| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.5, | |
| "eval_steps": 500, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05555555555555555, | |
| "grad_norm": 0.19568008184432983, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 0.743, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.1111111111111111, | |
| "grad_norm": 0.1960965245962143, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 0.9395, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.16666666666666666, | |
| "grad_norm": 0.19083181023597717, | |
| "learning_rate": 3e-06, | |
| "loss": 0.9456, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.2222222222222222, | |
| "grad_norm": 0.21329426765441895, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.8674, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.2777777777777778, | |
| "grad_norm": 0.22335226833820343, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8332, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.3333333333333333, | |
| "grad_norm": 0.193553164601326, | |
| "learning_rate": 6e-06, | |
| "loss": 0.7133, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.3888888888888889, | |
| "grad_norm": 0.1858656108379364, | |
| "learning_rate": 7e-06, | |
| "loss": 0.9214, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 0.214676171541214, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.9407, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.20595382153987885, | |
| "learning_rate": 9e-06, | |
| "loss": 0.8862, | |
| "step": 9 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 54, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 9, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9.330744982304195e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |