| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 74, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06756756756756757, | |
| "grad_norm": 3.487422983128833, | |
| "learning_rate": 4.9977343997179584e-05, | |
| "loss": 1.3887, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.13513513513513514, | |
| "grad_norm": 1.8321234958904027, | |
| "learning_rate": 4.91891643656567e-05, | |
| "loss": 1.1604, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.20270270270270271, | |
| "grad_norm": 1.3823622572346563, | |
| "learning_rate": 4.731339946677661e-05, | |
| "loss": 1.0813, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2702702702702703, | |
| "grad_norm": 1.1989778681772267, | |
| "learning_rate": 4.444410798508125e-05, | |
| "loss": 1.0505, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.33783783783783783, | |
| "grad_norm": 1.3833109036656768, | |
| "learning_rate": 4.072516817658065e-05, | |
| "loss": 1.0114, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.40540540540540543, | |
| "grad_norm": 1.2598330739042463, | |
| "learning_rate": 3.634306321221328e-05, | |
| "loss": 0.9935, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.47297297297297297, | |
| "grad_norm": 1.0072567023808396, | |
| "learning_rate": 3.1517530132969326e-05, | |
| "loss": 0.9805, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.5405405405405406, | |
| "grad_norm": 1.0103612562347322, | |
| "learning_rate": 2.6490541317113427e-05, | |
| "loss": 0.9777, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.6081081081081081, | |
| "grad_norm": 0.9975948250557232, | |
| "learning_rate": 2.1514170974749814e-05, | |
| "loss": 0.952, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.6756756756756757, | |
| "grad_norm": 0.9348745107618643, | |
| "learning_rate": 1.6837955094357533e-05, | |
| "loss": 0.9379, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.7432432432432432, | |
| "grad_norm": 1.0583691291023873, | |
| "learning_rate": 1.2696378666356468e-05, | |
| "loss": 0.9411, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.8108108108108109, | |
| "grad_norm": 0.9530754345041429, | |
| "learning_rate": 9.297117626563687e-06, | |
| "loss": 0.9244, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.8783783783783784, | |
| "grad_norm": 0.9611949274162079, | |
| "learning_rate": 6.810625117592363e-06, | |
| "loss": 0.9295, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.9459459459459459, | |
| "grad_norm": 0.9123028897014349, | |
| "learning_rate": 5.361584256530833e-06, | |
| "loss": 0.9192, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 74, | |
| "total_flos": 144123444068352.0, | |
| "train_loss": 1.0135428261112522, | |
| "train_runtime": 2145.3277, | |
| "train_samples_per_second": 4.41, | |
| "train_steps_per_second": 0.034 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 74, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 144123444068352.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |