| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.02868617326448652, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005737234652897303, | |
| "eval_loss": 3.131199598312378, | |
| "eval_runtime": 35.5947, | |
| "eval_samples_per_second": 20.621, | |
| "eval_steps_per_second": 10.311, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002868617326448652, | |
| "grad_norm": 3.0306143760681152, | |
| "learning_rate": 5e-05, | |
| "loss": 3.2107, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.005737234652897304, | |
| "grad_norm": 4.1229472160339355, | |
| "learning_rate": 0.0001, | |
| "loss": 2.7002, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005737234652897304, | |
| "eval_loss": 2.3877382278442383, | |
| "eval_runtime": 35.6903, | |
| "eval_samples_per_second": 20.566, | |
| "eval_steps_per_second": 10.283, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.008605851979345954, | |
| "grad_norm": 2.491757392883301, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.0497, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.011474469305794608, | |
| "grad_norm": 2.128636360168457, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.3615, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.011474469305794608, | |
| "eval_loss": 1.3325064182281494, | |
| "eval_runtime": 35.7225, | |
| "eval_samples_per_second": 20.547, | |
| "eval_steps_per_second": 10.274, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01434308663224326, | |
| "grad_norm": 2.977811574935913, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.2361, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01721170395869191, | |
| "grad_norm": 2.637056350708008, | |
| "learning_rate": 5e-05, | |
| "loss": 1.2209, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01721170395869191, | |
| "eval_loss": 1.190410852432251, | |
| "eval_runtime": 36.0048, | |
| "eval_samples_per_second": 20.386, | |
| "eval_steps_per_second": 10.193, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.020080321285140562, | |
| "grad_norm": 2.392871379852295, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.2144, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.022948938611589215, | |
| "grad_norm": 3.025679588317871, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.1152, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.022948938611589215, | |
| "eval_loss": 1.143369197845459, | |
| "eval_runtime": 36.3087, | |
| "eval_samples_per_second": 20.216, | |
| "eval_steps_per_second": 10.108, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.025817555938037865, | |
| "grad_norm": 3.1788511276245117, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.1874, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.02868617326448652, | |
| "grad_norm": 2.724966049194336, | |
| "learning_rate": 0.0, | |
| "loss": 0.9904, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02868617326448652, | |
| "eval_loss": 1.1363798379898071, | |
| "eval_runtime": 35.8859, | |
| "eval_samples_per_second": 20.454, | |
| "eval_steps_per_second": 10.227, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4435234416230400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |