| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.04694394892498357, | |
| "eval_steps": 5000, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.009388789784996713, | |
| "grad_norm": 87.77811431884766, | |
| "learning_rate": 9.009854528390429e-07, | |
| "loss": 16.2337, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.018777579569993427, | |
| "grad_norm": 85.86430358886719, | |
| "learning_rate": 1.8395119662130456e-06, | |
| "loss": 13.5901, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.02816636935499014, | |
| "grad_norm": 14.885255813598633, | |
| "learning_rate": 2.7592679493195683e-06, | |
| "loss": 9.8565, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.03755515913998685, | |
| "grad_norm": 6.9691972732543945, | |
| "learning_rate": 3.6977944626935713e-06, | |
| "loss": 8.3332, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.04694394892498357, | |
| "grad_norm": 5.612818241119385, | |
| "learning_rate": 4.6363209760675744e-06, | |
| "loss": 8.1261, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 21302, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 128, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |