| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 1000, | |
| "global_step": 880, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.11363636363636363, | |
| "grad_norm": 3.531460762023926, | |
| "learning_rate": 9.889693803616793e-06, | |
| "loss": 6.6423, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.22727272727272727, | |
| "grad_norm": 1.5939303636550903, | |
| "learning_rate": 9.165160675191272e-06, | |
| "loss": 2.8506, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.3409090909090909, | |
| "grad_norm": 1.1622482538223267, | |
| "learning_rate": 7.859325160403073e-06, | |
| "loss": 2.8334, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.45454545454545453, | |
| "grad_norm": 0.9140934348106384, | |
| "learning_rate": 6.154433602223979e-06, | |
| "loss": 2.8299, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.5681818181818182, | |
| "grad_norm": 0.6150739789009094, | |
| "learning_rate": 4.2884258086335755e-06, | |
| "loss": 2.8284, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.6818181818181818, | |
| "grad_norm": 0.8906241059303284, | |
| "learning_rate": 2.5217274553677975e-06, | |
| "loss": 2.8265, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.7954545454545454, | |
| "grad_norm": 0.5590549111366272, | |
| "learning_rate": 1.1009042931438784e-06, | |
| "loss": 2.8271, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.9090909090909091, | |
| "grad_norm": 0.36989885568618774, | |
| "learning_rate": 2.242506878237538e-07, | |
| "loss": 2.8254, | |
| "step": 800 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 880, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 1000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.0685869290894131e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |