| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0012322479282831705, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00012322479282831706, | |
| "grad_norm": 10.744682312011719, | |
| "learning_rate": 2e-05, | |
| "loss": 6.768, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00012322479282831706, | |
| "eval_loss": 1.7490488290786743, | |
| "eval_runtime": 167.217, | |
| "eval_samples_per_second": 20.435, | |
| "eval_steps_per_second": 10.22, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002464495856566341, | |
| "grad_norm": 10.440014839172363, | |
| "learning_rate": 4e-05, | |
| "loss": 7.1368, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0003696743784849512, | |
| "grad_norm": 9.27723503112793, | |
| "learning_rate": 6e-05, | |
| "loss": 6.9491, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0003696743784849512, | |
| "eval_loss": 1.7332682609558105, | |
| "eval_runtime": 165.6489, | |
| "eval_samples_per_second": 20.628, | |
| "eval_steps_per_second": 10.317, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0004928991713132682, | |
| "grad_norm": 9.103442192077637, | |
| "learning_rate": 8e-05, | |
| "loss": 7.1104, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0006161239641415853, | |
| "grad_norm": 9.505884170532227, | |
| "learning_rate": 0.0001, | |
| "loss": 7.2781, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0007393487569699024, | |
| "grad_norm": 9.703471183776855, | |
| "learning_rate": 0.00012, | |
| "loss": 7.1455, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0007393487569699024, | |
| "eval_loss": 1.6274174451828003, | |
| "eval_runtime": 165.6634, | |
| "eval_samples_per_second": 20.626, | |
| "eval_steps_per_second": 10.316, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0008625735497982194, | |
| "grad_norm": 7.959197044372559, | |
| "learning_rate": 0.00014, | |
| "loss": 6.456, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0009857983426265365, | |
| "grad_norm": 6.794594764709473, | |
| "learning_rate": 0.00016, | |
| "loss": 5.9265, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0011090231354548535, | |
| "grad_norm": 8.632143020629883, | |
| "learning_rate": 0.00018, | |
| "loss": 6.55, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0011090231354548535, | |
| "eval_loss": 1.629472017288208, | |
| "eval_runtime": 165.6373, | |
| "eval_samples_per_second": 20.629, | |
| "eval_steps_per_second": 10.318, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0012322479282831705, | |
| "grad_norm": 6.596424102783203, | |
| "learning_rate": 0.0002, | |
| "loss": 6.0204, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2891908468703232.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |