| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0058867896760426055, | |
| "eval_steps": 500, | |
| "global_step": 120, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004905658063368838, | |
| "grad_norm": 55.75, | |
| "learning_rate": 1.471550032701112e-07, | |
| "loss": 106.74, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0009811316126737675, | |
| "grad_norm": 53.5, | |
| "learning_rate": 3.106605624591236e-07, | |
| "loss": 106.5866, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0014716974190106514, | |
| "grad_norm": 52.75, | |
| "learning_rate": 4.7416612164813603e-07, | |
| "loss": 107.8943, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.001962263225347535, | |
| "grad_norm": 68.5, | |
| "learning_rate": 6.376716808371485e-07, | |
| "loss": 109.0438, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.002452829031684419, | |
| "grad_norm": 53.75, | |
| "learning_rate": 8.011772400261609e-07, | |
| "loss": 106.0855, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0029433948380213027, | |
| "grad_norm": 63.25, | |
| "learning_rate": 9.646827992151733e-07, | |
| "loss": 106.0407, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.003433960644358187, | |
| "grad_norm": 54.0, | |
| "learning_rate": 1.1281883584041859e-06, | |
| "loss": 104.9819, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.00392452645069507, | |
| "grad_norm": 51.25, | |
| "learning_rate": 1.2916939175931983e-06, | |
| "loss": 108.4838, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.0044150922570319545, | |
| "grad_norm": 59.75, | |
| "learning_rate": 1.4551994767822106e-06, | |
| "loss": 104.6467, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.004905658063368838, | |
| "grad_norm": 53.25, | |
| "learning_rate": 1.618705035971223e-06, | |
| "loss": 105.9295, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.005396223869705722, | |
| "grad_norm": 55.0, | |
| "learning_rate": 1.7822105951602354e-06, | |
| "loss": 105.9408, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.0058867896760426055, | |
| "grad_norm": 44.0, | |
| "learning_rate": 1.945716154349248e-06, | |
| "loss": 106.3008, | |
| "step": 120 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 61155, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 20, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.2647464829845504e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |