| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0009173259947253755, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.057753315751252e-05, | |
| "eval_loss": 5.920693874359131, | |
| "eval_runtime": 475.6676, | |
| "eval_samples_per_second": 28.951, | |
| "eval_steps_per_second": 14.476, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 9.173259947253755e-05, | |
| "grad_norm": 28.084976196289062, | |
| "learning_rate": 6e-05, | |
| "loss": 5.2882, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0001834651989450751, | |
| "grad_norm": 31.341588973999023, | |
| "learning_rate": 0.00012, | |
| "loss": 5.7621, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00024462026526010015, | |
| "eval_loss": 3.7735867500305176, | |
| "eval_runtime": 476.248, | |
| "eval_samples_per_second": 28.916, | |
| "eval_steps_per_second": 14.459, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00027519779841761265, | |
| "grad_norm": 19.94017791748047, | |
| "learning_rate": 0.00018, | |
| "loss": 4.2871, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0003669303978901502, | |
| "grad_norm": 16.417518615722656, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 3.1526, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00045866299736268775, | |
| "grad_norm": 6.215631008148193, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 2.5912, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0004892405305202003, | |
| "eval_loss": 2.448812246322632, | |
| "eval_runtime": 477.9167, | |
| "eval_samples_per_second": 28.815, | |
| "eval_steps_per_second": 14.408, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0005503955968352253, | |
| "grad_norm": 6.208857536315918, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 2.7144, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0006421281963077629, | |
| "grad_norm": 7.5997843742370605, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 2.2168, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0007338607957803004, | |
| "grad_norm": 3.992175340652466, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 2.126, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0007338607957803004, | |
| "eval_loss": 2.126002550125122, | |
| "eval_runtime": 475.708, | |
| "eval_samples_per_second": 28.948, | |
| "eval_steps_per_second": 14.475, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.000825593395252838, | |
| "grad_norm": 3.2497498989105225, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 2.1988, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0009173259947253755, | |
| "grad_norm": 2.9368810653686523, | |
| "learning_rate": 0.0, | |
| "loss": 1.893, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 70, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1534751869501440.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |