": 8763348929740800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |