| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0016, | |
| "eval_steps": 500, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 8e-05, | |
| "grad_norm": 0.2126462459564209, | |
| "learning_rate": 0.0, | |
| "loss": 0.7797, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00016, | |
| "grad_norm": 0.22393645346164703, | |
| "learning_rate": 4e-05, | |
| "loss": 0.8394, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00024, | |
| "grad_norm": 0.2677486538887024, | |
| "learning_rate": 8e-05, | |
| "loss": 1.0813, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00032, | |
| "grad_norm": 0.22248658537864685, | |
| "learning_rate": 0.00012, | |
| "loss": 0.8929, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0004, | |
| "grad_norm": 0.21182884275913239, | |
| "learning_rate": 0.00016, | |
| "loss": 0.7681, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00048, | |
| "grad_norm": 0.22956359386444092, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9418, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00056, | |
| "grad_norm": 0.15817037224769592, | |
| "learning_rate": 0.00019636363636363636, | |
| "loss": 0.622, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00064, | |
| "grad_norm": 0.21448425948619843, | |
| "learning_rate": 0.00019272727272727274, | |
| "loss": 1.0023, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00072, | |
| "grad_norm": 0.13674581050872803, | |
| "learning_rate": 0.0001890909090909091, | |
| "loss": 0.8601, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0008, | |
| "grad_norm": 0.17133376002311707, | |
| "learning_rate": 0.00018545454545454545, | |
| "loss": 0.7606, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00088, | |
| "grad_norm": 0.14465345442295074, | |
| "learning_rate": 0.00018181818181818183, | |
| "loss": 0.8862, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00096, | |
| "grad_norm": 0.17820647358894348, | |
| "learning_rate": 0.0001781818181818182, | |
| "loss": 1.0947, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00104, | |
| "grad_norm": 0.19938325881958008, | |
| "learning_rate": 0.00017454545454545454, | |
| "loss": 0.9516, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.00112, | |
| "grad_norm": 0.1456458568572998, | |
| "learning_rate": 0.0001709090909090909, | |
| "loss": 0.643, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0012, | |
| "grad_norm": 0.15397219359874725, | |
| "learning_rate": 0.00016727272727272728, | |
| "loss": 0.8796, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00128, | |
| "grad_norm": 0.1823822557926178, | |
| "learning_rate": 0.00016363636363636366, | |
| "loss": 0.6386, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.00136, | |
| "grad_norm": 0.17513632774353027, | |
| "learning_rate": 0.00016, | |
| "loss": 1.0072, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.00144, | |
| "grad_norm": 0.18893581628799438, | |
| "learning_rate": 0.00015636363636363637, | |
| "loss": 0.8296, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00152, | |
| "grad_norm": 0.14288924634456635, | |
| "learning_rate": 0.00015272727272727275, | |
| "loss": 0.7706, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0016, | |
| "grad_norm": 0.19747687876224518, | |
| "learning_rate": 0.0001490909090909091, | |
| "loss": 0.9394, | |
| "step": 20 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 60, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2028615178407936.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |