| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0002701041926923311, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.7010419269233105e-05, | |
| "grad_norm": 0.8623080253601074, | |
| "learning_rate": 2e-05, | |
| "loss": 2.5139, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.7010419269233105e-05, | |
| "eval_loss": 2.4878077507019043, | |
| "eval_runtime": 857.3558, | |
| "eval_samples_per_second": 18.183, | |
| "eval_steps_per_second": 9.092, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 5.402083853846621e-05, | |
| "grad_norm": 1.2046571969985962, | |
| "learning_rate": 4e-05, | |
| "loss": 2.4404, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 8.103125780769932e-05, | |
| "grad_norm": 1.2379217147827148, | |
| "learning_rate": 6e-05, | |
| "loss": 2.4415, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 8.103125780769932e-05, | |
| "eval_loss": 2.4826765060424805, | |
| "eval_runtime": 850.2424, | |
| "eval_samples_per_second": 18.335, | |
| "eval_steps_per_second": 9.168, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00010804167707693242, | |
| "grad_norm": 1.1288055181503296, | |
| "learning_rate": 8e-05, | |
| "loss": 2.4938, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00013505209634616554, | |
| "grad_norm": 1.436876893043518, | |
| "learning_rate": 0.0001, | |
| "loss": 2.3032, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00016206251561539864, | |
| "grad_norm": 1.3907028436660767, | |
| "learning_rate": 0.00012, | |
| "loss": 2.3267, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00016206251561539864, | |
| "eval_loss": 2.3965697288513184, | |
| "eval_runtime": 849.1995, | |
| "eval_samples_per_second": 18.357, | |
| "eval_steps_per_second": 9.179, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00018907293488463174, | |
| "grad_norm": 1.208445429801941, | |
| "learning_rate": 0.00014, | |
| "loss": 2.1013, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00021608335415386484, | |
| "grad_norm": 1.384195327758789, | |
| "learning_rate": 0.00016, | |
| "loss": 2.3522, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00024309377342309797, | |
| "grad_norm": 1.4619507789611816, | |
| "learning_rate": 0.00018, | |
| "loss": 2.3595, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00024309377342309797, | |
| "eval_loss": 2.1295883655548096, | |
| "eval_runtime": 849.1542, | |
| "eval_samples_per_second": 18.358, | |
| "eval_steps_per_second": 9.18, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0002701041926923311, | |
| "grad_norm": 1.3736051321029663, | |
| "learning_rate": 0.0002, | |
| "loss": 2.202, | |
| "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": 3652889390088192.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |