| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.10810810810810811, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0036036036036036037, | |
| "eval_loss": 2.2794220447540283, | |
| "eval_runtime": 26.7462, | |
| "eval_samples_per_second": 4.374, | |
| "eval_steps_per_second": 2.206, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010810810810810811, | |
| "grad_norm": 2.174393892288208, | |
| "learning_rate": 6e-05, | |
| "loss": 8.4487, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.021621621621621623, | |
| "grad_norm": 2.042609214782715, | |
| "learning_rate": 0.00012, | |
| "loss": 7.9254, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02882882882882883, | |
| "eval_loss": 2.1537671089172363, | |
| "eval_runtime": 27.2912, | |
| "eval_samples_per_second": 4.287, | |
| "eval_steps_per_second": 2.162, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.032432432432432434, | |
| "grad_norm": 2.866565465927124, | |
| "learning_rate": 0.00018, | |
| "loss": 9.3699, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.043243243243243246, | |
| "grad_norm": 6.563762664794922, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 8.6299, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.05405405405405406, | |
| "grad_norm": 3.654428720474243, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 7.1947, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05765765765765766, | |
| "eval_loss": 1.9088410139083862, | |
| "eval_runtime": 27.3814, | |
| "eval_samples_per_second": 4.273, | |
| "eval_steps_per_second": 2.155, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.06486486486486487, | |
| "grad_norm": 4.6610107421875, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 7.7044, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.07567567567567568, | |
| "grad_norm": 9.290574073791504, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 6.7934, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.08648648648648649, | |
| "grad_norm": 5.527563571929932, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 7.2144, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.08648648648648649, | |
| "eval_loss": 1.7844364643096924, | |
| "eval_runtime": 27.3944, | |
| "eval_samples_per_second": 4.271, | |
| "eval_steps_per_second": 2.154, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0972972972972973, | |
| "grad_norm": 3.0254547595977783, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 7.2205, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.10810810810810811, | |
| "grad_norm": 6.862932205200195, | |
| "learning_rate": 0.0, | |
| "loss": 7.2248, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.90434898870272e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |