| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0007669446841146582, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.669446841146582e-05, | |
| "grad_norm": 0.2673566937446594, | |
| "learning_rate": 2e-05, | |
| "loss": 1.1216, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 7.669446841146582e-05, | |
| "eval_loss": 1.237951636314392, | |
| "eval_runtime": 287.6605, | |
| "eval_samples_per_second": 19.085, | |
| "eval_steps_per_second": 9.542, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00015338893682293164, | |
| "grad_norm": 0.28798797726631165, | |
| "learning_rate": 4e-05, | |
| "loss": 1.3984, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00023008340523439746, | |
| "grad_norm": 0.33419784903526306, | |
| "learning_rate": 6e-05, | |
| "loss": 1.3209, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00023008340523439746, | |
| "eval_loss": 1.2362302541732788, | |
| "eval_runtime": 287.0278, | |
| "eval_samples_per_second": 19.127, | |
| "eval_steps_per_second": 9.564, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0003067778736458633, | |
| "grad_norm": 0.31983721256256104, | |
| "learning_rate": 8e-05, | |
| "loss": 1.2404, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0003834723420573291, | |
| "grad_norm": 0.33530592918395996, | |
| "learning_rate": 0.0001, | |
| "loss": 1.0535, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0004601668104687949, | |
| "grad_norm": 0.43134039640426636, | |
| "learning_rate": 0.00012, | |
| "loss": 1.3889, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0004601668104687949, | |
| "eval_loss": 1.2214630842208862, | |
| "eval_runtime": 287.1863, | |
| "eval_samples_per_second": 19.117, | |
| "eval_steps_per_second": 9.558, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0005368612788802608, | |
| "grad_norm": 0.5418837070465088, | |
| "learning_rate": 0.00014, | |
| "loss": 1.5092, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0006135557472917265, | |
| "grad_norm": 0.31776854395866394, | |
| "learning_rate": 0.00016, | |
| "loss": 1.0678, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0006902502157031924, | |
| "grad_norm": 0.4036271870136261, | |
| "learning_rate": 0.00018, | |
| "loss": 1.1519, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0006902502157031924, | |
| "eval_loss": 1.161608338356018, | |
| "eval_runtime": 287.1988, | |
| "eval_samples_per_second": 19.116, | |
| "eval_steps_per_second": 9.558, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0007669446841146582, | |
| "grad_norm": 0.5535191893577576, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2668, | |
| "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": 3257466271825920.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |