| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.14035087719298245, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004678362573099415, | |
| "eval_loss": 10.380034446716309, | |
| "eval_runtime": 0.3461, | |
| "eval_samples_per_second": 260.048, | |
| "eval_steps_per_second": 130.024, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.014035087719298246, | |
| "grad_norm": 0.031849831342697144, | |
| "learning_rate": 6e-05, | |
| "loss": 10.379, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.028070175438596492, | |
| "grad_norm": 0.03441135212779045, | |
| "learning_rate": 0.00012, | |
| "loss": 10.38, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03742690058479532, | |
| "eval_loss": 10.379748344421387, | |
| "eval_runtime": 0.3416, | |
| "eval_samples_per_second": 263.439, | |
| "eval_steps_per_second": 131.719, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.042105263157894736, | |
| "grad_norm": 0.023490067571401596, | |
| "learning_rate": 0.00018, | |
| "loss": 10.3785, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.056140350877192984, | |
| "grad_norm": 0.024002039805054665, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 10.3785, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.07017543859649122, | |
| "grad_norm": 0.022689644247293472, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 10.3757, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07485380116959064, | |
| "eval_loss": 10.378988265991211, | |
| "eval_runtime": 0.375, | |
| "eval_samples_per_second": 239.988, | |
| "eval_steps_per_second": 119.994, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.08421052631578947, | |
| "grad_norm": 0.02695351094007492, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 10.3792, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.09824561403508772, | |
| "grad_norm": 0.022156137973070145, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 10.3772, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.11228070175438597, | |
| "grad_norm": 0.025620989501476288, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 10.3778, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.11228070175438597, | |
| "eval_loss": 10.37852954864502, | |
| "eval_runtime": 0.383, | |
| "eval_samples_per_second": 234.969, | |
| "eval_steps_per_second": 117.484, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.12631578947368421, | |
| "grad_norm": 0.02685621567070484, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 10.3773, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.14035087719298245, | |
| "grad_norm": 0.030803488567471504, | |
| "learning_rate": 0.0, | |
| "loss": 10.3782, | |
| "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": 784536698880.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |