| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00041316338546078046, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.131633854607805e-05, | |
| "grad_norm": 1.8011404275894165, | |
| "learning_rate": 2e-05, | |
| "loss": 3.329, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 4.131633854607805e-05, | |
| "eval_loss": 3.382368564605713, | |
| "eval_runtime": 218.0545, | |
| "eval_samples_per_second": 46.736, | |
| "eval_steps_per_second": 23.37, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 8.26326770921561e-05, | |
| "grad_norm": 1.2275283336639404, | |
| "learning_rate": 4e-05, | |
| "loss": 2.9, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00012394901563823413, | |
| "grad_norm": 1.4353392124176025, | |
| "learning_rate": 6e-05, | |
| "loss": 3.1675, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00012394901563823413, | |
| "eval_loss": 3.3809657096862793, | |
| "eval_runtime": 217.5195, | |
| "eval_samples_per_second": 46.851, | |
| "eval_steps_per_second": 23.428, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0001652653541843122, | |
| "grad_norm": 1.4254233837127686, | |
| "learning_rate": 8e-05, | |
| "loss": 3.0924, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00020658169273039023, | |
| "grad_norm": 1.1145923137664795, | |
| "learning_rate": 0.0001, | |
| "loss": 2.6058, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00024789803127646826, | |
| "grad_norm": 2.063946485519409, | |
| "learning_rate": 0.00012, | |
| "loss": 3.11, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00024789803127646826, | |
| "eval_loss": 3.3328495025634766, | |
| "eval_runtime": 220.5107, | |
| "eval_samples_per_second": 46.215, | |
| "eval_steps_per_second": 23.11, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0002892143698225463, | |
| "grad_norm": 1.6822401285171509, | |
| "learning_rate": 0.00014, | |
| "loss": 3.1236, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0003305307083686244, | |
| "grad_norm": 1.1016179323196411, | |
| "learning_rate": 0.00016, | |
| "loss": 2.671, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0003718470469147024, | |
| "grad_norm": 1.5902749300003052, | |
| "learning_rate": 0.00018, | |
| "loss": 2.8739, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0003718470469147024, | |
| "eval_loss": 3.211221933364868, | |
| "eval_runtime": 219.8062, | |
| "eval_samples_per_second": 46.364, | |
| "eval_steps_per_second": 23.184, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00041316338546078046, | |
| "grad_norm": 1.9983329772949219, | |
| "learning_rate": 0.0002, | |
| "loss": 2.6552, | |
| "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": 324298258513920.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |