| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0001332462790976562, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.332462790976562e-05, | |
| "grad_norm": 3.8944590091705322, | |
| "learning_rate": 2e-05, | |
| "loss": 6.9983, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.332462790976562e-05, | |
| "eval_loss": 11.747756958007812, | |
| "eval_runtime": 978.044, | |
| "eval_samples_per_second": 32.309, | |
| "eval_steps_per_second": 16.155, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.664925581953124e-05, | |
| "grad_norm": 5.631353378295898, | |
| "learning_rate": 4e-05, | |
| "loss": 11.2571, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 3.997388372929686e-05, | |
| "grad_norm": 3.3083231449127197, | |
| "learning_rate": 6e-05, | |
| "loss": 6.1349, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 3.997388372929686e-05, | |
| "eval_loss": 11.708211898803711, | |
| "eval_runtime": 977.0544, | |
| "eval_samples_per_second": 32.342, | |
| "eval_steps_per_second": 16.171, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 5.329851163906248e-05, | |
| "grad_norm": 7.106707572937012, | |
| "learning_rate": 8e-05, | |
| "loss": 9.4849, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 6.66231395488281e-05, | |
| "grad_norm": 6.543461322784424, | |
| "learning_rate": 0.0001, | |
| "loss": 10.7733, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 7.994776745859372e-05, | |
| "grad_norm": 8.153553009033203, | |
| "learning_rate": 0.00012, | |
| "loss": 10.9144, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 7.994776745859372e-05, | |
| "eval_loss": 10.732725143432617, | |
| "eval_runtime": 977.7582, | |
| "eval_samples_per_second": 32.319, | |
| "eval_steps_per_second": 16.159, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 9.327239536835933e-05, | |
| "grad_norm": 6.99206018447876, | |
| "learning_rate": 0.00014, | |
| "loss": 7.8463, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00010659702327812496, | |
| "grad_norm": 10.886411666870117, | |
| "learning_rate": 0.00016, | |
| "loss": 9.7471, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00011992165118789058, | |
| "grad_norm": 14.091718673706055, | |
| "learning_rate": 0.00018, | |
| "loss": 9.8832, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00011992165118789058, | |
| "eval_loss": 7.665093898773193, | |
| "eval_runtime": 976.7136, | |
| "eval_samples_per_second": 32.353, | |
| "eval_steps_per_second": 16.177, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0001332462790976562, | |
| "grad_norm": 8.954283714294434, | |
| "learning_rate": 0.0002, | |
| "loss": 6.1237, | |
| "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": 1849564248145920.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |