| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.98989898989899, | |
| "eval_steps": 500, | |
| "global_step": 49, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.10101010101010101, | |
| "grad_norm": 13.222509384155273, | |
| "learning_rate": 0.0001, | |
| "loss": 2.833, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.20202020202020202, | |
| "grad_norm": 7.568332195281982, | |
| "learning_rate": 8.863636363636364e-05, | |
| "loss": 2.3982, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.30303030303030304, | |
| "grad_norm": 7.395251750946045, | |
| "learning_rate": 7.727272727272727e-05, | |
| "loss": 1.9974, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.40404040404040403, | |
| "grad_norm": 6.726298809051514, | |
| "learning_rate": 6.59090909090909e-05, | |
| "loss": 1.8703, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.5050505050505051, | |
| "grad_norm": 5.273419380187988, | |
| "learning_rate": 5.4545454545454546e-05, | |
| "loss": 1.4627, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.6060606060606061, | |
| "grad_norm": 5.722088813781738, | |
| "learning_rate": 4.318181818181819e-05, | |
| "loss": 1.48, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.7070707070707071, | |
| "grad_norm": 7.1894941329956055, | |
| "learning_rate": 3.181818181818182e-05, | |
| "loss": 1.3753, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.8080808080808081, | |
| "grad_norm": 5.0429863929748535, | |
| "learning_rate": 2.0454545454545457e-05, | |
| "loss": 1.2283, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.9090909090909091, | |
| "grad_norm": 19.73174476623535, | |
| "learning_rate": 9.090909090909091e-06, | |
| "loss": 1.2801, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.98989898989899, | |
| "step": 49, | |
| "total_flos": 229900744138752.0, | |
| "train_loss": 1.73281158719744, | |
| "train_runtime": 13563.9029, | |
| "train_samples_per_second": 0.015, | |
| "train_steps_per_second": 0.004 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 49, | |
| "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": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 229900744138752.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |