| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.05102040816326531, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00510204081632653, | |
| "grad_norm": 0.07761654257774353, | |
| "learning_rate": 2e-05, | |
| "loss": 10.3789, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00510204081632653, | |
| "eval_loss": 10.380595207214355, | |
| "eval_runtime": 0.3069, | |
| "eval_samples_per_second": 136.845, | |
| "eval_steps_per_second": 68.423, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01020408163265306, | |
| "grad_norm": 0.07940847426652908, | |
| "learning_rate": 4e-05, | |
| "loss": 10.3877, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.015306122448979591, | |
| "grad_norm": 0.06227846071124077, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3831, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.015306122448979591, | |
| "eval_loss": 10.380550384521484, | |
| "eval_runtime": 0.3046, | |
| "eval_samples_per_second": 137.879, | |
| "eval_steps_per_second": 68.939, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.02040816326530612, | |
| "grad_norm": 0.1003938615322113, | |
| "learning_rate": 8e-05, | |
| "loss": 10.3859, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.025510204081632654, | |
| "grad_norm": 0.08336115628480911, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3787, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.030612244897959183, | |
| "grad_norm": 0.0812898501753807, | |
| "learning_rate": 0.00012, | |
| "loss": 10.3777, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.030612244897959183, | |
| "eval_loss": 10.380258560180664, | |
| "eval_runtime": 0.3166, | |
| "eval_samples_per_second": 132.644, | |
| "eval_steps_per_second": 66.322, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03571428571428571, | |
| "grad_norm": 0.060700736939907074, | |
| "learning_rate": 0.00014, | |
| "loss": 10.3771, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.04081632653061224, | |
| "grad_norm": 0.07724273949861526, | |
| "learning_rate": 0.00016, | |
| "loss": 10.3736, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.04591836734693878, | |
| "grad_norm": 0.0864340215921402, | |
| "learning_rate": 0.00018, | |
| "loss": 10.3787, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.04591836734693878, | |
| "eval_loss": 10.379778861999512, | |
| "eval_runtime": 0.3336, | |
| "eval_samples_per_second": 125.907, | |
| "eval_steps_per_second": 62.953, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.05102040816326531, | |
| "grad_norm": 0.07752110809087753, | |
| "learning_rate": 0.0002, | |
| "loss": 10.3777, | |
| "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": 523024465920.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |